Exploring ResNet50 with Advanced Learning Strategies for Improved Ocular Disease Diagnosis
Bibliographic record
Abstract
Diagnosing retinopathy accurately and promptly from fundus images is crucial, for preventing vision loss and determining the treatment. This study delves into how well deep learning models perform on the Ophthalmic Disease Recognition (ODIR) dataset in categorizing fundus images. Four models were analyzed namely a ResNet50 used as the baseline, ResNet with data augmentation, Bayesian Optimization and Learning Rate Scheduling for hyperparameter fine tuning. After testing the accuracy, sensitivity (recall) and specificity of these models were assessed to uncover their strengths and weaknesses. The Bayesian Optimization model stood out as the most effective achieving a 94% accuracy with excellent sensitivity and specificity. Data Augmentation also proved to enhance performance by enhancing accuracy and sensitivity. The performance boost from both models was statistically significant (at a = 0.05). This research highlights the importance of utilizing optimization methods like Bayesian Optimization to fine tune model hyperparameters for classification outcomes. These insights could have implications beyond retinopathy in medical image classification tasks paving the way for dependable models in clinical settings.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".