Breast density classification with deep convolutional neural networks
This work addresses breast cancer screening by providing a clinically realistic model, though it is incremental as it applies an existing method to new data.
The authors tackled breast density classification using a large dataset of over 200,000 breast cancer screening exams, finding that their deep convolutional neural network performed comparably to a human expert in a reader study.
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.