Patient-Specific 3D Volumetric Reconstruction of Bioresorbable Stents: A Method to Generate 3D Geometries for Computational Analysis of Coronaries Treated with Bioresorbable Stents

As experts continue to debate the optimal surgery practice for coronary disease - percutaneous coronary intervention (PCI) or coronary aortic bypass graft (CABG) - computational tools may provide a quantitative assessment of each option. Computational fluid dynamics (CFD) has been used to assess the interplay between hemodynamics and stent struts; it is of particular interest in Bioresorbable Vascular Stents (BVS), since their thicker struts may result in impacted flow patterns and possible pathological consequences. Many proofs of concept are presented in the literature; however, a practical method for extracting patient-specific stented coronary artery geometries from images over a large number of patients remains an open problem. This work provides a possible pipeline for the reconstruction of the BVS. Using Optical Coherence Tomographies (OCT) and Invasive Coronary Angiographies (ICA), we can reconstruct the 3D geometry of deployed BVS in vivo. We illustrate the stent reconstruction process: (i) automatic strut detection, (ii) identification of stent components, (iii) 3D registration of stent curvature, and (iv) final stent volume reconstruction. The methodology is designed for use on clinical OCT images, as opposed to approaches that relied on a small number of virtually deployed stents. The proposed reconstruction process is validated with a virtual phantom stent, providing quantitative assessment of the methodology, and with selected clinical cases, confirming feasibility. Using multimodality image analysis, we obtain reliable reconstructions within a reasonable timeframe. This work is the first step toward a fully automated reconstruction and simulation procedure aiming at an extensive quantitative analysis of the impact of BVS struts on hemodynamics via CFD in clinical trials, going beyond the proof-of-concept stage.

Development of deep learning algorithms to categorize free-text notes pertaining to diabetes: convolution neural networks achieve higher accuracy than support vector machines

Health professionals can use natural language processing (NLP) technologies when reviewing electronic health records (EHR). Machine learning free-text classifiers can help them identify problems and make critical decisions. We aim to develop deep learning neural network algorithms that identify EHR progress notes pertaining to diabetes and validate the algorithms at two institutions. The data used are 2,000 EHR progress notes retrieved from patients with diabetes and all notes were annotated manually as diabetic or non-diabetic. Several deep learning classifiers were developed, and their performances were evaluated with the area under the ROC curve (AUC). The convolutional neural network (CNN) model with a separable convolution layer accurately identified diabetes-related notes in the Brigham and Womens Hospital testing set with the highest AUC of 0.975. Deep learning classifiers can be used to identify EHR progress notes pertaining to diabetes. In particular, the CNN-based classifier can achieve a higher AUC than an SVM-based classifier.