FPN-IAIA-BL: A Multi-Scale Interpretable Deep Learning Model for Classification of Mass Margins in Digital Mammography

TL;DR

This paper introduces a multi-scale interpretable deep learning model for classifying mass margins in digital mammography, enhancing transparency and alignment with radiologist reasoning.

Contribution

It presents a novel architecture that combines multi-scale prototypes for improved interpretability and precise feature localization in mammogram analysis.

Findings

Achieves high accuracy in mass margin classification.

Provides interpretable explanations aligned with radiologist reasoning.

Offers a flexible architecture for computer vision tasks.

Abstract

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.