Eyes Tell the Truth: GazeVal Highlights Shortcomings of Generative AI in Medical Imaging
Abstract
The demand for high-quality synthetic data for model training and augmentation has never been greater in medical imaging. However, current evaluations predominantly rely on computational metrics that fail to align with human expert recognition. This leads to synthetic images that may appear realistic numerically but lack clinical authenticity, posing significant challenges in ensuring the reliability and effectiveness of AI-driven medical tools. To address this gap, we introduce GazeVal, a practical framework that synergizes expert eye-tracking data with direct radiological evaluations to assess the quality of synthetic medical images. GazeVal leverages gaze patterns of radiologists as they provide a deeper understanding of how experts perceive and interact with synthetic data in different tasks (i.e., diagnostic or Turing tests). Experiments with sixteen radiologists revealed that 96.6% of the generated images (by the most recent state-of-the-art AI algorithm) were identified as fake, demonstrating the limitations of generative AI in producing clinically accurate images.
Cite
Text
Wong et al. "Eyes Tell the Truth: GazeVal Highlights Shortcomings of Generative AI in Medical Imaging." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.Markdown
[Wong et al. "Eyes Tell the Truth: GazeVal Highlights Shortcomings of Generative AI in Medical Imaging." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/wong2025cvprw-eyes/)BibTeX
@inproceedings{wong2025cvprw-eyes,
title = {{Eyes Tell the Truth: GazeVal Highlights Shortcomings of Generative AI in Medical Imaging}},
author = {Wong, David C. and Wang, Bin and Durak, Gorkem and Tliba, Marouane and Chaudhari, Akshay and Chetouani, Aladine and Çetin, Ahmet Enis and Topel, Cagdas and Gennaro, Nicolo and Vendrami, Camila Lopes and Trabzonlu, Tugce Agirlar and Rahsepar, Amir Ali and Perronne, Laetitia and Antalek, Matthew and Ozturk, Onural and Okur, Gokcan and Gordon, Andrew C. and Pyrros, Ayis and Miller, Frank H. and Borhani, Amir and Savas, Hatice and Hart, Eric M. and Torigian, Drew A. and Udupa, Jayaram K. and Krupinski, Elizabeth A. and Bagci, Ulas},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2025},
pages = {3167-3175},
url = {https://mlanthology.org/cvprw/2025/wong2025cvprw-eyes/}
}