Diabetic Retinopathy Detection from Fundus Images Using Deep Convolutional Neural Networks
Bibliographic record
Abstract
Diabetic Retinopathy (DR) is one of the primary causes of blindness. The earlier it gets detected; the earlier patients get the treatment. Currently, diagnosis of DR depends on traditional manual methods and resources, which often leads to human error and wrong diagnosis. This issue can be avoided through the development of an automated system for accurately detecting DR. In this research work, we are proposing an approach to detecting DR through deep Convolutional Neural Networks (CNNs) trained using fundus images (photos of the retina of the eye with a fundus camera). The developed CNN model detected the severity of diabetic retinopathy from fundus images with the highest probability. The final model with the best performance was achieved through iterative fine-tuning of the hyperparameters and changing of the layers. The model was tested to avoid overfitting or underfitting issues. We developed models for supervised multiclass classification as well as binary classification, where ‘No DR’ was considered as a single class, and the other types of DR were combined to make a ‘DR’ class. In binary classification, the best model achieved a validation accuracy of 96% and testing accuracy of 95%. This study highlights the potential of deep learning models to automate the detection of diabetic retinopathy, offering the possibility of more efficient and scalable screening methods which could significantly reduce the incidence of blindness from this condition.
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 | 0.000 |
| 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".