A Multi-Scale CNN and Curriculum Learning Strategy for Mammogram Classification

TL;DR

This paper introduces a multi-scale CNN trained with curriculum learning to improve mammogram classification accuracy, effectively addressing the challenge of detecting small lesions within large images, achieving high AUROC scores.

Contribution

The study presents a novel multi-scale CNN architecture combined with curriculum learning for mammogram classification, leveraging lesion segmentation to enhance whole-image diagnostic performance.

Findings

Achieved 0.92 AUROC on DDSM dataset.

Effective handling of small lesion detection within large images.

Improved classification accuracy over existing methods.

Abstract

Screening mammography is an important front-line tool for the early detection of breast cancer, and some 39 million exams are conducted each year in the United States alone. Here, we describe a multi-scale convolutional neural network (CNN) trained with a curriculum learning strategy that achieves high levels of accuracy in classifying mammograms. Specifically, we first train CNN-based patch classifiers on segmentation masks of lesions in mammograms, and then use the learned features to initialize a scanning-based model that renders a decision on the whole image, trained end-to-end on outcome data. We demonstrate that our approach effectively handles the "needle in a haystack" nature of full-image mammogram classification, achieving 0.92 AUROC on the DDSM dataset.