The performances of the systems proved to be site specific, depending on the DVF type and the platforms and the procedures used at the various centers. The pelvis was the most challenging site for most of the algorithms, which failed to achieve sub-voxel accuracy. Improved reproducibility was observed among the centers using the same hybrid registration algorithm.
Purpose:
Various commercial algorithms for deformable image registration (DIR) were tested to investigate their accuracy and robustness, against image noise and artifacts.
Methods:
Ten institutions with five available commercial solutions provided data to assess the agreement of DIR‐propagated ROIs with automatically drawn ROIs considered as ground‐truth for the comparison. The DIR algorithms were tested on real patient data (pelvis). A Deformation was applied to the reference data set (CTref) using the ImSimQA software, a (CTeval) and seven CBCT images with increasing level of noise and capping artifacts were simulated. Every center performed DIR between CTref, and the deformed datasets. The noise was defined as standard deviation normalized to signal in an homogeneous medium, artefacts as the difference of mean HU values between the central and peripheral region of an homogeneous medium. To investigate the relationship between image quality parameters and the DIR results a three way ANOVA was performed on logit function of DICE index.
Results:
Based on 480 DIR‐mapped ROIs the ANOVA test states that centers, ROIs and Image Quality are significant predictors of DIR performances. DIR conducted on CBCT simulated images is significant worst of the ones obtained on the original images. Increasing noise and artefacts didn't affect significantly DIR performances. Considering a limit for Dice Index of 0.75 one center underperform this level. DIR resulted significantly more accurate in rectal contours propagation.
Conclusion:
This work illustrates the effect of image noise to DIR performances in a ground truth provided scenario. Clinical issues like ART or Dose Accumulation need accurate and robust DIR software using CBCT images. For the range of artefacts and noise explored in this experiment the commercial software appeared to be robust. One centre didn't satisfy the minimum accuracy requirement showing that QA is mandatory to implement clinically DIR for ROI propagation.
Purpose:
To investigate the accuracy and robustness, against image noise and artifacts (typical of CBCT images), of a commercial algorithm for deformable image registration (DIR), to propagate regions of interest (ROIs) in computational phantoms based on real prostate patient images.
Methods:
The Anaconda DIR algorithm, implemented in RayStation was tested. Two specific Deformation Vector Fields (DVFs) were applied to the reference data set (CTref) using the ImSimQA software, obtaining two deformed CTs. For each dataset twenty‐four different level of noise and/or capping artifacts were applied to simulate CBCT images. DIR was performed between CTref and each deformed CTs and CBCTs. In order to investigate the relationship between image quality parameters and the DIR results (expressed by a logit transform of the Dice Index) a bilinear regression was defined.
Results:
More than 550 DIR‐mapped ROIs were analyzed. The Statistical analysis states that deformation strenght and artifacts were significant prognostic factors of DIR performances, while noise appeared to have a minor role in DIR process as implemented in RayStation as expected by the image similarity metric built in the registration algorithm. Capping artifacts reveals a determinant role for the accuracy of DIR results. Two optimal values for capping artifacts were found to obtain acceptable DIR results (DICE> 075/ 0.85). Various clinical CBCT acquisition protocol were reported to evaluate the significance of the study.
Conclusion:
This work illustrates the impact of image quality on DIR performance. Clinical issues like Adaptive Radiation Therapy (ART) and Dose Accumulation need accurate and robust DIR software. The RayStation DIR algorithm resulted robust against noise, but sensitive to image artifacts. This result highlights the need of robustness quality assurance against image noise and artifacts in the commissioning of a DIR commercial system and underlines the importance to adopt optimized protocols for CBCT image acquisitions in ART clinical implementation.
Purpose:
To investigate the accuracy of various algorithms for deformable image registration (DIR), to propagate regions of interest (ROIs) in computational phantoms based on patient images using different commercial systems. This work is part of an Italian multi‐institutional study to test on common datasets the accuracy, reproducibility and safety of DIR applications in Adaptive Radiotherapy.
Methods:
Eleven institutions with three available commercial solutions provided data to assess the agreement of DIR‐propagated ROIs with automatically drown ROIs considered as ground‐truth for the comparison. The DIR algorithms were tested on real patient data from three different anatomical districts: head and neck, thorax and pelvis. For every dataset two specific Deformation Vector Fields (DVFs) provided by ImSimQA software were applied to the reference data set. Three different commercial software were used in this study: RayStation, Velocity and Mirada. The DIR‐mapped ROIs were then compared with the reference ROIs using the Jaccard Conformity Index (JCI).
Results:
More than 600 DIR‐mapped ROIs were analyzed. Putting together all JCI data of all institutions for the first DVF, the mean JCI was 0.87 ± 0.7 (1 SD) while for the second DVF JCI was 0.8 ± 0.13 (1 SD). Several considerations on different structures are available from collected data: the standard deviation among different institutions on specific structure raise as the larger is the applied DVF. The higher value is 10% for bladder.
Conclusion:
Although the complexity of deformation of human body is very difficult to model, this work illustrates some clinical scenarios with well‐known DVFs provided by specific software. CI parameter gives the inter‐user variability and may put in evidence the need of improving the working protocol in order to reduce the inter‐institution JCI variability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.