Quantitative Comparison of White Matter Segmentation for Brain MR Images

Xianping Li, Jorgue Martinez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The volume of white matter in brain MR image is important for medical diagnosis, therefore, it is critical to obtain an accurate segmentation of the white matter. We compare quantitatively the up-to-date versions of three software packages: SPM, FSL, and FreeSurfer, for brain MR image segmentation, and then select the package that performs the best for white matter segmentation. Dice index (DSC), Hausdorff distance (HD), and modified Hausdorff distance (MHD) are chosen as the metrics for comparison. A new computational method is also proposed to calculate HD and MHD efficiently.

Original languageEnglish (US)
Title of host publicationAdvances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC
EditorsSupriya Kapoor, Kohei Arai
PublisherSpringer Verlag
Pages639-647
Number of pages9
ISBN (Print)9783030177942
DOIs
StatePublished - 2020
Externally publishedYes
EventComputer Vision Conference, CVC 2019 - Las Vegas, United States
Duration: Apr 25 2019Apr 26 2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume943
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceComputer Vision Conference, CVC 2019
Country/TerritoryUnited States
CityLas Vegas
Period4/25/194/26/19

Keywords

  • Brain MRI
  • Dice index
  • FLS
  • FreeSurfer
  • Hausdorff distance
  • Image segmentation
  • SPM
  • White matter

ASJC Scopus subject areas

  • Control and Systems Engineering
  • General Computer Science

Fingerprint

Dive into the research topics of 'Quantitative Comparison of White Matter Segmentation for Brain MR Images'. Together they form a unique fingerprint.

Cite this