Sci‐YIS Fri ‐ 01: A protocol for the validation of non‐linear image registration systems
Bibliographic record
Abstract
An important step in the image guided adaptive radiotherapy (IGAR) process is the registration of medical images. Image registration has been used in clinically for a number of years; however registration systems have been restricted to linear or rigid registration, meaning that they cannot take into account soft tissue or organ motion with respect to rigid bony structures. Among its applications, non‐linear or deformable registration will allow for more accurate delineation of tumours and critical structures by correcting for organ motion and patient miss‐alignment from image study to study. Since deformable registration is still in its infancy, a standard protocol for the validation of these systems does not exist. A comprehensive protocol to assess the accuracy of deformable registration systems over a wide range of clinical and research applications has been developed. The protocol has been applied to the Reveal‐MVS Fusion Workstation from Mirada Solutions Ltd. It consists of a preliminary phantom study designed to assess the registration of images with well‐defined objects that have known positions, sizes, and shapes. In addition, a collection of novel and established metrics are used to determine image registration accuracy for both, real and simulated patient images. Results show that the Reveal‐MVS system is well suited for some applications of non‐linear image registration, but not applicable for others. Results will be used to further refine and improve upon existing non‐linear image registration algorithms.
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 | 0.035 | 0.034 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.005 | 0.003 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.021 | 0.014 |
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".