Search

Thus, the aim of this study is to evaluate the performance of deep learning imaging reconstruction (DLIR) algorithm in different image sets derived from carotid dual-energy computed tomography angiography (DECTA) for evaluating cervical intervertebral discs (IVDs) and compare them with those reconstructed using adaptive statistical iterative reconstruction-Veo (ASiR-V). Forty-two patients who underwent carotid DECTA were included in this retrospective analysis. Three types of image sets (70 keV, water-iodine, and water-calcium) were reconstructed using 50% ASiR-V and DLIR at medium and high levels (DLIR-M and DLIR-H). The diagnostic acceptability and conspicuity of IVDs were assessed using a 5-point scale. Hounsfield Units (HU) and water concentration (WC) values of the IVDs; standard deviation (SD); and coefficient of variation (CV) were calculated. Measurement parameters of the 50% ASIR-V, DLIR-M, and DLIR-H groups were compared. The DLIR-H group showed higher scores for diagnostic acceptability and conspicuity, as well as lower SD values for HU and WC than the ASiR-V and DLIR-M groups for the 70 keV and water-iodine image sets (all p < .001). However, there was no significant difference in scores and SD among the three groups for the water-calcium image set (all p > .005). The water-calcium image set showed better diagnostic accuracy for evaluating IVDs compared to the other image sets. The inter-rater agreement using ASiR-V, DLIR-M, and DLIR-H was good for the 70 keV image set, excellent for the water-iodine and water-calcium image sets. DLIR improved the visualization of IVDs in the 70 keV and water-iodine image sets. However, its improvement on color-coded water-calcium image set was limited., (© 2024. The Author(s).)

Objective: To establish an automated, multitask, MRI-based deep learning system for the detailed evaluation of supraspinatus tendon (SST) injuries., Methods: According to arthroscopy findings, 3087 patients were divided into normal, degenerative, and tear groups (groups 0-2). Group 2 was further divided into bursal-side, articular-side, intratendinous, and full-thickness tear groups (groups 2.1-2.4), and external validation was performed with 573 patients. Visual geometry group network 16 (VGG16) was used for preliminary image screening. Then, the rotator cuff multitask learning (RC-MTL) model performed multitask classification (classifiers 1-4). A multistage decision model produced the final output. Model performance was evaluated by receiver operating characteristic (ROC) curve analysis and calculation of related parameters. McNemar's test was used to compare the differences in the diagnostic effects between radiologists and the model. The intraclass correlation coefficient (ICC) was used to assess the radiologists' reliability. p < 0.05 indicated statistical significance., Results: In the in-group dataset, the area under the ROC curve (AUC) of VGG16 was 0.92, and the average AUCs of RC-MTL classifiers 1-4 were 0.99, 0.98, 0.97, and 0.97, respectively. The average AUC of the automated multitask deep learning system for groups 0-2.4 was 0.98 and 0.97 in the in-group and out-group datasets, respectively. The ICCs of the radiologists were 0.97-0.99. The automated multitask deep learning system outperformed the radiologists in classifying groups 0-2.4 in both the in-group and out-group datasets (p < 0.001)., Conclusion: The MRI-based automated multitask deep learning system performed well in diagnosing SST injuries and is comparable to experienced radiologists., Clinical Relevance Statement: Our study established an automated multitask deep learning system to evaluate supraspinatus tendon (SST) injuries and further determine the location of SST tears. The model can potentially improve radiologists' diagnostic efficiency, reduce diagnostic variability, and accurately assess SST injuries., Key Points: • A detailed classification of supraspinatus tendon tears can help clinical decision-making. • Deep learning enables the detailed classification of supraspinatus tendon injuries. • The proposed automated multitask deep learning system is comparable to radiologists., (© 2023. The Author(s), under exclusive licence to European Society of Radiology.)

Purpose: MR arthrography (MRA) is the most accurate method for preoperatively diagnosing superior labrum anterior-posterior (SLAP) lesions, but diagnostic results can vary considerably due to factors such as experience. In this study, deep learning was used to facilitate the preliminary identification of SLAP lesions and compared with radiologists of different seniority., Methods: MRA data from 636 patients were retrospectively collected, and all patients were classified as having/not having SLAP lesions according to shoulder arthroscopy. The SLAP-Net model was built and tested on 514 patients (dataset 1) and independently tested on data from two other MRI devices (122 patients, dataset 2). Manual diagnosis was performed by three radiologists with different seniority levels and compared with SLAP-Net outputs. Model performance was evaluated by the receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), etc. McNemar's test was used to compare performance among models and between radiologists' models. The intraclass correlation coefficient (ICC) was used to assess the radiologists' reliability. p < 0.05 was considered statistically significant., Results: SLAP-Net had AUC = 0.98 and accuracy = 0.96 for classification in dataset 1 and AUC = 0.92 and accuracy = 0.85 in dataset 2. In dataset 1, SLAP-Net had diagnostic performance similar to that of senior radiologists (p = 0.055) but higher than that of early- and mid-career radiologists (p = 0.025 and 0.011). In dataset 2, SLAP-Net had similar diagnostic performance to radiologists of all three seniority levels (p = 0.468, 0.289, and 0.495, respectively)., Conclusions: Deep learning can be used to identify SLAP lesions upon initial MR arthrography examination. SLAP-Net performs comparably to senior radiologists., (© 2023. The Author(s).)

