Automated Identification of Clinically Relevant Regions in Glaucoma OCT Reports Using Expert Eye Tracking Data and Deep Learning
Translational Vision Science & Technology · 2024
DOI: 10.1167/tvst.13.10.24 ↗Kurz gefasst
Fachartikel in der Zeitschrift Translational Vision Science & Technology, 2024. Verfasst von Ye Tian und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Columbia University, New York, New York, USA. Hauptthemen laut MEDLINE: Deep Learning, Tomography, Optical Coherence, Glaucoma, Eye-Tracking Technology. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Purpose
To propose a deep learning-based approach for predicting the most-fixated regions on optical coherence tomography (OCT) reports using eye tracking data of ophthalmologists, assisting them in finding medically salient image regions.
Methods
We collected eye tracking data of ophthalmology residents, fellows, and faculty as they viewed OCT reports to detect glaucoma. We used a U-Net model as the deep learning backbone and quantized eye tracking coordinates by dividing the input report into an 11 × 11 grid. The model was trained to predict the grids on which fixations would land in unseen OCT reports. We investigated the contribution of different variables, including the viewer's level of expertise, model architecture, and number of eye gaze patterns included in training.
Results
Our approach predicted most-fixated regions in OCT reports with precision of 0.723, recall of 0.562, and f1-score of 0.609. We found that using a grid-based eye tracking structure enabled efficient training and using a U-Net backbone led to the best performance.
Conclusions
Our approach has the potential to assist ophthalmologists in diagnosing glaucoma by predicting the most medically salient regions on OCT reports. Our study suggests the value of eye tracking in guiding deep learning algorithms toward informative regions when experts may not be accessible. Translational Relevance: By suggesting important OCT report regions for a glaucoma diagnosis, our model could aid in medical education and serve as a precursor for self-supervised deep learning approaches to expedite early detection of irreversible vision loss owing to glaucoma.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biomedical Engineering, Columbia University, New York, New York, USA.
- Artificial Intelligence for Vision Science Laboratory, Edward S. Harkness Eye Institute, Department of Ophthalmology, Columbia University Irving Medical Center, New York, New York, USA.
- Data Science Institute, Columbia University, New York, New York, USA.
- Bernard and Shirlee Brown Glaucoma Research Laboratory, Edward S. Harkness Eye Institute, Department of Ophthalmology, Columbia University Irving Medical Center, New York, New York, USA.
- Department of Computer Science, Columbia University, New York, New York, USA.
Zitieren
APA
Tian, Y., Sharma, A., Mehta, S., Kaushal, S., Liebmann, J. M., Cioffi, G. A., & Thakoor, K. A. (2024). Automated Identification of Clinically Relevant Regions in Glaucoma OCT Reports Using Expert Eye Tracking Data and Deep Learning. Translational Vision Science & Technology. https://doi.org/10.1167/tvst.13.10.24
Vancouver
Tian Y, Sharma A, Mehta S, Kaushal S, Liebmann JM, Cioffi GA, et al. Automated Identification of Clinically Relevant Regions in Glaucoma OCT Reports Using Expert Eye Tracking Data and Deep Learning. Translational Vision Science & Technology. 2024. doi:10.1167/tvst.13.10.24
BibTeX
@article{Tian2024,
author = {Tian, Ye and Sharma, Anurag and Mehta, Shubh and Kaushal, Shubham and Liebmann, Jeffrey M and Cioffi, George A and Thakoor, Kaveri A},
title = {Automated Identification of Clinically Relevant Regions in Glaucoma OCT Reports Using Expert Eye Tracking Data and Deep Learning},
journal = {Translational Vision Science & Technology},
year = {2024},
doi = {10.1167/tvst.13.10.24}
}
EUVIMED