A Mixture of Views Network with Applications to the Classification of Breast Microcalcifications

TL;DR

This paper introduces a neural network-based data fusion method called Mixture of Views for classifying breast microcalcifications, effectively combining multi-view mammography data to improve diagnostic accuracy.

Contribution

The paper proposes a novel neural network architecture that explicitly models multi-view relevance, enhancing classification performance on mammography data.

Findings

Outperforms previous fusion methods on DDSM dataset

Effectively combines multi-view data for improved accuracy

Adapts to case-specific view relevance

Abstract

In this paper we examine data fusion methods for multi-view data classification. We present a decision concept which explicitly takes into account the input multi-view structure, where for each case there is a different subset of relevant views. This data fusion concept, which we dub Mixture of Views, is implemented by a special purpose neural network architecture. It is demonstrated on the task of classifying breast microcalcifications as benign or malignant based on CC and MLO mammography views. The single view decisions are combined by a data-driven decision, according to the relevance of each view in a given case, into a global decision. The method is evaluated on a large multi-view dataset extracted from the standardized digital database for screening mammography (DDSM). The experimental results show that our method outperforms previously suggested fusion methods.