Explainable coronary artery disease prediction model based on AutoGluon from AutoML framework.

Objective: This study focuses on the innovative application of Automated Machine Learning (AutoML) technology in cardiovascular medicine to construct an explainable Coronary Artery Disease (CAD) prediction model to support the clinical diagnosis of CAD. Methods: This study utilizes a combined data set of five public data sets related to CAD. An ensemble model is constructed using the AutoML open-source framework AutoGluon to evaluate the feasibility of AutoML in constructing a disease prediction model in cardiovascular medicine. The performance of the ensemble model is compared against individual baseline models. Finally, the disease prediction ensemble model is explained using SHapley Additive exPlanations (SHAP). Results: The experimental results show that the AutoGluon-based ensemble model performs better than the individual baseline models in predicting CAD. It achieved an accuracy of 0.9167 and an AUC of 0.9562 in 4-fold cross-bagging. SHAP measures the importance of each feature to the prediction of the model and explains the prediction results of the model. Conclusion: This study demonstrates the feasibility and efficacy of AutoML technology in cardiovascular medicine and highlights its potential in disease prediction. AutoML reduces the barriers to model building and significantly improves prediction accuracy. Additionally, the integration of SHAP enhances model transparency and explainability, which is critical to ensuring model credibility and widespread adoption in cardiovascular medicine.

End to end vision transformer architecture for brain stroke assessment based on multi-slice classification and localization using computed tomography.

BACKGROUND: Brain stroke is a leading cause of disability and death worldwide, and early diagnosis and treatment are critical to improving patient outcomes. Current stroke diagnosis methods are subjective and prone to errors, as radiologists rely on manual selection of the most important CT slice. This highlights the need for more accurate and reliable automated brain stroke diagnosis and localization methods to improve patient outcomes. PURPOSE: In this study, we aimed to enhance the vision transformer architecture for the multi-slice classification of CT scans of each patient into three categories, including Normal, Infarction, Hemorrhage, and patient-wise stroke localization, based on end-to-end vision transformer architecture. This framework can provide an automated, objective, and consistent approach to stroke diagnosis and localization, enabling personalized treatment plans based on the location and extent of the stroke. METHODS: We modified the Vision Transformer (ViT) in combination with neural network layers for the multi-slice classification of brain CT scans of each patient into normal, infarction, and hemorrhage classes. For stroke localization, we used the ViT architecture and convolutional neural network layers to detect stroke and localize it by bounding boxes for infarction and hemorrhage regions in a patient-wise manner based on multi slices. RESULTS: Our proposed framework achieved an overall accuracy of 87.51% in classifying brain CT scan slices and showed high precision in localizing the stroke patient-wise. Our results demonstrate the potential of our method for accurate and reliable stroke diagnosis and localization. CONCLUSION: Our study enhanced ViT architecture for automated stroke diagnosis and localization using brain CT scans, which could have significant implications for stroke management and treatment. The use of deep learning algorithms can provide a more objective and consistent approach to stroke diagnosis and potentially enable personalized treatment plans based on the location and extent of the stroke. Further studies are needed to validate our method on larger and more diverse datasets and to explore its clinical utility in real-world settings.

The synergy of cybernetical intelligence with medical image analysis for deep medicine: A methodological perspective.

CONCEPTUAL INTRODUCTION: To introduce the concept of cybernetical intelligence, deep learning, development history, international research, algorithms, and the application of these models in smart medical image analysis and deep medicine are reviewed in this paper. This study also defines the terminologies for cybernetical intelligence, deep medicine, and precision medicine. REVIEW OF METHODS: Through literature research and knowledge reorganization, this review explores the fundamental concepts and practical applications of various deep learning techniques and cybernetical intelligence by conducting extensive literature research and reorganizing existing knowledge in medical imaging and deep medicine. The discussion mainly centers on the applications of classical models in this field and addresses the limitations and challenges of these basic models. EVALUATION AND DISCUSSIONS: In this paper, the more comprehensive overview of the classical structural modules in convolutional neural networks is described in detail from the perspective of cybernetical intelligence in deep medicine. The results and data of major research contents of deep learning are consolidated and summarized. CONCLUSION: There are some problems in machine learning internationally, such as insufficient research techniques, unsystematic research methods, incomplete research depth, and incomplete evaluation research. Some suggestions are given in our review to solve the problems existing in the deep learning models. Cybernetical intelligence has proven to be a valuable and promising avenue for advancing various fields, including deep medicine and personalized medicine.

Characterization of Mechanical Properties of Tissue Scaffolds by Phase Contrast Imaging and Finite Element Modeling.

In tissue engineering, the cell and scaffold approach has shown promise as a treatment to regenerate diseased and/or damaged tissue. In this treatment, an artificial construct (scaffold) is seeded with cells, which organize and proliferate into new tissue. The scaffold itself biodegrades with time, leaving behind only newly formed tissue. The degradation qualities of the scaffold are critical during the treatment period, since the change in the mechanical properties of the scaffold with time can influence cell behavior. To observe in time the scaffold's mechanical properties, a straightforward method is to deform the scaffold and then characterize scaffold deflection accordingly. However, experimentally observing the scaffold deflection is challenging. This paper presents a novel study on characterization of mechanical properties of scaffolds by phase contrast imaging and finite element modeling, which specifically includes scaffold fabrication, scaffold imaging, image analysis, and finite elements (FEs) modeling of the scaffold mechanical properties. The innovation of the work rests on the use of in-line phase contrast X-ray imaging at 20 KeV to characterize tissue scaffold deformation caused by ultrasound radiation forces and the use of the Fourier transform to identify movement. Once deformation has been determined experimentally, it is then compared with the predictions given by the forward solution of a finite element model. A consideration of the number of separate loading conditions necessary to uniquely identify the material properties of transversely isotropic and fully orthotropic scaffolds is also presented, along with the use of an FE as a form of regularization.