Sci—Thur AM: YIS ‐ 10: Use of the Microsoft Kinect for applications of patient surface data to radiotherapy
Bibliographic record
Abstract
Current techniques to acquire patient surface data are often very expensive and lack flexibility. In this study, the use of the Microsoft Kinect to reliably acquire 3D scans of patient surface is investigated. A design is presented to make the system easily applicable to the clinic. Potential applications of the device to radiotherapy are also presented. Scan reproducibility was tested by repeatedly scanning an anthropomorphic phantom. Scan accuracy was tested by comparing Kinect scans to the surface extracted from a CT dataset of a Rando® anthropomorphic phantom, which was considered as the true reference surface. Average signed distances of 0.12 ± 2.34 mm and 0.13 ± 2.04 mm were obtained between the compared surfaces for reproducibility and accuracy respectively. This is conclusive, since it indicates that the variations observed come largely from noise distributed around an average distance close to 0 mm. Moreover, the range of the noise is small enough for the system to reliably capture a patient's surface. A system was also designed using two Kinects used together to acquire 3D surfaces in a quick and stable way that is applicable to the clinic. Finally, applications of the device to radiotherapy are demonstrated. Its use to detect local positioning errors is presented, where small local variations difficult to see with the naked eye are clearly visible. The system was also used to predict collisions using gantry and patient scans and thus ensure the safety of unconventional trajectories.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| 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) | 0.040 | 0.015 |
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".