LowRank-CAM: A Computationally Efficient and Interpretable Framework for Medical Image Analysis (Student Abstract)

Abstract Deep learning has advanced medical imaging, but limited interpretability hinders clinical adoption. Class activation maps (CAM) provide visual explanations, yet methods such as Score-CAM are computationally expensive, requiring a forward pass for each activation map and limiting real-time applicability despite their high fidelity. To overcome this limitation, LowRank-CAM is proposed, which aggregates activation maps into a global matrix and applies singular value decomposition (SVD) to extract dominant spatial modes. The resulting top-r low-rank attention masks, with r << K (r denotes the low-rank dimension and K is the total number of activation maps) replace per-channel perturbations and require only r forward passes through the classifier head. The resulting top-r low-rank attention masks, with r << K, replace per-channel perturbations and require only r forward passes through the classifier head. This low-rank formulation substantially reduces complexity while preserving class-discriminatory importance. Experiments on Inception-v3 musculoskeletal radiographs (MURA) demonstrate that LowRank-CAM achieves a 4.73× speedup over Score-CAM while maintaining comparable visual clarity and diagnostic relevance.