Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 8, 2026

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

Using manifold learning for atlas selection in multi-atlas segmentation.

Albert K Hoang Duc¹, Marc Modat, Kelvin K Leung

¹Centre for Medical Image Computing, University College London, London, United Kingdom. albert.hoang.duc.10@ucl.ac.uk

|August 13, 2013

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

Predictive radiomics for evaluation of cancer immune signature in glioblastoma: The PRECISE-GBM study.

Neuro-oncology advances·2026

Same author

From Offline to Inline Without Pain: A Practical Framework for Translating Offline MR Reconstructions to Inline Deployment Using the Gadgetron Platform.

Magnetic resonance in medicine·2026

Same author

In silico modelling of changes in spinal cord blood flow after endovascular aortic aneurysm repair.

Computer methods and programs in biomedicine·2026

Same author

Location patterns and longitudinal progression of white matter hyperintensities.

medRxiv : the preprint server for health sciences·2026

Same author

Examining the role of systemic inflammation as a mediator of the glycaemia-brain volume associations in women.

PloS one·2026

Same author

Retention and longitudinal change in Insight 46, an intensive neuroscience sub-study of the 1946 British birth cohort.

BMC research notes·2026

Same journal

Thymidylate synthase inhibitory drugs induce p53-dependent pathways differently.

PloS one·2026

Same journal

Top-down and bottom-up attention for joint pattern classification and reconstruction.

PloS one·2026

Same journal

Short- and long-term scaling behavior of blood pressure and pulse arrival time during sleep in healthy controls and patients with obstructive sleep apnea.

PloS one·2026

Same journal

Double DQN-based secrecy energy efficiency and fairness performance in IRS-assisted NOMA systems with friendly jamming.

PloS one·2026

Same journal

10 recommendations for strengthening citizen science for improved societal and ecological outcomes: A co-produced analysis of challenges and opportunities in the 21st century.

PloS one·2026

Same journal

Paying in public: Peer effects, impression management, and willingness to pay on digital payment platforms.

PloS one·2026

See all related articles

Manifold learning improves anatomical structure segmentation by optimizing atlas selection. Locally Linear Embedding demonstrated superior performance in selecting the best atlases for multi-atlas segmentation, enhancing accuracy.

Area of Science:

Medical Image Analysis
Computational Anatomy
Machine Learning in Healthcare

Background:

Multi-atlas segmentation relies on accurate atlas selection for segmenting anatomical structures.
Manifold learning offers a novel approach to atlas selection, but different techniques yield varied results.
Previous studies lacked systematic comparison and justification for chosen manifold learning methods and parameters.

Purpose of the Study:

To systematically compare three manifold learning techniques (Isomap, Laplacian Eigenmaps, Locally Linear Embedding) for atlas selection in multi-atlas segmentation.
To identify the optimal manifold learning technique and parameters for enhancing segmentation accuracy.
To evaluate the performance of manifold learning-based atlas selection against state-of-the-art methods.

Main Methods:

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: May 8, 2026

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

A leave-one-out cross-validation experiment was conducted on 110 manually segmented hippocampal atlases.
Three manifold learning techniques were compared: Isomap, Laplacian Eigenmaps, and Locally Linear Embedding.
The optimal technique and parameters were applied to segment 30 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset.

Main Results:

Locally Linear Embedding (LLE) provided the best atlas selection results for the studied dataset.
Manifold learning-based atlas selection achieved segmentation accuracy comparable to or exceeding state-of-the-art methods.
Fine-tuning manifold learning parameters further improved segmentation accuracy.

Conclusions:

Manifold learning is an effective strategy for optimizing atlas selection in multi-atlas segmentation.
Locally Linear Embedding shows particular promise for improving segmentation accuracy in neuroimaging.
Systematic evaluation and parameter optimization of manifold learning techniques are crucial for maximizing segmentation performance.