Creation of a Head Tracking Dataset for Motion Correction in High Resolution Brain PET Imaging
Bibliographic record
Abstract
Head motion is a source of spatial blurring in brain PET imaging that is becoming increasingly important with the renewed interest in the development of dedicated ultra-high resolution PET scanners. External head tracking can provide accurate position correction, but is cumbersome and difficult to implement on a regular basis in the clinical setting. Data-driven head motion detection can also be used, but its accuracy is currently limited. Deep-learning based data-driven motion tracking can potentially provide suitable correction for patient movements. A large dataset of accurate motion-encoded PET data would be required for training a neural network, which would be difficult to build from PET imaging of human subjects. As a surrogate of PET data, we propose to build a dataset of typical head motion in the brain PET imaging context using an external motion tracking system. The goal of this dataset will be to enable the simulation of realistic motion-plagued brain PET acquisitions which would then be used to develop regularization methods for data-driven motion tracking and correction. This paper describes the proposed methodology to create this dataset. During the investigation, we discovered that the external tracking system suffers from a significant loss of accuracy when tracking relative to a reference fiducial. A solution based on the filtering of the reference fiducial orientation vector is demonstrated to mitigate this loss.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| 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".