Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation

TL;DR

This paper introduces a multi-view analysis method for mammogram classification that mimics radiologists' reading process, leveraging local co-occurrence and global consistency learning to improve accuracy and generalization across datasets.

Contribution

The paper presents a novel multi-view global-local analysis approach that enhances mammogram classification by integrating local and global information, inspired by radiologists' procedures.

Findings

Model outperforms existing methods in accuracy.

Improves generalization across datasets.

Effective in leveraging multi-view information.

Abstract

When analysing screening mammograms, radiologists can naturally process information across two ipsilateral views of each breast, namely the cranio-caudal (CC) and mediolateral-oblique (MLO) views. These multiple related images provide complementary diagnostic information and can improve the radiologist's classification accuracy. Unfortunately, most existing deep learning systems, trained with globally-labelled images, lack the ability to jointly analyse and integrate global and local information from these multiple views. By ignoring the potentially valuable information present in multiple images of a screening episode, one limits the potential accuracy of these systems. Here, we propose a new multi-view global-local analysis method that mimics the radiologist's reading procedure, based on a global consistency learning and local co-occurrence learning of ipsilateral views in mammograms. Extensive experiments show that our model outperforms competing methods, in terms of classification accuracy and generalisation, on a large-scale private dataset and two publicly available datasets, where models are exclusively trained and tested with global labels.