Search

In recent years, there has been a dramatic increase in research papers about machine learning (ML) and artificial intelligence in radiology. With so many papers around, it is of paramount importance to make a proper scientific quality assessment as to their validity, reliability, effectiveness, and clinical applicability. Due to methodological complexity, the papers on ML in radiology are often hard to evaluate, requiring a good understanding of key methodological issues. In this review, we aimed to guide the radiology community about key methodological aspects of ML to improve their academic reading and peer-review experience. Key aspects of ML pipeline were presented within four broad categories: study design, data handling, modelling, and reporting. Sixteen key methodological items and related common pitfalls were reviewed with a fresh perspective: database size, robustness of reference standard, information leakage, feature scaling, reliability of features, high dimensionality, perturbations in feature selection, class balance, bias-variance trade-off, hyperparameter tuning, performance metrics, generalisability, clinical utility, comparison with traditional tools, data sharing, and transparent reporting. Key Points • Machine learning is new and rather complex for the radiology community. • Validity, reliability, effectiveness, and clinical applicability of studies on machine learning can be evaluated with a proper understanding of key methodological concepts about study design, data handling, modelling, and reporting. • Understanding key methodological concepts will provide a better academic reading and peer-review experience for the radiology community. [ABSTRACT FROM AUTHOR]

Artificial intelligence developments are essential to the successful deployment of community-wide, MRI-driven prostate cancer diagnosis. AI systems should ensure that the main benefits of biopsy avoidance are delivered while maintaining consistent high specificities, at a range of disease prevalences. Since all current artificial intelligence / computer-aided detection systems for prostate cancer detection are experimental, multiple developmental efforts are still needed to bring the vision to fruition. Initial work needs to focus on developing systems as diagnostic supporting aids so their results can be integrated into the radiologists' workflow including gland and target outlining tasks for fusion biopsies. Developing AI systems as clinical decision-making tools will require greater efforts. The latter encompass larger multicentric, multivendor datasets where the different needs of patients stratified by diagnostic settings, disease prevalence, patient preference, and clinical setting are considered. AI-based, robust, standard operating procedures will increase the confidence of patients and payers, thus enabling the wider adoption of the MRI-directed approach for prostate cancer diagnosis. Key Points: • AI systems need to ensure that the benefits of biopsy avoidance are delivered with consistent high specificities, at a range of disease prevalence. • Initial work has focused on developing systems as diagnostic supporting aids for outlining tasks, so they can be integrated into the radiologists' workflow to support MRI-directed biopsies. • Decision support tools require a larger body of work including multicentric, multivendor studies where the clinical needs, disease prevalence, patient preferences, and clinical setting are additionally defined. [ABSTRACT FROM AUTHOR]

Objective: There has been a large amount of research in the field of artificial intelligence (AI) as applied to clinical radiology. However, these studies vary in design and quality and systematic reviews of the entire field are lacking.This systematic review aimed to identify all papers that used deep learning in radiology to survey the literature and to evaluate their methods. We aimed to identify the key questions being addressed in the literature and to identify the most effective methods employed. Methods: We followed the PRISMA guidelines and performed a systematic review of studies of AI in radiology published from 2015 to 2019. Our published protocol was prospectively registered. Results: Our search yielded 11,083 results. Seven hundred sixty-seven full texts were reviewed, and 535 articles were included. Ninety-eight percent were retrospective cohort studies. The median number of patients included was 460. Most studies involved MRI (37%). Neuroradiology was the most common subspecialty. Eighty-eight percent used supervised learning. The majority of studies undertook a segmentation task (39%). Performance comparison was with a state-of-the-art model in 37%. The most used established architecture was UNet (14%). The median performance for the most utilised evaluation metrics was Dice of 0.89 (range.49–.99), AUC of 0.903 (range 1.00–0.61) and Accuracy of 89.4 (range 70.2–100). Of the 77 studies that externally validated their results and allowed for direct comparison, performance on average decreased by 6% at external validation (range increase of 4% to decrease 44%). Conclusion: This systematic review has surveyed the major advances in AI as applied to clinical radiology. Key Points: • While there are many papers reporting expert-level results by using deep learning in radiology, most apply only a narrow range of techniques to a narrow selection of use cases. • The literature is dominated by retrospective cohort studies with limited external validation with high potential for bias. • The recent advent of AI extensions to systematic reporting guidelines and prospective trial registration along with a focus on external validation and explanations show potential for translation of the hype surrounding AI from code to clinic. [ABSTRACT FROM AUTHOR]

Objective: Although artificial intelligence (AI) has demonstrated promise in enhancing breast cancer diagnosis, the implementation of AI algorithms in clinical practice encounters various barriers. This scoping review aims to identify these barriers and facilitators to highlight key considerations for developing and implementing AI solutions in breast cancer imaging. Method: A literature search was conducted from 2012 to 2022 in six databases (PubMed, Web of Science, CINHAL, Embase, IEEE, and ArXiv). The articles were included if some barriers and/or facilitators in the conception or implementation of AI in breast clinical imaging were described. We excluded research only focusing on performance, or with data not acquired in a clinical radiology setup and not involving real patients. Results: A total of 107 articles were included. We identified six major barriers related to data (B1), black box and trust (B2), algorithms and conception (B3), evaluation and validation (B4), legal, ethical, and economic issues (B5), and education (B6), and five major facilitators covering data (F1), clinical impact (F2), algorithms and conception (F3), evaluation and validation (F4), and education (F5). Conclusion: This scoping review highlighted the need to carefully design, deploy, and evaluate AI solutions in clinical practice, involving all stakeholders to yield improvement in healthcare. Clinical relevance statement: The identification of barriers and facilitators with suggested solutions can guide and inform future research, and stakeholders to improve the design and implementation of AI for breast cancer detection in clinical practice. Key Points: • Six major identified barriers were related to data; black-box and trust; algorithms and conception; evaluation and validation; legal, ethical, and economic issues; and education. • Five major identified facilitators were related to data, clinical impact, algorithms and conception, evaluation and validation, and education. • Coordinated implication of all stakeholders is required to improve breast cancer diagnosis with AI. [ABSTRACT FROM AUTHOR]

Objectives: To develop a deep learning methodology that distinguishes early from late stages of avascular necrosis of the hip (AVN) to determine treatment decisions. Methods: Three convolutional neural networks (CNNs) VGG-16, Inception ResnetV2, InceptionV3 were trained with transfer learning (ImageNet) and finetuned with a retrospectively collected cohort of (n = 104) MRI examinations of AVN patients, to differentiate between early (ARCO 1–2) and late (ARCO 3–4) stages. A consensus CNN ensemble decision was recorded as the agreement of at least two CNNs. CNN and ensemble performance was benchmarked on an independent cohort of 49 patients from another country and was compared to the performance of two MSK radiologists. CNN performance was expressed with areas under the curve (AUC), the respective 95% confidence intervals (CIs) and precision, and recall and f1-scores. AUCs were compared with DeLong's test. Results: On internal testing, Inception-ResnetV2 achieved the highest individual performance with an AUC of 99.7% (95%CI 99–100%), followed by InceptionV3 and VGG-16 with AUCs of 99.3% (95%CI 98.4–100%) and 97.3% (95%CI 95.5–99.2%) respectively. The CNN ensemble the same AUCs Inception ResnetV2. On external validation, model performance dropped with VGG-16 achieving the highest individual AUC of 78.9% (95%CI 51.6–79.6%) The best external performance was achieved by the model ensemble with an AUC of 85.5% (95%CI 72.2–93.9%). No significant difference was found between the CNN ensemble and expert MSK radiologists (p = 0.22 and 0.092 respectively). Conclusion: An externally validated CNN ensemble accurately distinguishes between the early and late stages of AVN and has comparable performance to expert MSK radiologists. Clinical relevance statement: This paper introduces the use of deep learning for the differentiation between early and late avascular necrosis of the hip, assisting in a complex clinical decision that can determine the choice between conservative and surgical treatment. Key Points: • A convolutional neural network ensemble achieved excellent performance in distinguishing between early and late avascular necrosis. • The performance of the deep learning method was similar to the performance of expert readers. [ABSTRACT FROM AUTHOR]

Objectives: To analyze the performance of deep learning in isodense/obscure masses in dense breasts. To build and validate a deep learning (DL) model using core radiology principles and analyze its performance in isodense/obscure masses. To show performance on screening mammography as well as diagnostic mammography distribution. Methods: This was a retrospective, single-institution, multi-centre study with external validation. For model building, we took a 3-pronged approach. First, we explicitly taught the network to learn features other than density differences: such as spiculations and architectural distortion. Second, we used the opposite breast to enable the detection of asymmetries. Third, we systematically enhanced each image by piece-wise-linear transformation. We tested the network on a diagnostic mammography dataset (2569 images with 243 cancers, January to June 2018) and a screening mammography dataset (2146 images with 59 cancers, patient recruitment from January to April 2021) from a different centre (external validation). Results: When trained with our proposed technique (and compared with baseline network), sensitivity for malignancy increased from 82.7 to 84.7% at 0.2 False positives per image (FPI) in the diagnostic mammography dataset, 67.9 to 73.8% in the subset of patients with dense breasts, 74.6 to 85.3 in the subset of patients with isodense/obscure cancers and 84.9 to 88.7 in an external validation test set with a screening mammography distribution. We showed that our sensitivity exceeded currently reported values (0.90 at 0.2 FPI) on a public benchmark dataset (INBreast). Conclusion: Modelling traditional mammographic teaching into a DL framework can help improve cancer detection accuracy in dense breasts. Clinical relevance statement: Incorporating medical knowledge into neural network design can help us overcome some limitations associated with specific modalities. In this paper, we show how one such deep neural network can help improve performance on mammographically dense breasts. Key Points: • Although state-of-the-art deep learning networks achieve good results in cancer detection in mammography in general, isodense, obscure masses and mammographically dense breasts posed a challenge to deep learning networks. • Collaborative network design and incorporation of traditional radiology teaching into the deep learning approach helped mitigate the problem. • The accuracy of deep learning networks may be translatable to different patient distributions. We showed the results of our network on screening as well as diagnostic mammography datasets. [ABSTRACT FROM AUTHOR]

Objectives: Automatic bone lesions detection and classifications present a critical challenge and are essential to support radiologists in making an accurate diagnosis of bone lesions. In this paper, we aimed to develop a novel deep learning model called You Only Look Once (YOLO) to handle detecting and classifying bone lesions on full-field radiographs with limited manual intervention. Methods: In this retrospective study, we used 1085 bone tumor radiographs and 345 normal bone radiographs from two centers between January 2009 and December 2020 to train and test our YOLO deep learning (DL) model. The trained model detected bone lesions and then classified these radiographs into normal, benign, intermediate, or malignant types. The intersection over union (IoU) was used to assess the model's performance in the detection task. Confusion matrices and Cohen's kappa scores were used for evaluating classification performance. Two radiologists compared diagnostic performance with the trained model using the external validation set. Results: In the detection task, the model achieved accuracies of 86.36% and 85.37% in the internal and external validation sets, respectively. In the DL model, radiologist 1 and radiologist 2 achieved Cohen's kappa scores of 0.8187, 0.7927, and 0.9077 for four-way classification in the external validation set, respectively. The YOLO DL model illustrated a significantly higher accuracy for intermediate bone tumor classification than radiologist 1 (95.73% vs 88.08%, p = 0.004). Conclusions: The developed YOLO DL model could be used to assist radiologists at all stages of bone lesion detection and classification in full-field bone radiographs. Key Points: • YOLO DL model can automatically detect bone neoplasms from full-field radiographs in one shot and then simultaneously classify radiographs into normal, benign, intermediate, or malignant. • The dataset used in this retrospective study includes normal bone radiographs. • YOLO can detect even some challenging cases with small volumes. [ABSTRACT FROM AUTHOR]

