FPN-IAIA-BL: A Multi-Scale Interpretable Deep Learning Model for Classification of Mass Margins in Digital Mammography
This addresses the need for interpretable models in high-stakes radiology, though it appears incremental by building on existing prototype-based methods.
The paper tackles the problem of imprecise feature localization in interpretable deep learning models for mammography by proposing a multi-scale interpretable model, achieving high accuracy in mass margin classification with reasoning aligned with radiologist practices.
Digital mammography is essential to breast cancer detection, and deep learning offers promising tools for faster and more accurate mammogram analysis. In radiology and other high-stakes environments, uninterpretable ("black box") deep learning models are unsuitable and there is a call in these fields to make interpretable models. Recent work in interpretable computer vision provides transparency to these formerly black boxes by utilizing prototypes for case-based explanations, achieving high accuracy in applications including mammography. However, these models struggle with precise feature localization, reasoning on large portions of an image when only a small part is relevant. This paper addresses this gap by proposing a novel multi-scale interpretable deep learning model for mammographic mass margin classification. Our contribution not only offers an interpretable model with reasoning aligned with radiologist practices, but also provides a general architecture for computer vision with user-configurable prototypes from coarse- to fine-grained prototypes.