Purposes: To develop a deep learning (DL) model to measure the sagittal Cobb angle of the cervical spine on computed tomography (CT)., Materials and Methods: Two VB-Net-based DL models for cervical vertebra segmentation and key-point detection were developed. Four-points and line-fitting methods were used to calculate the sagittal Cobb angle automatically. The average value of the sagittal Cobb angle was manually measured by two doctors as the reference standard. The percentage of correct key points (PCK), matched samples t test, intraclass correlation coefficient (ICC), Pearson correlation coefficient, mean absolute error (MAE), and Bland‒Altman plots were used to evaluate the performance of the DL model and the robustness and generalization of the model on the external test set., Results: A total of 991 patients were included in the internal data set, and 112 patients were included in the external data set. The PCK of the DL model ranged from 78 to 100% in the test set. The four-points method, line-fitting method, and reference standard measured sagittal Cobb angles were - 1.10 ± 18.29°, 0.30 ± 13.36°, and 0.50 ± 12.83° in the internal test set and 4.55 ± 20.01°, 3.66 ± 18.55°, and 1.83 ± 12.02° in the external test set, respectively. The sagittal Cobb angle calculated by the four-points method and the line-fitting method maintained high consistency with the reference standard (internal test set: ICC = 0.75 and 0.97; r = 0.64 and 0.94; MAE = 5.42° and 3.23°, respectively; external test set: ICC = 0.74 and 0.80, r = 0.66 and 0.974, MAE = 5.25° and 4.68°, respectively)., Conclusions: The DL model can accurately measure the sagittal Cobb angle of the cervical spine on CT. The line-fitting method shows a higher consistency with the doctors and a minor average absolute error., (© 2023. The Author(s).)

Background: Diagnosing anterior talofibular ligament (ATFL) injuries differs among radiologists. Further assessment of ATFL tears is valuable for clinical decision-making., Purpose: To establish a deep learning method for classifying ATFL injuries based on magnetic resonance imaging (MRI)., Study Type: Retrospective., Population: One thousand seventy-three patients from a single center with ankle MRI within 1 month of reference standard arthroscopy (in-group dataset), were divided into training, validation, and test sets in a ratio of 8:1:1. Additionally, 167 patients from another center were used as an independent out-group dataset., Field Strength/sequence: Fat-saturation proton density-weighted fast spin-echo sequence at 1.5/3.0 T., Assessment: Patients were divided into normal, strain and degeneration, partial tear and complete tear groups (groups 0-3). The complete tear group was divided into five sub-groups by location and the potential avulsion fracture (groups 3.1-3.5). All images were input into AlexNet, VGG11, Small-Sample-Attention Net (SSA-Net), and SSA-Net + Weight Loss for classification. The results were compared with four radiologists with 5-30 years of experience., Statistical Tests: Model performance was evaluated by the receiver operating characteristic (ROC) curve, the area under the ROC curve (AUC), and so on. McNemar's test was used to compare performance among the different models, and between the radiologists and models. The intraclass correlation coefficient (ICC) was used to assess the reliability of the radiologists. P < 0.05 was considered statistically significant., Results: The average AUC of AlexNet, VGG11, SAA-Net, and SSA-Net + Weight Loss was 0.95, 0.99, 0.99, 0.99 in groups 0-3 and 0.96, 0.99, 0.99, 0.99 in groups 3.1-3.5. The effect of SSA-Net + Weight Loss was similar to SSA-Net but better than AlexNet and VGG11. In the out-group test set, the AUC of SSA-Net + Weight Loss ranged from 0.89 to 0.99. The ICC of radiologists was 0.97-1.00. The effect of SSA-Net + Weight Loss was better than each radiologist in the in-group and out-group test sets., Data Conclusion: Deep learning has potential to be used for classifying ATFL injuries. SSA-Net + Weight Loss has a better diagnostic effect than radiologists with different experience levels., Level of Evidence: 4 TECHNICAL EFFICACY: Stage 2., (© 2023 International Society for Magnetic Resonance in Medicine.)