Purpose: This work aims to assess standard evaluation practices used by the research community for evaluating medical imaging classifiers, with a specific focus on the implications of class imbalance. The analysis is performed on chest X-rays as a case study and encompasses a comprehensive model performance definition, considering both discriminative capabilities and model calibration.We conduct a concise literature review to examine prevailing scientific practices used when evaluating X-ray classifiers. Then, we perform a systematic experiment on two major chest X-ray datasets to showcase a didactic example of the behavior of several performance metrics under different class ratios and highlight how widely adopted metrics can conceal performance in the minority class.Our literature study confirms that: (1) even when dealing with highly imbalanced datasets, the community tends to use metrics that are dominated by the majority class; and (2) it is still uncommon to include calibration studies for chest X-ray classifiers, albeit its importance in the context of healthcare. Moreover, our systematic experiments confirm that current evaluation practices may not reflect model performance in real clinical scenarios and suggest complementary metrics to better reflect the performance of the system in such scenarios.Our analysis underscores the need for enhanced evaluation practices, particularly in the context of class-imbalanced chest X-ray classifiers. We recommend the inclusion of complementary metrics such as the area under the precision-recall curve (AUC-PR), adjusted AUC-PR, and balanced Brier score, to offer a more accurate depiction of system performance in real clinical scenarios, considering metrics that reflect both, discrimination and calibration performance.This study underscores the critical need for refined evaluation metrics in medical imaging classifiers, emphasizing that prevalent metrics may mask poor performance in minority classes, potentially impacting clinical diagnoses and healthcare outcomes.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Materials and methods: This work aims to assess standard evaluation practices used by the research community for evaluating medical imaging classifiers, with a specific focus on the implications of class imbalance. The analysis is performed on chest X-rays as a case study and encompasses a comprehensive model performance definition, considering both discriminative capabilities and model calibration.We conduct a concise literature review to examine prevailing scientific practices used when evaluating X-ray classifiers. Then, we perform a systematic experiment on two major chest X-ray datasets to showcase a didactic example of the behavior of several performance metrics under different class ratios and highlight how widely adopted metrics can conceal performance in the minority class.Our literature study confirms that: (1) even when dealing with highly imbalanced datasets, the community tends to use metrics that are dominated by the majority class; and (2) it is still uncommon to include calibration studies for chest X-ray classifiers, albeit its importance in the context of healthcare. Moreover, our systematic experiments confirm that current evaluation practices may not reflect model performance in real clinical scenarios and suggest complementary metrics to better reflect the performance of the system in such scenarios.Our analysis underscores the need for enhanced evaluation practices, particularly in the context of class-imbalanced chest X-ray classifiers. We recommend the inclusion of complementary metrics such as the area under the precision-recall curve (AUC-PR), adjusted AUC-PR, and balanced Brier score, to offer a more accurate depiction of system performance in real clinical scenarios, considering metrics that reflect both, discrimination and calibration performance.This study underscores the critical need for refined evaluation metrics in medical imaging classifiers, emphasizing that prevalent metrics may mask poor performance in minority classes, potentially impacting clinical diagnoses and healthcare outcomes.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Results: This work aims to assess standard evaluation practices used by the research community for evaluating medical imaging classifiers, with a specific focus on the implications of class imbalance. The analysis is performed on chest X-rays as a case study and encompasses a comprehensive model performance definition, considering both discriminative capabilities and model calibration.We conduct a concise literature review to examine prevailing scientific practices used when evaluating X-ray classifiers. Then, we perform a systematic experiment on two major chest X-ray datasets to showcase a didactic example of the behavior of several performance metrics under different class ratios and highlight how widely adopted metrics can conceal performance in the minority class.Our literature study confirms that: (1) even when dealing with highly imbalanced datasets, the community tends to use metrics that are dominated by the majority class; and (2) it is still uncommon to include calibration studies for chest X-ray classifiers, albeit its importance in the context of healthcare. Moreover, our systematic experiments confirm that current evaluation practices may not reflect model performance in real clinical scenarios and suggest complementary metrics to better reflect the performance of the system in such scenarios.Our analysis underscores the need for enhanced evaluation practices, particularly in the context of class-imbalanced chest X-ray classifiers. We recommend the inclusion of complementary metrics such as the area under the precision-recall curve (AUC-PR), adjusted AUC-PR, and balanced Brier score, to offer a more accurate depiction of system performance in real clinical scenarios, considering metrics that reflect both, discrimination and calibration performance.This study underscores the critical need for refined evaluation metrics in medical imaging classifiers, emphasizing that prevalent metrics may mask poor performance in minority classes, potentially impacting clinical diagnoses and healthcare outcomes.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Conclusion: This work aims to assess standard evaluation practices used by the research community for evaluating medical imaging classifiers, with a specific focus on the implications of class imbalance. The analysis is performed on chest X-rays as a case study and encompasses a comprehensive model performance definition, considering both discriminative capabilities and model calibration.We conduct a concise literature review to examine prevailing scientific practices used when evaluating X-ray classifiers. Then, we perform a systematic experiment on two major chest X-ray datasets to showcase a didactic example of the behavior of several performance metrics under different class ratios and highlight how widely adopted metrics can conceal performance in the minority class.Our literature study confirms that: (1) even when dealing with highly imbalanced datasets, the community tends to use metrics that are dominated by the majority class; and (2) it is still uncommon to include calibration studies for chest X-ray classifiers, albeit its importance in the context of healthcare. Moreover, our systematic experiments confirm that current evaluation practices may not reflect model performance in real clinical scenarios and suggest complementary metrics to better reflect the performance of the system in such scenarios.Our analysis underscores the need for enhanced evaluation practices, particularly in the context of class-imbalanced chest X-ray classifiers. We recommend the inclusion of complementary metrics such as the area under the precision-recall curve (AUC-PR), adjusted AUC-PR, and balanced Brier score, to offer a more accurate depiction of system performance in real clinical scenarios, considering metrics that reflect both, discrimination and calibration performance.This study underscores the critical need for refined evaluation metrics in medical imaging classifiers, emphasizing that prevalent metrics may mask poor performance in minority classes, potentially impacting clinical diagnoses and healthcare outcomes.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Clinical relevance statement: This work aims to assess standard evaluation practices used by the research community for evaluating medical imaging classifiers, with a specific focus on the implications of class imbalance. The analysis is performed on chest X-rays as a case study and encompasses a comprehensive model performance definition, considering both discriminative capabilities and model calibration.We conduct a concise literature review to examine prevailing scientific practices used when evaluating X-ray classifiers. Then, we perform a systematic experiment on two major chest X-ray datasets to showcase a didactic example of the behavior of several performance metrics under different class ratios and highlight how widely adopted metrics can conceal performance in the minority class.Our literature study confirms that: (1) even when dealing with highly imbalanced datasets, the community tends to use metrics that are dominated by the majority class; and (2) it is still uncommon to include calibration studies for chest X-ray classifiers, albeit its importance in the context of healthcare. Moreover, our systematic experiments confirm that current evaluation practices may not reflect model performance in real clinical scenarios and suggest complementary metrics to better reflect the performance of the system in such scenarios.Our analysis underscores the need for enhanced evaluation practices, particularly in the context of class-imbalanced chest X-ray classifiers. We recommend the inclusion of complementary metrics such as the area under the precision-recall curve (AUC-PR), adjusted AUC-PR, and balanced Brier score, to offer a more accurate depiction of system performance in real clinical scenarios, considering metrics that reflect both, discrimination and calibration performance.This study underscores the critical need for refined evaluation metrics in medical imaging classifiers, emphasizing that prevalent metrics may mask poor performance in minority classes, potentially impacting clinical diagnoses and healthcare outcomes.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Key Points: This work aims to assess standard evaluation practices used by the research community for evaluating medical imaging classifiers, with a specific focus on the implications of class imbalance. The analysis is performed on chest X-rays as a case study and encompasses a comprehensive model performance definition, considering both discriminative capabilities and model calibration.We conduct a concise literature review to examine prevailing scientific practices used when evaluating X-ray classifiers. Then, we perform a systematic experiment on two major chest X-ray datasets to showcase a didactic example of the behavior of several performance metrics under different class ratios and highlight how widely adopted metrics can conceal performance in the minority class.Our literature study confirms that: (1) even when dealing with highly imbalanced datasets, the community tends to use metrics that are dominated by the majority class; and (2) it is still uncommon to include calibration studies for chest X-ray classifiers, albeit its importance in the context of healthcare. Moreover, our systematic experiments confirm that current evaluation practices may not reflect model performance in real clinical scenarios and suggest complementary metrics to better reflect the performance of the system in such scenarios.Our analysis underscores the need for enhanced evaluation practices, particularly in the context of class-imbalanced chest X-ray classifiers. We recommend the inclusion of complementary metrics such as the area under the precision-recall curve (AUC-PR), adjusted AUC-PR, and balanced Brier score, to offer a more accurate depiction of system performance in real clinical scenarios, considering metrics that reflect both, discrimination and calibration performance.This study underscores the critical need for refined evaluation metrics in medical imaging classifiers, emphasizing that prevalent metrics may mask poor performance in minority classes, potentially impacting clinical diagnoses and healthcare outcomes.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading.We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios.We propose adopting alternative metrics based on experimental evaluation on large-scale datasets. [ABSTRACT FROM AUTHOR]

This letter to the editor responds to a recent paper on the accurate measurement of the Magnetic Resonance Parkinsonism Index (MRPI) using deep learning technology. The authors express their appreciation for the development of an automated method for measuring the MRPI, a biomarker they developed 15 years ago. However, they raise concerns about the methodology employed in the paper, stating that the authors did not use their original automated algorithm and instead developed a semi-automated algorithm. They argue that this misrepresentation of their method may have led to misleading conclusions. The authors emphasize the importance of transparency and rigorous methodology in scientific comparisons. [Extracted from the article]

Objectives: To evaluate AI biases and errors in estimating bone age (BA) by comparing AI and radiologists' clinical determinations of BA. Methods: We established three deep learning models from a Chinese private dataset (CHNm), an American public dataset (USAm), and a joint dataset combining the above two datasets (JOIm). The test data CHNt (n = 1246) were labeled by ten senior pediatric radiologists. The effects of data site differences, interpretation bias, and interobserver variability on BA assessment were evaluated. The differences between the AI models' and radiologists' clinical determinations of BA (normal, advanced, and delayed BA groups by using the Brush data) were evaluated by the chi-square test and Kappa values. The heatmaps of CHNm-CHNt were generated by using Grad-CAM. Results: We obtained an MAD value of 0.42 years on CHNm-CHNt; this result indicated an appropriate accuracy for the whole group but did not indicate an accurate estimation of individual BA because with a kappa value of 0.714, the agreement between AI and human clinical determinations of BA was significantly different. The features of the heatmaps were not fully consistent with the human vision on the X-ray films. Variable performance in BA estimation by different AI models and the disagreement between AI and radiologists' clinical determinations of BA may be caused by data biases, including patients' sex and age, institutions, and radiologists. Conclusions: The deep learning models outperform external validation in predicting BA on both internal and joint datasets. However, the biases and errors in the models' clinical determinations of child development should be carefully considered. Key Points: • With a kappa value of 0.714, clinical determinations of bone age by using AI did not accord well with clinical determinations by radiologists. • Several biases, including patients' sex and age, institutions, and radiologists, may cause variable performance by AI bone age models and disagreement between AI and radiologists' clinical determinations of bone age. • AI heatmaps of bone age were not fully consistent with human vision on X-ray films. [ABSTRACT FROM AUTHOR]

Objectives: The aim of this study was to systematically review the literature and perform a meta-analysis of machine learning (ML) diagnostic accuracy studies focused on clinically significant prostate cancer (csPCa) identification on MRI. Methods: Multiple medical databases were systematically searched for studies on ML applications in csPCa identification up to July 31, 2019. Two reviewers screened all papers independently for eligibility. The area under the receiver operating characteristic curves (AUC) was pooled to quantify predictive accuracy. A random-effects model estimated overall effect size while statistical heterogeneity was assessed with the I2 value. A funnel plot was used to investigate publication bias. Subgroup analyses were performed based on reference standard (biopsy or radical prostatectomy) and ML type (deep and non-deep). Results: After the final revision, 12 studies were included in the analysis. Statistical heterogeneity was high both in overall and in subgroup analyses. The overall pooled AUC for ML in csPCa identification was 0.86, with 0.81–0.91 95% confidence intervals (95%CI). The biopsy subgroup (n = 9) had a pooled AUC of 0.85 (95%CI = 0.79–0.91) while the radical prostatectomy one (n = 3) of 0.88 (95%CI = 0.76–0.99). Deep learning ML (n = 4) had a 0.78 AUC (95%CI = 0.69–0.86) while the remaining 8 had AUC = 0.90 (95%CI = 0.85–0.94). Conclusions: ML pipelines using prostate MRI to identify csPCa showed good accuracy and should be further investigated, possibly with better standardisation in design and reporting of results. Key Points: • Overall pooled AUC was 0.86 with 0.81–0.91 95% confidence intervals. • In the reference standard subgroup analysis, algorithm accuracy was similar with pooled AUCs of 0.85 (0.79–0.91 95% confidence intervals) and 0.88 (0.76–0.99 95% confidence intervals) for studies employing biopsies and radical prostatectomy, respectively. • Deep learning pipelines performed worse (AUC = 0.78, 0.69–0.86 95% confidence intervals) than other approaches (AUC = 0.90, 0.85–0.94 95% confidence intervals). [ABSTRACT FROM AUTHOR]

