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

Machine learning for predicting surgical difficulty of laparoscopic total mesorectal excision for rectal cancer: integrating MR-based pelvimetry and peritoneal reflection.

Frontiers in medicine·2026

Same author

Deep mutational scanning reveals the antibody escape and infectivity landscape of SARS-CoV-2 Omicron JN.1 and XEC receptor-binding domains.

Emerging microbes & infections·2026

Same author

WRCANet: wavelet residual cross-attention network for meibomian gland segmentation.

Biomedical optics express·2026

Same author

OphFusionNet: Uncertainty-driven multi-scale multimodal feature fusion network for ophthalmic diseases classification.

IEEE transactions on medical imaging·2026

Same author

Refining feature representation for accurate fundus lesion segmentation.

Medical physics·2026

Same author

PNET-PRISM: a multicenter-validated radiomics nomogram for noninvasive grading of pancreatic neuroendocrine tumors.

Insights into imaging·2026

Search research articles

Related Experiment Video

Updated: Aug 22, 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

Semi-supervised interactive fusion network for MR image segmentation.

Wenxuan Xu¹, Yun Bian², Yuxuan Lu¹

¹School of Electronic and Information Engineering, Soochow University, Jiangsu, China.

Medical Physics

|November 8, 2022

Summary

This summary is machine-generated.

This study introduces SFI-Net, a novel deep learning model that enhances medical image segmentation for cancer diagnosis. The semi-supervised approach improves accuracy in segmenting tumors and organs in MR images.

Keywords:

dual sequences feature interactive fusion semi-supervision

More Related Videos

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

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: Aug 22, 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

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Medical imaging analysis
Deep learning for medical applications
Cancer diagnosis and treatment

Background:

Medical image segmentation is crucial for cancer diagnosis and treatment.
Challenges include low contrast and complex anatomical structures in MR images.
Accurate segmentation of organs and lesions remains a significant hurdle.

Purpose of the Study:

To enhance the accuracy of organ and lesion segmentation in magnetic resonance (MR) images.
To provide improved tools for clinical diagnosis and cancer treatment planning.
To address the limitations of current segmentation techniques in MR imaging.

Main Methods:

Developed a selective feature interaction (SFI) module for extracting similar sequence image features.
Introduced a multi-scale guided feature reconstruction (MGFR) module for low-level features, small targets, and edge details.
Implemented a semi-supervised training method with uncertainty estimation to reduce manual annotation and boost accuracy.

Main Results:

Evaluated on 395 pancreatic cancer and 259 brain tumor MR datasets using cross-validation.
The proposed SFI-Net demonstrated superior segmentation performance compared to existing deep learning methods.
Achieved better segmentation of pancreas and tumors in MR images.

Conclusions:

SFI-Net effectively fuses dual-sequence MR images for pancreas and tumor segmentation.
The proposed semi-supervised strategy significantly enhances the performance of SFI-Net.
The method offers a promising advancement for cancer segmentation in clinical practice.