Deep Learning Under the Microscope: Improving the Interpretability of Medical Imaging Neural Networks
This work addresses interpretability for medical imaging, specifically in histology, which is crucial for clinical applications, though it appears incremental as it builds on existing methods like MIL.
The paper tackled the problem of interpreting deep neural networks for medical imaging by proposing a novel method tailored to histological Whole Slide Image processing, resulting in quantitative and qualitative outperformance over baselines on two datasets and expert pathologist acknowledgment of its clinical potential.
In this paper, we propose a novel interpretation method tailored to histological Whole Slide Image (WSI) processing. A Deep Neural Network (DNN), inspired by Bag-of-Features models is equipped with a Multiple Instance Learning (MIL) branch and trained with weak supervision for WSI classification. MIL avoids label ambiguity and enhances our model's expressive power without guiding its attention. We utilize a fine-grained logit heatmap of the models activations to interpret its decision-making process. The proposed method is quantitatively and qualitatively evaluated on two challenging histology datasets, outperforming a variety of baselines. In addition, two expert pathologists were consulted regarding the interpretability provided by our method and acknowledged its potential for integration into several clinical applications.