PulseAugur
EN
LIVE 06:10:17

GazeRefine uses expert gaze for training-free medical image segmentation

By PulseAugur Editorial · [1 sources] ·

Researchers have developed GazeRefine, a novel framework that utilizes expert gaze as a prompt for training-free medical image segmentation. This method converts sparse gaze fixations into foreground and background priors, which are then refined in a frozen DINOv3 feature space. GazeRefine eliminates the need for segmentation masks, fine-tuning, or gradient updates, demonstrating strong performance on polyp segmentation and competitive results on prostate MRI segmentation. AI

IMPACT This training-free approach could significantly reduce the need for extensive expert annotations in medical imaging tasks.

RANK_REASON The item describes a new research paper detailing a novel framework for medical image segmentation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

GazeRefine uses expert gaze for training-free medical image segmentation

How we ranked this

Signal score
34 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes a new research paper detailing a novel framework for medical image segmentation. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Mohammed Oussama Benyahia, Marouane Tliba, Mohamed Amine Kerkouri, Taifour Yousra, Bin Wang, Max Bengtsson, Gorkem Durak, Elif Keles, Zuheng Ming, Marek Penhaker, Azeddine Beghdadi, Ulas Bagci, Aladine Chetouani ·

    GazeRefine: Expert Gaze as a Test-Time Prompt for Training-Free Medical Image Segmentation

    arXiv:2609.01310v1 Announce Type: cross Abstract: Medical image segmentation remains difficult to scale because high-performing methods typically rely on dense expert annotations and task-specific training. We introduce GazeRefine, a training-free framework that uses gaze as an i…

RELATED ENTITIES

RELATED TOPICS