New AI model TrailNet uses gaze data for medical image segmentation

Researchers have developed TrailNet, a novel network designed for weakly supervised medical image segmentation. This system effectively utilizes gaze data, including fixations and trajectories, to model temporal context and enhance perception of target regions in medical images. To address noise in gaze data and enable gaze-free inference, TrailNet incorporates a trajectory-guided spatio-temporal encoder, a multi-scale uncertainty decoder, and a cycle distillation strategy. Experiments show TrailNet outperforms existing methods, achieving Dice scores of 81.25% and 81.85% on two public datasets. AI

IMPACT This research could lead to more efficient and less labor-intensive medical image annotation processes.

RANK_REASON The cluster contains a research paper detailing a new AI model and its experimental results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• CatalyzeX
• Connected Papers
• DagsHub
• Gotit.pub
• Hugging Face
• Litmaps
• ScienceCast
• scite Smart Citations
• TrailNet

• paper
• other

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