Enhancing Choroidal Nevus Position Identification through CNN-Based Segmentation of Eye Fundus Images
Bibliographic record
Abstract
Diagnosing choroidal nevus in color fundus images is challenging for clinicians not regularly practicing it. Machine learning (ML) has proven effective in detecting and analyzing such abnormalities with high accuracy and efficiencyThis research is part of a larger project to develop a decision support system for choroidal nevus diagnosis, focusing on creating a segmentation algorithm to identify key areas in color fundus images. The study evaluates and compares the efficacy of various convolutional neural network (CNN) segmentation models, a crucial step for improved image analysis accuracyFundus images from the Alberta Ocular Brachytherapy Program, including healthy and choroidal nevus-affected eyes, were used. An ocular oncologist provided a ground truth mask dataset for training the models. Preprocessing improved image features, and multiple CNN models segmented the images to detect lesions. Model performance was compared to find the most accurate and efficient approach, with external validation using a separate test set and ophthalmology expertsFour CNN models - U-net, Residual U-net, Attention U-net, and a voting-based Ensemble - were developed for segmentation. Their effectiveness was measured by accuracy metrics, achieving Dice Coefficient scores of 85.02%, 85.66%, 86.89%, and 87.7% respectively.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".