Learning Cataract Severity Using the Contrast Sensetivity Scale: A Thick Data Approach
Bibliographic record
Abstract
Cataract image severity classification according to contrast sensitivity chart like VTSC represents a challenge to classical machine learning. Typically cataract images hide significant retina features because of the fogy nature of these images. Contrast sensitivity measurement provides important information on the functioning of the visual system that cannot simple detected by the visual acuity tests. In this paper, we are introducing a framework for segmenting fundus images into regions of salient contrast. The framework start by converting the RGB color channels into joint entropy where it can be used to categorized anchor images into contrast based classes. It has been found that classes like normal fundus, fundus with cataract or fundus having cataract with additional complications like availability of cotton-wool spots or fibrosis. We found that contrast sensitivity scoring correlate nicely with the joint entropy scoring. For this purpose, our last level of the framework employs a triplet loss Siamese neural network that has been trained on few contrast classified fundus images to detect the severity of the cataract. We used a similar contrast sensitivity scale like those used by the optometrist with classification rate that reaches 72%.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 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".