The authors have assessed the performance of a previously trained model (UNETM) in the task of automatically detecting and annotating csPCa lesions on biparametric prostate MRI scans [[6]]. Of note, the test dataset can be considered of high quality both in terms of overall size (640 cases in total) and diversification of sources (two separate institutions and a public dataset, multiple scanner vendors). [Extracted from the article]

This editorial comment refers to the article: "Diagnosing autism spectrum disorder in children using conventional MRI and apparent diffusion coefficient based deep learning algorithms" by Guo et al. (Eur Radiol, 2021). Key Points: •Deep learning may help to uncover imaging features of autism spectrum disorder on MRI. [ABSTRACT FROM AUTHOR]

Objectives: There is a need for CT pulmonary angiography (CTPA) lung segmentation models. Clinical translation requires radiological evaluation of model outputs, understanding of limitations, and identification of failure points. This multicentre study aims to develop an accurate CTPA lung segmentation model, with evaluation of outputs in two diverse patient cohorts with pulmonary hypertension (PH) and interstitial lung disease (ILD). Methods: This retrospective study develops an nnU-Net-based segmentation model using data from two specialist centres (UK and USA). Model was trained (n = 37), tested (n = 12), and clinically evaluated (n = 176) on a diverse 'real-world' cohort of 225 PH patients with volumetric CTPAs. Dice score coefficient (DSC) and normalised surface distance (NSD) were used for testing. Clinical evaluation of outputs was performed by two radiologists who assessed clinical significance of errors. External validation was performed on heterogenous contrast and non-contrast scans from 28 ILD patients. Results: A total of 225 PH and 28 ILD patients with diverse demographic and clinical characteristics were evaluated. Mean accuracy, DSC, and NSD scores were 0.998 (95% CI 0.9976, 0.9989), 0.990 (0.9840, 0.9962), and 0.983 (0.9686, 0.9972) respectively. There were no segmentation failures. On radiological review, 82% and 71% of internal and external cases respectively had no errors. Eighteen percent and 25% respectively had clinically insignificant errors. Peripheral atelectasis and consolidation were common causes for suboptimal segmentation. One external case (0.5%) with patulous oesophagus had a clinically significant error. Conclusion: State-of-the-art CTPA lung segmentation model provides accurate outputs with minimal clinical errors on evaluation across two diverse cohorts with PH and ILD. Clinical relevance: Clinical translation of artificial intelligence models requires radiological review and understanding of model limitations. This study develops an externally validated state-of-the-art model with robust radiological review. Intended clinical use is in techniques such as lung volume or parenchymal disease quantification. Key Points: • Accurate, externally validated CT pulmonary angiography (CTPA) lung segmentation model tested in two large heterogeneous clinical cohorts (pulmonary hypertension and interstitial lung disease). • No segmentation failures and robust review of model outputs by radiologists found 1 (0.5%) clinically significant segmentation error. • Intended clinical use of this model is a necessary step in techniques such as lung volume, parenchymal disease quantification, or pulmonary vessel analysis. [ABSTRACT FROM AUTHOR]

Objectives: To perform a comprehensive within-subject image quality analysis of abdominal CT examinations reconstructed with DLIR and to evaluate diagnostic accuracy compared to the routinely applied adaptive statistical iterative reconstruction (ASiR-V) algorithm. Materials and methods: Oncologic patients were prospectively enrolled and underwent contrast-enhanced CT. Images were reconstructed with DLIR with three intensity levels of reconstruction (high, medium, and low) and ASiR-V at strength levels from 10 to 100% with a 10% interval. Three radiologists characterized the lesions and two readers assessed diagnostic accuracy and calculated signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), figure of merit (FOM), and subjective image quality, the latter with a 5-point Likert scale. Results: Fifty patients (mean age: 70 ± 10 years, 23 men) were enrolled and 130 liver lesions (105 benign lesions, 25 metastases) were identified. DLIR_H achieved the highest SNR and CNR, comparable to ASiR-V 100% (p ≥.051). DLIR_M returned the highest subjective image quality (score: 5; IQR: 4–5; p ≤.001) and significant median increase (29%) in FOM (p <.001). Differences in detection were identified only for lesions ≤ 0.5 cm: 32/33 lesions were detected with DLIR_M and 26 lesions were detected with ASiR-V 50% (p =.031). Lesion accuracy of was 93.8% (95% CI: 88.1, 97.3; 122 of 130 lesions) for DLIR and 87.7% (95% CI: 80.8, 92.8; 114 of 130 lesions) for ASiR-V 50%. Conclusions: DLIR yields superior image quality and provides higher diagnostic accuracy compared to ASiR-V in the assessment of hypovascular liver lesions, in particular for lesions ≤ 0.5 cm. Clinical relevance statement: Deep learning image reconstruction algorithm demonstrates higher diagnostic accuracy compared to iterative reconstruction in the identification of hypovascular liver lesions, especially for lesions ≤ 0.5 cm. Key Points: • Iterative reconstruction algorithm impacts image texture, with negative effects on diagnostic capabilities. • Medium-strength deep learning image reconstruction algorithm outperforms iterative reconstruction in the diagnostic accuracy of ≤ 0.5 cm hypovascular liver lesions (93.9% vs 78.8%), also granting higher objective and subjective image quality. • Deep learning image reconstruction algorithm can be safely implemented in routine abdominal CT protocols in place of iterative reconstruction. [ABSTRACT FROM AUTHOR]

Objectives: Evaluation of in-stent restenosis (ISR), especially for small stents, remains challenging during computed tomography (CT) angiography. We used deep learning reconstruction to quantify stent strut thickness and lumen vessel diameter at the stent and compared it with values obtained using conventional reconstruction strategies. Methods: We examined 166 stents in 85 consecutive patients who underwent CT and invasive coronary angiography (ICA) within 3 months of each other from 2019–2021 after percutaneous coronary intervention with coronary stent placement. The presence of ISR was defined as percent diameter stenosis ≥ 50% on ICA. We compared a super-resolution deep learning reconstruction, Precise IQ Engine (PIQE), and a model-based iterative reconstruction, Forward projected model-based Iterative Reconstruction SoluTion (FIRST). All images were reconstructed using PIQE and FIRST and assessed by two blinded cardiovascular radiographers. Results: PIQE had a larger full width at half maximum of the lumen and smaller strut than FIRST. The image quality score in PIQE was higher than that in FIRST (4.2 ± 1.1 versus 2.7 ± 1.2, p < 0.05). In addition, the specificity and accuracy of ISR detection were better in PIQE than in FIRST (p < 0.05 for both), with particularly pronounced differences for stent diameters < 3.0 mm. Conclusion: PIQE provides superior image quality and diagnostic accuracy for ISR, even with stents measuring < 3.0 mm in diameter. Clinical relevance statement: With improvements in the diagnostic accuracy of in-stent stenosis, CT angiography could become a gatekeeper for ICA in post-stenting cases, obviating ICA in many patients after recent stenting with infrequent ISR and allowing non-invasive ISR detection in the late phase. Key Points: • Despite CT technology advancements, evaluating in-stent stenosis severity, especially in small-diameter stents, remains challenging. • Compared with conventional methods, the Precise IQ Engine uses deep learning to improve spatial resolution. • Improved diagnostic accuracy of CT angiography helps avoid invasive coronary angiography after coronary artery stenting. [ABSTRACT FROM AUTHOR]

Objectives: The differential between high-grade glioma (HGG) and metastasis remains challenging in common radiological practice. We compare different natural language processing (NLP)–based deep learning models to assist radiologists based on data contained in radiology reports. Methods: This retrospective study included 185 MRI reports between 2010 and 2022 from two different institutions. A total of 117 reports were used for the training and 21 were reserved for the validation set, while the rest were used as a test set. A comparison of the performance of different deep learning models for HGG and metastasis classification has been carried out. Specifically, Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), a hybrid version of BiLSTM and CNN, and a radiology-specific Bidirectional Encoder Representations from Transformers (RadBERT) model were used. Results: For the classification of MRI reports, the CNN network provided the best results among all tested, showing a macro-avg precision of 87.32%, a sensitivity of 87.45%, and an F1 score of 87.23%. In addition, our NLP algorithm detected keywords such as tumor, temporal, and lobe to positively classify a radiological report as HGG or metastasis group. Conclusions: A deep learning model based on CNN enables radiologists to discriminate between HGG and metastasis based on MRI reports with high-precision values. This approach should be considered an additional tool in diagnosing these central nervous system lesions. Clinical relevance statement: The use of our NLP model enables radiologists to differentiate between patients with high-grade glioma and metastasis based on their MRI reports and can be used as an additional tool to the conventional image-based approach for this challenging task. Key Points: • Differential between high-grade glioma and metastasis is still challenging in common radiological practice. • Natural language processing (NLP)–based deep learning models can assist radiologists based on data contained in radiology reports. • We have developed and tested a natural language processing model for discriminating between high-grade glioma and metastasis based on MRI reports that show high precision for this task. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to evaluate the image quality and lesion conspicuity of the deep learning image reconstruction (DLIR) algorithm compared with standard image reconstruction algorithms on abdominal enhanced computed tomography (CT) scanning with a wide range of body mass indexes (BMIs). Methods: A total of 112 participants who underwent contrast-enhanced abdominal CT scans were divided into three groups according to BMIs: the 80-kVp group (BMI ≤ 23.9 kg/m2), 100-kVp group (BMI 24–28.9 kg/m2), and 120-kVp group (BMI ≥ 29 kg/m2). All images were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction-V of 50% level (IR), and DLIR at low, medium, and high levels (DL, DM, and DH, respectively). Subjective noise, artifact, overall image quality, and low- and high-contrast hepatic lesion conspicuity were all graded on a 5-point scale. The CT attenuation value (in HU), image noise, and contrast-to-noise ratio (CNR) were quantified and compared. Results: DM and DH improved the qualitative and quantitative parameters compared with FBP and IR for all three BMI groups. DH had the lowest image noise and highest CNR value, while DM had the highest subjective overall image quality and low- and high-contrast lesion conspicuity scores for the three BMI groups. Based on the FBP, the improvement in image quality and lesion conspicuity of DM and DH images was greater in the 80-kVp group than in the 100-kVp and 120-kVp groups. Conclusion: For all BMIs, DLIR improves both image quality and hepatic lesion conspicuity, of which DM would be the best choice to balance both. Clinical relevance statement: The study suggests that utilizing DLIR, particularly at the medium level, can significantly enhance image quality and lesion visibility on abdominal CT scans across a wide range of BMIs. Key Points: • DLIR improved the image quality and lesion conspicuity across a wide range of BMIs. • DLIR at medium level had the highest subjective parameters and lesion conspicuity scores among all reconstruction levels. • On the basis of the FBP, the 80-kVp group had improved image quality and lesion conspicuity more than the 100-kVp and 120-kVp groups. [ABSTRACT FROM AUTHOR]

Objectives: We aimed to evaluate whether deep learning–based detection and quantification of brain metastasis (BM) may suggest treatment options for patients with BMs. Methods: The deep learning system (DLS) for detection and quantification of BM was developed in 193 patients and applied to 112 patients that were newly detected on black-blood contrast-enhanced T1-weighted imaging. Patients were assigned to one of 3 treatment suggestion groups according to the European Association of Neuro-Oncology (EANO)-European Society for Medical Oncology (ESMO) recommendations using number and volume of the BMs detected by the DLS: short-term imaging follow-up without treatment (group A), surgery or stereotactic radiosurgery (limited BM, group B), or whole-brain radiotherapy or systemic chemotherapy (extensive BM, group C). The concordance between the DLS-based groups and clinical decisions was analyzed with or without consideration of targeted agents. The performance of distinguishing high-risk (B + C) was calculated. Results: Among 112 patients (mean age 64.3 years, 63 men), group C had the largest number and volume of BM, followed by group B (4.4 and 851.6 mm3) and A (1.5 and 15.5 mm3). The DLS-based groups were concordant with the actual clinical decisions, with an accuracy of 76.8% (86 of 112). Modified accuracy considering targeted agents was 81.3% (91 of 112). The DLS showed 95% (82/86) sensitivity and 81% (21/26) specificity for distinguishing the high risk. Conclusion: DLS-based detection and quantification of BM have the potential to be helpful in the determination of treatment options for both low- and high-risk groups of limited and extensive BMs. Clinical relevance statement: For patients with newly diagnosed brain metastasis, deep learning–based detection and quantification may be used in clinical settings where prompt and accurate treatment decisions are required, which can lead to better patient outcomes. Key Points: • Deep learning–based brain metastasis detection and quantification showed excellent agreement with ground-truth classifications. • By setting an algorithm to suggest treatment based on the number and volume of brain metastases detected by the deep learning system, the concordance was 81.3%. • When dividing patients into low- and high-risk groups, the sensitivity for detecting the latter was 95%. [ABSTRACT FROM AUTHOR]

