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

Confocal Fluorescence Microscopy

Confocal Fluorescence Microscopy

Confocal microscopy is an advanced microscopic technique. The prime advantage of the confocal microscope over other microscopy techniques is its ability to block the out-of-focus light from the illuminated samples using pinholes. It is widely used with fluorescence optics to obtain high-resolution, sharp contrast images. Unlike optical microscopes, confocal microscopes use a focused beam of light laser to scan the entire sample surface at different z-planes. These microscopes are, therefore,...

You might also read

Related Articles

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

Sort by

Same author

Bimodality in pan-cancer proteomics reveals new opportunities for biomarker discovery.

Genome biology·2026

Same author

Construction of an Effector-Target Interaction Network for Identification of Immune-Related Effectors in Ralstonia pseudosolanacearum.

Molecular plant pathology·2026

Same author

Immune dysregulation and cellular dysfunction mediate di-n-pentyl phthalate-induced hepatotoxicity: Insights from single-cell RNA sequencing.

Food and chemical toxicology : an international journal published for the British Industrial Biological Research Association·2026

Same author

Enabling cross-indication protein expression analysis using a curated pan-cancer dataset and a tailored workflow.

Scientific reports·2026

Same author

Di-n-pentyl phthalate exposure alters intestinal structure and gut microbiota composition and characteristics in mice.

Ecotoxicology and environmental safety·2026

Same author

Transformer-based self-supervised learning of pixel- and frequency-domain features for DMI grading on OCTA images.

Applied optics·2025

Search research articles

Related Experiment Video

Updated: Jun 20, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

DFMF: Harnessing spectral-spatial synergy for MR image segmentation through Dual-Task Feature Mining Framework.

Wenyan Zhong¹, Zailiang Chen¹, Hailan Shen¹

¹School of Computer Science, Central South University, No. 932, Lushan South Road, Changsha, 410083, Hunan Province, China.

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

|July 19, 2025

Summary

This study introduces a Dual-task Feature Mining Framework (DFMF) for automated Magnetic Resonance (MR) image segmentation. The novel approach enhances segmentation accuracy by leveraging unlabeled data and rich anatomical information, outperforming existing methods.

Keywords:

Consistency regularization Dual-task learning Image inpainting MRI Medical image segmentation

More Related Videos

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

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jun 20, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

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

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Automated segmentation of Magnetic Resonance (MR) images is crucial for medical applications like tumor delineation and lesion tracking.
Traditional supervised learning methods require extensive annotated data, which is costly and time-consuming to acquire.
MR images possess inherent anatomical information that remains underexploited for improving segmentation performance.

Purpose of the Study:

To develop a novel framework that effectively utilizes inherent anatomical information in MR images for enhanced segmentation.
To reduce reliance on heavily annotated datasets by integrating self-supervised and semi-supervised learning paradigms.
To improve the discriminative power of feature representations for complex anatomical structures.

Main Methods:

Proposed a Dual-task Feature Mining Framework (DFMF) that simultaneously performs image inpainting and segmentation.
Introduced a Self-consistency Loss to enforce consistency between inpainted and original images, maximizing the utility of unlabeled data.
Employed a Hybrid Receptive Field Network (HRFNet) backbone to capture both global frequency-domain information and fine spatial details.

Main Results:

The DFMF achieved superior segmentation performance compared to state-of-the-art methods across four MR image datasets.
The dual-task mechanism effectively extracted richer and more discriminative feature representations.
Ablation studies confirmed the significant contribution of each component within the DFMF.

Conclusions:

The proposed DFMF framework offers a powerful approach for automated MR image segmentation, particularly in scenarios with limited annotated data.
Integrating self-supervised and semi-supervised learning through dual-task optimization enhances feature representation and segmentation accuracy.
The HRFNet backbone effectively balances global and local feature extraction for improved performance.