P.50 Radial Artery Phenotyping in Fibromuscular Dysplasia Through Ultra-High Frequency Ultrasound: A Radiomic Approach
Bibliographic record
Abstract
Abstract Rationale and Aim This study is aimed at identifying possible patterns of vascular wall disarray and remodeling in radial arteries of patients with fibromuscular dysplasia (FMD), by means of ultrahigh frequency ultrasound (UHFUS). Methods UHFUS scans of the radial arteries and of 30 FMD patients and 30 healthy controls were obtained by VevoMD (70 MHz probe, FUJIFILM, VisualSonics, Toronto, Canada). 10 end-diastolic frames for each subject were analyzed. 74 radiomic features and 4 engineered parameters were extracted: intima-media thickness (IMT) and adventitia thickness (AT), an adjunctive acoustic interface for each layer (IMT and AT triple signal). The extracted parameters were used to train classification models, using Support Vector Machine Linear (SVM), K-Nearest Neighbors (KNN), Logistic Regression, Linear Discriminant Analysis (LDA). The models were then tested on an independent validation population (38 FMD patients and 28 healthy subjects). Results IMT (185 ± 46 vs 168 ± 37, p =) and AT (104 ± 34 vs 96 ± 35, p = 0.004) were significantly higher in FMD than in controls. IMT and AT triple signal were also more frequent in FMD than in control images ( p < for both). The most accurate classification models were LDA (sensitivity = 0.67, specificity = 0.76, accuracy = 0.71, AUC = 0.71) and Logistic Regression (sensitivity = 0.71, specificity = 0.72, accuracy = 0.71, AUC = 0.71). The models showed and accuracy of about 70% when tested on the validation population. Conclusions Wall ultrastructure of radial arteries of FMD patients is extensively altered: IMT and AT are thickened and the first and/or second layer of the arterial wall is splitted, showing a triple signal feature. Radiomic descriptors combined with engineered parameters allow to distinguish between radial images from FMD patients and controls with a 70% accuracy.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".