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

An international study of factors affecting variability of dosimetry calculations, part 5: impact of segmentation methods.

EJNMMI physics·2026

Same author

Mitochondrial diseases: from molecular mechanisms to therapeutic advances.

Signal transduction and targeted therapy·2025

Same author

Social isolation and depressive symptoms among chinese older adults: Serial mediating roles of social support and resilience.

Geriatric nursing (New York, N.Y.)·2025

Same author

Mitochondria-Targeting Virus-Like Gold Nanoparticles Enhance Chemophototherapeutic Efficacy Against Pancreatic Cancer in a Xenograft Mouse Model.

International journal of nanomedicine·2025

Same author

Non-surgery strategy versus hepatectomy in hepatocellular carcinoma patients with complete response after conversion therapy: a meta-analysis.

World journal of surgical oncology·2024

Same author

Epigenome-Wide and Methylation Risk Score Analysis of Body Mass Index Among People with HIV.

Epigenomes·2024

Search research articles

Related Experiment Video

Updated: Aug 27, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

TransMorph: Transformer for unsupervised medical image registration.

Junyu Chen¹, Eric C Frey¹, Yufan He²

¹Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Medical Institutes, Baltimore, MD, USA; Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA.

Medical Image Analysis

|September 26, 2022

Summary

This summary is machine-generated.

TransMorph, a novel hybrid Transformer-ConvNet model, enhances medical image registration by better capturing spatial relationships. This Transformer-based approach significantly improves accuracy in 3D medical image registration tasks.

Keywords:

Computerized phantom Deep learning Image registration Vision transformer

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Related Experiment Videos

Last Updated: Aug 27, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Convolutional Neural Networks (ConvNets) dominate medical image analysis but struggle with long-range spatial relationships.
Vision Transformers offer improved performance by addressing ConvNet limitations in medical imaging applications.

Purpose of the Study:

Introduce TransMorph, a hybrid Transformer-ConvNet model for volumetric medical image registration.
Develop diffeomorphic and Bayesian variants of TransMorph for topology preservation and uncertainty estimation.

Main Methods:

Proposed TransMorph, a hybrid model integrating Transformer and ConvNet architectures.
Developed diffeomorphic variants for topology-preserving deformations.
Created a Bayesian variant for registration uncertainty estimation.
Validated models on 3D brain MRI and CT datasets across multiple registration applications.

Main Results:

TransMorph demonstrated substantial performance improvements over baseline methods in qualitative and quantitative evaluations.
Transformer-based registration showed superior spatial correspondence comprehension.
Diffeomorphic and Bayesian variants provided enhanced registration accuracy and reliable uncertainty estimates.

Conclusions:

TransMorph effectively leverages Transformer architectures for superior medical image registration.
The proposed model offers significant advancements in accuracy and reliability for 3D medical image analysis.
Transformers are a promising direction for future medical image registration research.