Automated Optic Disc Tilt Classification in Fundus Photography: Segmentation and Elliptical Ratio Across External Clinical Validation (Preprint)
Bibliographic record
Abstract
<sec> <title>BACKGROUND</title> Optic disc tilt is a morphological change in myopic eyes that complicates clinical interpretation and artificial intelligence (AI)-based analysis of fundus images. Accurate detection of optic disc tilt is necessary to avoid misinterpretation of disc morphology and enhance diagnostic reliability across different disease types. </sec> <sec> <title>OBJECTIVE</title> This study developed and externally validated an end-to-end AI-based pipeline for optic disc segmentation and quantitative tilt classification in color fundus photographs (CFPs), offering an objective alternative to manual segmentation and subjective clinical assessments. </sec> <sec> <title>METHODS</title> We trained a nnU-Net-based optic disc segmentation model on the Standardized Multi-Channel Dataset for Glaucoma (SMDG; 3,103 CFPs) and externally validated it on the Samsung Medical Center dataset (2,448 CFPs; 1,958 patients). Tilt was classified using the ratio of the long-distance diameter to short-distance diameter, with a ratio ≥ 1.3 indicating tilt. Segmentation performance was evaluated using the dice similarity coefficient (DSC), intersection over union (IoU), and pixel accuracy on the SMDG and the clinical acceptance rate via expert review. </sec> <sec> <title>RESULTS</title> Using the SMDG, nnU-Net achieved outstanding performance (mean ± SD: DSC, 0.961 ± 0.055; IoU, 0.927 ± 0.057) across eight datasets. With the SMC dataset, expert review showed a mean clinical acceptance rate of 98.61% across disease types, ranging from 86.40% (edema) to 99.59% (pallor). Tilt was detected in 7.5% (186/2,448) of images, with rates of 9.7% (normal), 3.9% (glaucoma), 7.8% (pallor), and 14.2% (edema). Segmentation errors occurred in 1.4% (34/2,448) of cases, mainly due to edema-related swelling, peripapillary atrophy, and vessel confusion. </sec> <sec> <title>CONCLUSIONS</title> Our pipeline provides objective and reproducible detection of optic disc tilt on CFPs, with strong generalization to clinical images. Replacing manual segmentation and subjective assessments, the pipeline supports tilt-aware AI diagnostics and scalable screening for myopia-related conditions, with future refinements needed for edema-related challenges. </sec>
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 | 0.003 | 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 | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".