A Multicenter Study on Carotid Ultrasound Plaque Tissue Characterization and Classification Using Six Deep Artificial Intelligence Models: A Stroke Application
Bibliographic record
Abstract
Atherosclerotic plaque in carotid arteries can ultimately lead to cerebrovascular events if not monitored. The objectives of this study are (a) to design a set of artificial intelligence (AI)-based tissue characterization and classification (TCC) systems (Atheromatic 2.0, AtheroPoint, CA, USA) using ultrasound-based carotid artery plaque scans collected from multiple centers and (b) to evaluate the AI performance. We hypothesize that symptomatic plaque is more scattered than asymptomatic plaque. Therefore, the AI system can learn, characterize, and classify them automatically. We developed six kinds of AI systems: four machine learning (ML) systems, one transfer learning (TL) system, and one deep learning (DL) architecture with different layers. Atheromatic 2.0 uses two types of plaque characterization: (a) an AI-based mean feature strength (MFS) and (b) bispectrum analysis. Three kinds of data were collected: London, Lisbon, and Combined (London + Lisbon). We balanced and then augmented five folds to conduct 3-D optimization for optimal number of AI layers versus folds. Using K10 (90% training, 10% testing), the mean accuracies for DL, TL, and ML over the mean of the three data sets were 93.55%, 94.55%, and 89%, respectively. The corresponding mean AUCs were 0.938, 0.946, and 0.889 (p <; 0.0001), respectively. AI paradigms showed an improvement by 10.41% and 3.32% for London and Lisbon in comparison to Atheromatic 1.0, respectively. On characterization, for all three data sets, MFS (symptomatic) > MFS (asymptomatic) by 46.56%, 19.40%, and 53.84%, respectively, thus validating our hypothesis. Atheromatic 2.0 showed consistent and stable results and is useful for carotid plaque tissue classification and characterization for vascular surgery applications.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".