Evaluation of CT to CBCT non-linear dense anatomical block matching registration for prostate patients
Bibliographic record
Abstract
Abstract Deformable image registration (DIR) is a rapidly developing discipline in the field of medical imaging that has found numerous applications in modern radiation therapy. To be used in the clinical environment, DIR requires an accurate and robust algorithm supported by the careful evaluation. The purpose of this study was to evaluate the performance of the non-linear Dense Anatomical Block Matching (DABM) algorithm for CT-CBCT image registration of prostate cancer patients. Pre-treatment CT (pCT) images of five prostate patients that underwent intensity modulated radiation therapy (IMRT) were selected for this work. Mid-treatment CBCT data sets acquired during radiotherapy course were used to help validate the algorithm performance and benchmark against other commonly used DIR algorithms. Rigid alignment was followed by the DIR of considered images. After registration, structures (PTV, GTV, Bladder and Rectum) delineated on the pCT were deformed using the obtained deformation vector fields (DVFs), then propagated to the CBCT images and compared to the analogous contours delineated on the CBCT by an experienced radiation oncologist. The accuracy of image registration was assessed by several quantitative metrics: Dice Similarity Coefficient (DSC), Hausdorff Distances (HD; average and 95th percentile), Center of the Mass Shift (COM) as well as by physician validation. The topology of the obtained deformation vector fields was analyzed by the Jacobian determinant. The accuracy of the inverted DFVs was investigated by the application of the Inverse Consistency Error (ICE). The performance of the DABM algorithm was quantitatively compared to Rigid, Affine and B-spline algorithms. Results indicate that for all the patients and anatomical structures considered here, both the accuracy and the consistency of the DABM algorithm are considerably better than the other evaluated registration methods. Generated DVFs have a well-preserved topology and small ICEs. Presented findings show that DABM is a promising alternative to the existing common strategies for CT-CBCT image registration and its application in the adaptive radiation therapy of the pelvic region.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".