Optic cup segmentation: type-II fuzzy thresholding approach and blood vessel extraction
Bibliographic record
Abstract
We introduce here a new technique for segmenting optic cup using two-dimensional fundus images. Cup segmentation is the most challenging part of image processing of the optic nerve head due to the complexity of its structure. Using the blood vessels to segment the cup is important. Here, we report on blood vessel extraction using first a top-hat transform and Otsu's segmentation function to detect the curves in the blood vessels (kinks) which indicate the cup boundary. This was followed by an interval type-II fuzzy entropy procedure. Finally, the Hough transform was applied to approximate the cup boundary. The algorithm was evaluated on 550 fundus images from a large dataset, which contained three different sets of images, where the cup was manually marked by six ophthalmologists. On one side, the accuracy of the algorithm was tested on the three image sets independently. The final cup detection accuracy in terms of area and centroid was calculated to be 78.2% of 441 images. Finally, we compared the algorithm performance with manual markings done by the six ophthalmologists. The agreement was determined between the ophthalmologists as well as the algorithm. The best agreement was between ophthalmologists one, two and five in 398 of 550 images, while the algorithm agreed with them in 356 images.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".