Objectives: Evaluate the performance of a deep learning (DL)–based model for multiple sclerosis (MS) lesion segmentation and compare it to other DL and non-DL algorithms. Methods: This ambispective, multicenter study assessed the performance of a DL-based model for MS lesion segmentation and compared it to alternative DL- and non-DL-based methods. Models were tested on internal (n = 20) and external (n = 18) datasets from Latin America, and on an external dataset from Europe (n = 49). We also examined robustness by rescanning six patients (n = 6) from our MS clinical cohort. Moreover, we studied inter-human annotator agreement and discussed our findings in light of these results. Performance and robustness were assessed using intraclass correlation coefficient (ICC), Dice coefficient (DC), and coefficient of variation (CV). Results: Inter-human ICC ranged from 0.89 to 0.95, while spatial agreement among annotators showed a median DC of 0.63. Using expert manual segmentations as ground truth, our DL model achieved a median DC of 0.73 on the internal, 0.66 on the external, and 0.70 on the challenge datasets. The performance of our DL model exceeded that of the alternative algorithms on all datasets. In the robustness experiment, our DL model also achieved higher DC (ranging from 0.82 to 0.90) and lower CV (ranging from 0.7 to 7.9%) when compared to the alternative methods. Conclusion: Our DL-based model outperformed alternative methods for brain MS lesion segmentation. The model also proved to generalize well on unseen data and has a robust performance and low processing times both on real-world and challenge-based data. Clinical relevance statement: Our DL-based model demonstrated superior performance in accurately segmenting brain MS lesions compared to alternative methods, indicating its potential for clinical application with improved accuracy, robustness, and efficiency. Key Points: • Automated lesion load quantification in MS patients is valuable; however, more accurate methods are still necessary. • A novel deep learning model outperformed alternative MS lesion segmentation methods on multisite datasets. • Deep learning models are particularly suitable for MS lesion segmentation in clinical scenarios. [ABSTRACT FROM AUTHOR]

Objectives: To develop a deep-learning method for whole-body fetal segmentation based on MRI; to assess the method's repeatability, reproducibility, and accuracy; to create an MRI-based normal fetal weight growth chart; and to assess the sensitivity to detect fetuses with growth restriction (FGR). Methods: Retrospective data of 348 fetuses with gestational age (GA) of 19–39 weeks were included: 249 normal appropriate for GA (AGA), 19 FGR, and 80 Other (having various imaging abnormalities). A fetal whole-body segmentation model with a quality estimation module was developed and evaluated in 169 cases. The method was evaluated for its repeatability (repeated scans within the same scanner, n = 22), reproducibility (different scanners, n = 6), and accuracy (compared with birth weight, n = 7). A normal MRI-based growth chart was derived. Results: The method achieved a Dice = 0.973, absolute volume difference ratio (VDR) = 1.8% and VDR mean difference = 0.75% ( CI 95 % : − 3.95%, 5.46), and high agreement with the gold standard. The method achieved a repeatability coefficient = 4.01%, ICC = 0.99, high reproducibility with a mean difference = 2.21% ( CI 95 % : − 1.92%, 6.35%), and high accuracy with a mean difference between estimated fetal weight (EFW) and birth weight of − 0.39% ( CI 95 % : − 8.23%, 7.45%). A normal growth chart (n = 246) was consistent with four ultrasound charts. EFW based on MRI correctly predicted birth-weight percentiles for all 18 fetuses ≤ 10thpercentile and for 14 out of 17 FGR fetuses below the 3rd percentile. Six fetuses referred to MRI as AGA were found to be < 3rd percentile. Conclusions: The proposed method for automatic MRI-based EFW demonstrated high performance and sensitivity to identify FGR fetuses. Clinical relevance statement: Results from this study support the use of the automatic fetal weight estimation method based on MRI for the assessment of fetal development and to detect fetuses at risk for growth restriction. Key Points: • An AI-based segmentation method with a quality assessment module for fetal weight estimation based on MRI was developed, achieving high repeatability, reproducibility, and accuracy. • An MRI-based fetal weight growth chart constructed from a large cohort of normal and appropriate gestational-age fetuses is proposed. • The method showed a high sensitivity for the diagnosis of small fetuses suspected of growth restriction. [ABSTRACT FROM AUTHOR]

Objectives: With the popularization of chest computed tomography (CT) screening, there are more sub-centimeter (≤ 1 cm) pulmonary nodules (SCPNs) requiring further diagnostic workup. This area represents an important opportunity to optimize the SCPN management algorithm avoiding "one-size fits all" approach. One critical problem is how to learn the discriminative multi-view characteristics and the unique context of each SCPN. Methods: Here, we propose a multi-view coupled self-attention module (MVCS) to capture the global spatial context of the CT image through modeling the association order of space and dimension. Compared with existing self-attention methods, MVCS uses less memory consumption and computational complexity, unearths dimension correlations that previous methods have not found, and is easy to integrate with other frameworks. Results: In total, a public dataset LUNA16 from LIDC-IDRI, 1319 SCPNs from 1069 patients presenting to a major referral center, and 160 SCPNs from 137 patients from three other major centers were analyzed to pre-train, train, and validate the model. Experimental results showed that performance outperforms the state-of-the-art models in terms of accuracy and stability and is comparable to that of human experts in classifying precancerous lesions and invasive adenocarcinoma. We also provide a fusion MVCS network (MVCSN) by combining the CT image with the clinical characteristics and radiographic features of patients. Conclusion: This tool may ultimately aid in expediting resection of the malignant SCPNs and avoid over-diagnosis of the benign ones, resulting in improved management outcomes. Clinical relevance statement: In the diagnosis of sub-centimeter lung adenocarcinoma, fusion MVCSN can help doctors improve work efficiency and guide their treatment decisions to a certain extent. Key Points: • Advances in computed tomography (CT) not only increase the number of nodules detected, but also the nodules that are identified are smaller, such as sub-centimeter pulmonary nodules (SCPNs). • We propose a multi-view coupled self-attention module (MVCS), which could model spatial and dimensional correlations sequentially for learning global spatial contexts, which is better than other attention mechanisms. • MVCS uses fewer huge memory consumption and computational complexity than the existing self-attention methods when dealing with 3D medical image data. Additionally, it reaches promising accuracy for SCPNs' malignancy evaluation and has lower training cost than other models. [ABSTRACT FROM AUTHOR]

Objectives: To develop an end-to-end deep neural network for the classification of contrast-enhanced mammography (CEM) images to facilitate breast cancer diagnosis in the clinic. Methods: In this retrospective mono-centric study, patients who underwent CEM examinations from January 2019 to August 2021 were enrolled. A multi-feature fusion network combining low-energy (LE) and dual-energy subtracted (DES) images and dual view, as well as bilateral information, was trained and tested using a large CEM dataset with a diversity of breast tumors for breast lesion classification. Its generalization performance was further evaluated on two external datasets. Results were reported using AUC, accuracy, sensitivity, and specificity. Results: A total of 2496 patients (mean age, 53 years ± 12 (standard deviation)) were included and divided into a training set (1718), a validation set (255), and a testing set (523). The proposed CEM-based multi-feature fusion network achieved the best diagnosis performance with an AUC of 0.96 (95% confidence interval (CI): 0.95, 0.97), compared with the no-fusion model, the left-right fusion model, and the multi-feature fusion network with only LE image inputs. Our models reached an AUC of 0.90 (95% CI: 0.85, 0.94) on a full-field digital mammograph (FFDM) external dataset (86 patients), and an AUC of 0.92 (95% CI: 0.89, 0.95) on a CEM external dataset (193 patients). Conclusion: The developed multi-feature fusion neural network achieved high performance in CEM image classification and was able to facilitate CEM-based breast cancer diagnosis. Clinical relevance statement: Compared with low-energy images, CEM images have greater sensitivity and similar specificity in malignant breast lesion detection. The multi-feature fusion neural network is a promising computer-aided diagnostic tool for the clinical diagnosis of breast cancer. Key Points: • Deep convolutional neural networks have the potential to facilitate contrast-enhanced mammography-based breast cancer diagnosis. • The multi-feature fusion neural network reaches high accuracies in the classification of contrast-enhanced mammography images. • The developed model is a promising diagnostic tool to facilitate clinical breast cancer diagnosis. [ABSTRACT FROM AUTHOR]

Objectives: To explore the performance of low-dose computed tomography (LDCT) with deep learning reconstruction (DLR) for the improvement of image quality and assessment of lung parenchyma. Methods: Sixty patients underwent chest regular-dose CT (RDCT) followed by LDCT during the same examination. RDCT images were reconstructed with hybrid iterative reconstruction (HIR) and LDCT images were reconstructed with HIR and DLR, both using lung algorithm. Radiation exposure was recorded. Image noise, signal-to-noise ratio, and subjective image quality of normal and abnormal CT features were evaluated and compared using the Kruskal–Wallis test with Bonferroni correction. Results: The effective radiation dose of LDCT was significantly lower than that of RDCT (0.29 ± 0.03 vs 2.05 ± 0.65 mSv, p < 0.001). The mean image noise ± standard deviation was 33.9 ± 4.7, 39.6 ± 4.3, and 31.1 ± 3.2 HU in RDCT, LDCT HIR-Strong, and LDCT DLR-Strong, respectively (p < 0.001). The overall image quality of LDCT DLR-Strong was significantly better than that of LDCT HIR-Strong (p < 0.001) and comparable to that of RDCT (p > 0.05). LDCT DLR-Strong was comparable to RDCT in evaluating solid nodules, increased attenuation, linear opacity, and airway lesions (all p > 0.05). The visualization of subsolid nodules and decreased attenuation was better with DLR than with HIR in LDCT but inferior to RDCT (all p < 0.05). Conclusion: LDCT DLR can effectively reduce image noise and improve image quality. LDCT DLR provides good performance for evaluating pulmonary lesions, except for subsolid nodules and decreased lung attenuation, compared to RDCT-HIR. Clinical relevance statement: The study prospectively evaluated the contribution of DLR applied to chest low-dose CT for image quality improvement and lung parenchyma assessment. DLR can be used to reduce radiation dose and keep image quality for several indications. Key Points: • DLR enables LDCT maintaining image quality even with very low radiation doses. • Chest LDCT with DLR can be used to evaluate lung parenchymal lesions except for subsolid nodules and decreased lung attenuation. • Diagnosis of pulmonary emphysema or subsolid nodules may require higher radiation doses. [ABSTRACT FROM AUTHOR]

Objectives: Existing brain extraction models should be further optimized to provide more information for oncological analysis. We aimed to develop an nnU-Net–based deep learning model for automated brain extraction on contrast-enhanced T1-weighted (T1CE) images in presence of brain tumors. Methods: This is a multi-center, retrospective study involving 920 patients. A total of 720 cases with four types of intracranial tumors from private institutions were collected and set as the training group and the internal test group. Mann–Whitney U test (U test) was used to investigate if the model performance was associated with pathological types and tumor characteristics. Then, the generalization of model was independently tested on public datasets consisting of 100 glioma and 100 vestibular schwannoma cases. Results: In the internal test, the model achieved promising performance with median Dice similarity coefficient (DSC) of 0.989 (interquartile range (IQR), 0.988–0.991), and Hausdorff distance (HD) of 6.403 mm (IQR, 5.099–8.426 mm). U test suggested a slightly descending performance in meningioma and vestibular schwannoma group. The results of U test also suggested that there was a significant difference in peritumoral edema group, with median DSC of 0.990 (IQR, 0.989–0.991, p = 0.002), and median HD of 5.916 mm (IQR, 5.000–8.000 mm, p = 0.049). In the external test, our model also showed to be robust performance, with median DSC of 0.991 (IQR, 0.983–0.998) and HD of 8.972 mm (IQR, 6.164–13.710 mm). Conclusions: For automated processing of MRI neuroimaging data presence of brain tumors, the proposed model can perform brain extraction including important superficial structures for oncological analysis. Clinical relevance statement: The proposed model serves as a radiological tool for image preprocessing in tumor cases, focusing on superficial brain structures, which could streamline the workflow and enhance the efficiency of subsequent radiological assessments. Key Points: • The nnU-Net–based model is capable of segmenting significant superficial structures in brain extraction. • The proposed model showed feasible performance, regardless of pathological types or tumor characteristics. • The model showed generalization in the public datasets. [ABSTRACT FROM AUTHOR]

