Segmentation d’image échotomographique par régions actives géodésiques
Bibliographic record
Abstract
Dans cette etude nous nous interessons a la segmentation d’images ultrasonores vasculaire in vivo. Nous developpons une methode de segmentation utilisant, d’une facon originale, le modele de regions actives geodesiques. Cette approche tient compte a la fois des informations contours et regions. Nous exploitons les proprietes statistiques de ces informations. Pour cela l’information region est approchee par un modele de distribution de niveaux de gris de la region. La recherche des contours est faite par la methode des ensembles de niveaux a partir d’une courbe initiale. Nous avons teste notre algorithme sur des images ultrasonores reelles, images echotomographiques veineuses in vivo presentant un thrombus que nous cherchons a isoler. Les resultats experimentaux obtenus illustrent bien les bonnes performances de notre algorithme pour detecter et localiser le thrombus, et montrent aussi que notre methode est bien adaptee a la segmentation des images ultrasonores vasculaire. English version:In this paper a new segmentation method for ultrasound vascular images is developed, applying a geodesic active region model. This approach takes into account both boundary and region information. The region information are approached with a gray level distribution model. The evolution of initial curve has been implemented using a level set method. The algorithm was tested in vivo on real B-mode ultrasound images, to isolate the thrombus in venous ultrasound images. The experimental results confirmed the relevance of this approach to detect and locate the thrombus, and showed also that the method is adapted to ultrasound vascular images.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".