# Expert identification of visual primitives used by CNNs during mammogram classification

arXiv: https://arxiv.org/abs/1803.04858 · HTML: https://mlsanity.com/paper/1803.04858/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2018.

## Built on by (most cited first, 3 of 3)

- [Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions](https://mlsanity.com/paper/2304.06662/) (2023)
- [Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challenges](https://mlsanity.com/paper/2403.20260/) (2024)
- [Mask-Free Neuron Concept Annotation for Interpreting Neural Networks in Medical Domain](https://mlsanity.com/paper/2407.11375/) (2024)

## Abstract (arXiv)

This work interprets the internal representations of deep neural networks trained for classification of diseased tissue in 2D mammograms. We propose an expert-in-the-loop interpretation method to label the behavior of internal units in convolutional neural networks (CNNs). Expert radiologists identify that the visual patterns detected by the units are correlated with meaningful medical phenomena such as mass tissue and calcificated vessels. We demonstrate that several trained CNN models are able to produce explanatory descriptions to support the final classification decisions. We view this as an important first step toward interpreting the internal representations of medical classification CNNs and explaining their predictions.