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

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Optimal reactive power dispatch based on a multitask-assisted constrained multimodal multi-objective evolutionary algorithm.

iScience·2026

Same author

ITGB4 up-regulated by STAT3 reduces the sensitivity of bladder cancer to cisplatin by suppressing p53.

British journal of cancer·2026

Same author

Effects of different deodorization methods on eel flavor quality: A multidimensional volatile analysis.

Food research international (Ottawa, Ont.)·2026

Same author

DeepHSI: A transferable and expandable hyperspectral framework for industrial plant origin identification: A case study of Pogostemon cablin (Blanco) Benth.

Talanta·2026

Same author

mRNA Rather than Protein Expression of Hepatic Selenoprotein H is More Sensitive to Short-term Low Aflatoxin B<sub>1</sub> Exposure in Mice with Varying Selenium Intake.

Biological trace element research·2026

Same author

A diagnostic model based on clinical and enhanced computed tomography features to identify gastric schwannoma and gastric stromal tumor of different sizes: a multi-institution retrospective study.

Quantitative imaging in medicine and surgery·2026

Search research articles

Related Experiment Video

Updated: Jul 11, 2025

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

DC-SiamNet: Deep contrastive Siamese network for self-supervised MRI reconstruction.

Yanghui Yan¹, Tiejun Yang², Xiang Zhao¹

¹School of Information Science and Engineering, Henan University of Technology, Zhengzhou, 450001, China.

Computers in Biology and Medicine

|November 5, 2023

Summary

Deep learning accelerates magnetic resonance imaging (MRI) reconstruction. A novel self-supervised Deep Contrastive Siamese Network (DC-SiamNet) improves reconstruction accuracy without fully sampled data, outperforming existing methods.

Keywords:

Contrastive learning Deep learning MRI reconstruction Self-supervised learning

More Related Videos

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Related Experiment Videos

Last Updated: Jul 11, 2025

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

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Area of Science:

Medical Imaging
Deep Learning
Image Reconstruction

Background:

Deep learning significantly reduces MRI acquisition time.
Supervised methods require fully sampled data, limiting clinical use and performance with unavailable high-quality images.
Existing self-supervised methods struggle with structural accuracy due to lack of complete reference data.

Purpose of the Study:

To develop a self-supervised method for fast MRI reconstruction that overcomes limitations of existing approaches.
To enhance structural accuracy and texture details in reconstructed MRI images.
To enable high-quality MRI reconstruction even with undersampled data.

Main Methods:

Proposed a self-supervised Deep Contrastive Siamese Network (DC-SiamNet) utilizing a Siamese unrolled structure.
Incorporated an attention-weighted average pooling module for effective feature aggregation.
Designed a hybrid loss function for simultaneous reconstruction and contrastive learning across multiple domains (frequency, image, latent).

Main Results:

Achieved high reconstruction accuracy (0.93 SSIM, 33.984 dB PSNR) on the IXI brain dataset at 8x acceleration.
Demonstrated superior performance compared to other methods, approaching fully supervised results, especially at low sampling rates.
Validated strong cross-domain reconstruction ability for different brain contrast images.

Conclusions:

DC-SiamNet effectively addresses the limitations of self-supervised MRI reconstruction.
The proposed method achieves state-of-the-art performance, enabling faster and more accurate MRI acquisition.
DC-SiamNet shows promise for clinical applications requiring rapid, high-quality MRI scans.