Background: For knee osteoarthritis, the commonly used radiology severity criteria Kellgren-Lawrence lead to variability among surgeons. Most existing diagnosis models require preprocessed radiographs and specific equipment., Methods: All enrolled patients diagnosed with KOA who met the criteria were obtained from **** Hospital. This study included 2579 images shot from posterior-anterior X-rays of 2,378 patients. We used RefineDet to train and validate this deep learning-based diagnostic model. After developing the model, 823 images of 697 patients were enrolled as the test set. The whole test set was assessed by up to 5 surgeons and this diagnostic model. To evaluate the model's performance we compared the results of the model with the KOA severity diagnoses of surgeons based on K-L scales., Results: Compared to the diagnoses of surgeons, the model achieved an overall accuracy of 0.977. Its sensitivity (recall) for K-L 0 to 4 was 1.0, 0.972, 0.979, 0.983 and 0.989, respectively; for these diagnoses, the specificity of this model was 0.992, 0.997, 0.994, 0.991 and 0.995. The precision and F1-score were 0.5 and 0.667 for K-L 0, 0.914 and 0.930 for K-L 1, 0.978 and 0.971 for K-L 2, 0.981 and 0.974 for K-L 3, and 0.988 and 0.985 for K-L 4, respectively. All K-L scales perform AUC > 0.90. The quadratic weighted Kappa coefficient between the diagnostic model and surgeons was 0.815 (P < 0.01, 95% CI 0.727-0.903). The performance of the model is comparable to the clinical diagnosis of KOA. This model improved the efficiency and avoided cumbersome image preprocessing., Conclusion: The deep learning-based diagnostic model can be used to assess the severity of KOA in portable devices according to the Kellgren-Lawrence scale. On the premise of improving diagnostic efficiency, the results are highly reliable and reproducible., (© 2022. The Author(s).)

Background: The diagnosis of labral injury on MRI is time-consuming and potential for incorrect diagnoses., Purpose: To explore the feasibility of applying deep learning to diagnose and classify labral injuries with MRI., Study Type: Retrospective., Population: A total of 1016 patients were divided into normal (n = 168, class 0) and abnormal labrum (n = 848) groups. The abnormal group consisted of n = 111 with class 1 (degeneration), n = 437 with class 2 (partial or complete tear), and n = 300 with unclassified injury. Patients were randomly divided into training, validation, and test cohort according to the ratio of 55%:15%:30%., Field Strength/sequence: Fat-saturation proton density-weighted fast spin-echo sequence at 3.0 T., Assessment: Convolutional neural network-6 (CNN-6) was used to extract, discriminate, and detect oblique coronal (OCOR) and oblique sagittal (OSAG) images. Mask R-CNN was used for segmentation. LeNet-5 was used to diagnose and classify labral injuries. The weighting method combined the models of OCOR and OSAG. The output-input connection was used to correlate the whole diagnosis/classification system. Four radiologists performed subjective diagnoses to obtain the diagnosis results., Statistical Tests: CNN-6 and LeNet-5 were evaluated by area under the receiver operating characteristic (ROC) curve and related parameters. The mean average precision (MAP) evaluated the Mask R-CNN. McNemar's test was used to compare the radiologists and models. A P value < 0.05 was considered statistically significant., Results: The area under the curve (AUC) of CNN-6 was 0.99 for extraction, discrimination, and detection. MAP values of Mask R-CNN for OCOR and OSAG image segmentation were 0.96 and 0.99. The accuracies of LeNet-5 in the diagnosis and classification were 0.94/0.94 (OCOR) and 0.92/0.91 (OSAG), respectively. The accuracy of the weighted models in the diagnosis and classification were 0.94 and 0.97, respectively. The accuracies of radiologists in the diagnosis and classification of labrum injuries ranged from 0.85 to 0.92 and 0.78 to 0.94, respectively., Data Conclusion: Deep learning can assist radiologists in diagnosing and classifying labrum injuries., Evidence Level: 3 TECHNICAL EFFICACY: Stage 2., (© 2022 International Society for Magnetic Resonance in Medicine.)

