Search

Abstract Background Single-photon emission computed tomography (SPECT) analysis relies on qualitative visual assessment or semi-quantitative measures like total perfusion deficit that play a critical role in the non-invasive diagnosis of coronary artery disease by assessing regional blood flow abnormalities. Recently, machine learning (ML) -based analysis of SPECT images for coronary artery disease diagnosis has shown promise, with its utility in predicting long-term patient outcomes (prognosis) remaining an active area of investigation. In this review, we comprehensively examine the current landscape of ML-based analysis of SPECT imaging with an emphasis on prognostication of coronary artery disease. Main body Our systematic search yielded twelve retrospective studies, investigating SPECT-based ML models for prognostic prediction in coronary artery disease patients, with a total sample size of 73,023 individuals. Several of these studies demonstrate the superior prognostic capabilities of ML models over traditional logistic regression (LR) models and total perfusion deficit, especially when incorporating demographic data alongside SPECT imaging. Meta-analysis of 6 studies revealed promising performance of the included ML models, with sensitivity and specificity exceeding 65% for major adverse cardiovascular events and all-cause mortality. Notably, the integration of demographic information with SPECT imaging in ML frameworks shows statistically significant improvements in prognostic performance. Conclusion Our review suggests that ML models either independently or in combination with demographic data enhance prognostic prediction in coronary artery disease.

Cardiovascular magnetic (CMR) resonance is a versatile tool for diagnosing cardiovascular diseases. While gadolinium-based contrast agents are the gold standard for identifying myocardial infarction (MI), their use is limited in patients with allergies or impaired kidney function, affecting a significant portion of the MI population. This has led to a growing interest in developing artificial intelligence (AI)-powered CMR techniques for MI detection without contrast agents. This mini-review focuses on recent advancements in AI-powered contrast-free CMR for MI detection. We explore various AI models employed in the literature and delve into their strengths and limitations, paving the way for a comprehensive understanding of this evolving field.

Capsule networks promise significant benefits over convolutional neural networks (CNN) by storing stronger internal representations and routing information based on the agreement between intermediate representations’ projections. Despite this, their success has been limited to small‐scale classification datasets due to their computationally expensive nature. Though memory‐efficient, convolutional capsules impose geometric constraints that fundamentally limit the ability of capsules to model the pose/deformation of objects. Further, they do not address the bigger memory concern of class capsules scaling up to bigger tasks such as detection or large‐scale classification. Herein, a new family of capsule networks, deformable capsules (DeformCaps), is introduced to address object detection problem in computer vision. Two new algorithms associated with our DeformCaps, a novel capsule structure (SplitCaps), and a novel dynamic routing algorithm (SE‐Routing), which balance computational efficiency with the need for modeling a large number of objects and classes, are proposed. This has never been achieved with capsule networks before. The proposed methods efficiently scale up to create the first‐ever capsule network for object detection in the literature. The proposed architecture is a one‐stage detection framework and it obtains results on microsoft common objects in context which are on par with state‐of‐the‐art one‐stage CNN‐based methods, while producing fewer false‐positive detection, generalizing to unusual poses/viewpoints of objects.

Background: Currently, recommended pre-operative risk assessment models including the revised cardiac risk index (RCRI) are not very effective in predicting postoperative myocardial damage after non-elective surgery, especially for elderly patients. Aims: This study aimed to create a new risk prediction model to assess myocardial injury after non-cardiac surgery (MINS) in elderly patients and compare it with the RCRI, a well-known pre-operative risk prediction model. Materials and Methods: This retrospective study included 370 elderly patients who were over 65 years of age and had non-elective surgery in a tertiary hospital. Each patient underwent detailed physical evaluations before the surgery. The study cohort was divided into two groups: patients who had MINS and those who did not. Results: In total, 13% (48 out of 370 patients) of the patients developed MINS. Multivariable analysis revealed that creatinine, lymphocyte, aortic regurgitation (moderate-severe), stroke, hemoglobin, ejection fraction, and D-dimer were independent determinants of MINS. By using these parameters, a model called “CLASHED” was developed to predict postoperative MINS. The ROC analysis comparison demonstrated that the new risk prediction model was significantly superior to the RCRI in predicting MINS in elderly patients undergoing non-elective surgery (AUC: 0.788 vs. AUC: 0.611, p < 0.05). Conclusions: Our study shows that the new risk preoperative model successfully predicts MINS in elderly patients undergoing non-elective surgery. In addition, this new model is found to be superior to the RCRI in predicting MINS.

