Eye Tracking-Enhanced Deep Learning for Medical Image Analysis: A Systematic Review on Data Efficiency, Interpretability, and Multimodal Integration
Bioengineering · 05.09.2025 · 12 (9) · 954
DOI: 10.3390/bioengineering12090954 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Bioengineering, online erschienen am 05.09.2025. Verfasst von Jiangxia Duan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Military Biomedical Engineering, Air Force Medical University, No. 169 Changle West Road, Xi'an 710032, China. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 120 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program, Quick Response Plan of Air Force Military Medical University, National Natural Science Foundation of China.
Abstract (Originalsprache)
Deep learning (DL) has revolutionized medical image analysis (MIA), enabling early anomaly detection, precise lesion segmentation, and automated disease classification. However, its clinical integration faces two major challenges: reliance on limited, narrowly annotated datasets that inadequately capture real-world patient diversity, and the inherent “black-box” nature of DL decision-making, which complicates physician scrutiny and accountability. Eye tracking (ET) technology offers a transformative solution by capturing radiologists’ gaze patterns to generate supervisory signals. These signals enhance DL models through two key mechanisms: providing weak supervision to improve feature recognition and diagnostic accuracy, particularly when labeled data are scarce, and enabling direct comparison between machine and human attention to bridge interpretability gaps and build clinician trust. This approach also extends effectively to multimodal learning models (MLMs) and vision–language models (VLMs), supporting the alignment of machine reasoning with clinical expertise by grounding visual observations in diagnostic context, refining attention mechanisms, and validating complex decision pathways. Conducted in accordance with the PRISMA statement and registered in PROSPERO (ID: CRD42024569630), this review synthesizes state-of-the-art strategies for ET-DL integration. We further propose a unified framework in which ET innovatively serves as a data efficiency optimizer, a model interpretability validator, and a multimodal alignment supervisor. This framework paves the way for clinician-centered AI systems that prioritize verifiable reasoning, seamless workflow integration, and intelligible performance, thereby addressing key implementation barriers and outlining a path for future clinical deployment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Military Biomedical Engineering, Air Force Medical University, No. 169 Changle West Road, Xi'an 710032, China.
- Shaanxi Provincial Key Laboratory of Bioelectromagnetic Detection and Intelligent Perception, No. 169 Changle West Road, Xi'an 710032, China.
- College of Electrical Engineering, Chongqing University, No. 174, Shazheng Street, Shapingba District, Chongqing 400000, China.
ORCID-Profile: Meiwei Zhang, Xiaopan Xu, Hongbing Lu
Förderung
- National Key Research and Development Program
- Quick Response Plan of Air Force Military Medical University
- National Natural Science Foundation of China
- Sword Action Talent Program
- Joint Founding Project of Innovation Research Institute of Xijing Hospital
Zitieren
APA
Duan, J., Zhang, M., Song, M., Xu, X., & Lu, H. (2025). Eye Tracking-Enhanced Deep Learning for Medical Image Analysis: A Systematic Review on Data Efficiency, Interpretability, and Multimodal Integration. Bioengineering, 12(9), 954. https://doi.org/10.3390/bioengineering12090954
Vancouver
Duan J, Zhang M, Song M, Xu X, Lu H. Eye Tracking-Enhanced Deep Learning for Medical Image Analysis: A Systematic Review on Data Efficiency, Interpretability, and Multimodal Integration. Bioengineering. 2025;12(9):954. doi:10.3390/bioengineering12090954
BibTeX
@article{Duan2025,
author = {Duan, Jiangxia and Zhang, Meiwei and Song, Minghui and Xu, Xiaopan and Lu, Hongbing},
title = {Eye Tracking-Enhanced Deep Learning for Medical Image Analysis: A Systematic Review on Data Efficiency, Interpretability, and Multimodal Integration},
journal = {Bioengineering},
year = {2025},
volume = {12},
number = {9},
pages = {954},
doi = {10.3390/bioengineering12090954}
}
EUVIMED