EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Eye-Guided Multimodal Fusion: Toward an Adaptive Learning Framework Using Explainable Artificial Intelligence

Sahar Moradizeyveh, Ambreen Hanif, Sidong Liu iD, Yuankai Qi, Amin Beheshti iD, Antonio Di Ieva iD

Sensors · 24.07.2025 · 25 (15) · 4575

DOI: 10.3390/s25154575 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.07.2025. Verfasst von Sahar Moradizeyveh und 5 weiteren Autor:innen. Beteiligte Einrichtung: Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Faculty of Medicine, Health and Human Sciences, Macquarie University, Sydney 2113, Au…. Hauptthemen laut MEDLINE: Artificial Intelligence. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interpreting diagnostic imaging and identifying clinically relevant features remain challenging tasks, particularly for novice radiologists who often lack structured guidance and expert feedback. To bridge this gap, we propose an Eye-Gaze Guided Multimodal Fusion framework that leverages expert eye-tracking data to enhance learning and decision-making in medical image interpretation. By integrating chest X-ray (CXR) images with expert fixation maps, our approach captures radiologists’ visual attention patterns and highlights regions of interest (ROIs) critical for accurate diagnosis. The fusion model utilizes a shared backbone architecture to jointly process image and gaze modalities, thereby minimizing the impact of noise in fixation data. We validate the system’s interpretability using Gradient-weighted Class Activation Mapping (Grad-CAM) and assess both classification performance and explanation alignment with expert annotations. Comprehensive evaluations, including robustness under gaze noise and expert clinical review, demonstrate the framework’s effectiveness in improving model reliability and interpretability. This work offers a promising pathway toward intelligent, human-centered AI systems that support both diagnostic accuracy and medical training.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceHumansEye-Tracking TechnologyAlgorithms

Stichwörter der Autor:innen

artificial intelligence in healthdeep learningexplanationeye-gaze tracking

Autor:innen und Institutionen

  • Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Faculty of Medicine, Health and Human Sciences, Macquarie University, Sydney 2113, Australia.
  • Centre for Applied Artificial Intelligence, School of Computing, Faculty of Science and Engineering, Macquarie University, Sydney 2113, Australia.

ORCID-Profile: Sidong Liu, Amin Beheshti, Antonio Di Ieva

Zitieren

APA

Moradizeyveh, S., Hanif, A., Liu, S., Qi, Y., Beheshti, A., & Di Ieva, A. (2025). Eye-Guided Multimodal Fusion: Toward an Adaptive Learning Framework Using Explainable Artificial Intelligence. Sensors, 25(15), 4575. https://doi.org/10.3390/s25154575

Vancouver

Moradizeyveh S, Hanif A, Liu S, Qi Y, Beheshti A, Di Ieva A. Eye-Guided Multimodal Fusion: Toward an Adaptive Learning Framework Using Explainable Artificial Intelligence. Sensors. 2025;25(15):4575. doi:10.3390/s25154575

BibTeX
@article{Moradizeyveh2025,
  author = {Moradizeyveh, Sahar and Hanif, Ambreen and Liu, Sidong and Qi, Yuankai and Beheshti, Amin and Di Ieva, Antonio},
  title = {Eye-Guided Multimodal Fusion: Toward an Adaptive Learning Framework Using Explainable Artificial Intelligence},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {15},
  pages = {4575},
  doi = {10.3390/s25154575}
}
Kostenlos starten →