Multitask Classification and Segmentation for Cancer Diagnosis in Mammography

TL;DR

This paper proposes a multi-task learning approach combining segmentation and classification in ConvNets to improve mammography-based cancer diagnosis, effectively utilizing heterogeneous annotation levels to enhance predictive performance.

Contribution

It introduces a novel multi-task training scheme that leverages both image-level and pixel-level annotations to regularize deep neural networks for mammography analysis.

Findings

Improved diagnostic accuracy on DDSM dataset

Effective use of heterogeneous annotations for training

Enhanced deep feature representations

Abstract

Annotation cost is a bottleneck for collecting massive data in mammography, especially for training deep neural networks. In this paper, we study the use of heterogeneous levels of annotation granularity to improve predictive performances. More precisely, we introduce a multi-task learning scheme for training convolutional neural network (ConvNets), which combines segmentation and classification, using image-level and pixel-level annotations. In this way, different objectives can be used to regularize training by sharing intermediate deep representations. Successful experiments are carried out on the Digital Database of Screening Mammography (DDSM) to validate the relevance of the proposed approach.