TY - JOUR
T1 - An MRI sequence independent convolutional neural network for synthetic head CT generation in proton therapy
AU - Zimmermann, Lukas
AU - Knäusl, Barbara
AU - Stock, Markus
AU - Lütgendorf-Caucig, Carola
AU - Georg, Dietmar
AU - Kuess, Peter
N1 - Copyright © 2021. Published by Elsevier GmbH.
PY - 2022/5
Y1 - 2022/5
N2 - A magnetic resonance imaging (MRI) sequence independent deep learning technique was developed and validated to generate synthetic computed tomography (sCT) scans for MR guided proton therapy. 47 meningioma patients previously undergoing proton therapy based on pencil beam scanning were divided into training (33), validation (6), and test (8) cohorts. T1, T2, and contrast enhanced T1 (T1CM) MRI sequences were used in combination with the planning CT (pCT) data to train a 3D U-Net architecture with ResNet-Blocks. A hyperparameter search was performed including two loss functions, two group sizes of normalisation, and depth of the network. Training outcome was compared between models trained for each individual MRI sequence and for all sequences combined. The performance was evaluated based on a metric and dosimetric analysis as well as spot difference maps. Furthermore, the influence of immobilisation masks that are not visible on MRIs was investigated. Based on the hyperparameter search, the final model was trained with fixed features per group for the group normalisation, six down-convolution steps, an input size of 128 × 192 × 192, and feature loss. For the test dataset for body/bone the mean absolute error (MAE) values were on average 79.8/216.3 Houndsfield unit (HU) when trained using T1 images, 71.1/186.1 HU for T2, and 82.9/236.4 HU for T1CM. The structural similarity metric (SSIM) ranged from 0.95 to 0.98 for all sequences. The investigated dose parameters of the target structures agreed within 1% between original proton treatment plans and plans recalculated on sCTs. The spot difference maps had peaks at ±0.2 cm and for 98% of all spots the difference was less than 1 cm. A novel MRI sequence independent sCT generator was developed, which suggests that the training phase of neural networks can be disengaged from specific MRI acquisition protocols. In contrast to previous studies, the patient cohort consisted exclusively of actual proton therapy patients (i.e. “real-world data”).
AB - A magnetic resonance imaging (MRI) sequence independent deep learning technique was developed and validated to generate synthetic computed tomography (sCT) scans for MR guided proton therapy. 47 meningioma patients previously undergoing proton therapy based on pencil beam scanning were divided into training (33), validation (6), and test (8) cohorts. T1, T2, and contrast enhanced T1 (T1CM) MRI sequences were used in combination with the planning CT (pCT) data to train a 3D U-Net architecture with ResNet-Blocks. A hyperparameter search was performed including two loss functions, two group sizes of normalisation, and depth of the network. Training outcome was compared between models trained for each individual MRI sequence and for all sequences combined. The performance was evaluated based on a metric and dosimetric analysis as well as spot difference maps. Furthermore, the influence of immobilisation masks that are not visible on MRIs was investigated. Based on the hyperparameter search, the final model was trained with fixed features per group for the group normalisation, six down-convolution steps, an input size of 128 × 192 × 192, and feature loss. For the test dataset for body/bone the mean absolute error (MAE) values were on average 79.8/216.3 Houndsfield unit (HU) when trained using T1 images, 71.1/186.1 HU for T2, and 82.9/236.4 HU for T1CM. The structural similarity metric (SSIM) ranged from 0.95 to 0.98 for all sequences. The investigated dose parameters of the target structures agreed within 1% between original proton treatment plans and plans recalculated on sCTs. The spot difference maps had peaks at ±0.2 cm and for 98% of all spots the difference was less than 1 cm. A novel MRI sequence independent sCT generator was developed, which suggests that the training phase of neural networks can be disengaged from specific MRI acquisition protocols. In contrast to previous studies, the patient cohort consisted exclusively of actual proton therapy patients (i.e. “real-world data”).
KW - MRI-only
KW - Proton therapy
KW - Synthetic CT
KW - Transfer learning
KW - Neural Networks, Computer
KW - Head
KW - Radiotherapy Planning, Computer-Assisted/methods
KW - Humans
KW - Image Processing, Computer-Assisted/methods
KW - Proton Therapy/methods
KW - Magnetic Resonance Imaging/methods
KW - Tomography, X-Ray Computed
UR - http://www.scopus.com/inward/record.url?scp=85121770411&partnerID=8YFLogxK
U2 - 10.1016/j.zemedi.2021.10.003
DO - 10.1016/j.zemedi.2021.10.003
M3 - Journal article
C2 - 34920940
AN - SCOPUS:85121770411
SN - 0939-3889
VL - 32
SP - 218
EP - 227
JO - Zeitschrift fur Medizinische Physik
JF - Zeitschrift fur Medizinische Physik
IS - 2
ER -