Xue Li1, Poonam Yadav2, Alan B McMillan3. 1. Departments of Radiology. 2. Human Oncology, School of Medicine and Public Health, University of Wisconsin, Madison, Wisconsin. 3. Departments of Radiology. Electronic address: amcmillan@uwhealth.org.
Abstract
PURPOSE: Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast, which makes it useful for delineating tumor and normal structures in radiation therapy planning, but MRI cannot readily provide electron density for dose calculation. Computed tomography (CT) is used but introduces registration uncertainty between MRI and CT. Previous studies have shown that synthetic CTs (sCTs) can be generated directly from MRI images with deep learning methods. However, mainly high-field MRI images have been validated. This study tested whether acceptable sCTs for MR-only radiation therapy planning can be synthesized using an integrated MR-guided linear accelerator at 0.35T, using MRI images and treatment plans in the liver region. METHODS AND MATERIALS: Two models were investigated in this study: a convolutional neural network (Unet) with conventional mean square error (MSE) loss and a Unet using a secondary convolutional neural network for perceptual loss. A total of 37 cases were used in this study with 10-fold cross validation, and 37 treatment plans were generated and evaluated for target coverage and dose to organs at risk (OARs) in the MSE loss model, perceptual loss model, and original CT. RESULTS: The sCTs predicted by the perceptual loss model had improved subjective visual quality compared with those predicted by the MSE loss model, but both were similar in mean absolute error (MAE), peak-signal-to-noise ratio (PSNR), and normalized cross-correlation (NCC). The MAE, PSNR, and NCC for the perceptual loss model were 35.64, 24.11, and 0.9539, respectively, and those for the MSE loss model were 35.67, 24.36, and 0.9566, respectively. No significant differences in target coverage and dose to OARs were found between the sCT predicted by the perceptual loss model or by the MSE model and the original CT image. CONCLUSIONS: This study indicated that a Unet with both MSE loss and perceptual loss models can be used for generating sCT images from a 0.35T integrated MR linear accelerator.
PURPOSE: Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast, which makes it useful for delineating tumor and normal structures in radiation therapy planning, but MRI cannot readily provide electron density for dose calculation. Computed tomography (CT) is used but introduces registration uncertainty between MRI and CT. Previous studies have shown that synthetic CTs (sCTs) can be generated directly from MRI images with deep learning methods. However, mainly high-field MRI images have been validated. This study tested whether acceptable sCTs for MR-only radiation therapy planning can be synthesized using an integrated MR-guided linear accelerator at 0.35T, using MRI images and treatment plans in the liver region. METHODS AND MATERIALS: Two models were investigated in this study: a convolutional neural network (Unet) with conventional mean square error (MSE) loss and a Unet using a secondary convolutional neural network for perceptual loss. A total of 37 cases were used in this study with 10-fold cross validation, and 37 treatment plans were generated and evaluated for target coverage and dose to organs at risk (OARs) in the MSE loss model, perceptual loss model, and original CT. RESULTS: The sCTs predicted by the perceptual loss model had improved subjective visual quality compared with those predicted by the MSE loss model, but both were similar in mean absolute error (MAE), peak-signal-to-noise ratio (PSNR), and normalized cross-correlation (NCC). The MAE, PSNR, and NCC for the perceptual loss model were 35.64, 24.11, and 0.9539, respectively, and those for the MSE loss model were 35.67, 24.36, and 0.9566, respectively. No significant differences in target coverage and dose to OARs were found between the sCT predicted by the perceptual loss model or by the MSE model and the original CT image. CONCLUSIONS: This study indicated that a Unet with both MSE loss and perceptual loss models can be used for generating sCT images from a 0.35T integrated MR linear accelerator.
Authors: Mikael Karlsson; Magnus G Karlsson; Tufve Nyholm; Christopher Amies; Björn Zackrisson Journal: Int J Radiat Oncol Biol Phys Date: 2009-06-01 Impact factor: 7.038
Authors: S L Kwa; J C Theuws; M van Herk; E M Damen; L J Boersma; P Baas; S H Muller; J V Lebesque Journal: J Nucl Med Date: 1998-06 Impact factor: 10.057
Authors: Anna M Dinkla; Mateusz C Florkow; Matteo Maspero; Mark H F Savenije; Frank Zijlstra; Patricia A H Doornaert; Marijn van Stralen; Marielle E P Philippens; Cornelis A T van den Berg; Peter R Seevinck Journal: Med Phys Date: 2019-07-09 Impact factor: 4.071
Authors: Jie Fu; Kamal Singhrao; Minsong Cao; Victoria Yu; Anand P Santhanam; Yingli Yang; Minghao Guo; Ann C Raldow; Dan Ruan; John H Lewis Journal: Biomed Phys Eng Express Date: 2020-01-30
Authors: Samaneh Kazemifar; Sarah McGuire; Robert Timmerman; Zabi Wardak; Dan Nguyen; Yang Park; Steve Jiang; Amir Owrangi Journal: Radiother Oncol Date: 2019-04-11 Impact factor: 6.280
Authors: Yingzi Liu; Yang Lei; Yinan Wang; Tonghe Wang; Lei Ren; Liyong Lin; Mark McDonald; Walter J Curran; Tian Liu; Jun Zhou; Xiaofeng Yang Journal: Phys Med Biol Date: 2019-07-16 Impact factor: 3.609