Fast‐marching segmentation of three‐dimensional intravascular ultrasound images: A pre‐ and post‐intervention study
Bibliographic record
Abstract
PURPOSE: Intravascular ultrasound (IVUS) is a vascular imaging technique that is used to study atherosclerosis since it has the ability to show the lumen and the vessel wall. Cross-sectional images of blood vessels are produced and they provide quantitative assessment of the vascular wall, information about the nature of atherosclerotic lesions, as well as the plaque shape and size. Due to the ultrasound speckle, catheter artifacts, or calcification shadows, the automated analysis of large IVUS data sets represents an important challenge. METHODS: A multiple interface 3D fast-marching method is presented for the detection of the lumen and external vessel wall boundaries. The segmentation is based on a combination of region and contour information, namely, the gray level probability density functions of the vessel structures and the intensity gradient. The detection of the lumen boundary is fully automatic. The segmentation method includes an interactive initialization procedure of the external vessel wall border. The segmentation method was applied to 20 in vivo IVUS data sets acquired from femoral arteries. This database contained three subgroups: Pullbacks acquired before balloon angioplasty (n=7), after the intervention (n=7), and at a 1 yr follow-up examination (n=6). Results were compared to validation contours that were manually traced by two experts on more than 1500 individual frames. RESULTS: For all subgroups, no significant difference was found between the area measurements of the segmentation and validation contours for the lumen and external vessel wall. Moreover, high intraclass correlation coefficients (> 0.96) between the area of the manually traced contours and detected boundaries with the fast-marching method were obtained for both vessel layers over the whole database. The segmentation performance was also evaluated with point-to-point contour distances between segmentation results and manually traced contours. A good overall accuracy was obtained with average distances < 0.13 mm and maximum distances < 0.46 mm, indicating a good performance in regions lacking information or containing artifacts. Only small differences of less than a pixel (0.02 mm) were observed between the average distance metrics of each subgroup, which prove the segmentation consistency. CONCLUSIONS: This new IVUS segmentation method provides accurate results that correspond well to the experts' manually traced contours, but requires much less manual interactions and is faster.
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 | 0.001 |
| 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".