Objectives: To assess image quality and liver metastasis detection of reduced-dose dual-energy CT (DECT) with deep learning image reconstruction (DLIR) compared to standard-dose single-energy CT (SECT) with DLIR or iterative reconstruction (IR). Methods: In this prospective study, two groups of 40 participants each underwent abdominal contrast-enhanced scans with full-dose SECT (120-kVp images, DLIR and IR algorithms) or reduced-dose DECT (40- to 60-keV virtual monochromatic images [VMIs], DLIR algorithm), with 122 and 106 metastases, respectively. Groups were matched by age, sex ratio, body mass index, and cross-sectional area. Noise power spectrum of liver images and task-based transfer function of metastases were calculated to assess the noise texture and low-contrast resolution. The image noise, signal-to-noise ratios (SNR) of liver and portal vein, liver-to-lesion contrast-to-noise ratio (LLR), lesion conspicuity, lesion detection rate, and the subjective image quality metrics were compared between groups on 1.25-mm reconstructed images. Results: Compared to 120-kVp images with IR, 40- and 50-keV VMIs with DLIR showed similar noise texture and LLR, similar or higher image noise and low-contrast resolution, improved SNR and lesion conspicuity, and similar or better perceptual image quality. When compared to 120-kVp images with DLIR, 50-keV VMIs with DLIR had similar low-contrast resolution, SNR, LLR, lesion conspicuity, and perceptual image quality but lower frequency noise texture and higher image noise. For the detection of hepatic metastases, reduced-dose DECT by 34% maintained observer lesion detection rates. Conclusion: DECT assisted with DLIR enables a 34% dose reduction for detecting hepatic metastases while maintaining comparable perceptual image quality to full-dose SECT. Clinical relevance statement: Reduced-dose dual-energy CT with deep learning image reconstruction is as accurate as standard-dose single-energy CT for the detection of liver metastases and saves more than 30% of the radiation dose. Key Points: • The 40- and 50-keV virtual monochromatic images (VMIs) with deep learning image reconstruction (DLIR) improved lesion conspicuity compared with 120-kVp images with iterative reconstruction while providing similar or better perceptual image quality. • The 50-keV VMIs with DLIR provided comparable perceptual image quality and lesion conspicuity to 120-kVp images with DLIR. • The reduction of radiation by 34% by DLIR in low-keV VMIs is clinically sufficient for detecting low-contrast hepatic metastases. [ABSTRACT FROM AUTHOR]

Objectives: This study aims at a fully automatic pipeline for measuring the magnetic resonance parkinsonism index (MRPI) using deep learning methods. Methods: MRPI is defined as the product of the pons area to the midbrain area ratio and the middle cerebellar peduncle (MCP) width to the superior cerebellar peduncle (SCP) width ratio. In our proposed pipeline, we first used nnUNet to segment the brainstem and then employed HRNet to identify two key boundary points so as to sub-divide the whole brainstem into midbrain and pons. HRNet was also employed to predict the MCP endpoints for measuring the MCP width. Finally, we segmented the SCP on an oblique coronal plane and calculated its width. A total of 400 T1-weighted magnetic resonance images (MRIs) were used to train the nnUNet and HRNet models. Five-fold cross-validation was conducted to evaluate our proposed pipeline's performance on the training dataset. We also evaluated the performance of our proposed pipeline on three external datasets. Two of them had two raters manually measuring the MRPI values, providing insights into automatic accuracy versus inter-rater variability. Results: We obtained average absolute percentage errors (APEs) of 17.21%, 18.17%, 20.83%, and 22.83% on the training dataset and the three external validation datasets, while the inter-rater average APE measured on the first two external validation datasets was 11.31%. Our proposed pipeline significantly improved the MRPI quantification accuracy over a representative state-of-the-art traditional approach (p < 0.001). Conclusion: The proposed automatic pipeline can accurately predict MRPI that is comparable with manual measurement. Clinical relevance statement: This study presents an automated magnetic resonance parkinsonism index measurement tool that can analyze large amounts of magnetic resonance images, enhance the efficiency of Parkinsonism-Plus syndrome diagnosis, reduce the workload of clinicians, and minimize the impact of human factors on diagnosis. Key Points: • We propose an automatic pipeline for measuring the magnetic resonance parkinsonism index from magnetic resonance images. • The effectiveness of the proposed pipeline is successfully established on multiple datasets and comparisons with inter-rater measurements. • The proposed pipeline significantly outperforms a state-of-the-art quantification approach, being much closer to ground truth. [ABSTRACT FROM AUTHOR]

Objectives: To develop and validate a machine learning model based on contrast-enhanced CT to predict the risk of occurrence of the composite clinical endpoint (hospital-based intervention or death) in cirrhotic patients with acute variceal bleeding (AVB). Methods: This retrospective study enrolled 330 cirrhotic patients with AVB between January 2017 and December 2020 from three clinical centers. Contrast-enhanced CT and clinical data were collected. Centers A and B were divided 7:3 into a training set and an internal test set, and center C served as a separate external test set. A well-trained deep learning model was applied to segment the liver and spleen. Then, we extracted 106 original features of the liver and spleen separately based on the Image Biomarker Standardization Initiative (IBSI). We constructed the Liver-Spleen (LS) model based on the selected radiomics features. The performance of LS model was evaluated by receiver operating characteristics and calibration curves. The clinical utility of models was analyzed using decision curve analyses (DCA). Results: The LS model demonstrated the best diagnostic performance in predicting the composite clinical endpoint of AVB in patients with cirrhosis, with an AUC of 0.782 (95% CI 0.650–0.882) and 0.789 (95% CI 0.674–0.878) in the internal test and external test groups, respectively. Calibration curves and DCA indicated the LS model had better performance than traditional clinical scores. Conclusion: A novel machine learning model outperforms previously known clinical risk scores in assessing the prognosis of cirrhotic patients with AVB Clinical relevance statement: The Liver-Spleen model based on contrast-enhanced CT has proven to be a promising tool to predict the prognosis of cirrhotic patients with acute variceal bleeding, which can facilitate decision-making and personalized therapy in clinical practice. Key Points: • The Liver-Spleen machine learning model (LS model) showed good performance in assessing the clinical composite endpoint of cirrhotic patients with AVB (AUC ≥ 0.782, sensitivity ≥ 80%). • The LS model outperformed the clinical scores (AUC ≤ 0.730, sensitivity ≤ 70%) in both internal and external test cohorts. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the effect of super-resolution deep-learning-based reconstruction (SR-DLR) on the image quality of coronary CT angiography (CCTA). Methods: Forty-one patients who underwent CCTA using a 320-row scanner were retrospectively included. Images were reconstructed with hybrid (HIR), model-based iterative reconstruction (MBIR), normal-resolution deep-learning-based reconstruction (NR-DLR), and SR-DLR algorithms. For each image series, image noise, and contrast-to-noise ratio (CNR) at the left main trunk, right coronary artery, left anterior descending artery, and left circumflex artery were quantified. Blooming artifacts from calcified plaques were measured. Image sharpness, noise magnitude, noise texture, edge smoothness, overall quality, and delineation of the coronary wall, calcified and noncalcified plaques, cardiac muscle, and valves were subjectively ranked on a 4-point scale (1, worst; 4, best). The quantitative parameters and subjective scores were compared among the four reconstructions. Task-based image quality was assessed with a physical evaluation phantom. The detectability index for the objects simulating the coronary lumen, calcified plaques, and noncalcified plaques was calculated from the noise power spectrum (NPS) and task-based transfer function (TTF). Results: SR-DLR yielded significantly lower image noise and blooming artifacts with higher CNR than HIR, MBIR, and NR-DLR (all p < 0.001). The best subjective scores for all the evaluation criteria were attained with SR-DLR, with significant differences from all other reconstructions (p < 0.001). In the phantom study, SR-DLR provided the highest NPS average frequency, TTF50%, and detectability for all task objects. Conclusion: SR-DLR considerably improved the subjective and objective image qualities and object detectability of CCTA relative to HIR, MBIR, and NR-DLR algorithms. Clinical relevance statement: The novel SR-DLR algorithm has the potential to facilitate accurate assessment of coronary artery disease on CCTA by providing excellent image quality in terms of spatial resolution, noise characteristics, and object detectability. Key Points: • SR-DLR designed for CCTA improved image sharpness, noise property, and delineation of cardiac structures with reduced blooming artifacts from calcified plaques relative to HIR, MBIR, and NR-DLR. • In the task-based image-quality assessments, SR-DLR yielded better spatial resolution, noise property, and detectability for objects simulating the coronary lumen, coronary calcifications, and noncalcified plaques than other reconstruction techniques. • The image reconstruction times of SR-DLR were shorter than those of MBIR, potentially serving as a novel standard-of-care reconstruction technique for CCTA performed on a 320-row CT scanner. [ABSTRACT FROM AUTHOR]

Objectives: To compare liver metastases changes in CT assessed by radiologists using RECIST 1.1 and with aided simultaneous deep learning–based volumetric lesion changes analysis. Methods: A total of 86 abdominal CT studies from 43 patients (prior and current scans) of abdominal CT scans of patients with 1041 liver metastases (mean = 12.1, std = 11.9, range 1–49) were analyzed. Two radiologists performed readings of all pairs; conventional with RECIST 1.1 and with computer-aided assessment. For computer-aided reading, we used a novel simultaneous multi-channel 3D R2U-Net classifier trained and validated on other scans. The reference was established by having an expert radiologist validate the computed lesion detection and segmentation. The results were then verified and modified as needed by another independent radiologist. The primary outcome measure was the disease status assessment with the conventional and the computer-aided readings with respect to the reference. Results: For conventional and computer-aided reading, there was a difference in disease status classification in 40 out of 86 (46.51%) and 10 out of 86 (27.9%) CT studies with respect to the reference, respectively. Computer-aided reading improved conventional reading in 30 CT studies by 34.5% for two readers (23.2% and 46.51%) with respect to the reference standard. The main reason for the difference between the two readings was lesion volume differences (p = 0.01). Conclusions: AI-based computer-aided analysis of liver metastases may improve the accuracy of the evaluation of neoplastic liver disease status. Clinical relevance statement: AI may aid radiologists to improve the accuracy of evaluating changes over time in metastasis of the liver. Key Points: • Classification of liver metastasis changes improved significantly in one-third of the cases with an automatically generated comprehensive lesion and lesion changes report. • Simultaneous deep learning changes detection and volumetric assessment may improve the evaluation of liver metastases temporal changes potentially improving disease management. [ABSTRACT FROM AUTHOR]

Objective: Based on ultrasound (US) images, this study aimed to detect and quantify calcifications of thyroid nodules, which are regarded as one of the most important features in US diagnosis of thyroid cancer, and to further investigate the value of US calcifications in predicting the risk of lymph node metastasis (LNM) in papillary thyroid cancer (PTC). Methods: Based on the DeepLabv3+ networks, 2992 thyroid nodules in US images were used to train a model to detect thyroid nodules, of which 998 were used to train a model to detect and quantify calcifications. A total of 225 and 146 thyroid nodules obtained from two centers, respectively, were used to test the performance of these models. A logistic regression method was used to construct the predictive models for LNM in PTCs. Results: Calcifications detected by the network model and experienced radiologists had an agreement degree of above 90%. The novel quantitative parameters of US calcification defined in this study showed a significant difference between PTC patients with and without cervical LNM (p < 0.05). The calcification parameters were beneficial to predicting the LNM risk in PTC patients. The LNM prediction model using these calcification parameters combined with patient age and other US nodular features showed a higher specificity and accuracy than the calcification parameters alone. Conclusions: Our models not only detect the calcifications automatically, but also have value in predicting cervical LNM risk of PTC patients, thereby making it possible to investigate the relationship between calcifications and highly invasive PTC in detail. Clinical relevance statement: Due to the high association of US microcalcifications with thyroid cancers, our model will contribute to the differential diagnosis of thyroid nodules in daily practice. Key Points: • We developed an ML-based network model for automatically detecting and quantifying calcifications within thyroid nodules in US images. • Three novel parameters for quantifying US calcifications were defined and verified. • These US calcification parameters showed value in predicting the risk of cervical LNM in PTC patients. [ABSTRACT FROM AUTHOR]

