Aortic and mitral flow quantification using dynamic valve tracking and machine learning: Prospective study assessing static and dynamic plane repeatability, variability and agreement
Bibliographic record
Abstract
Background Blood flow is a crucial measurement in the assessment of heart valve disease. Time-resolved flow using magnetic resonance imaging (4 D flow MRI) can provide a comprehensive assessment of heart valve hemodynamics but it relies in manual plane analysis. In this study, we aimed to demonstrate the feasibility of automate the detection and tracking of aortic and mitral valve planes to assess blood flow from 4 D flow MRI. Methods In this prospective study, a total of n = 106 subjects were enrolled: 19 patients with mitral disease, 65 aortic disease patients and 22 healthy controls. Machine learning was employed to detect aortic and mitral location and motion in a cine three-chamber plane and a perpendicular projection was co-registered to the 4 D flow MRI dataset to quantify flow volume, regurgitant fraction, and a peak velocity. Static and dynamic plane association and agreement were evaluated. Intra- and inter-observer, and scan-rescan reproducibility were also assessed. Results Aortic regurgitant fraction was elevated in aortic valve disease patients as compared with controls and mitral valve disease patients ( p < 0.05). Similarly, mitral regurgitant fraction was higher in mitral valve patients ( p < 0.05). Both aortic and mitral total flow were high in aortic patients. Static and dynamic were good (r > 0.6, p < 0.005) for aortic total flow and peak velocity, and mitral peak velocity and regurgitant fraction. All measurements showed good inter- and intra-observer, and scan-rescan reproducibility. Conclusion We demonstrated that aortic and mitral hemodynamics can efficiently be quantified from 4 D flow MRI using assisted valve detection with machine learning.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| 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".