An Automatic Cardiac Segmentation Framework based on Multi-sequence MR Image

TL;DR

This paper presents an automatic cardiac segmentation framework for LGE CMR images that uses data augmentation and CNNs, achieving competitive results in a cardiac MR segmentation challenge.

Contribution

It introduces a novel automatic segmentation framework utilizing histogram matching for data augmentation and CNNs, evaluated on multi-sequence cardiac MR data.

Findings

Achieved Dice score of 0.8087 on test data.

Demonstrated effective data augmentation with histogram matching.

Performed well in the 2019 Multi-sequence Cardiac MR Segmentation Challenge.

Abstract

LGE CMR is an efficient technology for detecting infarcted myocardium. An efficient and objective ventricle segmentation method in LGE can benefit the location of the infarcted myocardium. In this paper, we proposed an automatic framework for LGE image segmentation. There are just 5 labeled LGE volumes with about 15 slices of each volume. We adopted histogram match, an invariant of rotation registration method, on the other labeled modalities to achieve effective augmentation of the training data. A CNN segmentation model was trained based on the augmented training data by leave-one-out strategy. The predicted result of the model followed a connected component analysis for each class to remain the largest connected component as the final segmentation result. Our model was evaluated by the 2019 Multi-sequence Cardiac MR Segmentation Challenge. The mean testing result of 40 testing volumes on Dice score, Jaccard score, Surface distance, and Hausdorff distance is 0.8087, 0.6976, 2.8727mm, and 15.6387mm, respectively. The experiment result shows a satisfying performance of the proposed framework. Code is available at https://github.com/Suiiyu/MS-CMR2019.