AI-Assisted Optical Coherence Tomography Segmentation for Enhanced Diagnosis of Inherited Retinal Diseases.
Bibliographic record
Abstract
Purpose Inherited retinal diseases (IRDs) are rare and diverse, posing a diagnostic challenge in ophthalmology. This study aimed to determine whether artificial intelligence (AI)-assisted image processing can improve IRD diagnosis and provide insights into disease characteristics. We used an optical coherence tomography (OCT) segmentation algorithm to characterize retinal features in IRDs. Two control groups were included to enhance the contextual understanding of these features: healthy eyes and eyes with age-related macular degeneration (AMD). An AI-driven classification model was then used to classify the data into disease and control groups. Methods We analyzed 327 images from 181 patients with IRD and 146 control individuals, including healthy subjects and patients with AMD. IRD cases were stratified into macular and retinal dystrophies. Automated segmentation of six retinal layers and detection of nine biomarkers were performed on retinal OCT images using the AI-based RetinAI Discovery tool. A random forest classifier differentiated macular IRD, retinal IRD, and controls. Results The model detected IRD with 91% accuracy and achieved 91% accuracy in differentiating macular from retinal IRD. Key OCT features for differentiation included reduced perifoveal photoreceptor and outer nuclear layer thicknesses and increased retinal nerve fiber layer thickness in retinal IRD. Macular IRD featured significant foveal photoreceptor and outer nuclear layer thinning. Conclusions This study shows that standardized OCT image analysis combined with AI-based classification can accurately detect and stratify IRDs. The model's high accuracy highlights its potential as a reliable diagnostic tool in ophthalmology. Translational Relevance This AI-assisted OCT evaluation approach enhances ophthalmic diagnostics by improving IRD detection and classification.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".