Automated detection of Focal Cortical Dysplasia lesions on T1-weighted MRI using volume-based distributional features

Chin Ann Yang, Mostafa Kaveh, Bradley J. Erickson

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

6 Scopus citations

Abstract

A new procedure is proposed for the automated detection of Focal Cortical Dysplasia (FCD) lesions on T1-weighted MRIs using volume-based discriminative features. Statistical features are obtained from of a set of neighboring voxels without using any computation that requires hard labeling of grey matter and white matter tissues. The significance of the proposed features is quantitatively evaluated with a Naive Bayes probabilistic approach, which is used for classification, and experiments are conducted on a total of 21 subjects with FCD lesions. The experimental results indicate that using the proposed features can achieve better detection rate and lower false positive rate for the FCD lesions compared to the widely used Antel's features [1].

Original languageEnglish (US)
Title of host publication2011 8th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, ISBI'11
Pages865-870
Number of pages6
DOIs
StatePublished - 2011
Event2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL, United States
Duration: Mar 30 2011Apr 2 2011

Publication series

NameProceedings - International Symposium on Biomedical Imaging
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Other

Other2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
Country/TerritoryUnited States
CityChicago, IL
Period3/30/114/2/11

Keywords

  • MRI
  • blurriness
  • cortical thickness
  • detection
  • focal cortical dysplasia

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Automated detection of Focal Cortical Dysplasia lesions on T1-weighted MRI using volume-based distributional features'. Together they form a unique fingerprint.

Cite this