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

Hippocampus Segmentation Based on Local Linear Mapping.

Shumao Pang1, Jun Jiang2, Zhentai Lu1

  • 1Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China.

Scientific Reports
|April 4, 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

[A case of successful transcatheter aortic valve implantation for severe noncalcified aortic regurgitation].

Zhonghua xin xue guan bing za zhi·2015
Same author

Infrared spectra of small anionic water clusters from density functional theory and wavefunction theory calculations.

Physical chemistry chemical physics : PCCP·2015
Same author

Steering charge kinetics in photocatalysis: intersection of materials syntheses, characterization techniques and theoretical simulations.

Chemical Society reviews·2015
Same author

Genetic diversity of HIV-1 and transmitted drug resistance among newly diagnosed individuals with HIV infection in Hangzhou, China.

Journal of medical virology·2015
Same author

Metformin represses androgen-dependent and androgen-independent prostate cancers by targeting androgen receptor.

The Prostate·2015
Same author

Dietary riboflavin deficiency decreases immunity and antioxidant capacity, and changes tight junction proteins and related signaling molecules mRNA expression in the gills of young grass carp (Ctenopharyngodon idella).

Fish & shellfish immunology·2015

Local Linear Mapping (LLM) offers automatic hippocampus segmentation using distance fields (DF) and magnetic resonance (MR) data. This novel framework achieves high accuracy, demonstrating its effectiveness for brain image analysis.

Area of Science:

  • Medical Imaging
  • Computational Neuroscience
  • Machine Learning

Background:

  • Accurate hippocampus segmentation is crucial for diagnosing neurological disorders.
  • Existing methods often struggle with the complexity and variability of brain structures.
  • Developing automated and robust segmentation techniques is a significant challenge.

Purpose of the Study:

  • To introduce a novel fusion framework, Local Linear Mapping (LLM), for automatic hippocampus segmentation.
  • To leverage both magnetic resonance (MR) and distance field (DF) data for improved segmentation accuracy.
  • To evaluate the performance of LLM on a dataset of human brain images.

Main Methods:

  • Proposed a k-means clustering method for constructing MR and DF dictionaries.

Related Experiment Videos

  • Utilized a locally linear mapping assumption between MR and DF manifolds.
  • Combined MR and DF dictionaries for predicting DF, followed by a confidence-based weighted average for final segmentation.

    • Main Results:

    • The LLM framework demonstrated effective hippocampus segmentation on 35 subjects from the SATA dataset.
    • Achieved high mean Dice similarity coefficients: 0.8697 (left), 0.8770 (right), and 0.8734 (bilateral).
    • The method successfully estimated hippocampus labels based on the predicted distance fields.

    Conclusions:

    • Local Linear Mapping (LLM) provides an effective and accurate approach for automatic hippocampus segmentation.
    • The fusion of MR and DF data within the LLM framework enhances segmentation performance.
    • This method holds promise for clinical applications requiring precise brain structure analysis.