Background and purpose: Comprehensive dosimetric analysis is required prior to the clinical implementation of pelvic MR-only sites, other than prostate, due to the limited number of site specific synthetic-CT (sCT) dosimetric assessments in the literature. This study aims to provide a comprehensive assessment of a deep learning-based, conditional generative adversarial network (cGAN) model for a large ano-rectal cancer cohort. The following challenges were investigated; T2-SPACE MR sequences, patient data from multiple centres and the impact of sex and cancer site on sCT quality. Method: RT treatment position CT and T2-SPACE MR scans, from two centres, were collected for 90 anorectal patients. A cGAN model trained using a focal loss function, was trained and tested on 46 and 44 CT-MR ano-rectal datasets, paired using deformable registration, respectively. VMAT plans were created on CT and recalculated on sCT. Dose differences and gamma indices assessed sCT dosimetric accuracy. A linear mixed effect (LME) model assessed the impact of centre, sex and cancer site. Results: A mean PTV D95% dose difference of 0.1% (range: À0.5% to 0.7%) was found between CT and sCT. All gamma index (1%/1 mm threshold) measurements were >99.0%. The LME model found the impact of modality, cancer site, sex and centre was clinically insignificant (effect ranges: À0.4% and 0.3%). The mean dose difference for all OAR constraints was 0.1%. Conclusion: Focal loss cGAN models using T2-SPACE MR sequences from multiple centres can produce generalisable, dosimetrically accurate sCTs for ano-rectal cancers.
The choice of DIR algorithm was limited to those available in the RayStation 9B Treatment Planning System. However, these algorithms are representative of the range of approaches available commercially, encompassing grey-scale driven (correlation and mutual information), biomechanical and contour-driven methods. The Anaconda algorithm is capable of combining greyscale and contour registration and, herein, we have additionally combined biomechanical registration with Anaconda.Whilst many other DIR software platforms and algorithms exist, these do not fundamentally differ from the algorithms used here. Our focus was to explore the potential for combinations of existing DIR methods to overcome challenges in the case of extreme pelvic anatomical changes, so we have not attempted an algorithmic comparison. However, we would expect our findings to apply to any combination of similar grey-scale and biomechanical DIR algorithms in other contexts and systems, given an appropriate workflow as outlined below. 2 and Figure 3 and 4):
DIR results (see also Supplementary Table
Jacobian analysis:Clinical significance for reRT was assessed by overlaying the negative element mask onto the reRT CT image and combined dose distribution. In two cases the folding was <1 grid voxel (2.5 mm) and clinically insignificant. In one case, folding ~20 mm was observed, along the bladder-rectal interface. This case fell >3 s.d. from the mean for bladder DSC (0.
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.