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

Search research articles

Related Experiment Video

Updated: Apr 30, 2026

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

GiTNet: A graph-based trajectory-informed network for gaze-supervised medical image segmentation.

Shaoxuan Wu¹, Xiao Zhang¹, Jingkun Chen²

¹College of Computer Science, Northwest University, Xi'an, China.

Medical Image Analysis

|April 28, 2026

Summary

This summary is machine-generated.

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

Achieving Ultrahigh Light Yield with Trace Lithium Doping: Synergistic Defect Passivation in Large-Sized Rb<sub>2</sub>CuBr<sub>3</sub> Scintillators.

The journal of physical chemistry letters·2026

Same author

From Gaze to Insight: Bridging Human Visual Attention and Vision Language Model Explanation for Weakly-Supervised Medical Image Segmentation.

IEEE transactions on medical imaging·2025

Same author

High-Performance X-Ray Detection and Optical Information Storage via Dual-Mode Luminescent Modulation in Na<sub>3</sub>KMg<sub>7</sub>(PO<sub>4</sub>)<sub>6</sub>:Eu.

Molecules (Basel, Switzerland)·2025

Same author

The Chemotherapy Medication of <i>Evodia lepta</i> (Spreng). Merr. on the Viability of Tongue Cancer Cells Through the PD-L1/MMP14/HSPA5 Pathway.

Cancer management and research·2025

Same author

HELPNet: Hierarchical perturbations consistency and entropy-guided ensemble for scribble supervised medical image segmentation.

Medical image analysis·2025

Same author

H-Calibration: Rethinking Classifier Recalibration With Probabilistic Error-Bounded Objective.

IEEE transactions on pattern analysis and machine intelligence·2025

Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026

Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026

Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026

Same journal

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026

Same journal

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026

Same journal

Annotation-efficient medical image segmentation via cross-latent graphs and vector-quantized memory.

Medical image analysis·2026

See all related articles

This study introduces GiTNet, a novel network for medical image segmentation that effectively uses eye-tracking data. GiTNet improves segmentation accuracy by integrating gaze trajectories and graph structures, outperforming existing methods.

Area of Science:

Medical Image Analysis
Computer Vision
Artificial Intelligence

Background:

Medical image segmentation is crucial but annotation-intensive and costly.
Eye tracking offers an economical annotation solution, but gaze inaccuracies and underutilized dynamic trajectories limit its effectiveness.
Existing methods struggle with ambiguous regions and complex anatomical structures.

Purpose of the Study:

To develop an efficient gaze-supervision method for medical image segmentation.
To leverage both static fixations and dynamic gaze trajectories for improved segmentation accuracy.
To address limitations of current eye-tracking-based supervision in medical imaging.

Main Methods:

Proposed the graph-based trajectory-informed network (GiTNet).

Keywords:

Eye-tracking Graph neural network Medical image segmentation Trajectory relational alignment

More Related Videos

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: Apr 30, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Integrated static fixations with dynamic trajectories for comprehensive anatomical and lesion modeling.

Introduced trajectory relational alignment (TRA), neighbor-aware pseudo supervision (NAP), and graph representational consistency (GRC) to enhance supervision and reduce noise.

Main Results:

GiTNet effectively models complex anatomical relationships and potential lesion areas.
The proposed methods (TRA, NAP, GRC) strengthen focus on relevant regions and reduce uncertainty in gaze data.
GiTNet demonstrated superior performance compared to state-of-the-art weakly supervised methods on two public datasets.

Conclusions:

GiTNet offers a powerful and efficient approach to weakly supervised medical image segmentation using eye-tracking data.
The integration of dynamic gaze trajectories and graph-based modeling significantly enhances segmentation accuracy, especially in ambiguous areas.
This work paves the way for more effective and less labor-intensive medical image annotation.