A novel multi-view deep learning approach for BI-RADS and density assessment of mammograms

TL;DR

This paper introduces a multi-view deep learning method combining convolutional features and gradient boosting to improve BI-RADS and density assessment accuracy in mammograms, outperforming single-view models.

Contribution

It presents a novel multi-view deep learning framework that integrates convolutional features with LightGBM for enhanced mammogram classification.

Findings

Outperforms single-view models with +5% F1-score on internal dataset.

Achieves +10% F1-score improvement on DDSM dataset.

Demonstrates the importance of multi-view analysis in breast cancer risk prediction.

Abstract

Advanced deep learning (DL) algorithms may predict the patient's risk of developing breast cancer based on the Breast Imaging Reporting and Data System (BI-RADS) and density standards. Recent studies have suggested that the combination of multi-view analysis improved the overall breast exam classification. In this paper, we propose a novel multi-view DL approach for BI-RADS and density assessment of mammograms. The proposed approach first deploys deep convolutional networks for feature extraction on each view separately. The extracted features are then stacked and fed into a Light Gradient Boosting Machine (LightGBM) classifier to predict BI-RADS and density scores. We conduct extensive experiments on both the internal mammography dataset and the public dataset Digital Database for Screening Mammography (DDSM). The experimental results demonstrate that the proposed approach outperforms the single-view classification approach on two benchmark datasets by huge F1-score margins (+5% on the internal dataset and +10% on the DDSM dataset). These results highlight the vital role of combining multi-view information to improve the performance of breast cancer risk prediction.