Robustness and Generalizability of Deep Learning Synthetic Computed Tomography for Positron Emission Tomography/Magnetic Resonance Imaging–Based Radiation Therapy Planning of Patients With Head and Neck Cancer
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Robustness and Generalizability of Deep Learning Synthetic Computed Tomography for Positron Emission Tomography/Magnetic Resonance Imaging–Based Radiation Therapy Planning of Patients With Head and Neck Cancer. / Olin, Anders B.; Thomas, Christopher; Hansen, Adam E.; Rasmussen, Jacob H.; Krokos, Georgios; Urbano, Teresa Guerrero; Michaelidou, Andriana; Jakoby, Björn; Ladefoged, Claes N.; Berthelsen, Anne K.; Håkansson, Katrin; Vogelius, Ivan R.; Specht, Lena; Barrington, Sally F.; Andersen, Flemming L.; Fischer, Barbara M.
I: Advances in Radiation Oncology, Bind 6, Nr. 6, 100762, 2021.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Robustness and Generalizability of Deep Learning Synthetic Computed Tomography for Positron Emission Tomography/Magnetic Resonance Imaging–Based Radiation Therapy Planning of Patients With Head and Neck Cancer
AU - Olin, Anders B.
AU - Thomas, Christopher
AU - Hansen, Adam E.
AU - Rasmussen, Jacob H.
AU - Krokos, Georgios
AU - Urbano, Teresa Guerrero
AU - Michaelidou, Andriana
AU - Jakoby, Björn
AU - Ladefoged, Claes N.
AU - Berthelsen, Anne K.
AU - Håkansson, Katrin
AU - Vogelius, Ivan R.
AU - Specht, Lena
AU - Barrington, Sally F.
AU - Andersen, Flemming L.
AU - Fischer, Barbara M.
N1 - Publisher Copyright: © 2021 The Authors
PY - 2021
Y1 - 2021
N2 - Purpose: Radiotherapy planning based only on positron emission tomography/magnetic resonance imaging (PET/MRI) lacks computed tomography (CT) information required for dose calculations. In this study, a previously developed deep learning model for creating synthetic CT (sCT) from MRI in patients with head and neck cancer was evaluated in 2 scenarios: (1) using an independent external dataset, and (2) using a local dataset after an update of the model related to scanner software-induced changes to the input MRI. Methods and Materials: Six patients from an external site and 17 patients from a local cohort were analyzed separately. Each patient underwent a CT and a PET/MRI with a Dixon MRI sequence over either one (external) or 2 (local) bed positions. For the external cohort, a previously developed deep learning model for deriving sCT from Dixon MRI was directly applied. For the local cohort, we adapted the model for an upgraded MRI acquisition using transfer learning and evaluated it in a leave-one-out process. The sCT mean absolute error for each patient was assessed. Radiotherapy dose plans based on sCT and CT were compared by assessing relevant absorbed dose differences in target volumes and organs at risk. Results: The MAEs were 78 ± 13 HU and 76 ± 12 HU for the external and local cohort, respectively. For the external cohort, absorbed dose differences in target volumes were within ± 2.3% and within ± 1% in 95% of the cases. Differences in organs at risk were <2%. Similar results were obtained for the local cohort. Conclusions: We have demonstrated a robust performance of a deep learning model for deriving sCT from MRI when applied to an independent external dataset. We updated the model to accommodate a larger axial field of view and software-induced changes to the input MRI. In both scenarios dose calculations based on sCT were similar to those of CT suggesting a robust and reliable method.
AB - Purpose: Radiotherapy planning based only on positron emission tomography/magnetic resonance imaging (PET/MRI) lacks computed tomography (CT) information required for dose calculations. In this study, a previously developed deep learning model for creating synthetic CT (sCT) from MRI in patients with head and neck cancer was evaluated in 2 scenarios: (1) using an independent external dataset, and (2) using a local dataset after an update of the model related to scanner software-induced changes to the input MRI. Methods and Materials: Six patients from an external site and 17 patients from a local cohort were analyzed separately. Each patient underwent a CT and a PET/MRI with a Dixon MRI sequence over either one (external) or 2 (local) bed positions. For the external cohort, a previously developed deep learning model for deriving sCT from Dixon MRI was directly applied. For the local cohort, we adapted the model for an upgraded MRI acquisition using transfer learning and evaluated it in a leave-one-out process. The sCT mean absolute error for each patient was assessed. Radiotherapy dose plans based on sCT and CT were compared by assessing relevant absorbed dose differences in target volumes and organs at risk. Results: The MAEs were 78 ± 13 HU and 76 ± 12 HU for the external and local cohort, respectively. For the external cohort, absorbed dose differences in target volumes were within ± 2.3% and within ± 1% in 95% of the cases. Differences in organs at risk were <2%. Similar results were obtained for the local cohort. Conclusions: We have demonstrated a robust performance of a deep learning model for deriving sCT from MRI when applied to an independent external dataset. We updated the model to accommodate a larger axial field of view and software-induced changes to the input MRI. In both scenarios dose calculations based on sCT were similar to those of CT suggesting a robust and reliable method.
U2 - 10.1016/j.adro.2021.100762
DO - 10.1016/j.adro.2021.100762
M3 - Journal article
C2 - 34585026
AN - SCOPUS:85122681519
VL - 6
JO - Advances in Radiation Oncology
JF - Advances in Radiation Oncology
SN - 2452-1094
IS - 6
M1 - 100762
ER -
ID: 302072643