OD-DeepNet: Semantic Classification by Deep Learning for Optic Disc Localization
Bibliographic record
Abstract
The early detection of abnormal changes in the Optic Disc (OD) and optic cup in the retina is a highly challenging task since there are no initial signs when glaucoma develops.The primary indicator for glaucoma is the ratio between the optic cup and OD.To compute the cup-to-disc ratio, the localization of OD is very important.This paper presents an approach for Optic Disc Localization (ODL) using semantic classification by deep learning.A computerized intact ODL system is developed by integrating the following two important modules; Preprocessing and localization modules.The initial area of interest around the OD is selected in the former module.Then, OD-DeepNet is specially designed to classify the pixels in the OD region by semantic approach.The dilated convolutions are recently gaining more attention in the field of image segmentation, and thus the proposed OD-DeepNet uses dilated convolutions with different dilation rates (4, 8, and 16).The analysis of the ODL system is performed on DRISHTI-GS1 (101 images) and RIM-ONE (169 images) database fundus images with nested (double) k-fold validation.The localized OD is evaluated in terms of accuracy, Dice coefficient, and Jaccard index.The OD-DeepNet provides 93.25% of average accuracy with a Dice coefficient of 0.921 and Jaccard index of 0.919.It is also observed that applying batch normalization with a batch size of 32 during training provides promising results.
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) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.007 | 0.004 |
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".