Cardiac segmentation on late gadolinium enhancement MRI: A benchmark study from multi-sequence cardiac MR segmentation challenge

This paper presents the selective results from the Multi-Sequence Cardiac MR (MS-CMR) Segmentation challenge, offering a data set of paired MS-CMR images, including auxiliary CMR sequences as well as Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR), from 45 patients who underwent cardiomyopathy. It was aimed to develop new algorithms, as well as benchmark existing ones for LGE CMR segmentation focusing on myocardial wall of the left ventricle and blood cavity of the two ventricles. The paired MS-CMR images could also enable algorithms to combine the complementary information from the other sequences for the ventricle segmentation of LGE CMR. Nine representative works were selected for evaluation and comparisons, among which three methods are unsupervised domain adaptation (UDA) methods and the other six are supervised. The success of these methods was mainly attributed to the inclusion of the auxiliary sequences from the MS-CMR images, which provide important label information for the training of deep neural networks.

The challenge continues as an ongoing resource.

To read more: