Search research articles

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

Laser-Based Micro/Nano Additive Manufacturing of Conductive Structures on Transparent Substrates: Technical Approaches, Challenges, and Future Prospects.

Langmuir : the ACS journal of surfaces and colloids·2025

Same author

Medical image segmentation using dual-decoder mutual teaching with a mean teacher framework.

Pattern recognition·2025

Same author

A deep semi-supervised learning approach to the detection of glaucoma on out-of-distribution retinal fundus image datasets.

BMC ophthalmology·2025

Same author

Adaptive boundary-enhanced Dice loss for image segmentation.

Biomedical signal processing and control·2025

Same author

Parameter Optimization for Laser Peen Forming on 6005A-T6 Aluminum Alloy Plates to Enhance the Constrained Deformation of Integral Stiffened Plates.

Materials (Basel, Switzerland)·2024

Same author

Semi-supervised image segmentation using a residual-driven mean teacher and an exponential Dice loss.

Artificial intelligence in medicine·2024

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

Search research articles

Related Experiment Video

Updated: Jun 28, 2025

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

UGLS: an uncertainty guided deep learning strategy for accurate image segmentation.

Xiaoguo Yang¹, Yanyan Zheng¹, Chenyang Mei²

¹Wenzhou People's Hospital, The Third Affiliated Hospital of Shanghai University, Wenzhou, China.

Frontiers in Physiology

|April 23, 2024

Summary

This study introduces an uncertainty-guided deep learning strategy (UGLS) to improve image segmentation accuracy. The novel method enhances U-Net performance for segmenting optic cup and lung regions in medical images.

Keywords:

deep learning fundus image image segmentation optic cup optic cup deep learning training strategy

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: Jun 28, 2025

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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

Computer Vision
Medical Image Analysis
Deep Learning

Background:

Accurate image segmentation is vital for computer vision and medical diagnostics.
Existing neural networks like U-Net require enhancement for precise multi-object segmentation across diverse image modalities.

Purpose of the Study:

To develop and validate a novel uncertainty-guided deep learning strategy (UGLS) for improved image segmentation.
To enhance the performance of the U-Net architecture in segmenting multiple objects of interest.

Main Methods:

Developed a novel uncertainty-guided deep learning strategy (UGLS).
Introduced a boundary uncertainty map based on coarse segmentation from U-Net.
Combined uncertainty maps with input images for fine object segmentation.

Main Results:

Achieved an average Dice Score (DS) of 0.8791 and sensitivity (SEN) of 0.8858 for optic cup segmentation.
Obtained high Dice Scores (0.9605-0.9668) for left and right lung segmentation from X-ray images.
Demonstrated superior or comparable performance against five advanced segmentation networks.

Conclusions:

The UGLS significantly improves U-Net's segmentation performance.
The method is effective for segmenting optic cup regions in fundus images and lung regions in X-ray images.
UGLS offers a promising approach for enhancing medical image segmentation accuracy.