Enhanced diabetic retinopathy detection using U-shaped network and capsule network-driven deep learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Glaucoma, a severe eye disease leading to irreversible vision loss if untreated, remains a significant challenge in healthcare due to the complexity of its detection. Traditional methods rely on clinical examinations of fundus images, assessing features like optic cup and disc sizes, rim thickness, and other ocular deformities. Recent advancements in artificial intelligence have introduced new opportunities for enhancing glaucoma detection. This research explores a hybrid approach combining UNet++ and Capsule Network (CapsNet) architectures for accurate glaucoma diagnosis. UNet++ is employed for semantic segmentation, focusing on defining optic discs and cups, which are crucial for detecting the disease. CapsNet leverages its ability to recognize hierarchical patterns, providing more sensitive detection of glaucomatous changes than conventional Convolutional Neural Networks. Pre-processing of retinal images involves advanced techniques like Histogram Equalization and Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance image quality. The model is trained and tested on benchmark datasets, showing superior performance in optic cup/disc segmentation and glaucoma detection accuracy compared to existing state-of-the-art models.•Hybrid Model Efficiency: The combined use of UNet++ and CapsNet offers improved accuracy in optic cup and disc segmentation.•Enhanced Image Quality: Application of Histogram Equalization and CLAHE techniques significantly boosts the quality of retinal images.•Superior Performance: The hybrid approach outperforms traditional and contemporary models in glaucoma detection accuracy.
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.
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 | 0.001 | 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 it