Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Kernel Fisher discriminant for shape-based classification in epilepsy.

S Kodipaka1, B C Vemuri, A Rangarajan

  • 1Department of Computer and Information Science and Engineering, University of Florida, Gainesville, FL 32611, USA.

Medical Image Analysis
|December 13, 2006
PubMed
Summary

Kernel Fisher discriminant effectively analyzes hippocampal shape deformations to locate epileptic foci. This method significantly improves distinguishing between healthy individuals and epilepsy patients, outperforming traditional volume-based analyses.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Feasibility of Passive ECG Bio-sensing and EMA Emotion Reporting Technologies and Acceptability of Just-in-Time Content in a Well-being Intervention, Considerations for Scalability and Improved Uptake.

Affective science·2022
Same author

Data-Driven Discovery of Extravasation Pathway in Circulating Tumor Cells.

Scientific reports·2017
Same author

Do we have the right PROMs for measuring outcomes in lumbar spinal surgery?

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2017
Same author

Thrombospondin-1 repression is mediated via distinct mechanisms in fibroblasts and epithelial cells.

Oncogene·2015
Same author

Thrombospondin-1 repression is mediated via distinct mechanisms in fibroblasts and epithelial cells.

Oncogene·2014
Same author

A NOVEL INTRINSIC UNSCENTED KALMAN FILTER FOR TRACTOGRAPHY FROM HARDI*

Proceedings. IEEE International Symposium on Biomedical Imaging·2014

Area of Science:

  • Medical image analysis
  • Neurology
  • Statistical pattern recognition

Background:

  • Epilepsy diagnosis relies on identifying the location of epileptic foci.
  • Current methods for determining hemispheric focus location have limitations.
  • Automated identification of hemispheric epileptic foci has not been previously reported.

Purpose of the Study:

  • To apply kernel Fisher discriminant for statistical analysis of shape deformations indicating epileptic focus laterality.
  • To compare the efficacy of shape-based versus volume-based features in classifying epilepsy patients.
  • To introduce and evaluate a novel feature (normalized histogram of 3D displacement field) for improved classification.

Main Methods:

  • Utilized kernel Fisher discriminant for statistical analysis of shape deformations.

Related Experiment Videos

  • Derived shape-based features from the displacement field of non-rigid hippocampal deformations.
  • Compared shape-based features against volume-based features for classification accuracy.
  • Introduced and analyzed the normalized histogram of the 3D displacement field as a novel feature.

    • Main Results:

    • Shape-based features demonstrated significant improvement in distinguishing healthy controls from epilepsy patients (RATL and LATL) compared to volume-based features.
    • The novel normalized histogram of the 3D displacement field feature achieved significant improvement over volume-based features in classifying patients into LATL or RATL classes.
    • This study presents the first reported automated identification of hemispheric epileptic foci.

    Conclusions:

    • Kernel Fisher discriminant applied to hippocampal shape analysis is a promising method for identifying the hemispheric location of epileptic foci.
    • Shape-based features, particularly the normalized histogram of the 3D displacement field, offer superior performance over volume-based features for epilepsy classification.
    • This automated approach has the potential to enhance clinical diagnosis and treatment planning for epilepsy.