| Title: | Color Fundus Photography and Deep Learning Applications in Alzheimer Disease |
| Journal: | Mayo Clinic Proceedings Digital Health |
| Published: | 26 Aug 2024 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/39748801/ |
| DOI: | https://doi.org/10.1016/j.mcpdig.2024.08.005 |
Publication 12936
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Objective: To report the development and performance of 2 distinct deep learning models trained exclusively on retinal color fundus photographs to classify Alzheimer disease (AD).</p>
Patients and Methods: Two independent datasets (UK Biobank and our tertiary academic institution) of good-quality retinal photographs derived from patients with AD and controls were used to build 2 deep learning models, between April 1, 2021, and January 30, 2024. ADVAS is a U-Net-based architecture that uses retinal vessel segmentation. ADRET is a bidirectional encoder representations from transformers style self-supervised learning convolutional neural network pretrained on a large data set of retinal color photographs from UK Biobank. The models' performance to distinguish AD from non-AD was determined using mean accuracy, sensitivity, specificity, and receiving operating curves. The generated attention heatmaps were analyzed for distinctive features.</p>
Results: The self-supervised ADRET model had superior accuracy when compared with ADVAS, in both UK Biobank (98.27% vs 77.20%; P<.001) and our institutional testing data sets (98.90% vs 94.17%; P=.04). No major differences were noted between the original and binary vessel segmentation and between both eyes vs single-eye models. Attention heatmaps obtained from patients with AD highlighted regions surrounding small vascular branches as areas of highest relevance to the model decision making.</p>
Conclusion: A bidirectional encoder representations from transformers style self-supervised convolutional neural network pretrained on a large data set of retinal color photographs alone can screen symptomatic AD with high accuracy, better than U-Net-pretrained models. To be translated in clinical practice, this methodology requires further validation in larger and diverse populations and integrated techniques to harmonize fundus photographs and attenuate the imaging-associated noise.</p>
12 Authors
- Oana M. Dumitrascu
- Xin Li
- Wenhui Zhu
- Bryan K. Woodruff
- Simona Nikolova
- Jacob Sobczak
- Amal Youssef
- Siddhant Saxena
- Janine Andreev
- Richard J. Caselli
- John J. Chen
- Yalin Wang
Enabling scientific discoveries that improve human health