Background and Objectives: Studies have shown that inflammation markers can be used as prognostic tools in predicting acute ischemic stroke. In this study, we conducted a comparison of several inflammation scores in predicting left atrial thrombosis (LAT) in patients with ischemic stroke without AF. Materials and Methods: In this single-center, retrospective study, we included 303 consecutive patients with ischemic stroke. Each patient underwent a transesophageal echocardiography (TEE) examination within 10 days of admission to detect the presence of LAT. To identify independent predictors of LAT, we conducted a multivariate logistic regression analysis. Results: In total, 303 patients who had ischemic stroke were included in the analysis. LAT was detached in 34 patients at the time of the TEE examination. The patients were categorized into two groups based on their LAT status. The Prognostic Nutritional Index (PNI), HALP score, and C-reactive Protein–Albumin Ratio (CAR) were identified as statistically significant predictors of LAT. Based on the results of the multivariate regression analysis, the CAR emerged as the only independent predictor of LAT. Conclusions: Among several inflammation scores, the PNI, HALP, and CAR were statistically significant predictors of LAT in ischemic stroke patients without AF. CAR was identified as the optimal score for the prediction of LAT in patients with stroke and without AF.

Abstract Machine learning and deep learning are two subsets of artificial intelligence that involve teaching computers to learn and make decisions from any sort of data. Most recent developments in artificial intelligence are coming from deep learning, which has proven revolutionary in almost all fields, from computer vision to health sciences. The effects of deep learning in medicine have changed the conventional ways of clinical application significantly. Although some sub-fields of medicine, such as pediatrics, have been relatively slow in receiving the critical benefits of deep learning, related research in pediatrics has started to accumulate to a significant level, too. Hence, in this paper, we review recently developed machine learning and deep learning-based solutions for neonatology applications. We systematically evaluate the roles of both classical machine learning and deep learning in neonatology applications, define the methodologies, including algorithmic developments, and describe the remaining challenges in the assessment of neonatal diseases by using PRISMA 2020 guidelines. To date, the primary areas of focus in neonatology regarding AI applications have included survival analysis, neuroimaging, analysis of vital parameters and biosignals, and retinopathy of prematurity diagnosis. We have categorically summarized 106 research articles from 1996 to 2022 and discussed their pros and cons, respectively. In this systematic review, we aimed to further enhance the comprehensiveness of the study. We also discuss possible directions for new AI models and the future of neonatology with the rising power of AI, suggesting roadmaps for the integration of AI into neonatal intensive care units.

Background: Pan-immuno-inflammation value (PIV) is a new and comprehensive index that reflects both the immune response and systemic inflammation in the body. Objective: The aim of this study was to investigate the prognostic relevance of PIV in predicting in-hospital mortality in acute pulmonary embolism (PE) patients and to compare it with the well-known risk scoring system, PE severity index (PESI), which is commonly used for a short-term mortality prediction in such patients. Methods: In total, 373 acute PE patients diagnosed with contrast-enhanced computed tomography were included in the study. Detailed cardiac evaluation of each patient was performed and PESI and PIV were calculated. Results: In total, 60 patients died during their hospital stay. The multivariable logistic regression analysis revealed that baseline heart rate, N-terminal pro–B-type natriuretic peptide, lactate dehydrogenase, PIV, and PESI were independent risk factors for in-hospital mortality in acute PE patients. When comparing with PESI, PIV was non-inferior in terms of predicting the survival status in patients with acute PE. Conclusion: In our study, we found that the PIV was statistically significant in predicting in-hospital mortality in acute PE patients and was non-inferior to the PESI.

