TY - JOUR
T1 - Deep learning-based synthetic CT generation for MR-only radiotherapy of prostate cancer patients with 0.35T MRI linear accelerator
AU - Farjam, Reza
AU - Nagar, Himanshu
AU - Kathy Zhou, Xi
AU - Ouellette, David
AU - Chiara Formenti, Silvia
AU - DeWyngaert, J. Keith
N1 - Funding Information:
This work is financially supported by ViewRay Inc.
Publisher Copyright:
© 2021 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine
PY - 2021/8
Y1 - 2021/8
N2 - Purpose: To develop a deep learning model to generate synthetic CT for MR-only radiotherapy of prostate cancer patients treated with 0.35 T MRI linear accelerator. Materials and Methods: A U-NET convolutional neural network was developed to translate 0.35 T TRUFI MRI into electron density map using a novel cost function equalizing the contribution of various tissue types including fat, muscle, bone, and background air in training. The impact of training time, dataset size, image standardization, and data augmentation approaches was also quantified. Mean absolute error (MAE) between synthetic and planning CTs was calculated to measure the goodness of the model. Results: With 20 patients in training, our U-NET model has the potential to generate synthetic CT with a MAE of about 29.68 ± 4.41, 16.34 ± 2.67, 23.36 ± 2.85, and 105.90 ± 22.80 HU over the entire body, fat, muscle, and bone tissues, respectively. As expected, we found that the number of patients used for training and MAE are nonlinearly correlated. Data augmentation and our proposed loss function were effective to improve MAE by ~9% and ~18% in bony voxels, respectively. Increasing the training time and image standardization did not improve the accuracy of the model. Conclusion: A U-NET model has been developed and tested numerically to generate synthetic CT from 0.35T TRUFI MRI for MR-only radiotherapy of prostate cancer patients. Dosimetric evaluation using a large and independent dataset warrants the validity of the proposed model and the actual number of patients needed for the safe usage of the model in routine clinical workflow.
AB - Purpose: To develop a deep learning model to generate synthetic CT for MR-only radiotherapy of prostate cancer patients treated with 0.35 T MRI linear accelerator. Materials and Methods: A U-NET convolutional neural network was developed to translate 0.35 T TRUFI MRI into electron density map using a novel cost function equalizing the contribution of various tissue types including fat, muscle, bone, and background air in training. The impact of training time, dataset size, image standardization, and data augmentation approaches was also quantified. Mean absolute error (MAE) between synthetic and planning CTs was calculated to measure the goodness of the model. Results: With 20 patients in training, our U-NET model has the potential to generate synthetic CT with a MAE of about 29.68 ± 4.41, 16.34 ± 2.67, 23.36 ± 2.85, and 105.90 ± 22.80 HU over the entire body, fat, muscle, and bone tissues, respectively. As expected, we found that the number of patients used for training and MAE are nonlinearly correlated. Data augmentation and our proposed loss function were effective to improve MAE by ~9% and ~18% in bony voxels, respectively. Increasing the training time and image standardization did not improve the accuracy of the model. Conclusion: A U-NET model has been developed and tested numerically to generate synthetic CT from 0.35T TRUFI MRI for MR-only radiotherapy of prostate cancer patients. Dosimetric evaluation using a large and independent dataset warrants the validity of the proposed model and the actual number of patients needed for the safe usage of the model in routine clinical workflow.
KW - 0.35 T MRI-Linac
KW - deep learning
KW - synthetic CT
UR - http://www.scopus.com/inward/record.url?scp=85111142655&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85111142655&partnerID=8YFLogxK
U2 - 10.1002/acm2.13327
DO - 10.1002/acm2.13327
M3 - Article
C2 - 34184390
AN - SCOPUS:85111142655
SN - 1526-9914
VL - 22
SP - 93
EP - 104
JO - Journal of applied clinical medical physics
JF - Journal of applied clinical medical physics
IS - 8
ER -