A new automated method for grading retinal tessellation in myopic eyes using fundus images
Bibliographic record
Abstract
The tessellation of the retina is of clinical importance, especially in the study of myopia. This paper presents an automated grading algorithm for tessellation based on the calculation of three Tessellated Fundus Indices (TFIs). Our new algorithm utilizes the red (R), green (G), and blue (B) color components of the region of interest (ROI) surrounding the fovea in fundus images to determine the degree of tessellation, categorized into grades 0, 1, and 2. Excessive brightness in fundus images can result in overexposure, which in turn can introduce inaccuracies when calculating TFI values in the region of interest (ROI) using the red, green, and blue (R, G, B) components. Prior to calculating the TFIs, the method applies luminosity and contrast variation correction to the fundus images automatically. This correction process is achieved through a series of steps: first, applying row-wise and column-wise 1-dimensional low-pass filtering (1DLF); then, computing the luminosity surface by subtracting the smoothed image from the original grayscale image. To maintain luminosity consistency, the original image channels are equalized using the luminosity surface, followed by histogram stretching for enhanced contrast. Finally, the algorithm computes B/R (Blue/Red) and G/R (Green/Red) ratios for each pixel in the original image and multiplies them by the red channel of the contrast-stretched image. The proposed algorithm was evaluated on a dataset of 60 fundus images from varying degrees of myopia, demonstrating its effectiveness in grading tessellation accurately. The automated approach streamlines the grading process, offering potential benefits in clinical settings and facilitating large-scale screenings for myopic eyes.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 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".