Metraipolis › archive › dc_e138cc96ec7f
GazeRIB: Systematic Evaluation of Multi-Reader Gaze-Guided Chest X-ray Learning — arXiv:2610.42152
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.42152
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T05:40:29.202Z
- SHA-256 of the archived text
06ede6952b6dabd3e6fb256b5384f88ddde000218ebd69469bdaef81c6e5a3af- Stable URL of this page
https://metraipolis.com/documento/dc_e138cc96ec7f
How to cite
GazeRIB: Systematic Evaluation of Multi-Reader Gaze-Guided Chest X-ray Learning — arXiv:2610.42152 — arXiv (en), https://arxiv.org/abs/2610.42152 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e138cc96ec7f (Metraipolis archive dc_e138cc96ec7f, sha256 06ede6952b6dabd3e6fb256b5384f88ddde000218ebd69469bdaef81c6e5a3af)
BibTeX
@misc{dce138cc96ec7f,
title = {GazeRIB: Systematic Evaluation of Multi-Reader Gaze-Guided Chest X-ray Learning — arXiv:2610.42152},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.42152},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e138cc96ec7f; sha256 06ede6952b6dabd3e6fb256b5384f88ddde000218ebd69469bdaef81c6e5a3af},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42152. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Radiologists' visual attention can supervise medical image learning, but how reader panel composition affects its value remains untested. We evaluated GazeRIB (Gaze-guided Radiologist-Informed Blackout), which masks unviewed regions during training and uses unmasked images at inference. Eight experts repeatedly read the same 80 chest X-rays (CXRs). We compared individual readers with three-, five- and eight-reader panels across seven architectures and 10 seeds, evaluating 910 models on a separate 2,897-CXR cohort for four-class severity prediction. Every panel improved macro F1 over the no-gaze baseline by 5.33-7.47 percentage points (pp; Bonferroni-adjusted p < 0.007); no individual reader reached significance on this endpoint. Three readers captured 73-80% of the eight-reader gain in macro F1, the area under the receiver-operating-characteristic curve (ROC-AUC) and the area under the precision-recall curve (AU-PRC). On external validation without retraining, all four panels improved ROC-AUC on SIIM-FISABIO-RSNA by +1.93 to +4.24 pp (p <= 0.004); on MIMIC-Eye no panel differed significantly from baseline, whereas the single-reader average declined (-1.40 pp, p = 0.008). Reader composition therefore influenced performance, although transfer depended on the cohort. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC); Image and Video Processing (eess.IV); Signal Processing (eess.SP). Pagina del lavoro: https://arxiv.org/abs/2610.42152 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T05:23:57.973Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).