Objectives: This study investigated the technical feasibility of focused view CTA for the selective visualization of stroke related arteries. Methods: A total of 141 CTA examinations for acute ischemic stroke evaluation were divided into a set of 100 cases to train a deep learning algorithm (dubbed "focused view CTA") that selectively extracts brain (including intracranial arteries) and extracranial arteries, and a test set of 41 cases. The visibility of anatomic structures at focused view and unmodified CTA was assessed using the following scoring system: 5 = completely visible, diagnostically sufficient; 4 = nearly completely visible, diagnostically sufficient; 3 = incompletely visible, barely diagnostically sufficient; 2 = hardly visible, diagnostically insufficient; 1 = not visible, diagnostically insufficient. Results: At focused view CTA, median scores for the aortic arch, subclavian arteries, common carotid arteries, C1, C6, and C7 segments of the internal carotid arteries, V4 segment of the vertebral arteries, basilar artery, cerebellum including cerebellar arteries, cerebrum including cerebral arteries, and dural venous sinuses, were all 4. Median scores for the C2 to C5 segments of the internal carotid arteries, and V1 to V3 segments of the vertebral arteries ranged between 3 and 2. At unmodified CTA, median score for all above-mentioned anatomic structures was 5, which was significantly higher (p < 0.0001) than that at focused view CTA. Conclusion: Focused view CTA shows promise for the selective visualization of stroke-related arteries. Further improvements should focus on more accurately visualizing the smaller and tortuous internal carotid and vertebral artery segments close to bone. Clinical relevance: Focused view CTA may speed up image interpretation time for LVO detection and may potentially be used as a tool to study the clinical relevance of incidental findings in future prospective long-term follow-up studies. Key Points: • A deep learning–based algorithm ("focused view CTA") was developed to selectively visualize relevant structures for acute ischemic stroke evaluation at CTA. • The elimination of unrequested anatomic background information was complete in all cases. • Focused view CTA may be used to study the clinical relevance of incidental findings. [ABSTRACT FROM AUTHOR]

Objectives: To develop a deep learning (DL) method that can determine the Liver Imaging Reporting and Data System (LI-RADS) grading of high-risk liver lesions and distinguish hepatocellular carcinoma (HCC) from non-HCC based on multiphase CT. Methods: This retrospective study included 1049 patients with 1082 lesions from two independent hospitals that were pathologically confirmed as HCC or non-HCC. All patients underwent a four-phase CT imaging protocol. All lesions were graded (LR 4/5/M) by radiologists and divided into an internal (n = 886) and external cohort (n = 196) based on the examination date. In the internal cohort, Swin-Transformer based on different CT protocols were trained and tested for their ability to LI-RADS grading and distinguish HCC from non-HCC, and then validated in the external cohort. We further developed a combined model with the optimal protocol and clinical information for distinguishing HCC from non-HCC. Results: In the test and external validation cohorts, the three-phase protocol without pre-contrast showed κ values of 0.6094 and 0.4845 for LI-RADS grading, and its accuracy was 0.8371 and 0.8061, while the accuracy of the radiologist was 0.8596 and 0.8622, respectively. The AUCs in distinguishing HCC from non-HCC were 0.865 and 0.715 in the test and external validation cohorts, while those of the combined model were 0.887 and 0.808. Conclusion: The Swin-Transformer based on three-phase CT protocol without pre-contrast could feasibly simplify LI-RADS grading and distinguish HCC from non-HCC. Furthermore, the DL model have the potential in accurately distinguishing HCC from non-HCC using imaging and highly characteristic clinical data as inputs. Clinical relevance statement: The application of deep learning model for multiphase CT has proven to improve the clinical applicability of the Liver Imaging Reporting and Data System and provide support to optimize the management of patients with liver diseases. Key Points: • Deep learning (DL) simplifies LI-RADS grading and helps distinguish hepatocellular carcinoma (HCC) from non-HCC. • The Swin-Transformer based on the three-phase CT protocol without pre-contrast outperformed other CT protocols. • The Swin-Transformer provide help in distinguishing HCC from non-HCC by using CT and characteristic clinical information as inputs. [ABSTRACT FROM AUTHOR]

Objectives: To present software for automated adipose tissue quantification of abdominal magnetic resonance imaging (MRI) data using fully convolutional networks (FCN) and to evaluate its overall performance—accuracy, reliability, processing effort, and time—in comparison with an interactive reference method. Materials and methods: Single-center data of patients with obesity were analyzed retrospectively with institutional review board approval. Ground truth for subcutaneous (SAT) and visceral adipose tissue (VAT) segmentation was provided by semiautomated region-of-interest (ROI) histogram thresholding of 331 full abdominal image series. Automated analyses were implemented using UNet-based FCN architectures and data augmentation techniques. Cross-validation was performed on hold-out data using standard similarity and error measures. Results: The FCN models reached Dice coefficients of up to 0.954 for SAT and 0.889 for VAT segmentation during cross-validation. Volumetric SAT (VAT) assessment resulted in a Pearson correlation coefficient of 0.999 (0.997), relative bias of 0.7% (0.8%), and standard deviation of 1.2% (3.1%). Intraclass correlation (coefficient of variation) within the same cohort was 0.999 (1.4%) for SAT and 0.996 (3.1%) for VAT. Conclusion: The presented methods for automated adipose-tissue quantification showed substantial improvements over common semiautomated approaches (no reader dependence, less effort) and thus provide a promising option for adipose tissue quantification. Clinical relevance statement: Deep learning techniques will likely enable image-based body composition analyses on a routine basis. The presented fully convolutional network models are well suited for full abdominopelvic adipose tissue quantification in patients with obesity. Key Points: • This work compared the performance of different deep-learning approaches for adipose tissue quantification in patients with obesity. • Supervised deep learning–based methods using fully convolutional networks were suited best. • Measures of accuracy were equal to or better than the operator-driven approach. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the performance of automatic deep learning (DL) algorithm for size, mass, and volume measurements in predicting prognosis of lung adenocarcinoma (LUAD) and compared with manual measurements. Methods: A total of 542 patients with clinical stage 0-I peripheral LUAD and with preoperative CT data of 1-mm slice thickness were included. Maximal solid size on axial image (MSSA) was evaluated by two chest radiologists. MSSA, volume of solid component (SV), and mass of solid component (SM) were evaluated by DL. Consolidation-to-tumor ratios (CTRs) were calculated. For ground glass nodules (GGNs), solid parts were extracted with different density level thresholds. The prognosis prediction efficacy of DL was compared with that of manual measurements. Multivariate Cox proportional hazards model was used to find independent risk factors. Results: The prognosis prediction efficacy of T-staging (TS) measured by radiologists was inferior to that of DL. For GGNs, MSSA-based CTR measured by radiologists (RMSSA%) could not stratify RFS and OS risk, whereas measured by DL using 0HU (2D−AIMSSA0HU%) could by using different cutoffs. SM and SV measured by DL using 0 HU (AISM0HU% and AISV0HU%) could effectively stratify the survival risk regardless of different cutoffs and were superior to 2D−AIMSSA0HU%. AISM0HU% and AISV0HU% were independent risk factors. Conclusion: DL algorithm can replace human for more accurate T-staging of LUAD. For GGNs, 2D−AIMSSA0HU% could predict prognosis rather than RMSSA%. The prediction efficacy of AISM0HU% and AISV0HU% was more accurate than of 2D−AIMSSA0HU% and both were independent risk factors. Clinical relevance statement: Deep learning algorithm could replace human for size measurements and could better stratify prognosis than manual measurements in patients with lung adenocarcinoma. Key Points: • Deep learning (DL) algorithm could replace human for size measurements and could better stratify prognosis than manual measurements in patients with lung adenocarcinoma (LUAD). • For GGNs, maximal solid size on axial image (MSSA)–based consolidation-to-tumor ratio (CTR) measured by DL using 0 HU could stratify survival risk than that measured by radiologists. • The prediction efficacy of mass- and volume-based CTRs measured by DL using 0 HU was more accurate than of MSSA-based CTR and both were independent risk factors. [ABSTRACT FROM AUTHOR]

Objective: We propose a deep learning-guided approach to generate voxel-based absorbed dose maps from whole-body CT acquisitions. Methods: The voxel-wise dose maps corresponding to each source position/angle were calculated using Monte Carlo (MC) simulations considering patient- and scanner-specific characteristics (SP_MC). The dose distribution in a uniform cylinder was computed through MC calculations (SP_uniform). The density map and SP_uniform dose maps were fed into a residual deep neural network (DNN) to predict SP_MC through an image regression task. The whole-body dose maps reconstructed by the DNN and MC were compared in the 11 test cases scanned with two tube voltages through transfer learning with/without tube current modulation (TCM). The voxel-wise and organ-wise dose evaluations, such as mean error (ME, mGy), mean absolute error (MAE, mGy), relative error (RE, %), and relative absolute error (RAE, %), were performed. Results: The model performance for the 120 kVp and TCM test set in terms of ME, MAE, RE, and RAE voxel-wise parameters was − 0.0302 ± 0.0244 mGy, 0.0854 ± 0.0279 mGy, − 1.13 ± 1.41%, and 7.17 ± 0.44%, respectively. The organ-wise errors for 120 kVp and TCM scenario averaged over all segmented organs in terms of ME, MAE, RE, and RAE were − 0.144 ± 0.342 mGy, and 0.23 ± 0.28 mGy, − 1.11 ± 2.90%, 2.34 ± 2.03%, respectively. Conclusion: Our proposed deep learning model is able to generate voxel-level dose maps from a whole-body CT scan with reasonable accuracy suitable for organ-level absorbed dose estimation. Clinical relevance statement: We proposed a novel method for voxel dose map calculation using deep neural networks. This work is clinically relevant since accurate dose calculation for patients can be carried out within acceptable computational time compared to lengthy Monte Carlo calculations. Key Points: • We proposed a deep neural network approach as an alternative to Monte Carlo dose calculation. • Our proposed deep learning model is able to generate voxel-level dose maps from a whole-body CT scan with reasonable accuracy, suitable for organ-level dose estimation. • By generating a dose distribution from a single source position, our model can generate accurate and personalized dose maps for a wide range of acquisition parameters. [ABSTRACT FROM AUTHOR]

Objectives: This study aims to develop a deep learning algorithm, Pneumonia-Plus, based on computed tomography (CT) images for accurate classification of bacterial, fungal, and viral pneumonia. Methods: A total of 2763 participants with chest CT images and definite pathogen diagnosis were included to train and validate an algorithm. Pneumonia-Plus was prospectively tested on a nonoverlapping dataset of 173 patients. The algorithm's performance in classifying three types of pneumonia was compared to that of three radiologists using the McNemar test to verify its clinical usefulness. Results: Among the 173 patients, area under the curve (AUC) values for viral, fungal, and bacterial pneumonia were 0.816, 0.715, and 0.934, respectively. Viral pneumonia was accurately classified with sensitivity, specificity, and accuracy of 0.847, 0.919, and 0.873. Three radiologists also showed good consistency with Pneumonia-Plus. The AUC values of bacterial, fungal, and viral pneumonia were 0.480, 0.541, and 0.580 (radiologist 1: 3-year experience); 0.637, 0.693, and 0.730 (radiologist 2: 7-year experience); and 0.734, 0.757, and 0.847 (radiologist 3: 12-year experience), respectively. The McNemar test results for sensitivity showed that the diagnostic performance of the algorithm was significantly better than that of radiologist 1 and radiologist 2 (p < 0.05) in differentiating bacterial and viral pneumonia. Radiologist 3 had a higher diagnostic accuracy than the algorithm. Conclusions: The Pneumonia-Plus algorithm is used to differentiate between bacterial, fungal, and viral pneumonia, which has reached the level of an attending radiologist and reduce the risk of misdiagnosis. The Pneumonia-Plus is important for appropriate treatment and avoiding the use of unnecessary antibiotics, and provide timely information to guide clinical decision-making and improve patient outcomes. Clinical relevance statement: Pneumonia-Plus algorithm could assist in the accurate classification of pneumonia based on CT images, which has great clinical value in avoiding the use of unnecessary antibiotics, and providing timely information to guide clinical decision-making and improve patient outcomes. Key Points: • The Pneumonia-Plus algorithm trained from data collected from multiple centers can accurately identify bacterial, fungal, and viral pneumonia. • The Pneumonia-Plus algorithm was found to have better sensitivity in classifying viral and bacterial pneumonia in comparison to radiologist 1 (5-year experience) and radiologist 2 (7-year experience). • The Pneumonia-Plus algorithm is used to differentiate between bacterial, fungal, and viral pneumonia, which has reached the level of an attending radiologist. [ABSTRACT FROM AUTHOR]

