Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge

TL;DR

This paper evaluates various algorithms for whole heart segmentation using a public challenge dataset, highlighting the performance of deep learning methods versus traditional approaches in clinical imaging.

Contribution

It provides a comprehensive comparison of 21 algorithms from 12 groups for multi-modality heart segmentation, including a publicly available dataset and evaluation framework.

Findings

Deep learning methods achieved high accuracy despite limited training data.

Traditional multi-atlas segmentation algorithms showed robust and stable performance.

Overfitting affected some deep learning models' performance in blinded tests.

Abstract

Knowledge of whole heart anatomy is a prerequisite for many clinical applications. Whole heart segmentation (WHS), which delineates substructures of the heart, can be very valuable for modeling and analysis of the anatomy and functions of the heart. However, automating this segmentation can be arduous due to the large variation of the heart shape, and different image qualities of the clinical data. To achieve this goal, a set of training data is generally needed for constructing priors or for training. In addition, it is difficult to perform comparisons between different methods, largely due to differences in the datasets and evaluation metrics used. This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017. The challenge provides 120 three-dimensional cardiac images covering the whole heart, including 60 CT and 60 MRI volumes, all acquired in clinical environments with manual delineation. Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelve groups, have been evaluated. The results show that many of the deep learning (DL) based methods achieved high accuracy, even though the number of training datasets was limited. A number of them also reported poor results in the blinded evaluation, probably due to overfitting in their training. The conventional algorithms, mainly based on multi-atlas segmentation, demonstrated robust and stable performance, even though the accuracy is not as good as the best DL method in CT segmentation. The challenge, including the provision of the annotated training data and the blinded evaluation for submitted algorithms on the test data, continues as an ongoing benchmarking resource via its homepage (\url{www.sdspeople.fudan.edu.cn/zhuangxiahai/0/mmwhs/}).