A Pyramid-Based Feature Fusion Framework for Keratoconus Detection Using LightGBM
Bibliographic record
Abstract
Keratoconus is a degenerative eye disorder that affects the cornea.It is a progressive eye disorder that leads to irregular astigmatism and decrease in visual acuity as the cornea deforms and protrudes outward assuming a cone shape.The early diagnosis can be challenging as the disease can be asymptomatic.This study proposes a machine learning pipeline for the classification of the keratoconus using multi-scale feature extraction from Pentacam derived corneal topographic maps.A labeled dataset comprising 2961 images, categorized into Keratoconus, Normal and Suspect classes, is used in this study.Multi scale image representations are generated using Gaussian and Laplacian pyramids, alongside a patch-based pyramid.Gradient-based features are extracted from multi-scaled images using Histogram of Oriented Gradients (HOG) and L1-regularised Logistic Regression is used for feature selection.An optimized Light Gradient Boosting Machine (LightGBM) classifier is employed for classification.Experimental results show that Gaussian pyramid based multiscale HOG features consistently outperformed Laplacian and patch-based approaches with an overall accuracy of 85.62%, F1-score of 0.85 and AUC score of 0.95, confirming the effectiveness of multi-scale analysis in corneal disease classification.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".