As the world gradually recovers from the impacts of COVID-19, the recent global spread of Monkeypox disease has raised concerns about another potential pandemic, highlighting the urgency of early detection and intervention to curb its transmission. Deep Learning (DL)-based disease prediction presents a promising solution, offering affordable and accessible diagnostic services. In this study, we harnessed Transfer Learning (TL) techniques to tweak and assess the performance of an array of six different DL models, encompassing VGG16, InceptionResNetV2, ResNet50, ResNet101, MobileNetV2, VGG19, and Vision Transformer (ViT). Among this diverse collection, it was the modified versions of the VGG19 and MobileNetV2 models that outshone the others, boasting striking accuracy rates ranging from an impressive 93% to an astounding 99%. Our results echo the findings of recent research endeavors that similarly showcase enhanced performance when developing disease diagnostic models armed with the power of TL. To add to this, we used Local Interpretable Model Agnostic Explanations (LIME) to lend a sense of transparency to our model’s predictions and identify the crucial features correlating with the onset of Monkeypox disease. These findings offer significant implications for disease prevention and control efforts, particularly in remote and resource-limited areas.

PurposeThe goal of this work is to explore the best optimizers for deep learning in the context of medical image segmentation and to provide guidance on how to design segmentation networks with effective optimization strategies.ApproachMost successful deep learning networks are trained using two types of stochastic gradient descent (SGD) algorithms: adaptive learning and accelerated schemes. Adaptive learning helps with fast convergence by starting with a larger learning rate (LR) and gradually decreasing it. Momentum optimizers are particularly effective at quickly optimizing neural networks within the accelerated schemes category. By revealing the potential interplay between these two types of algorithms [LR and momentum optimizers or momentum rate (MR) in short], in this article, we explore the two variants of SGD algorithms in a single setting. We suggest using cyclic learning as the base optimizer and integrating optimal values of learning rate and momentum rate. The new optimization function proposed in this work is based on the Nesterov accelerated gradient optimizer, which is more efficient computationally and has better generalization capabilities compared to other adaptive optimizers.ResultsWe investigated the relationship of LR and MR under an important problem of medical image segmentation of cardiac structures from MRI and CT scans. We conducted experiments using the cardiac imaging dataset from the ACDC challenge of MICCAI 2017, and four different architectures were shown to be successful for cardiac image segmentation problems. Our comprehensive evaluations demonstrated that the proposed optimizer achieved better results (over a 2% improvement in the dice metric) than other optimizers in the deep learning literature with similar or lower computational cost in both single and multi-object segmentation settings.ConclusionsWe hypothesized that the combination of accelerated and adaptive optimization methods can have a drastic effect in medical image segmentation performances. To this end, we proposed a new cyclic optimization method (Cyclic Learning/Momentum Rate) to address the efficiency and accuracy problems in deep learning–based medical image segmentation. The proposed strategy yielded better generalization in comparison to adaptive optimizers.

