Comprehensive dose evaluation of a Deep Learning based synthetic Computed Tomography algorithm for pelvic Magnetic Resonance-only radiotherapy

Jonathan J Wyatt; Sandeep Kaushik; Cristina Cozzini; Rachel A Pearson; Steven Petit; Marta Capala; Juan A Hernandez-Tamames; Katalin Hideghéty; Ross J Maxwell; Florian Wiesinger; Hazel M McCallum

doi:10.1016/j.radonc.2023.109692

Comprehensive dose evaluation of a Deep Learning based synthetic Computed Tomography algorithm for pelvic Magnetic Resonance-only radiotherapy

Jonathan J Wyatt, Sandeep Kaushik, Cristina Cozzini, Rachel A Pearson, Steven Petit, Marta Capala, Juan A Hernandez-Tamames, Katalin Hideghéty, Ross J Maxwell, Florian Wiesinger, Hazel M McCallum

Research output: Contribution to journal › Article › Academic › peer-review

16 Citations (Scopus)

9 Downloads (Pure)

Abstract

BACKGROUND AND PURPOSE: Magnetic Resonance (MR)-only radiotherapy enables the use of MR without the uncertainty of MR-Computed Tomography (CT) registration. This requires a synthetic CT (sCT) for dose calculations, which can be facilitated by a novel Zero Echo Time (ZTE) sequence where bones are visible and images are acquired in 65 seconds. This study evaluated the dose calculation accuracy for pelvic sites of a ZTE-based Deep Learning sCT algorithm developed by GE Healthcare.

MATERIALS AND METHODS: ZTE and CT images were acquired in 56 pelvic radiotherapy patients in the radiotherapy position. A 2D U-net convolutional neural network was trained using pairs of deformably registered CT and ZTE images from 36 patients. In the remaining 20 patients the dosimetric accuracy of the sCT was assessed using cylindrical dummy Planning Target Volumes (PTVs) positioned at four different central axial locations, as well as the clinical treatment plans (for prostate (n=10), rectum (n=4) and anus (n=6) cancers). The sCT was rigidly and deformably registered, the plan recalculated and the doses compared using mean differences and gamma analysis.

RESULTS: Mean dose differences to the PTV D98% were ≤ 0.5% for all dummy PTVs and clinical plans (rigid registration). Mean gamma pass rates at 1%/1 mm were 98.0 ± 0.4% (rigid) and 100.0 ± 0.0% (deformable), 96.5 ± 0.8% and 99.8 ± 0.1%, and 95.4 ± 0.6% and 99.4 ± 0.4% for the clinical prostate, rectum and anus plans respectively.

CONCLUSIONS: A ZTE-based sCT algorithm with high dose accuracy throughout the pelvis has been developed. This suggests the algorithm is sufficiently accurate for MR-only radiotherapy for all pelvic sites.

Original language	English
Article number	109692
Journal	Radiotherapy and Oncology
Volume	184
Early online date	6 May 2023
DOIs	https://doi.org/10.1016/j.radonc.2023.109692
Publication status	Published - Jul 2023

Bibliographical note

Funding Information:
This research is part of the Deep MR-only Radiation Therapy activity (project numbers: 19037, 20648, 210995) that has received funding from EIT Health. EIT Health is supported by the European Institute of Innovation and Technology (EIT), a body of the European Union and receives support from the European Union’s Horizon 2020 Research and innovation program.

Funding Information:
This research is part of the Deep MR-only Radiation Therapy activity (project numbers: 19037, 20648, 210995) that has received funding from EIT Health. EIT Health is supported by the European Institute of Innovation and Technology (EIT), a body of the European Union and receives support from the European Union's Horizon 2020 Research and innovation program. Sandeep Kaushik, Cristina Cozzini and Florian Wiesinger are employees of GE Healthcare.

Publisher Copyright:
© 2023 The Author(s)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.radonc.2023.109692Licence: CC BY

1-s2.0-S016781402300230X-mainFinal published version, 1.18 MBLicence: CC BY

Cite this

Wyatt, J. J., Kaushik, S., Cozzini, C., Pearson, R. A., Petit, S., Capala, M., Hernandez-Tamames, J. A., Hideghéty, K., Maxwell, R. J., Wiesinger, F., & McCallum, H. M. (2023). Comprehensive dose evaluation of a Deep Learning based synthetic Computed Tomography algorithm for pelvic Magnetic Resonance-only radiotherapy. Radiotherapy and Oncology, 184, Article 109692. https://doi.org/10.1016/j.radonc.2023.109692

