Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2503.20967 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913760947470336 |
|---|---|
| author | Wong, David Wang, Bin Durak, Gorkem Tliba, Marouane Chaudhari, Akshay Chetouani, Aladine Cetin, Ahmet Enis Topel, Cagdas Gennaro, Nicolo Vendrami, Camila Lopes Trabzonlu, Tugce Agirlar Rahsepar, Amir Ali Perronne, Laetitia Antalek, Matthew Ozturk, Onural Okur, Gokcan Gordon, Andrew C. Pyrros, Ayis Miller, Frank H. Borhani, Amir Savas, Hatice Hart, Eric Torigian, Drew Udupa, Jayaram K. Krupinski, Elizabeth Bagci, Ulas |
| author_facet | Wong, David Wang, Bin Durak, Gorkem Tliba, Marouane Chaudhari, Akshay Chetouani, Aladine Cetin, Ahmet Enis Topel, Cagdas Gennaro, Nicolo Vendrami, Camila Lopes Trabzonlu, Tugce Agirlar Rahsepar, Amir Ali Perronne, Laetitia Antalek, Matthew Ozturk, Onural Okur, Gokcan Gordon, Andrew C. Pyrros, Ayis Miller, Frank H. Borhani, Amir Savas, Hatice Hart, Eric Torigian, Drew Udupa, Jayaram K. Krupinski, Elizabeth Bagci, Ulas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20967 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Eyes Tell the Truth: GazeVal Highlights Shortcomings of Generative AI in Medical Imaging Wong, David Wang, Bin Durak, Gorkem Tliba, Marouane Chaudhari, Akshay Chetouani, Aladine Cetin, Ahmet Enis Topel, Cagdas Gennaro, Nicolo Vendrami, Camila Lopes Trabzonlu, Tugce Agirlar Rahsepar, Amir Ali Perronne, Laetitia Antalek, Matthew Ozturk, Onural Okur, Gokcan Gordon, Andrew C. Pyrros, Ayis Miller, Frank H. Borhani, Amir Savas, Hatice Hart, Eric Torigian, Drew Udupa, Jayaram K. Krupinski, Elizabeth Bagci, Ulas Computer Vision and Pattern Recognition 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. |
| title | Eyes Tell the Truth: GazeVal Highlights Shortcomings of Generative AI in Medical Imaging |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.20967 |