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

A comparison of accurate automatic hippocampal segmentation methods.

Azar Zandifar1, Vladimir Fonov2, Pierrick Coupé3

  • 1McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University, Montreal, Canada; Department of Biomedical Engineering, McGill University, Montreal, Canada.

Neuroimage
|April 14, 2017
PubMed
Summary
This summary is machine-generated.

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

Cardiovascular risk and hippocampal-cognitive coupling in Alzheimer's disease.

medRxiv : the preprint server for health sciences·2026
Same author

A digital twin methodology using retrospective patient data for sample size reduction in Alzheimer's disease clinical trials.

Alzheimer's research & therapy·2026
Same author

Ventricular enlargement is associated with early Alzheimer's disease pathophysiology.

Brain communications·2026
Same author

Choroidal-ventricular system abnormalities are linked to amyloid-β aggregation in Alzheimer's disease.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

Quantitative susceptibility mapping of the brain is associated with inflammatory changes in Alzheimer's disease related areas.

Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism·2026
Same author

Remote collaboration in virtual reality induces physiological synchrony comparable to face-to-face interaction.

Scientific reports·2026

This study compared automated methods for segmenting the hippocampus, a brain region affected by Alzheimer's disease (AD). A nonlinear patch-based method with error correction showed the highest accuracy and conformity with manual segmentation.

Area of Science:

  • Neuroimaging
  • Alzheimer's Disease Research
  • Brain Anatomy

Background:

  • The hippocampus is an early target of Alzheimer's disease (AD).
  • Accurate hippocampal segmentation is crucial for AD diagnosis and monitoring.
  • Existing automated segmentation methods lack comprehensive comparative validation.

Purpose of the Study:

  • To compare four fully automated hippocampal segmentation methods.
  • To evaluate their conformity with manual segmentation and utility as AD biomarkers.
  • To assess the impact of error correction on segmentation accuracy and classification performance.

Main Methods:

  • Four automated hippocampal segmentation algorithms were applied to the same dataset.
  • Manual segmentation was used as the gold standard for comparison.
Keywords:
Alzheimer's diseaseArea under receiver operating characteristic curveCohen's dDice's κHippocampal segmentation

Related Experiment Videos

  • Error correction techniques were applied to enhance segmentation accuracy.
  • Classification performance was evaluated using effect size and receiver operating characteristic (ROC) analysis for Alzheimer's disease (AD) vs. normal control (NC) and stable mild cognitive impairment (sMCI) vs. progressive mild cognitive impairment (pMCI) groups.

    • Main Results:

    • The nonlinear patch-based segmentation method with error correction demonstrated the highest accuracy and conformity with manual segmentation (κ=0.894).
    • FreeSurfer, with error correction, yielded the largest effect size for distinguishing between AD/NC and sMCI/pMCI groups.
    • Using hippocampal volume, age, and sex, ROC analysis achieved up to 0.8813 for AD vs. NC and 0.6451 for sMCI vs. pMCI.

    Conclusions:

    • Automated hippocampal segmentation methods, even with error correction, did not show significant differences in overall performance for clinical biomarker applications.
    • The nonlinear patch-based method offers superior accuracy and manual segmentation conformity.
    • Further research may be needed to optimize automated methods for robust clinical utility in AD detection and progression monitoring.