Abstract 151: Optical Coherence Tomography post-processing towards an automated quantification of coronary artery wall alteration subsequent to Kawasaki Disease
Bibliographic record
Abstract
Introduction: Statistical mathematical processing of medical imaging promotes operator-independent interpretation. We sought to identify discriminative image features for a histological disambiguation of KD related coronary (CA) lesions. The ultimate goal is to develop a fully automated algorithm for the quantification of the degradation/healing state of the CA wall structure post KD. Methods: We analyzed OCT CA recordings from two KD patients with (KD + AN + ) and two patients with no history of CA aneurysm (KD + AN [[Unable to Display Character: –]] ), vs a non KD patient (KD [[Unable to Display Character: –]] ). Results: In KD [[Unable to Display Character: –]] , regardless of the radial region of interest (ROI) position in the image, the OCT mean signal intensity presents centrifugally two peaks corresponding to the intima and media, constantly separated (17.1± 2.0 pixels) (fig. 1A). In KD + AN [[Unable to Display Character: –]] the peaks may disappear (Fig. 1-B left medial hyperplasia) and the distance between remaining crests vary between ROIs (22.7±6.9 Pixels). In KD + AN + these peaks disappear (Figure1-C) and the signal intensity changes drastically between ROIs due to wall restructuration. Figure1-C shows a hatched signal that maybe that of a laminar structure. In this case the variation of gradient intensity may be a discriminative feature. Conclusion: Mathematical modeling of CA wall layers is feasible. While the consistency of the distance between media and intima peaks may discriminate KD [[Unable to Display Character: –]] from KD + and while the gradient intensity may detect restructuration in KD + AN + , ongoing investigation to discriminate CA lesions include signal homogeneity, energy and contrast. Texture analysis with anatomical correlates (e.g., calcium, fibrosis and clots) may allow automated diagnoses.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".