SU‐FF‐J‐130: Validation of Non‐Linear Image Registration‐Based Correction Method for Motion Artifacts in 4D‐CT
Bibliographic record
Abstract
Purpose: Motion artifacts in CT can be reduced by using 4D‐CT acquisition techniques where image slices are retrospectively binned according to breathing phase as determined by a breathing trace. However, motion artifacts may still occur due to breathing irregularities. Such artifacts affect organ delineation and lead to complications when using 4D CT data for dose calculation and accumulation. We propose a method for correcting such artifacts by temporal interpolation using non‐linear image registration. Method and Materials: The ANIMAL non‐linear image registration algorithm was used to determine the transformation between artifact‐free phases adjacent to the phase containing the motion artifacts. The weighting factor which, when applied to the transformation, most closely reconstructs the anatomy at the phase to be corrected was determined. CT values in regions of the image containing the artifacts were then replaced with the corresponding CT values from the reconstructed image. The accuracy of the temporal interpolation method was evaluated by simulating motion artifacts resulting from different breathing amplitudes using the NCAT numerical breathing phantom for which the artifact‐free image is available by definition. The reconstructed image was compared to the artifact‐free image. The temporal interpolation method was applied to correct motion artifacts in patient 4D CT data and the corrected images were compared to physician‐delineated contours. Results: Correlation between the NCAT phantom images with and without artifacts was improved from 0.971 to 0.992 after correction of the artifacts by temporal interpolation. The quality of the patient 4D CT data was improved after temporal interpolation and the reconstructed anatomy was consistent with manual contours. Conclusion: We have developed a method for reconstructing anatomy on 4D CT images in the presence of motion artifacts. The temporal interpolation method was demonstrated to reduce the appearance of these artifacts and therefore improve the accuracy of organ delineation and dose calculation.
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 | 0.004 | 0.010 |
| 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 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".