Mateusz C Florkow1, Filipa Guerreiro2, Frank Zijlstra3, Enrica Seravalli4, Geert O Janssens5, John H Maduro6, Antje C Knopf7, René M Castelein8, Marijn van Stralen9, Bas W Raaymakers10, Peter R Seevinck11. 1. Image Sciences Institute, University Medical Centre Utrecht, Utrecht, The Netherlands. Electronic address: m.c.florkow@umcutrecht.nl. 2. Department of Radiotherapy, University Medical Centre Utrecht, Utrecht, The Netherlands. Electronic address: f.guerreiro@umcutrecht.nl. 3. Image Sciences Institute, University Medical Centre Utrecht, Utrecht, The Netherlands. Electronic address: f.zijlstra-2@umcutrecht.nl. 4. Department of Radiotherapy, University Medical Centre Utrecht, Utrecht, The Netherlands. Electronic address: e.seravalli@umcutrecht.nl. 5. Department of Radiation Oncology, University Medical Centre Utrecht, Utrecht, The Netherlands; Princess Máxima Centre for Paediatric Oncology, Utrecht, The Netherlands. Electronic address: g.o.r.janssens@umcutrecht.nl. 6. Department of Radiation Oncology, University Medical Centre Groningen, University of Groningen, The Netherlands. Electronic address: j.h.maduro@umcg.nl. 7. Department of Radiation Oncology, University Medical Centre Groningen, University of Groningen, The Netherlands. Electronic address: a.c.knopf@umcg.nl. 8. Department of Orthopaedics, University Medical Centre Utrecht, Utrecht, The Netherlands. Electronic address: r.m.castelein@umcutrecht.nl. 9. Image Sciences Institute, University Medical Centre Utrecht, Utrecht, The Netherlands; MRIguidance B.V., Utrecht, The Netherlands. Electronic address: m.vanstralen-2@umcutrecht.nl. 10. Department of Radiotherapy, University Medical Centre Utrecht, Utrecht, The Netherlands. Electronic address: b.w.raaymakers@umcutrecht.nl. 11. Image Sciences Institute, University Medical Centre Utrecht, Utrecht, The Netherlands; MRIguidance B.V., Utrecht, The Netherlands. Electronic address: p.seevinck@umcutrecht.nl.
Abstract
PURPOSE: To assess the feasibility of magnetic resonance imaging (MRI)-only treatment planning for photon and proton radiotherapy in children with abdominal tumours. MATERIALS AND METHODS: The study was conducted on 66 paediatric patients with Wilms' tumour or neuroblastoma (age 4 ± 2 years) who underwent MR and computed tomography (CT) acquisition on the same day as part of the clinical protocol. MRI intensities were converted to CT Hounsfield units (HU) by means of a UNet-like neural network trained to generate synthetic CT (sCT) from T1- and T2-weighted MR images. The CT-to-sCT image similarity was evaluated by computing the mean error (ME), mean absolute error (MAE), peak signal-to-noise ratio (PSNR) and Dice similarity coefficient (DSC). Synthetic CT dosimetric accuracy was verified against CT-based dose distributions for volumetric-modulated arc therapy (VMAT) and intensity-modulated pencil-beam scanning (PBS). Relative dose differences (Ddiff) in the internal target volume and organs-at-risk were computed and a three-dimensional gamma analysis (2 mm, 2%) was performed. RESULTS: The average ± standard deviation ME was -5 ± 12 HU, MAE was 57 ± 12 HU, PSNR was 30.3 ± 1.6 dB and DSC was 76 ± 8% for bones and 92 ± 9% for lungs. Average Ddiff were <0.5% for both VMAT (range [-2.5; 2.4]%) and PBS (range [-2.7; 3.7]%) dose distributions. The average gamma pass-rates were >99% (range [85; 100]%) for VMAT and >96% (range [87; 100]%) for PBS. CONCLUSION: The deep learning-based model generated accurate sCT from planning T1w- and T2w-MR images. Most dosimetric differences were within clinically acceptable criteria for photon and proton radiotherapy, demonstrating the feasibility of an MRI-only workflow for paediatric patients with abdominal tumours.
PURPOSE: To assess the feasibility of magnetic resonance imaging (MRI)-only treatment planning for photon and proton radiotherapy in children with abdominal tumours. MATERIALS AND METHODS: The study was conducted on 66 paediatric patients with Wilms' tumour or neuroblastoma (age 4 ± 2 years) who underwent MR and computed tomography (CT) acquisition on the same day as part of the clinical protocol. MRI intensities were converted to CT Hounsfield units (HU) by means of a UNet-like neural network trained to generate synthetic CT (sCT) from T1- and T2-weighted MR images. The CT-to-sCT image similarity was evaluated by computing the mean error (ME), mean absolute error (MAE), peak signal-to-noise ratio (PSNR) and Dice similarity coefficient (DSC). Synthetic CT dosimetric accuracy was verified against CT-based dose distributions for volumetric-modulated arc therapy (VMAT) and intensity-modulated pencil-beam scanning (PBS). Relative dose differences (Ddiff) in the internal target volume and organs-at-risk were computed and a three-dimensional gamma analysis (2 mm, 2%) was performed. RESULTS: The average ± standard deviation ME was -5 ± 12 HU, MAE was 57 ± 12 HU, PSNR was 30.3 ± 1.6 dB and DSC was 76 ± 8% for bones and 92 ± 9% for lungs. Average Ddiff were <0.5% for both VMAT (range [-2.5; 2.4]%) and PBS (range [-2.7; 3.7]%) dose distributions. The average gamma pass-rates were >99% (range [85; 100]%) for VMAT and >96% (range [87; 100]%) for PBS. CONCLUSION: The deep learning-based model generated accurate sCT from planning T1w- and T2w-MR images. Most dosimetric differences were within clinically acceptable criteria for photon and proton radiotherapy, demonstrating the feasibility of an MRI-only workflow for paediatric patients with abdominal tumours.
Authors: Khadija Sheikh; Dezhi Liu; Heng Li; Sahaja Acharya; Matthew M Ladra; William T Hrinivich Journal: J Appl Clin Med Phys Date: 2022-04-12 Impact factor: 2.243
Authors: Mateusz C Florkow; Koen Willemsen; Vasco V Mascarenhas; Edwin H G Oei; Marijn van Stralen; Peter R Seevinck Journal: J Magn Reson Imaging Date: 2022-01-19 Impact factor: 5.119