Effect of Random Histogram Equalization on Breast Calcification Analysis Using Deep Learning

TL;DR

This paper shows that applying random histogram equalization as data augmentation improves deep learning classification of breast calcifications in mammograms, leading to statistically significant accuracy gains.

Contribution

It introduces a novel data augmentation technique using random histogram equalization to enhance deep learning performance in mammogram calcification analysis.

Findings

Over 1% improvement in accuracy and F1-score.

Statistically significant results with p<0.0001.

Effective on CBIS-DDSM dataset for two classification tasks.

Abstract

Early detection and analysis of calcifications in mammogram images is crucial in a breast cancer diagnosis workflow. Management of calcifications that require immediate follow-up and further analyzing its benignancy or malignancy can result in a better prognosis. Recent studies have shown that deep learning-based algorithms can learn robust representations to analyze suspicious calcifications in mammography. In this work, we demonstrate that randomly equalizing the histograms of calcification patches as a data augmentation technique can significantly improve the classification performance for analyzing suspicious calcifications. We validate our approach by using the CBIS-DDSM dataset for two classification tasks. The results on both the tasks show that the proposed methodology gains more than 1% mean accuracy and F1-score when equalizing the data with a probability of 0.4 when compared to not using histogram equalization. This is further supported by the t-tests, where we obtain a p-value of p<0.0001, thus showing the statistical significance of our approach.