Objectives: To develop and validate a fully automated AI system to extract standard planes, assess early gestational weeks, and compare the performance of the developed system to sonographers. Methods: In this three-center retrospective study, 214 consecutive pregnant women that underwent transvaginal ultrasounds between January and December 2018 were selected. Their ultrasound videos were automatically split into 38,941 frames using a particular program. First, an optimal deep-learning classifier was selected to extract the standard planes with key anatomical structures from the ultrasound frames. Second, an optimal segmentation model was selected to outline gestational sacs. Third, novel biometry was used to measure, select the largest gestational sac in the same video, and assess gestational weeks automatically. Finally, an independent test set was used to compare the performance of the system with that of sonographers. The outcomes were analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and mean similarity between two samples (mDice). Results: The standard planes were extracted with an AUC of 0.975, a sensitivity of 0.961, and a specificity of 0.979. The gestational sacs' contours were segmented with a mDice of 0.974 (error less than 2 pixels). The comparison showed that the relative error of the tool in assessing gestational weeks was 12.44% and 6.92% lower and faster (min, 0.17 vs. 16.6 and 12.63) than that of the intermediate and senior sonographers, respectively. Conclusions: This proposed end-to-end tool allows automatic assessment of gestational weeks in early pregnancy and may reduce manual analysis time and measurement errors. Clinical relevance statement: The fully automated tool achieved high accuracy showing its potential to optimize the increasingly scarce resources of sonographers. Explainable predictions can assist in their confidence in assessing gestational weeks and provide a reliable basis for managing early pregnancy cases. Key Points: • The end-to-end pipeline enabled automatic identification of the standard plane containing the gestational sac in an ultrasound video, as well as segmentation of the sac contour, automatic multi-angle measurements, and the selection of the sac with the largest mean internal diameter to calculate the early gestational week. • This fully automated tool combining deep learning and intelligent biometry may assist the sonographer in assessing the early gestational week, increasing accuracy and reducing the analyzing time, thereby reducing observer dependence. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate a fully automatic deep learning system to detect and segment clinically significant prostate cancer (csPCa) on same-vendor prostate MRI from two different institutions not contributing to training of the system. Materials and methods: In this retrospective study, a previously bi-institutionally validated deep learning system (UNETM) was applied to bi-parametric prostate MRI data from one external institution (A), a PI-RADS distribution-matched internal cohort (B), and a csPCa stratified subset of single-institution external public challenge data (C). csPCa was defined as ISUP Grade Group ≥ 2 determined from combined targeted and extended systematic MRI/transrectal US-fusion biopsy. Performance of UNETM was evaluated by comparing ROC AUC and specificity at typical PI-RADS sensitivity levels. Lesion-level analysis between UNETM segmentations and radiologist-delineated segmentations was performed using Dice coefficient, free-response operating characteristic (FROC), and weighted alternative (waFROC). The influence of using different diffusion sequences was analyzed in cohort A. Results: In 250/250/140 exams in cohorts A/B/C, differences in ROC AUC were insignificant with 0.80 (95% CI: 0.74–0.85)/0.87 (95% CI: 0.83–0.92)/0.82 (95% CI: 0.75–0.89). At sensitivities of 95% and 90%, UNETM achieved specificity of 30%/50% in A, 44%/71% in B, and 43%/49% in C, respectively. Dice coefficient of UNETM and radiologist-delineated lesions was 0.36 in A and 0.49 in B. The waFROC AUC was 0.67 (95% CI: 0.60–0.83) in A and 0.7 (95% CI: 0.64–0.78) in B. UNETM performed marginally better on readout-segmented than on single-shot echo-planar-imaging. Conclusion: For same-vendor examinations, deep learning provided comparable discrimination of csPCa and non-csPCa lesions and examinations between local and two independent external data sets, demonstrating the applicability of the system to institutions not participating in model training. Clinical relevance statement: A previously bi-institutionally validated fully automatic deep learning system maintained acceptable exam-level diagnostic performance in two independent external data sets, indicating the potential of deploying AI models without retraining or fine-tuning, and corroborating evidence that AI models extract a substantial amount of transferable domain knowledge about MRI-based prostate cancer assessment. Key Points: • A previously bi-institutionally validated fully automatic deep learning system maintained acceptable exam-level diagnostic performance in two independent external data sets. • Lesion detection performance and segmentation congruence was similar on the institutional and an external data set, as measured by the weighted alternative FROC AUC and Dice coefficient. • Although the system generalized to two external institutions without re-training, achieving expected sensitivity and specificity levels using the deep learning system requires probability thresholds to be adjusted, underlining the importance of institution-specific calibration and quality control. [ABSTRACT FROM AUTHOR]

Objectives: Siamese neural networks (SNN) were used to classify the presence of radiopaque beads as part of a colonic transit time study (CTS). The SNN output was then used as a feature in a time series model to predict progression through a CTS. Methods: This retrospective study included all patients undergoing a CTS in a single institution from 2010 to 2020. Data were partitioned in an 80/20 Train/Test split. Deep learning models based on a SNN architecture were trained and tested to classify images according to the presence, absence, and number of radiopaque beads and to output the Euclidean distance between the feature representations of the input images. Time series models were used to predict the total duration of the study. Results: In total, 568 images of 229 patients (143, 62% female, mean age 57) patients were included. For the classification of the presence of beads, the best performing model (Siamese DenseNET trained with a contrastive loss with unfrozen weights) achieved an accuracy, precision, and recall of 0.988, 0.986, and 1. A Gaussian process regressor (GPR) trained on the outputs of the SNN outperformed both GPR using only the number of beads and basic statistical exponential curve fitting with MAE of 0.9 days compared to 2.3 and 6.3 days (p < 0.05) respectively. Conclusions: SNNs perform well at the identification of radiopaque beads in CTS. For time series prediction our methods were superior at identifying progression through the time series compared to statistical models, enabling more accurate personalised predictions. Clinical relevance statement: Our radiologic time series model has potential clinical application in use cases where change assessment is critical (e.g. nodule surveillance, cancer treatment response, and screening programmes) by quantifying change and using it to make more personalised predictions. Key Points: • Time series methods have improved but application to radiology lags behind computer vision. Colonic transit studies are a simple radiologic time series measuring function through serial radiographs. • We successfully employed a Siamese neural network (SNN) to compare between radiographs at different points in time and then used the output of SNN as a feature in a Gaussian process regression model to predict progression through the time series. • This novel use of features derived from a neural network on medical imaging data to predict progression has potential clinical application in more complex use cases where change assessment is critical such as in oncologic imaging, monitoring for treatment response, and screening programmes. [ABSTRACT FROM AUTHOR]

Objective: To assess the prognostic significance of automatically quantified interstitial lung abnormality (ILA) according to the definition by the Fleischner Society in patients with resectable non-small-cell lung cancer (NSCLC). Methods: Patients who underwent lobectomy or pneumonectomy for NSCLC between January 2015 and December 2019 were retrospectively included. Preoperative CT scans were analyzed using the commercially available deep-learning-based automated quantification software for ILA. According to quantified results and the definition by the Fleischner Society and multidisciplinary discussion, patients were divided into normal, ILA, and interstitial lung disease (ILD) groups. Results: Of the 1524 patients, 87 (5.7%) and 20 (1.3%) patients had ILA and ILD, respectively. Both ILA (HR, 1.81; 95% CI: 1.25–2.61; p =.002) and ILD (HR, 5.26; 95% CI: 2.99–9.24; p <.001) groups had poor recurrence-free survival (RFS). Overall survival (OS) decreased (HR 2.13 [95% CI: 1.27–3.58; p =.004] for the ILA group and 7.20 [95% CI: 3.80–13.62, p <.001] for the ILD group) as the disease severity increased. Both quantified fibrotic and non-fibrotic ILA components were associated with poor RFS (HR, 1.57; 95% CI: 1.12–2.21; p =.009; and HR, 1.11; 95% CI: 1.01–1.23; p =.03) and OS (HR, 1.59; 95% CI: 1.06–2.37; p =.02; and HR, 1.17; 95% CI: 1.03–1.33; and p =.01) in normal and ILA groups. Conclusions: The automated CT quantification of ILA based on the definition by the Fleischner Society predicts outcomes of patients with resectable lung cancer based on the disease category and quantified fibrotic and non-fibrotic ILA components. Clinical relevance statement: Quantitative CT assessment of ILA provides prognostic information for lung cancer patients after surgery, which can help in considering active surveillance for recurrence, especially in those with a larger extent of quantified ILA. Key Points: • Of the 1524 patients with resectable lung cancer, 1417 (93.0%) patients were categorized as normal, 87 (5.7%) as interstitial lung abnormality (ILA), and 20 (1.3%) as interstitial lung disease (ILD). • Both ILA and ILD groups were associated with poor recurrence-free survival (hazard ratio [HR], 1.81, p =.002; HR, 5.26, p <.001, respectively) and overall survival (HR, 2.13; p =.004; HR, 7.20; p <.001). • Both quantified fibrotic and non-fibrotic ILA components were associated with recurrence-free survival and overall survival in normal and ILA groups. [ABSTRACT FROM AUTHOR]

Objectives: To determine the clinical feasibility of T2-weighted turbo spin-echo (T2-TSE) imaging with deep learning reconstruction (DLR) in female pelvic MRI compared with conventional T2 TSE in terms of image quality and scan time. Methods: Between May 2021 and September 2021, 52 women (mean age, 44 years ± 12) who underwent 3-T pelvic MRI with additional T2-TSE using a DLR algorithm were included in this single-center prospective study with patient's informed consents. Conventional, DLR, and DLR T2-TSE images with reduced scan times were independently assessed and compared by four radiologists. The overall image quality, differentiation of anatomic details, lesion conspicuity, and artifacts were evaluated using a 5-point scale. Inter-observer agreement of the qualitative scores was compared and reader protocol preferences were then evaluated. Results: In the qualitative analysis of all readers, fast DLR T2-TSE showed significantly better overall image quality, differentiation of anatomic regions, lesion conspicuity, and lesser artifacts than conventional T2-TSE and DLR T2-TSE, despite approximately 50% reduction in scan time (all p < 0.05). The inter-reader agreement for the qualitative analysis was moderate to good. All readers preferred DLR over conventional T2-TSE regardless of scan time and preferred fast DLR T2-TSE (57.7–78.8%), except for one who preferred DLR over fast DLR T2-TSE (53.8% vs. 46.1%). Conclusion: In female pelvic MRI, image quality and accelerated image acquisition for T2-TSE can be significantly improved by using DLR compared to conventional T2-TSE. Fast DLR T2-TSE was non-inferior to DLR T2-TSE in terms of reader preference and image quality. Clinical relevance statement: DLR of T2-TSE in female pelvic MRI enables fast imaging along with maintaining optimal image quality compared with parallel imaging-based conventional T2-TSE. Key Points: • Conventional T2 turbo spin-echo based on parallel imaging has limitations for accelerated image acquisition while maintaining good image quality. • Deep learning image reconstruction showed better image quality in both images obtained using the same or accelerated image acquisition parameters compared with conventional T2 turbo spin-echo in female pelvic MRI. • Deep learning image reconstruction enables accelerated image acquisition while maintaining good image quality in the T2-TSE of female pelvic MRI. [ABSTRACT FROM AUTHOR]

Objective: To conduct a comprehensive bibliometric analysis of artificial intelligence (AI) and its subfields as well as radiomics in Radiology, Nuclear Medicine, and Medical Imaging (RNMMI). Methods: Web of Science was queried for relevant publications in RNMMI and medicine along with their associated data from 2000 to 2021. Bibliometric techniques utilised were co-occurrence, co-authorship, citation burst, and thematic evolution analyses. Growth rate and doubling time were also estimated using log-linear regression analyses. Results: According to the number of publications, RNMMI (11,209; 19.8%) was the most prominent category in medicine (56,734). USA (44.6%) and China (23.1%) were the two most productive and collaborative countries. USA and Germany experienced the strongest citation bursts. Thematic evolution has recently exhibited a significant shift toward deep learning. In all analyses, the annual number of publications and citations demonstrated exponential growth, with deep learning-based publications exhibiting the most prominent growth pattern. Estimated continuous growth rate, annual growth rate, and doubling time of the AI and machine learning publications in RNMMI were 26.1% (95% confidence interval [CI], 12.0–40.2%), 29.8% (95% CI, 12.7–49.5%), and 2.7 years (95% CI, 1.7–5.8), respectively. In the sensitivity analysis using data from the last 5 and 10 years, these estimates ranged from 47.6 to 51.1%, 61.0 to 66.7%, and 1.4 to 1.5 years. Conclusion: This study provides an overview of AI and radiomics research conducted mainly in RNMMI. These results may assist researchers, practitioners, policymakers, and organisations in gaining a better understanding of both the evolution of these fields and the importance of supporting (e.g., financial) these research activities. Key Points: • In terms of the number of publications on AI and ML, Radiology, Nuclear Medicine, and Medical Imaging was the most prominent category compared to the other categories related to medicine (e.g., Health Policy & Services, Surgery). • All evaluated analyses (i.e., AI, its subfields, and radiomics), based on the annual number of publications and citations, demonstrated exponential growth, with decreasing doubling time, which indicates increasing interest from researchers, journals, and, in turn, the medical imaging community. • The most prominent growth pattern was observed in deep learning-based publications. However, the further thematic analysis demonstrated that deep learning has been underdeveloped but highly relevant to the medical imaging community. [ABSTRACT FROM AUTHOR]

