DeepMiner: Discovering Interpretable Representations for Mammogram Classification and Explanation

We propose DeepMiner, a framework to discover interpretable representations in deep neural networks and to build explanations for medical predictions. By probing convolutional neural networks (CNNs) trained to classify cancer in mammograms, we show that many individual units in the final convolution...

Full description

Saved in:
Bibliographic Details
Main Authors: Wu, Jimmy, Zhou, Bolei, Peck, Diondra, Hsieh, Scott, Dialani, Vandana, Mackey, Lester, Patterson, Genevieve
Format: Journal Article
Language:English
Published: 18-08-2021
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose DeepMiner, a framework to discover interpretable representations in deep neural networks and to build explanations for medical predictions. By probing convolutional neural networks (CNNs) trained to classify cancer in mammograms, we show that many individual units in the final convolutional layer of a CNN respond strongly to diseased tissue concepts specified by the BI-RADS lexicon. After expert annotation of the interpretable units, our proposed method is able to generate explanations for CNN mammogram classification that are consistent with ground truth radiology reports on the Digital Database for Screening Mammography. We show that DeepMiner not only enables better understanding of the nuances of CNN classification decisions but also possibly discovers new visual knowledge relevant to medical diagnosis.
DOI:10.48550/arxiv.1805.12323