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 Videos

Fast cortical thickness estimation using deep learning-based anatomy segmentation and diffeomorphic registration.

Jiong Wu¹, Shuang Zhou²

¹School of Computer and Electrical Engineering, Hunan University of Arts and Science, Changde, 415000, Hunan, China.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society

|May 16, 2025

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

Current practices and trends of axillary surgery de-escalation and lymphedema management for breast cancer in China: a nationwide cross-sectional survey.

World journal of surgical oncology·2026

Same author

Spatially interpretable artificial intelligence framework to tailored neoadjuvant dual HER2 blockade in HER2-positive breast cancer.

Signal transduction and targeted therapy·2026

Same author

Standard: human breast cancer organoids derived from diverse clinical sample sources.

Cell regeneration (London, England)·2026

Same author

Exploratory pilot study of minimally invasive therapy: laser ablation combined with acellular dermal matrix implantation for recurrent sacrococcygeal pilonidal disease.

Frontiers in bioengineering and biotechnology·2026

Same author

Preparation and application of IgM monoclonal antibodies in half-smooth tongue sole (Cynoglossus semilaevis).

Fish & shellfish immunology·2026

Same author

Shifting Practice Patterns in Implant-based Breast Reconstruction in China: Insights From a 13-year Large-scale Retrospective Cohort.

Plastic and reconstructive surgery. Global open·2026

Same journal

RGCNN-nnUNet: Recurrent group equivariant nnU-Net for robust brain tissue segmentation on stroke NCCT.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Same journal

Self-supervised isotropic reconstruction for abnormality detection in anisotropic MRI.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Same journal

WDBDM: Wavelet-based dual-branch diffusion model for low-dose CT and PET denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Same journal

ScribSAM: A robust scribble-supervised framework for spatiotemporal segmentation of breast lesions in ultrasound videos.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Same journal

Anatomically and biochemically guided deep image prior for sodium MRI denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Same journal

Segment Anything Model for medical image segmentation: A review.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

See all related articles

This study introduces a faster, more consistent deep learning framework for estimating cortical thickness from MRIs. The new method improves upon traditional techniques, making brain imaging analysis more efficient for large datasets.

Area of Science:

Neuroimaging
Computational Neuroscience
Medical Image Analysis

Background:

Accurate cortical thickness estimation from MRI is vital for neuroscience and clinical applications.
Traditional methods like Diffeomorphic Registration-based Cortical Thickness Estimation (DiReCT) are computationally intensive and lack reproducibility.
Limitations hinder the application of current methods in large-scale studies and real-time scenarios.

Purpose of the Study:

To develop a novel framework for efficient and reproducible cortical thickness estimation using deep learning and diffeomorphic registration.
To overcome the computational time and consistency limitations of existing methods.
To provide a publicly available tool for the research community.

Main Methods:

Utilizing a convolutional neural network (CNN) for accurate brain anatomy segmentation from MRIs.

Keywords:

Anatomy segmentation Cortical thickness Deep learning Diffeomorphic registration MRI Thickness propagation

Related Experiment Videos

Employing distance maps derived from segmentation in an unsupervised deep learning registration network for fast, diffeomorphic registration.

Implementing a novel algorithm based on time-point diffeomorphisms for final thickness map calculation.

Main Results:

The proposed deep learning framework significantly reduces computational time compared to traditional DiReCT.
The method demonstrates superior consistency and accuracy, validated against FreeSurfer's surface-based measures across two datasets.
Experimental results show improved performance over DiReCT and DL+DiReCT in efficiency and FreeSurfer consistency.

Conclusions:

The developed deep learning framework offers a highly efficient and reproducible solution for cortical thickness estimation from MRIs.
This approach is suitable for large-scale neuroimaging studies and real-time applications.
The availability of code and pre-trained models facilitates broader adoption and further research.