TU‐FF‐A4‐02: Active Tool/Fiducial Segmentation and Tracking in Multiple Modalities
Bibliographic record
Abstract
Purpose: To build a tracking framework that, given a description of a tool/fiducial, the geometry of the imaging system and a sequence of images, outputs estimates of selected kinematics of the tool/fiducial along with a measure of the uncertainty in these estimates. The output of the system may be used as feedback to actively modify the imaging system parameters in order to achieve the desired precision with which the object is tracked while minimizing other parameters (eg. dose delivered to the patient). Method and Materials: A two stage approach is employed where (i) the object is segmented using its invariant features, its model, and other prior information that may be available and (ii) a particle filter is applied to the results of the segmentation for robustly tracking the object. A particle filter is chosen because of its simplicity, its robustness to noise and occlusion, its ability to represent multimodal beliefs, and also because its performance approaches that of the optimal Kalman filter given enough samples. Results: This approach has been applied to a (physically) simulated brachytherapy procedure to track the position of a needle loaded with seeds in an X‐ray fluoroscopic sequence. The system outputs the 3D position and orientation of the needle along with a confidence measure along each dimension. This output is robust to noise and partial occlusion. Conclusion: This work provides a generic framework for segmentation and tracking across multiple modalities that also reports a confidence measure for each estimated parameter. Such a system has many online applications such as radiation therapy guidance, intra‐operative image‐guided laparoscopic surgery, brachytherapy and various biopsy procedures.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".