Segmentation challenge on the quantification of left atrial wall thickness

Abstract

This paper presents an image database for the Left Atrial Wall Thickness Quantification challenge at the MICCAI STACOM 2016 workshop along with some preliminary results. The image database consists of both CT (n = 10) and MRI (n = 10) datasets. Expert delineations from two observers were obtained for each image in the CT set and a single-observer segmentation was obtained for each image in the MRI set included in this study. Computer algorithms for segmentation of wall thickness from three research groups contributed to this challenge. The algorithms were evaluated on the basis of wall thickness measurements obtained from the segmentation masks.