DeepRetNet: Retinal Disease Classification using Attention UNet++ based Segmentation and Optimized Deep Learning Technique
Bibliographic record
Abstract
Abstract Human eyesight depends significantly on retinal tissue. The loss of eyesight may result from infections of the retinal tissue that are treated slowly or not at all. Furthermore, when a large dataset is involved, the diagnosis is susceptible to inaccuracies. Hence, a fully automated approach based on deep learning for diagnosing retinal illness is proposed in order to minimise human intervention while maintaining high precision in classification. The proposed Attention UNet++ based Deep Retinal Network (Attn_UNet++ based DeepRetNet) is designed for classifying the retinal disease along with the segmentation criteria. In this, the Attn_UNet++ is employed for segmentation, wherein the UNet++ with dense connection is hybridized with Attention module for enhancing the segmentation accuracy. Then, the disease classification is performed using the DeepRetNet, wherein the loss function optimization is employed using the Improved Gazelle optimization (ImGaO) algorithm. Here, the adaptive weighting strategy is added with the conventional Gazelle algorithm for enhancing the global search with fast convergence rate. The performance analysis of proposed Attn_UNet++ based DeepRetNet based on Accuracy, Specificity, Precision, Recall, F1-Measure, and MSE accomplished the values of 97.20%, 98.36%, 95.90%, 95.50%, 96.53%, and 2.80% 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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| 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 | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".