The Role of Artificial Intelligence in the Identification and Evaluation of Bone Fractures.

Artificial intelligence (AI), particularly deep learning, has made enormous strides in medical imaging analysis. In the field of musculoskeletal radiology, deep-learning models are actively being developed for the identification and evaluation of bone fractures. These methods provide numerous benefits to radiologists such as increased diagnostic accuracy and efficiency while also achieving standalone performances comparable or superior to clinician readers. Various algorithms are already commercially available for integration into clinical workflows, with the potential to improve healthcare delivery and shape the future practice of radiology. In this systematic review, we explore the performance of current AI methods in the identification and evaluation of fractures, particularly those in the ankle, wrist, hip, and ribs. We also discuss current commercially available products for fracture detection and provide an overview of the current limitations of this technology and future directions of the field.

Quantitative Assessment of Mitochondrial Morphology and Electrophysiological Function in the Diabetic Heart.

Mitochondria within a cardiomyocyte form a highly dynamic network that undergoes fusion and fission events in response to acute and chronic stressors, such as hyperglycemia and diabetes mellitus. Changes in mitochondrial architecture and morphology not only reflect their capacity for oxidative phosphorylation and ATP synthesis but also impact their subcellular localization and interaction with other organelles. The role of these ultrastructural abnormalities in modulating electrophysiological properties and excitation-contraction coupling remains largely unknown and warrants direct investigation considering the growing appreciation of the functional and structural coupling between the mitochondrial network, the calcium cycling machinery, and sarcolemmal ion channels in the cardiac myocyte. In this Methods in Molecular Biology chapter, we provide a protocol that allows for a quantitative assessment of mitochondrial shape and morphology in control and diabetic hearts that had undergone detailed electrophysiological measurements using high resolution optical action potential (AP) mapping.

Computational design of custom therapeutic cells to correct failing human cardiomyocytes.

Background: Myocardial delivery of non-excitable cells-namely human mesenchymal stem cells (hMSCs) and c-kit+ cardiac interstitial cells (hCICs)-remains a promising approach for treating the failing heart. Recent empirical studies attempt to improve such therapies by genetically engineering cells to express specific ion channels, or by creating hybrid cells with combined channel expression. This study uses a computational modeling approach to test the hypothesis that custom hypothetical cells can be rationally designed to restore a healthy phenotype when coupled to human heart failure (HF) cardiomyocytes. Methods: Candidate custom cells were simulated with a combination of ion channels from non-excitable cells and healthy human cardiomyocytes (hCMs). Using a genetic algorithm-based optimization approach, candidate cells were accepted if a root mean square error (RMSE) of less than 50% relative to healthy hCM was achieved for both action potential and calcium transient waveforms for the cell-treated HF cardiomyocyte, normalized to the untreated HF cardiomyocyte. Results: Custom cells expressing only non-excitable ion channels were inadequate to restore a healthy cardiac phenotype when coupled to either fibrotic or non-fibrotic HF cardiomyocytes. In contrast, custom cells also expressing cardiac ion channels led to acceptable restoration of a healthy cardiomyocyte phenotype when coupled to fibrotic, but not non-fibrotic, HF cardiomyocytes. Incorporating the cardiomyocyte inward rectifier K+ channel was critical to accomplishing this phenotypic rescue while also improving single-cell action potential metrics associated with arrhythmias, namely resting membrane potential and action potential duration. The computational approach also provided insight into the rescue mechanisms, whereby heterocellular coupling enhanced cardiomyocyte L-type calcium current and promoted calcium-induced calcium release. Finally, as a therapeutically translatable strategy, we simulated delivery of hMSCs and hCICs genetically engineered to express the cardiomyocyte inward rectifier K+ channel, which decreased action potential and calcium transient RMSEs by at least 24% relative to control hMSCs and hCICs, with more favorable single-cell arrhythmia metrics. Conclusion: Computational modeling facilitates exploration of customizable engineered cell therapies. Optimized cells expressing cardiac ion channels restored healthy action potential and calcium handling phenotypes in fibrotic HF cardiomyocytes and improved single-cell arrhythmia metrics, warranting further experimental validation studies of the proposed custom therapeutic cells.

Noninvasive localization of cardiac arrhythmias using electromechanical wave imaging.

Cardiac arrhythmias are a major cause of morbidity and mortality worldwide. The 12-lead electrocardiogram (ECG) is the current noninvasive clinical tool used to diagnose and localize cardiac arrhythmias. However, it has limited accuracy and is subject to operator bias. Here, we present electromechanical wave imaging (EWI), a high-frame rate ultrasound technique that can noninvasively map with high accuracy the electromechanical activation of atrial and ventricular arrhythmias in adult patients. This study evaluates the accuracy of EWI for localization of various arrhythmias in all four chambers of the heart before catheter ablation. Fifty-five patients with an accessory pathway (AP) with Wolff-Parkinson-White (WPW) syndrome, premature ventricular complexes (PVCs), atrial tachycardia (AT), or atrial flutter (AFL) underwent transthoracic EWI and 12-lead ECG. Three-dimensional (3D) rendered EWI isochrones and 12-lead ECG predictions by six electrophysiologists were applied to a standardized segmented cardiac model and subsequently compared to the region of successful ablation on 3D electroanatomical maps generated by invasive catheter mapping. There was significant interobserver variability among 12-lead ECG reads by expert electrophysiologists. EWI correctly predicted 96% of arrhythmia locations as compared with 71% for 12-lead ECG analyses [unadjusted for arrhythmia type: odds ratio (OR), 11.8; 95% confidence interval (CI), 2.2 to 63.2; P = 0.004; adjusted for arrhythmia type: OR, 12.1; 95% CI, 2.3 to 63.2; P = 0.003]. This double-blinded clinical study demonstrates that EWI can localize atrial and ventricular arrhythmias including WPW, PVC, AT, and AFL. EWI when used with ECG may allow for improved treatment for patients with arrhythmias.