Histogram Matching Augmentation for Domain Adaptation with Application to Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Image Segmentation

TL;DR

This paper introduces a histogram matching data augmentation technique to reduce domain gaps in cardiac MRI segmentation, improving model robustness across different scanners and clinical centers.

Contribution

The proposed histogram matching augmentation method effectively transfers intensity distributions to mitigate domain differences in multi-center cardiac MRI segmentation.

Findings

Achieved high Dice scores on MICCAI 2020 M&Ms challenge

Ranked third in the challenge

Method is simple and plug-and-play

Abstract

Convolutional Neural Networks (CNNs) have achieved high accuracy for cardiac structure segmentation if training cases and testing cases are from the same distribution. However, the performance would be degraded if the testing cases are from a distinct domain (e.g., new MRI scanners, clinical centers). In this paper, we propose a histogram matching (HM) data augmentation method to eliminate the domain gap. Specifically, our method generates new training cases by using HM to transfer the intensity distribution of testing cases to existing training cases. The proposed method is quite simple and can be used in a plug-and-play way in many segmentation tasks. The method is evaluated on MICCAI 2020 M\&Ms challenge, and achieves average Dice scores of 0.9051, 0.8405, and 0.8749, and Hausdorff Distances of 9.996, 12.49, and 12.68 for the left ventricular, myocardium, and right ventricular, respectively. Our results rank the third place in MICCAI 2020 M\&Ms challenge. The code and trained models are publicly available at \url{https://github.com/JunMa11/HM_DataAug}.