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

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

Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation.

IEEE transactions on medical imaging·2026

Same author

M$^{2}$SegMamba: Mamba-Based Incomplete Multimodal Learning for Brain Tumor Segmentation With Few Samples.

IEEE journal of biomedical and health informatics·2025

Same author

Deep Learning Models Connecting Images and Text: A Primer for Radiologists.

Radiographics : a review publication of the Radiological Society of North America, Inc·2025

Same author

Towards reliable WMH segmentation under domain shift: An application study using maximum entropy regularization to improve uncertainty estimation.

Computers in biology and medicine·2025

Same author

Prompt Learning With Bounding Box Constraints for Medical Image Segmentation.

IEEE transactions on bio-medical engineering·2025

Same author

Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation.

Medical image analysis·2025

Search research articles

Related Experiment Video

Updated: Mar 3, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study.

Jose Dolz¹, Christian Desrosiers¹, Ismail Ben Ayed¹

¹LIVIA Laboratory, École de technologie supérieure (ETS), Montreal, QC, Canada.

|April 29, 2017

Summary

This study introduces an efficient 3D convolutional neural network (CNN) for segmenting subcortical brain structures in MRI scans. The novel approach achieves state-of-the-art results on large, diverse datasets, offering a faster alternative to traditional methods.

Keywords:

3D CNN Brain Deep learning Fully CNN MRI segmentation

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

Published on: February 4, 2022

Related Experiment Videos

Last Updated: Mar 3, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

Published on: February 4, 2022

Area of Science:

Neuroimaging
Artificial Intelligence
Medical Image Analysis

Background:

Subcortical brain structure segmentation is crucial for neuroimaging studies.
Traditional methods often require registration and normalization, increasing computational cost.
3D Convolutional Neural Networks (CNNs) offer potential but face computational challenges.

Purpose of the Study:

To develop an efficient 3D CNN for subcortical brain structure segmentation in MRI.
To address the computational and memory demands of 3D CNNs.
To achieve robust and accurate segmentation across diverse datasets.

Main Methods:

A 3D fully convolutional neural network (CNN) architecture utilizing small kernels for deeper networks.
Integration of local and global context by embedding intermediate-layer features.
End-to-end, single-stage training on GPUs, leveraging dense inference.

Main Results:

State-of-the-art performance achieved on the ISBR dataset.
Demonstrated robustness and high consistency with atlas-based methods on the large-scale ABIDE dataset (1112 subjects, 17 sites).
Significantly faster segmentation compared to atlas-based methods, avoiding registration/normalization.

Conclusions:

The proposed 3D CNN method provides an efficient and accurate solution for subcortical brain structure segmentation.
The model's robustness across diverse acquisition protocols and demographics makes it suitable for large-scale neuroanatomical studies.
This work represents the first study of subcortical segmentation on such large-scale, heterogeneous data.