Nonlocal means filter-based speckle tracking
Bibliographic record
Abstract
The objective of sensorless freehand 3-D ultrasound imaging is to eliminate the need for additional tracking hardware and reduce cost and complexity. However, the accuracy of current out-of-plane pose estimation is main obstacle for full 6-degree-of-freedom (DoF) tracking. We propose a new filter-based speckle tracking framework to increase the accuracy of out-of-plane displacement estimation. In this framework, we use the displacement estimation not only for the specific speckle pattern, but for the entire image. We develop a nonlocal means (NLM) filter based on a probabilistic normal variance mixture model of ultrasound, known as Rician-inverse Gaussian (RiIG). To aggregate the local displacement estimations, Stein's unbiased risk estimate (SURE) is used as a quality measure of the estimations. We derive an explicit analytical form of SURE for the RiIG model and use it as a weight factor. The proposed filter-based speckle tracking framework is formulated and evaluated for three commonly used noise models, including the RiIG model. The out-of-plane estimations are compared with our previously proposed model-based algorithm in a set of ex vivo experiments for different tissue types. We show that the proposed RiIG filter-based method is more accurate and less tissue-dependent than the other methods. The proposed method is also evaluated in vivo on the spines of five different subjects to assess the feasibility of a clinical application. The 6-DoF transform parameters are estimated and compared with the electromagnetic tracker measurements. The results show higher tracking accuracy for typical small lateral displacements and tilt rotations between image pairs.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".