Deep learning based MA detection with modified ResNet-50
Bibliographic record
Abstract
A deep understanding of retinal images is used to identify vascular diseases, such as Diabetic Retinopathy (DR) in individuals who experience high blood sugar levels and high blood pressure. DR is a progressive disease that starts from minute red saccular out pouches on blood vessels known as Micro-Aneurysm (MA). DR can be cured by eradicating MA on the retina. Detecting microaneurysms (MAs) in retinal digital images is a challenging task due to various factors. These factors include the diverse sizes, shapes, levels of noise, and contrasts exhibited by the images found in the publicly available datasets for Diabetic Retinopathy (DR). Moreover, the limited number of labelled examples in these datasets and the inherent difficulty faced by deep learning algorithms in accurately identifying small objects in retinal digital images further contribute to the complexity involved in MA detection. Here proposing a Deep Learning based MA detection using modified ResNet-50 with a Support Vector Machine. The suggested approach was training, tuning, and evaluation, both qualitatively and quantitatively, using publicly available datasets like E-ophthaMA and DIARETDB1. The suggested approach demonstrates improved outcomes in terms of time efficiency and resource utilisation.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 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 | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".