High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks

TL;DR

This paper introduces a multi-view deep convolutional neural network designed for high-resolution breast cancer screening, demonstrating that larger training sets and original image resolution significantly improve accuracy, achieving performance comparable to radiologists.

Contribution

The work presents a novel multi-view deep CNN architecture tailored for high-resolution medical images, addressing the limitations of models designed for natural images and emphasizing the importance of image resolution.

Findings

Performance improves with larger training datasets.

Using original image resolution yields the best accuracy.

Model achieves radiologist-level performance in a reader study.

Abstract

Advances in deep learning for natural images have prompted a surge of interest in applying similar techniques to medical images. The majority of the initial attempts focused on replacing the input of a deep convolutional neural network with a medical image, which does not take into consideration the fundamental differences between these two types of images. Specifically, fine details are necessary for detection in medical images, unlike in natural images where coarse structures matter most. This difference makes it inadequate to use the existing network architectures developed for natural images, because they work on heavily downscaled images to reduce the memory requirements. This hides details necessary to make accurate predictions. Additionally, a single exam in medical imaging often comes with a set of views which must be fused in order to reach a correct conclusion. In our work, we propose to use a multi-view deep convolutional neural network that handles a set of high-resolution medical images. We evaluate it on large-scale mammography-based breast cancer screening (BI-RADS prediction) using 886,000 images. We focus on investigating the impact of the training set size and image size on the prediction accuracy. Our results highlight that performance increases with the size of training set, and that the best performance can only be achieved using the original resolution. In the reader study, performed on a random subset of the test set, we confirmed the efficacy of our model, which achieved performance comparable to a committee of radiologists when presented with the same data.