Deep Learning for Coronary Artery Stenosis Segmentation: A Preliminary Study
Bibliographic record
Abstract
Manual stenosis interpretation in X-ray Coronary Angiography (XCA) is often subjective and prone to high inter-observer variability, primarily due to the small diameter of coronary arteries.Moreover, current automatic detection methods remain inadequate in addressing the wide variability in stenosis shapes and sizes.This study proposes a deep learning-based approach to enhance segmentation performance by focusing on the stenosis area through region-based cropping.The proposed method evaluates three CNN architectures-ResNet34, UNet, and Residual UNet-for a binary stenosis segmentation task using 100x100-pixel cropped patches.Residual UNet achieved the best performance, with 99.22% accuracy, 88.25% IoU, 87.82% precision, 86.89% recall, and an F1-score of 86.78%.These results highlight the potential of binary segmentation in reducing interobserver variability and improving CAD diagnostic support, particularly in resourceconstrained environments.Residual UNet also reduces reliance on manual interpretation.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".