Radiomics-guided prediction of overall survival (OS) in brain gliomas is seen as a significant problem in Neuro-oncology. The ultimate goal is to develop a robust MRI-based approach (i.e., a radiomics model) that can accurately classify a novel subject as a short-term survivor, a medium-term survivor, or a long-term survivor. The BraTS 2020 challenge provides radiological imaging and clinical data (178 subjects) to develop and validate radiomics-based methods for OS classification in brain gliomas. In this study, we empirically evaluated the efficacy of four multiregional radiomic models, for OS classification, and quantified the robustness of predictions to variations in automatic segmentation of brain tumor volume. More specifically, we evaluated four radiomic models, namely, the Whole Tumor (WT) radiomics model, the 3-subregions radiomics model, the 6-subregions radiomics model, and the 21-subregions radiomics model. The 3-subregions radiomics model is based on a physiological segmentation of whole tumor volume (WT) into three non-overlapping subregions. The 6-subregions and 21-subregions radiomic models are based on an anatomical segmentation of the brain tumor into 6 and 21 anatomical regions, respectively. Moreover, we employed six segmentation schemes – five CNNs and one STAPLE-fusion method – to quantify the robustness of radiomic models. Our experiments revealed that the 3-subregions radiomics model had the best predictive performance (mean AUC = 0.73) but poor robustness (RSD = 1.99) and the 6-subregions and 21-subregions radiomics models were more robust (RSD 1.39) with lower predictive performance (mean AUC 0.71). The poor robustness of the 3-subregions radiomics model was associated with highly variable and inferior segmentation of tumor core and active tumor subregions as quantified by the Hausdorff distance metric (4.4−6.5mm) across six segmentation schemes. Failure analysis revealed that the WT radiomics model, the 6-subregions radiomics model, and the 21-subregions radiomics model failed for the same subjects which is attributed to the common requirement of accurate segmentation of the WT volume. Moreover, short-term survivors were largely misclassified by the radiomic models and had large segmentation errors (average Hausdorff distance of 7.09mm). Lastly, we concluded that while STAPLE-fusion can reduce segmentation errors, it is not a solution to learning accurate and robust radiomic models.

In this study, we formulated an efficient deep learning-based classification strategy for characterizing metastatic bone lesions using computed tomography scans (CTs) of prostate cancer patients. For this purpose, 2,880 annotated bone lesions from CT scans of 114 patients diagnosed with prostate cancer were used for training, validation, and final evaluation. These annotations were in the form of lesion full segmentation, lesion type and labels of either benign or malignant. In this work, we present our approach in developing the state-of-the-art model to classify bone lesions as benign or malignant, where (1) we introduce a valuable dataset to address a clinically important problem, (2) we increase the reliability of our model by patient-level stratification of our dataset following lesion-aware distribution at each of the training, validation, and test splits, (3) we explore the impact of lesion texture, morphology, size, location, and volumetric information on the classification performance, (4) we investigate the functionality of lesion classification using different algorithms including lesion-based average 2D ResNet-50, lesion-based average 2D ResNeXt-50, 3D ResNet-18, 3D ResNet-50, as well as the ensemble of 2D ResNet-50 and 3D ResNet-18. For this purpose, we employed a train/validation/test split equal to 75%/12%/13% with several data augmentation methods applied to the training dataset to avoid overfitting and to increase reliability. We achieved an accuracy of 92.2% for correct classification of benign vs. malignant bone lesions in the test set using an ensemble of lesion-based average 2D ResNet-50 and 3D ResNet-18 with texture, volumetric information, and morphology having the greatest discriminative power respectively. To the best of our knowledge, this is the highest ever achieved lesion-level accuracy having a very comprehensive data set for such a clinically important problem. This level of classification performance in the early stages of metastasis development bodes well for clinical translation of this strategy.

Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Here, the authors present a multinational study on the application of deep learning algorithms for COVID-19 diagnosis against multiple lung conditions as controls.

Condition assessment of civil engineering structures has been an active research area due to growing concerns over the safety of aged as well as new civil structures. Utilization of emerging immersive visualization technologies such as Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR) in the architectural, engineering, and construction (AEC) industry has demonstrated that these visualization tools can be paradigm-shifting. Extended Reality (XR), an umbrella term for VR, AR, and MR technologies, has found many diverse use cases in the AEC industry. Despite this exciting trend, there is no review study on the usage of XR technologies for the condition assessment of civil structures. Thus, the present paper aims to fill this gap by presenting a literature review encompassing the utilization of XR technologies for the condition assessment of civil structures. This study aims to provide essential information and guidelines for practitioners and researchers on using XR technologies to maintain the integrity and safety of civil structures.