Purpose: To shorten positron emission tomography (PET) scanning time in diagnosing amyloid-β levels thus increasing the workflow in centers involving Alzheimer's Disease (AD) patients., Methods: PET datasets were collected for 25 patients injected with 18 F-AV45 radiopharmaceutical. To generate necessary training data, PET images from both normal-scanning-time (20-min) as well as so-called "shortened-scanning-time" (1-min, 2-min, 5-min, and 10-min) were reconstructed for each patient. Building on our earlier work on MCDNet (Monte Carlo Denoising Net) and a new Wasserstein-GAN algorithm, we developed a new denoising model called MCDNet-2 to predict normal-scanning-time PET images from a series of shortened-scanning-time PET images. The quality of the predicted PET images was quantitatively evaluated using objective metrics including normalized-root-mean-square-error (NRMSE), structural similarity (SSIM), and peak signal-to-noise ratio (PSNR). Furthermore, two radiologists performed subjective evaluations including the qualitative evaluation and a five-point grading evaluation. The denoising performance of the proposed MCDNet-2 was finally compared with those of U-Net, MCDNet, and a traditional denoising method called Gaussian Filtering., Results: The proposed MCDNet-2 can yield good denoising performance in 5-min PET images. In the comparison of denoising methods, MCDNet-2 yielded the best performance in the subjective evaluation although it is comparable with MCDNet in objective comparison (NRMSE, PSNR, and SSIM). In the qualitative evaluation of amyloid-β positive or negative results, MCDNet-2 was found to achieve a classification accuracy of 100%., Conclusions: The proposed denoising method has been found to reduce the PET scan time from the normal level of 20 min to 5 min but still maintaining acceptable image quality in correctly diagnosing amyloid-β levels. These results suggest strongly that deep learning-based methods such as ours can be an attractive solution to the clinical needs to improve PET imaging workflow., (Copyright © 2021 Elsevier Ltd. All rights reserved.)

In the case of hepatocellular carcinoma (HCC) samples, classification of differentiation is crucial for determining prognosis and treatment strategy decisions. However, a label-free and automated classification system for HCC grading has not been yet developed. Hence, in this study, we demonstrate the fusion of multiphoton microscopy and a deep-learning algorithm for classifying HCC differentiation to produce an innovative computer-aided diagnostic method. Convolutional neural networks based on the VGG-16 framework were trained using 217 combined two-photon excitation fluorescence and second-harmonic generation images; the resulting classification accuracy of the HCC differentiation grade was over 90%. Our results suggest that a combination of multiphoton microscopy and deep learning can realize label-free, automated methods for various tissues, diseases and other related classification problems., (© 2019 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.)

Predicting protein function is crucial for understanding biological life processes, preventing diseases and developing new drug targets. In recent years, methods based on sequence, structure and biological networks for protein function annotation have been extensively researched. Although obtaining a protein in three-dimensional structure through experimental or computational methods enhances the accuracy of function prediction, the sheer volume of proteins sequenced by high-throughput technologies presents a significant challenge. To address this issue, we introduce a deep neural network model DeepSS2GO (Secondary Structure to Gene Ontology). It is a predictor incorporating secondary structure features along with primary sequence and homology information. The algorithm expertly combines the speed of sequence-based information with the accuracy of structure-based features while streamlining the redundant data in primary sequences and bypassing the time-consuming challenges of tertiary structure analysis. The results show that the prediction performance surpasses state-of-the-art algorithms. It has the ability to predict key functions by effectively utilizing secondary structure information, rather than broadly predicting general Gene Ontology terms. Additionally, DeepSS2GO predicts five times faster than advanced algorithms, making it highly applicable to massive sequencing data. The source code and trained models are available at https://github.com/orca233/DeepSS2GO. [ABSTRACT FROM AUTHOR]

Excellent performance has been demonstrated in implementing challenging agricultural production processes using modern information technology, especially in the use of artificial intelligence methods to improve modern production environments. However, most of the existing work uses visual methods to train models that extract image features of organisms to analyze their behavior, and it may not be truly intelligent. Because vocal animals transmit information through grunts, the information obtained directly from the grunts of pigs is more useful to understand their behavior and emotional state, which is important for monitoring and predicting the health conditions and abnormal behavior of pigs. We propose a sound classification model called TransformerCNN, which combines the advantages of CNN spatial feature representation and the Transformer sequence coding to form a powerful global feature perception and local feature extraction capability. Through detailed qualitative and quantitative evaluations and by comparing state-of-the-art traditional animal sound recognition methods with deep learning methods, we demonstrate the advantages of our approach for classifying domestic pig sounds. The scores for domestic pig sound recognition accuracy, AUC and recall were 96.05%, 98.37% and 90.52%, respectively, all higher than the comparison model. In addition, it has good robustness and generalization capability with low variation in performance for different input features. [ABSTRACT FROM AUTHOR]