@article{175a0411ea234a9f89b2f0b60377efe3,

title = "Comprehensive dose evaluation of a Deep Learning based synthetic Computed Tomography algorithm for pelvic Magnetic Resonance-only radiotherapy",

abstract = "BACKGROUND AND PURPOSE: Magnetic Resonance (MR)-only radiotherapy enables the use of MR without the uncertainty of MR-Computed Tomography (CT) registration. This requires a synthetic CT (sCT) for dose calculations, which can be facilitated by a novel Zero Echo Time (ZTE) sequence where bones are visible and images are acquired in 65 seconds. This study evaluated the dose calculation accuracy for pelvic sites of a ZTE-based Deep Learning sCT algorithm developed by GE Healthcare.MATERIALS AND METHODS: ZTE and CT images were acquired in 56 pelvic radiotherapy patients in the radiotherapy position. A 2D U-net convolutional neural network was trained using pairs of deformably registered CT and ZTE images from 36 patients. In the remaining 20 patients the dosimetric accuracy of the sCT was assessed using cylindrical dummy Planning Target Volumes (PTVs) positioned at four different central axial locations, as well as the clinical treatment plans (for prostate (n=10), rectum (n=4) and anus (n=6) cancers). The sCT was rigidly and deformably registered, the plan recalculated and the doses compared using mean differences and gamma analysis.RESULTS: Mean dose differences to the PTV D98\% were ≤ 0.5\% for all dummy PTVs and clinical plans (rigid registration). Mean gamma pass rates at 1\%/1 mm were 98.0 ± 0.4\% (rigid) and 100.0 ± 0.0\% (deformable), 96.5 ± 0.8\% and 99.8 ± 0.1\%, and 95.4 ± 0.6\% and 99.4 ± 0.4\% for the clinical prostate, rectum and anus plans respectively.CONCLUSIONS: A ZTE-based sCT algorithm with high dose accuracy throughout the pelvis has been developed. This suggests the algorithm is sufficiently accurate for MR-only radiotherapy for all pelvic sites.",

author = "Wyatt, \{Jonathan J\} and Sandeep Kaushik and Cristina Cozzini and Pearson, \{Rachel A\} and Steven Petit and Marta Capala and Hernandez-Tamames, \{Juan A\} and Katalin Hidegh{\'e}ty and Maxwell, \{Ross J\} and Florian Wiesinger and McCallum, \{Hazel M\}",

note = "Funding Information: This research is part of the Deep MR-only Radiation Therapy activity (project numbers: 19037, 20648, 210995) that has received funding from EIT Health. EIT Health is supported by the European Institute of Innovation and Technology (EIT), a body of the European Union and receives support from the European Union{\textquoteright}s Horizon 2020 Research and innovation program. Funding Information: This research is part of the Deep MR-only Radiation Therapy activity (project numbers: 19037, 20648, 210995) that has received funding from EIT Health. EIT Health is supported by the European Institute of Innovation and Technology (EIT), a body of the European Union and receives support from the European Union's Horizon 2020 Research and innovation program. Sandeep Kaushik, Cristina Cozzini and Florian Wiesinger are employees of GE Healthcare. Publisher Copyright: {\textcopyright} 2023 The Author(s)",

year = "2023",

month = jul,

doi = "10.1016/j.radonc.2023.109692",

language = "English",

volume = "184",

journal = "Radiotherapy and Oncology",

issn = "0167-8140",

publisher = "Elsevier Ireland Ltd",

}

Wyatt, JJ, Kaushik, S, Cozzini, C, Pearson, RA, Petit, S , Capala, M , Hernandez-Tamames, JA, Hideghéty, K, Maxwell, RJ, Wiesinger, F & McCallum, HM 2023, 'Comprehensive dose evaluation of a Deep Learning based synthetic Computed Tomography algorithm for pelvic Magnetic Resonance-only radiotherapy', Radiotherapy and Oncology, vol. 184, 109692. https://doi.org/10.1016/j.radonc.2023.109692

TY - JOUR

T1 - Comprehensive dose evaluation of a Deep Learning based synthetic Computed Tomography algorithm for pelvic Magnetic Resonance-only radiotherapy

AU - Wyatt, Jonathan J

AU - Kaushik, Sandeep

AU - Cozzini, Cristina

AU - Pearson, Rachel A

AU - Petit, Steven

AU - Capala, Marta

AU - Hernandez-Tamames, Juan A

AU - Hideghéty, Katalin

AU - Maxwell, Ross J

AU - Wiesinger, Florian

AU - McCallum, Hazel M

N1 - Funding Information: This research is part of the Deep MR-only Radiation Therapy activity (project numbers: 19037, 20648, 210995) that has received funding from EIT Health. EIT Health is supported by the European Institute of Innovation and Technology (EIT), a body of the European Union and receives support from the European Union’s Horizon 2020 Research and innovation program. Funding Information: This research is part of the Deep MR-only Radiation Therapy activity (project numbers: 19037, 20648, 210995) that has received funding from EIT Health. EIT Health is supported by the European Institute of Innovation and Technology (EIT), a body of the European Union and receives support from the European Union's Horizon 2020 Research and innovation program. Sandeep Kaushik, Cristina Cozzini and Florian Wiesinger are employees of GE Healthcare. Publisher Copyright: © 2023 The Author(s)