A common task in brain image analysis includes diagnosis of a certain medical condition wherein groups of healthy controls and diseased subjects are analyzed and compared. On the other hand, for two groups of healthy participants with different proficiency in a certain skill, a distinctive analysis of the brain function remains a challenging problem. In this study, we develop new computational tools to explore the functional and anatomical differences that could exist between the brain of healthy individuals identified on the basis of different levels of task experience/proficiency. Toward this end, we look at a dataset of amateur and professional chess players, where we utilize resting-state functional magnetic resonance images to generate functional connectivity (FC) information. In addition, we utilize T1-weighted magnetic resonance imaging to estimate morphometric connectivity (MC) information. We combine functional and anatomical features into a new connectivity matrix, which we term as the functional morphometric similarity connectome (FMSC). Since, both the FC and MC information is susceptible to redundancy, the size of this information is reduced using statistical feature selection. We employ off-the-shelf machine learning classifier, support vector machine, for both single- and multi-modality classifications. From our experiments, we establish that the saliency and ventral attention network of the brain is functionally and anatomically different between two groups of healthy subjects (chess players). We argue that, since chess involves many aspects of higher order cognition such as systematic thinking and spatial reasoning and the identified network is task-positive to cognition tasks requiring a response, our results are valid and supporting the feasibility of the proposed computational pipeline. Moreover, we quantitatively validate an existing neuroscience hypothesis that learning a certain skill could cause a change in the brain (functional connectivity and anatomy) and this can be tested via our novel FMSC algorithm.

Objective: The aim of this research is to present a novel computer-aided decision support tool in analyzing, quantifying, and evaluating the retinal blood vessel structure from fluorescein angiogram (FA) videos.Methods: The proposed method consists of three phases: (i) image registration for large motion removal from fluorescein angiogram videos, followed by (ii) retinal vessel segmentation, and lastly, (iii) segmentation-guided video magnification. In the image registration phase, individual frames of the video are spatiotemporally aligned using a novel wavelet-based registration approach to compensate for the global camera and patient motion. In the second phase, a capsule-based neural network architecture is employed to perform the segmentation of retinal vessels for the first time in the literature. In the final phase, a segmentation-guided Eulerian video magnification is proposed for magnifying subtle changes in the retinal video produced by blood flow through the retinal vessels. The magnification is applied only to the segmented vessels, as determined by the capsule network. This minimizes the high levels of noise present in these videos and maximizes useful information, enabling ophthalmologists to more easily identify potential regions of pathology.Results: The collected fluorescein angiogram video dataset consists of 1, 402 frames from 10 normal subjects (prospective study). Experimental results for retinal vessel segmentation show that the capsule-based algorithm outperforms a state-of-the-art convolutional neural networks (U-Net), obtaining a higher dice coefficient (85.94%) and sensitivity (92.36%) while using just 5% of the network parameters. Qualitative analysis of these videos was performed after the final phase by expert ophthalmologists, supporting the claim that artificial intelligence assisted decision support tool can be helpful for providing a better analysis of blood flow dynamics.Conclusions: The authors introduce a novel computational tool, combining a wavelet-based video registration method with a deep learning capsule-based retinal vessel segmentation algorithm and a Eulerian video magnification technique to quantitatively and qualitatively analyze FA videos. To authors' best knowledge, this is the first-ever development of such a computational tool to assist ophthalmologists with analyzing blood flow in FA videos.

The success of surgical resection in epilepsy patients depends on preserving functionally critical brain regions, while removing pathological tissues. Being the gold standard, electro-cortical stimulation mapping (ESM) helps surgeons in localizing the function of eloquent cortex through electrical stimulation of electrodes placed directly on the cortical brain surface. Due to the potential hazards of ESM, including increased risk of provoked seizures, electrocorticography based functional mapping (ECoG-FM) was introduced as a safer alternative approach. However, ECoG-FM has a low success rate when compared to the ESM. In this study, we address this critical limitation by developing a new algorithm based on deep learning for ECoG-FM and thereby we achieve an accuracy comparable to ESM in identifying eloquent language cortex. In our experiments, with 11 epilepsy patients who underwent presurgical evaluation (through deep learning-based signal analysis on 637 electrodes), our proposed algorithm obtained an accuracy of 83.05% in identifying language regions, an exceptional 23% improvement with respect to the conventional ECoG-FM analysis (∼60%). Our findings have demonstrated, for the first time, that deep learning powered ECoG-FM can serve as a stand-alone modality and avoid likely hazards of the ESM in epilepsy surgery. Hence, reducing the potential for developing post-surgical morbidity in the language function.