Simple Summary: The incidence of endocrine cancers (e.g., thyroid, pancreas, and adrenal) has been increasing; these cancers have a high premature mortality rate. Traditional medical imaging methods (e.g., MRI and CT) might not be sufficient for accurate cancer screening. Elastography complements conventional medical imaging modalities by identifying abnormal tissue stiffness of the tumor, in which machine learning techniques can further improve accuracy and reliability. This review focuses on the applications and performance of machine-learning-based elastography in classifying endocrine tumors. Elastography complements traditional medical imaging modalities by mapping tissue stiffness to identify tumors in the endocrine system, and machine learning models can further improve diagnostic accuracy and reliability. Our objective in this review was to summarize the applications and performance of machine-learning-based elastography on the classification of endocrine tumors. Two authors independently searched electronic databases, including PubMed, Scopus, Web of Science, IEEEXpress, CINAHL, and EMBASE. Eleven (n = 11) articles were eligible for the review, of which eight (n = 8) focused on thyroid tumors and three (n = 3) considered pancreatic tumors. In all thyroid studies, the researchers used shear-wave ultrasound elastography, whereas the pancreas researchers applied strain elastography with endoscopy. Traditional machine learning approaches or the deep feature extractors were used to extract the predetermined features, followed by classifiers. The applied deep learning approaches included the convolutional neural network (CNN) and multilayer perceptron (MLP). Some researchers considered the mixed or sequential training of B-mode and elastographic ultrasound data or fusing data from different image segmentation techniques in machine learning models. All reviewed methods achieved an accuracy of ≥80%, but only three were ≥90% accurate. The most accurate thyroid classification (94.70%) was achieved by applying sequential training CNN; the most accurate pancreas classification (98.26%) was achieved using a CNN–long short-term memory (LSTM) model integrating elastography with B-mode and Doppler images. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is one of the most common cancers among women globally. Early and accurate screening of breast tumours can improve survival. Ultrasound elastography is a non-invasive and non-ionizing imaging approach to characterize lesions for breast cancer screening, while machine learning techniques could improve the accuracy and reliability of computer-aided diagnosis. This review focuses on the state-of-the-art development and application of the machine learning model in breast tumour classification. Ultrasound elastography can quantify stiffness distribution of tissue lesions and complements conventional B-mode ultrasound for breast cancer screening. Recently, the development of computer-aided diagnosis has improved the reliability of the system, whilst the inception of machine learning, such as deep learning, has further extended its power by facilitating automated segmentation and tumour classification. The objective of this review was to summarize application of the machine learning model to ultrasound elastography systems for breast tumour classification. Review databases included PubMed, Web of Science, CINAHL, and EMBASE. Thirteen (n = 13) articles were eligible for review. Shear-wave elastography was investigated in six articles, whereas seven studies focused on strain elastography (5 freehand and 2 Acoustic Radiation Force). Traditional computer vision workflow was common in strain elastography with separated image segmentation, feature extraction, and classifier functions using different algorithm-based methods, neural networks or support vector machines (SVM). Shear-wave elastography often adopts the deep learning model, convolutional neural network (CNN), that integrates functional tasks. All of the reviewed articles achieved sensitivity ≥80%, while only half of them attained acceptable specificity ≥95%. Deep learning models did not necessarily perform better than traditional computer vision workflow. Nevertheless, there were inconsistencies and insufficiencies in reporting and calculation, such as the testing dataset, cross-validation, and methods to avoid overfitting. Most of the studies did not report loss or hyperparameters. Future studies may consider using the deep network with an attention layer to locate the targeted object automatically and online training to facilitate efficient re-training for sequential data. [ABSTRACT FROM AUTHOR]

This paper employs deep learning in detecting the traffic accident from social media data. First, we thoroughly investigate the 1-year over 3 million tweet contents in two metropolitan areas: Northern Virginia and New York City. Our results show that paired tokens can capture the association rules inherent in the accident-related tweets and further increase the accuracy of the traffic accident detection. Second, two deep learning methods: Deep Belief Network (DBN) and Long Short-Term Memory (LSTM) are investigated and implemented on the extracted token. Results show that DBN can obtain an overall accuracy of 85% with about 44 individual token features and 17 paired token features. The classification results from DBN outperform those of Support Vector Machines (SVMs) and supervised Latent Dirichlet allocation (sLDA). Finally, to validate this study, we compare the accident-related tweets with both the traffic accident log on freeways and traffic data on local roads from 15,000 loop detectors. It is found that nearly 66% of the accident-related tweets can be located by the accident log and more than 80% of them can be tied to nearby abnormal traffic data. Several important issues of using Twitter to detect traffic accidents have been brought up by the comparison including the location and time bias, as well as the characteristics of influential users and hashtags. [ABSTRACT FROM AUTHOR]