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

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.

References in corpus (2)

• Understanding Neural Networks Through Deep Visualization
• Breast Mass Classification from Mammograms using Deep Convolutional Neural Networks

Cited by in corpus (23)

• Confounding variables can degrade generalization performance of radiological deep learning models
• A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?
• Domain generalization in deep learning-based mass detection in mammography: A large-scale multi-center study
• Multitask Classification and Segmentation for Cancer Diagnosis in Mammography
• Quantitative Phase Imaging and Artificial Intelligence: A Review
• Disentangling Label Distribution for Long-tailed Visual Recognition
• Weakly and Semi Supervised Detection in Medical Imaging via Deep Dual Branch Net
• An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
• Quantifying the Value of Lateral Views in Deep Learning for Chest X-rays
• Knowledge-Guided Multiview Deep Curriculum Learning for Elbow Fracture Classification
• SCREENet: A Multi-view Deep Convolutional Neural Network for Classification of High-resolution Synthetic Mammographic Screening Scans
• Use of Transfer Learning and Wavelet Transform for Breast Cancer Detection
• Improving Breast Cancer Detection using Symmetry Information with Deep Learning
• Breast density classification with deep convolutional neural networks
• Learning multiple non-mutually-exclusive tasks for improved classification of inherently ordered labels
• Designing for Democratization: Introducing Novices to Artificial Intelligence Via Maker Kits
• Mammography Dual View Mass Correspondence
• MamT${}^4$: Multi-view Attention Networks for Mammography Cancer Classification
• Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models
• A Multi-Scale CNN and Curriculum Learning Strategy for Mammogram Classification
• PECNet: A Deep Multi-Label Segmentation Network for Eosinophilic Esophagitis Biopsy Diagnostics
• A Unified Mammogram Analysis Method via Hybrid Deep Supervision
• Screening Mammogram Classification with Prior Exams