INSIGHT: Explainable Weakly-Supervised Medical Image Analysis

Processing such pathology images (WSIs) are often processed by extracting data end-to-end with deep neural networks is computationally embeddings from local regions and then an aggregator infeasible. Instead, pipelines rely on aggregators, which makes predictions from this set. However, current methods synthesize local embeddings extracted from tiles (WSIs) or require post-hoc visualization techniques (e.g., Grad-CAM) slices (volumes) into global predictions [5, 6, 23]. While and often fail to localize small yet clinically crucial details. this divide-and-conquer strategy is efficient, current methods To address these limitations, we introduce INSIGHT, a often discard spatial information during feature aggregation novel weakly-supervised aggregator that integrates heatmap and depend on post-hoc visualization tools, such as Grad-generation as an inductive bias. Starting from pre-trained CAM [33], to generate interpretable heatmaps. These visualizations feature maps, INSIGHT employs a detection module with are prone to missing clinically significant features small convolutional kernels to capture fine details and a and introduce additional complexity.