Breast density classification with deep convolutional neural networks

TL;DR

This paper demonstrates that a deep convolutional neural network can classify breast density effectively using a large, clinically realistic dataset, achieving performance comparable to human experts in breast cancer screening.

Contribution

It introduces a large-scale dataset and trains a CNN that performs breast density classification at a level comparable to human radiologists.

Findings

Model achieves performance comparable to human experts.

Large dataset improves clinical relevance of the results.

Demonstrates the potential of deep learning for automated breast density assessment.

Abstract

Breast density classification is an essential part of breast cancer screening. Although a lot of prior work considered this problem as a task for learning algorithms, to our knowledge, all of them used small and not clinically realistic data both for training and evaluation of their models. In this work, we explore the limits of this task with a data set coming from over 200,000 breast cancer screening exams. We use this data to train and evaluate a strong convolutional neural network classifier. In a reader study, we find that our model can perform this task comparably to a human expert.