Developing a bridge management strategy at the network level with efficient use of capital is very important for optimal infrastructure remediation. This paper introduces a novel decision support system that considers many aspects of bridge management and successfully implements the investigated methodology in a web-based platform. The proposed decision support system uses advanced prediction models, decision trees, and incremental machine learning algorithms to generate an optimal decision strategy. The system aims to achieve adaptive and flexible decision making while entailing powerful utilization of nondestructive evaluation (NDE) methods. The NDE data integration and visualization allow automatic retrieval of inspection results and overlaying the defects on a 3D bridge model. Furthermore, a deep learning-based damage growth prediction model estimates the future condition of the bridge elements and utilizes this information in the decision-making process. The decision ranking takes into account a wide range of factors including structural safety, serviceability, rehabilitation cost, life cycle cost, and societal and political factors to generate optimal maintenance strategies with multiple decision alternatives. This study aims to bring a complementary solution to currently in-use systems with the utilization of advanced machine-learning models and NDE data integration while still equipped with main bridge management functions of bridge management systems and capable of transferring data to other systems.

Stress research is a rapidly emerging area in the field of electroencephalography (EEG) signal processing. The use of EEG as an objective measure for cost effective and personalized stress management becomes important in situations like the nonavailability of mental health facilities. In this study, long-term stress was classified with machine learning algorithms using resting state EEG signal recordings. The labeling for the stress and control groups was performed using two currently accepted clinical practices: (i) the perceived stress scale score and (ii) expert evaluation. The frequency domain features were extracted from five-channel EEG recordings in addition to the frontal and temporal alpha and beta asymmetries. The alpha asymmetry was computed from four channels and used as a feature. Feature selection was also performed to identify statistically significant features for both stress and control groups (via t-test). We found that support vector machine was best suited to classify long-term human stress when used with alpha asymmetry as a feature. It was observed that the expert evaluation-based labeling method had improved the classification accuracy by up to 85.20%. Based on these results, it is concluded that alpha asymmetry may be used as a potential bio-marker for stress classification, when labels are assigned using expert evaluation.

We introduce a novel computational framework to enable automated identification of texture and shape features of lesions on (18)F-FDG-PET images through a graph-based image segmentation method. The proposed framework predicts future morphological changes of lesions with high accuracy. The presented methodology has several benefits over conventional qualitative and semi-quantitative methods, due to its fully quantitative nature and high accuracy in each step of (i) detection, (ii) segmentation, and (iii) feature extraction. To evaluate our proposed computational framework, thirty patients received 2 (18)F-FDG-PET scans (60 scans total), at two different time points. Metastatic papillary renal cell carcinoma, cerebellar hemongioblastoma, non-small cell lung cancer, neurofibroma, lymphomatoid granulomatosis, lung neoplasm, neuroendocrine tumor, soft tissue thoracic mass, nonnecrotizing granulomatous inflammation, renal cell carcinoma with papillary and cystic features, diffuse large B-cell lymphoma, metastatic alveolar soft part sarcoma, and small cell lung cancer were included in this analysis. The radiotracer accumulation in patients' scans was automatically detected and segmented by the proposed segmentation algorithm. Delineated regions were used to extract shape and textural features, with the proposed adaptive feature extraction framework, as well as standardized uptake values (SUV) of uptake regions, to conduct a broad quantitative analysis. Evaluation of segmentation results indicates that our proposed segmentation algorithm has a mean dice similarity coefficient of 85.75 ± 1.75%. We found that 28 of 68 extracted imaging features were correlated well with SUV(max) (p