Patch-Level Multiple Instance Learning 3D CNN Architecture for Coronary Artery Disease Classification

https://doi.org/10.5281/zenodo.18051463

Abstract

Coronary artery disease (CAD) remains a leading cause of morbidity and mortality worldwide, and accurate detection from cardiac imaging is critical for timely intervention. Traditional classification approaches often require both normal and abnormal cases, but clinical datasets frequently contain only CAD-positive patients, posing significant challenges for supervised learning. In this study, we propose a novel patch-level multiple instance learning (MIL) framework for CAD detection from 3D coronary CT angiography (CTA) images. The framework segments each 3D volume into artery-focused patches and extracts discriminative features using a context-preserving, multi-receptive-field 3D convolutional neural network. Patient-level CAD likelihood is then predicted by aggregating patch-level features through an attention-based MIL layer, enabling weakly supervised learning from positive-only datasets. The architecture addresses key limitations of conventional 3D CNNs, including over-compression of contextual information, vanishing gradients, layer-wise receptive field mismatches, and conflicting optimization between layers. Experimental results demonstrate that the proposed approach not only accurately identifies diseased regions but also provides interpretable patient-level CAD predictions, offering a robust solution for automated CAD analysis in real-world clinical settings.