Objectives: To develop an automated deep-learning algorithm for detection and 3D segmentation of incidental bone lesions in maxillofacial CBCT scans. Methods: The dataset included 82 cone beam CT (CBCT) scans, 41 with histologically confirmed benign bone lesions (BL) and 41 control scans (without lesions), obtained using three CBCT devices with diverse imaging protocols. Lesions were marked in all axial slices by experienced maxillofacial radiologists. All cases were divided into sub-datasets: training (20,214 axial images), validation (4530 axial images), and testing (6795 axial images). A Mask-RCNN algorithm segmented the bone lesions in each axial slice. Analysis of sequential slices was used for improving the Mask-RCNN performance and classifying each CBCT scan as containing bone lesions or not. Finally, the algorithm generated 3D segmentations of the lesions and calculated their volumes. Results: The algorithm correctly classified all CBCT cases as containing bone lesions or not, with an accuracy of 100%. The algorithm detected the bone lesion in axial images with high sensitivity (95.9%) and high precision (98.9%) with an average dice coefficient of 83.5%. Conclusions: The developed algorithm detected and segmented bone lesions in CBCT scans with high accuracy and may serve as a computerized tool for detecting incidental bone lesions in CBCT imaging. Clinical relevance: Our novel deep-learning algorithm detects incidental hypodense bone lesions in cone beam CT scans, using various imaging devices and protocols. This algorithm may reduce patients' morbidity and mortality, particularly since currently, cone beam CT interpretation is not always preformed. Key Points: • A deep learning algorithm was developed for automatic detection and 3D segmentation of various maxillofacial bone lesions in CBCT scans, irrespective of the CBCT device or the scanning protocol. • The developed algorithm can detect incidental jaw lesions with high accuracy, generates a 3D segmentation of the lesion, and calculates the lesion volume. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the image quality of the 3D hybrid profile order technique and deep-learning-based reconstruction (DLR) for 3D magnetic resonance cholangiopancreatography (MRCP) within a single breath-hold (BH) at 3 T magnetic resonance imaging (MRI). Methods: This retrospective study included 32 patients with biliary and pancreatic disorders. BH images were reconstructed with and without DLR. The signal-to-noise ratio (SNR), contrast, contrast-to-noise ratio (CNR) between the common bile duct (CBD) and periductal tissues, and full width at half maximum (FWHM) of CBD on 3D-MRCP were evaluated quantitatively. Two radiologists scored image noise, contrast, artifacts, blur, and overall image quality of the three image types using a 4-point scale. Quantitative and qualitative scores were compared using the Friedman test and post hoc Nemenyi test. Results: The SNR and CNR were not significantly different when under respiratory gating- and BH-MRCP without DLR. However, they were significantly higher under BH with DLR than under respiratory gating (SNR, p = 0.013; CNR, p = 0.027). The contrast and FWHM of MRCP under BH with and without DLR were lower than those under respiratory gating (contrast, p < 0.001; FWHM, p = 0.015). Qualitative scores for noise, blur, and overall image quality were higher under BH with DLR than those under respiratory gating (blur, p = 0.003; overall, p = 0.008). Conclusions: The combination of the 3D hybrid profile order technique and DLR is useful for MRCP within a single BH and does not lead to the deterioration of image quality and space resolution at 3 T MRI. Clinical relevance statement: Considering its advantages, this sequence might become the standard protocol for MRCP in clinical practice, at least at 3.0 T. Key Points: • The 3D hybrid profile order can achieve MRCP within a single breath-hold without a decrease in spatial resolution. • The DLR significantly improved the CNR and SNR of BH-MRCP. • The 3D hybrid profile order technique with DLR reduces the deterioration of image quality in MRCP within a single breath-hold. [ABSTRACT FROM AUTHOR]

A recent study published in European Radiology explores the use of deep learning models and natural language processing (NLP) to accurately differentiate between high-grade gliomas (HGGs) and brain metastasis based on MRI reports. The study compared various deep learning models and found that a convolutional neural network (CNN) was the most effective in classifying the two conditions. The NLP algorithm demonstrated its ability to identify critical keywords that played a significant role in classifying the radiological reports. While the study has limitations, such as a small sample size and lack of external validation, the findings highlight the potential of DL-based NLP models in improving diagnostic accuracy and supporting radiologists in this challenging task. [Extracted from the article]

Objectives: To develop an artificial intelligence (AI) system for predicting cervical lymph node metastasis (CLNM) preoperatively in patients with papillary thyroid cancer (PTC) based on CT images. Methods: This multicenter retrospective study included the preoperative CT of PTC patients who were divided into the development, internal, and external test sets. The region of interest of the primary tumor was outlined manually on the CT images by a radiologist who has eight years of experience. With the use of the CT images and lesions masks, the deep learning (DL) signature was developed by the DenseNet combined with convolutional block attention module. One-way analysis of variance and least absolute shrinkage and selection operator were used to select features, and a support vector machine was used to construct the radiomics signature. Random forest was used to combine the DL, radiomics, and clinical signature to perform the final prediction. The receiver operating characteristic curve, sensitivity, specificity, and accuracy were used by two radiologists (R1 and R2) to evaluate and compare the AI system. Results: For the internal and external test set, the AI system achieved excellent performance with AUCs of 0.84 and 0.81, higher than the DL (p =.03,.82), radiomics (p <.001,.04), and clinical model (p <.001,.006). With the aid of the AI system, the specificities of radiologists were improved by 9% and 15% for R1 and 13% and 9% for R2, respectively. Conclusions: The AI system can help predict CLNM in patients with PTC, and the radiologists' performance improved with AI assistance. Clinical relevance statement: This study developed an AI system for preoperative prediction of CLNM in PTC patients based on CT images, and the radiologists' performance improved with AI assistance, which could improve the effectiveness of individual clinical decision-making. Key Points: • This multicenter retrospective study showed that the preoperative CT image-based AI system has the potential for predicting the CLNM of PTC. • The AI system was superior to the radiomics and clinical model in predicting the CLNM of PTC. • The radiologists' diagnostic performance improved when they received the AI system assistance. [ABSTRACT FROM AUTHOR]

Objectives: Using contrast-enhanced computed tomography (CECT) and deep learning technology to develop a deep learning radiomics nomogram (DLRN) to preoperative predict risk status of patients with thymic epithelial tumors (TETs). Methods: Between October 2008 and May 2020, 257 consecutive patients with surgically and pathologically confirmed TETs were enrolled from three medical centers. We extracted deep learning features from all lesions using a transformer-based convolutional neural network and created a deep learning signature (DLS) using selector operator regression and least absolute shrinkage. The predictive capability of a DLRN incorporating clinical characteristics, subjective CT findings and DLS was evaluated by the area under the curve (AUC) of a receiver operating characteristic curve. Results: To construct a DLS, 25 deep learning features with non-zero coefficients were selected from 116 low-risk TETs (subtypes A, AB, and B1) and 141 high-risk TETs (subtypes B2, B3, and C). The combination of subjective CT features such as infiltration and DLS demonstrated the best performance in differentiating TETs risk status. The AUCs in the training, internal validation, external validation 1 and 2 cohorts were 0.959 (95% confidence interval [CI]: 0.924–0.993), 0.868 (95% CI: 0.765–0.970), 0.846 (95% CI: 0.750–0.942), and 0.846 (95% CI: 0.735–0.957), respectively. The DeLong test and decision in curve analysis revealed that the DLRN was the most predictive and clinically useful model. Conclusions: The DLRN comprised of CECT-derived DLS and subjective CT findings showed a high performance in predicting risk status of patients with TETs. Clinical relevance statement: Accurate risk status assessment of thymic epithelial tumors (TETs) may aid in determining whether preoperative neoadjuvant treatment is necessary. A deep learning radiomics nomogram incorporating enhancement CT-based deep learning features, clinical characteristics, and subjective CT findings has the potential to predict the histologic subtypes of TETs, which can facilitate decision-making and personalized therapy in clinical practice. Key Points: • A non-invasive diagnostic method that can predict the pathological risk status may be useful for pretreatment stratification and prognostic evaluation in TET patients. • DLRN demonstrated superior performance in differentiating the risk status of TETs when compared to the deep learning signature, radiomics signature, or clinical model. • The DeLong test and decision in curve analysis revealed that the DLRN was the most predictive and clinically useful in differentiating the risk status of TETs. [ABSTRACT FROM AUTHOR]

Objective: The clinical ability of radiomics to predict intracranial aneurysm rupture risk remains unexplored. This study aims to investigate the potential uses of radiomics and explore whether deep learning (DL) algorithms outperform traditional statistical methods in predicting aneurysm rupture risk. Methods: This retrospective study included 1740 patients with 1809 intracranial aneurysms confirmed by digital subtraction angiography at two hospitals in China from January 2014 to December 2018. We randomly divided the dataset (hospital 1) into training (80%) and internal validation (20%). External validation was performed using independent data collected from hospital 2. The prediction models were developed based on clinical, aneurysm morphological, and radiomics parameters by logistic regression (LR). Additionally, the DL model for predicting aneurysm rupture risk using integration parameters was developed and compared with other models. Results: The AUCs of LR models A (clinical), B (morphological), and C (radiomics) were 0.678, 0.708, and 0.738, respectively (all p < 0.05). The AUCs of the combined feature models D (clinical and morphological), E (clinical and radiomics), and F (clinical, morphological, and radiomics) were 0.771, 0.839, and 0.849, respectively. The DL model (AUC = 0.929) outperformed the machine learning (ML) (AUC = 0.878) and the LR models (AUC = 0.849). Also, the DL model has shown good performance in the external validation datasets (AUC: 0.876 vs 0.842 vs 0.823, respectively). Conclusion: Radiomics signatures play an important role in predicting aneurysm rupture risk. DL methods outperformed conventional statistical methods in prediction models for the rupture risk of unruptured intracranial aneurysms, integrating clinical, aneurysm morphological, and radiomics parameters. Key Points: • Radiomics parameters are associated with the rupture risk of intracranial aneurysms. • The prediction model based on integrating parameters in the deep learning model was significantly better than a conventional model. • The radiomics signature proposed in this study could guide clinicians in selecting appropriate patients for preventive treatment. [ABSTRACT FROM AUTHOR]

Objective: Breast arterial calcifications (BAC) are a sex-specific cardiovascular disease biomarker that might improve cardiovascular risk stratification in women. We implemented a deep convolutional neural network for automatic BAC detection and quantification. Methods: In this retrospective study, four readers labelled four-view mammograms as BAC positive (BAC+) or BAC negative (BAC−) at image level. Starting from a pretrained VGG16 model, we trained a convolutional neural network to discriminate BAC+ and BAC− mammograms. Accuracy, F1 score, and area under the receiver operating characteristic curve (AUC-ROC) were used to assess the diagnostic performance. Predictions of calcified areas were generated using the generalized gradient-weighted class activation mapping (Grad-CAM++) method, and their correlation with manual measurement of BAC length in a subset of cases was assessed using Spearman ρ. Results: A total 1493 women (198 BAC+) with a median age of 59 years (interquartile range 52–68) were included and partitioned in a training set of 410 cases (1640 views, 398 BAC+), validation set of 222 cases (888 views, 89 BAC+), and test set of 229 cases (916 views, 94 BAC+). The accuracy, F1 score, and AUC-ROC were 0.94, 0.86, and 0.98 in the training set; 0.96, 0.74, and 0.96 in the validation set; and 0.97, 0.80, and 0.95 in the test set, respectively. In 112 analyzed views, the Grad-CAM++ predictions displayed a strong correlation with BAC measured length (ρ = 0.88, p < 0.001). Conclusion: Our model showed promising performances in BAC detection and in quantification of BAC burden, showing a strong correlation with manual measurements. Clinical relevance statement: Integrating our model to clinical practice could improve BAC reporting without increasing clinical workload, facilitating large-scale studies on the impact of BAC as a biomarker of cardiovascular risk, raising awareness on women's cardiovascular health, and leveraging mammographic screening. Key Points: • We implemented a deep convolutional neural network (CNN) for BAC detection and quantification. • Our CNN had an area under the receiving operator curve of 0.95 for BAC detection in the test set composed of 916 views, 94 of which were BAC+. • Furthermore, our CNN showed a strong correlation with manual BAC measurements (ρ = 0.88) in a set of 112 views. [ABSTRACT FROM AUTHOR]