Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification

TL;DR

This paper introduces end-to-end deep multi-instance networks for classifying whole mammograms, eliminating the need for detailed ROI annotations and demonstrating improved robustness over previous methods.

Contribution

The authors propose three novel deep multi-instance network schemes for whole mammogram classification without relying on ROI annotations.

Findings

Robustness of proposed networks surpasses previous segmentation-based methods

Effective end-to-end training for mammogram classification

Three different multi-instance schemes evaluated on INbreast dataset

Abstract

Mammogram classification is directly related to computer-aided diagnosis of breast cancer. Traditional methods rely on regions of interest (ROIs) which require great efforts to annotate. Inspired by the success of using deep convolutional features for natural image analysis and multi-instance learning (MIL) for labeling a set of instances/patches, we propose end-to-end trained deep multi-instance networks for mass classification based on whole mammogram without the aforementioned ROIs. We explore three different schemes to construct deep multi-instance networks for whole mammogram classification. Experimental results on the INbreast dataset demonstrate the robustness of proposed networks compared to previous work using segmentation and detection annotations.