Segmentation of hippocampus guided by assembled and weighted coherent point drift registration

Segmentation of the subcortical structures in the brain such as the hippocampus, is known to be very challenging owing to its' image characteristics. In brain MR images, the hippocampus is observed as a gray matter structure that often exhibits very weak or unclear boundary definitions at some fragments of its' boundary. The unclear boundaries even cause the medical experts to misjudge the hippocampus boundary, especially at the head and tail. In this research, an automated segmentation approach, termed as Assembled and Weighted Coherent Point Drift is investigated to delineate the hippocampus accurately. Evaluations on public datasets produced an average Dice Similarity Coefficient of 0.8050, which appears better, in comparison to several other hippocampus segmentation approaches, especially against the well-known software program called Freesurfer. The study also revealed that the accuracy of the proposed segmentation approach seems on par with other various state-of-the-art approaches. (c) 2019 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

Segmentation of subcortical structures like the hippocampus in brain MR images is challenging due to weak or unclear boundary definitions, especially at the head and tail. An automated segmentation approach showed promising results with an average Dice Similarity Coefficient of 0.8050 on public datasets, comparable to other state-of-the-art approaches.