Search:
Match:
2 results
Research Paper#Eye-Tracking, Data Analysis, Adaptive Thresholding🔬 ResearchAnalyzed: Jan 3, 2026 16:55

Adaptive Thresholding for Eye-Tracking Data Analysis

Published:Dec 30, 2025 00:58
1 min read
ArXiv

Analysis

This paper addresses a critical issue in eye-tracking data analysis: the limitations of fixed thresholds in identifying fixations and saccades. It proposes and evaluates an adaptive thresholding method that accounts for inter-task and inter-individual variability, leading to more accurate and robust results, especially under noisy conditions. The research provides practical guidance for selecting and tuning classification algorithms based on data quality and analytical priorities, making it valuable for researchers in the field.
Reference

“Adaptive dispersion thresholds demonstrate superior noise robustness, maintaining accuracy above 81% even at extreme noise levels.”

PermalinkArXiv
Research Paper#Medical Imaging, Deep Learning, Computer Vision🔬 ResearchAnalyzed: Jan 3, 2026 19:46

AI Framework for CMIL Grading

Published:Dec 27, 2025 17:37
1 min read
ArXiv

Analysis

This paper introduces INTERACT-CMIL, a multi-task deep learning framework for grading Conjunctival Melanocytic Intraepithelial Lesions (CMIL). The framework addresses the challenge of accurately grading CMIL, which is crucial for treatment and melanoma prediction, by jointly predicting five histopathological axes. The use of shared feature learning, combinatorial partial supervision, and an inter-dependence loss to enforce cross-task consistency is a key innovation. The paper's significance lies in its potential to improve the accuracy and consistency of CMIL diagnosis, offering a reproducible computational benchmark and a step towards standardized digital ocular pathology.
Reference

“INTERACT-CMIL achieves consistent improvements over CNN and foundation-model (FM) baselines, with relative macro F1 gains up to 55.1% (WHO4) and 25.0% (vertical spread).”

PermalinkArXiv