Machine learning for optical coherence tomography angiography
Bibliographic record
Abstract
1. INTRODUCTION Optical coherence tomography angiography (OCT-A) is a non-invasive imaging modality allowing researchers and clinicians to view the retina in micrometer-scale detail. Acquired OCT-A volumes are three-dimensional, allowing the visualization of the superficial capillary plexus (SCP) and the deep capillary plexus (DCP). This provides valuable information towards the identification of pathologies such as diabetic retinopathy (DR). However, because an OCT-A volume is acquired over several seconds, motion artifacts caused by rapid movements of the subject’s eye (also known as micro-saccadic motion) can greatly reduce the quality, and subsequently the clinical utility, of the resulting volumes. Hardware motion tracking aims to reduce the effect of motion, but non-rigid registration is still often required for averaging sequentially acquired images. Furthermore, not all prototype OCT-A systems have tracking capabilities, particularly adaptive optics (AO) systems. Because of this, image registration is essential for the elimination of motion artifacts in OCT-A volumes, increasing their clinical diagnostic value. To further improve the clinical utility of these OCT-A images, segmentation is essential as it allows for the quantitative analysis of the microvasculature, which include the identification of the foveal avascular zone (FAZ) and areas of capillary non-perfusion (CNP), two biomarkers for the progression of DR.
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 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.018 | 0.011 |
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".