PY - 2023/7

Y1 - 2023/7

N2 - BACKGROUND AND PURPOSE: Magnetic Resonance (MR)-only radiotherapy enables the use of MR without the uncertainty of MR-Computed Tomography (CT) registration. This requires a synthetic CT (sCT) for dose calculations, which can be facilitated by a novel Zero Echo Time (ZTE) sequence where bones are visible and images are acquired in 65 seconds. This study evaluated the dose calculation accuracy for pelvic sites of a ZTE-based Deep Learning sCT algorithm developed by GE Healthcare.MATERIALS AND METHODS: ZTE and CT images were acquired in 56 pelvic radiotherapy patients in the radiotherapy position. A 2D U-net convolutional neural network was trained using pairs of deformably registered CT and ZTE images from 36 patients. In the remaining 20 patients the dosimetric accuracy of the sCT was assessed using cylindrical dummy Planning Target Volumes (PTVs) positioned at four different central axial locations, as well as the clinical treatment plans (for prostate (n=10), rectum (n=4) and anus (n=6) cancers). The sCT was rigidly and deformably registered, the plan recalculated and the doses compared using mean differences and gamma analysis.RESULTS: Mean dose differences to the PTV D98% were ≤ 0.5% for all dummy PTVs and clinical plans (rigid registration). Mean gamma pass rates at 1%/1 mm were 98.0 ± 0.4% (rigid) and 100.0 ± 0.0% (deformable), 96.5 ± 0.8% and 99.8 ± 0.1%, and 95.4 ± 0.6% and 99.4 ± 0.4% for the clinical prostate, rectum and anus plans respectively.CONCLUSIONS: A ZTE-based sCT algorithm with high dose accuracy throughout the pelvis has been developed. This suggests the algorithm is sufficiently accurate for MR-only radiotherapy for all pelvic sites.

AB - BACKGROUND AND PURPOSE: Magnetic Resonance (MR)-only radiotherapy enables the use of MR without the uncertainty of MR-Computed Tomography (CT) registration. This requires a synthetic CT (sCT) for dose calculations, which can be facilitated by a novel Zero Echo Time (ZTE) sequence where bones are visible and images are acquired in 65 seconds. This study evaluated the dose calculation accuracy for pelvic sites of a ZTE-based Deep Learning sCT algorithm developed by GE Healthcare.MATERIALS AND METHODS: ZTE and CT images were acquired in 56 pelvic radiotherapy patients in the radiotherapy position. A 2D U-net convolutional neural network was trained using pairs of deformably registered CT and ZTE images from 36 patients. In the remaining 20 patients the dosimetric accuracy of the sCT was assessed using cylindrical dummy Planning Target Volumes (PTVs) positioned at four different central axial locations, as well as the clinical treatment plans (for prostate (n=10), rectum (n=4) and anus (n=6) cancers). The sCT was rigidly and deformably registered, the plan recalculated and the doses compared using mean differences and gamma analysis.RESULTS: Mean dose differences to the PTV D98% were ≤ 0.5% for all dummy PTVs and clinical plans (rigid registration). Mean gamma pass rates at 1%/1 mm were 98.0 ± 0.4% (rigid) and 100.0 ± 0.0% (deformable), 96.5 ± 0.8% and 99.8 ± 0.1%, and 95.4 ± 0.6% and 99.4 ± 0.4% for the clinical prostate, rectum and anus plans respectively.CONCLUSIONS: A ZTE-based sCT algorithm with high dose accuracy throughout the pelvis has been developed. This suggests the algorithm is sufficiently accurate for MR-only radiotherapy for all pelvic sites.

UR - https://www.scopus.com/pages/publications/85159131076

U2 - 10.1016/j.radonc.2023.109692

DO - 10.1016/j.radonc.2023.109692

M3 - Article

C2 - 37150446

SN - 0167-8140

VL - 184

JO - Radiotherapy and Oncology

JF - Radiotherapy and Oncology

M1 - 109692

ER -

Comprehensive dose evaluation of a Deep Learning based synthetic Computed Tomography algorithm for pelvic Magnetic Resonance-only radiotherapy

Abstract

Bibliographical note

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this