Improved Lion Optimization and Faster Mask Recurrent CNN Developed for Diabetic Retinal Detachment Prediction
Bibliographic record
Abstract
The objective of this investigation was to formulate and validate a hybrid algorithm that predicts Diabetic Retinal (DR) detachment at early stages, capitalizing on a synergistic integration of image processing techniques and neural network architectures.Specifically, the focus of the research was on the timely detection of tractional retinal detachment following intravitreal injections of bevacizumab (Avastin), which is used as an adjuvant treatment for severe proliferative diabetic retinopathy in conjunction with vitrectomy.Convolutional neural networks (CNNs) are hindered by a significant challenge: obtaining big labeled datasets.This is a necessary but frequently difficult criterion for efficient CNN training.This problem is solved by integrating the Improved Lion Optimization (ILO) algorithm with the Faster Mask Recurrent Convolutional Neural Network (FMRCNN) to achieve the predicted gradient length.By adding a parallel branch for object mask prediction to the bounding box recognition branch, the ILO algorithm is altered to enhance the FMRCNN.The proposed ILO-FMRCNN model was rigorously tested across a diverse collection of retinal detachment images, demonstrating superior performance in detecting abnormalities related to Diabetic Retinopathy, particularly in advanced stages categorized as level 5 DR severity.Comparative analysis with existing and cutting-edge meta-heuristic algorithms established the proposed model's superiority.The performance metrics obtained from the Eye PACS benchmark CNN method-applied to a dataset comprising 54,000 retinopathy images-yielded an accuracy rate of 98%, sensitivity of 92.20%, specificity of 96%, and an F-score of 95.10%.These results underscore the high efficacy of the hybrid algorithm and its potential to significantly advance early diagnostic capabilities for Diabetic Retinal detachment.
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 | 0.000 | 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 | 0.000 |
| 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".