3D Shape-Based Myocardial Infarction Prediction Using Point Cloud Classification Networks
This work addresses improved prediction of myocardial infarction for clinical decision-making, but it is incremental as it applies existing point cloud methods to a new medical domain.
The authors tackled myocardial infarction (MI) prediction by using complete 3D cardiac shapes as point clouds, achieving improvements of ~13% for prevalent MI detection and ~5% for incident MI prediction over clinical benchmarks.
Myocardial infarction (MI) is one of the most prevalent cardiovascular diseases with associated clinical decision-making typically based on single-valued imaging biomarkers. However, such metrics only approximate the complex 3D structure and physiology of the heart and hence hinder a better understanding and prediction of MI outcomes. In this work, we investigate the utility of complete 3D cardiac shapes in the form of point clouds for an improved detection of MI events. To this end, we propose a fully automatic multi-step pipeline consisting of a 3D cardiac surface reconstruction step followed by a point cloud classification network. Our method utilizes recent advances in geometric deep learning on point clouds to enable direct and efficient multi-scale learning on high-resolution surface models of the cardiac anatomy. We evaluate our approach on 1068 UK Biobank subjects for the tasks of prevalent MI detection and incident MI prediction and find improvements of ~13% and ~5% respectively over clinical benchmarks. Furthermore, we analyze the role of each ventricle and cardiac phase for 3D shape-based MI detection and conduct a visual analysis of the morphological and physiological patterns typically associated with MI outcomes.