Med Phys. 2022 Nov 6. doi: 10.1002/mp.16087. Online ahead of print.
ABSTRACT
BACKGROUND: The growing adoption of MRI-guided radiation therapy (RT) platforms and a focus on MRI-only RT workflows has brought the technical challenge of synthetic CT (sCT) reconstruction to the forefront. Unpaired-data deep learning-based approaches to the problem offer the attractive characteristic of not requiring paired training data, but the gap between paired- and unpaired-data results can be limiting.
PURPOSE: We present two distinct approaches aimed at improving unpaired-data sCT reconstruction results: a cascade ensemble that combines multiple models and a personalized training strategy originally designed for the paired-data setting.
METHODS: Comparisons are made between the following models: 1) the paired-data fully convolutional DenseNet (FCDN), 2) the FCDN with the Intentional Deep Overfit Learning (IDOL) personalized training strategy, 3) the unpaired-data CycleGAN, 4) the CycleGAN with the IDOL training strategy, and 5) the CycleGAN as an intermediate model in a cascade ensemble approach. Evaluation of the various models over 25 total patients is carried out using a five-fold cross validation scheme, with the patient-specific IDOL models being trained for the five patients of fold 3, chosen at random.
RESULTS: In both the paired- and unpaired-data settings, adopting the IDOL training strategy led to improvements in the mean absolute error (MAE) between true CT images and sCT outputs within the body contour (mean improvement, paired- and unpaired-data approaches, respectively: 38%, 9%) and in regions of bone (52%, 5%), the peak signal to noise ratio (PSNR; 15%, 7%), and the structural similarity index (SSIM; 6%, <1%). The ensemble approach offered additional benefits over the IDOL approach in all three metrics (mean improvement over unpaired-data approach in fold 3; MAE: 20% bone MAE: 16% PSNR: 10% SSIM: 2%), and differences in body MAE between the ensemble approach and the paired-data approach are statistically insignificant.
CONCLUSIONS: We have demonstrated that both a cascade ensemble approach and a personalized training strategy designed initially for the paired-data setting offer significant improvements in image quality metrics for the unpaired-data sCT reconstruction task. Closing the gap between paired- and unpaired-data approaches is a step towards fully enabling these powerful and attractive unpaired-data frameworks. This article is protected by copyright. All rights reserved.
PMID:36336718 | DOI:10.1002/mp.16087
