A deep learning approach to generate synthetic CT in low field MR-guided radiotherapy for lung cases

Jacopo Lenkowicz, Matteo Nardini, Flaviovincenzo Quaranta, Luca Boldrini, Lorenzo Placidi, Angela Romano, Giuditta Chiloiro, Maria Antonietta Gambacorta, Gian Carlo Mattiucci, Luca Indovina, Vincenzo Valentini, Davide Cusumano

Risultato della ricerca: Contributo in rivistaArticolo in rivista


Introduction: This study aims to apply a conditional Generative Adversarial Network (cGAN) to generate synthetic Computed Tomography (sCT) from 0.35 Tesla Magnetic Resonance (MR) images of the thorax.Methods: Sixty patients treated for lung lesions were enrolled and divided into training (32), validation (8), internal (10,TA) and external (10,TB) test set. Image accuracy of generated sCT was evaluated comput-ing the mean absolute (MAE) and mean error (ME) with respect the original CT. Three treatment plans were calculated for each patient considering MRI as reference image: original CT, sCT (pure sCT) and sCT with GTV density override (hybrid sCT) were used as Electron Density (ED) map. Dose accuracy was evaluated comparing treatment plans in terms of gamma analysis and Dose Volume Histogram (DVH) parameters.Results: No significant difference was observed between the test sets for image and dose accuracy param-eters. Considering the whole test cohort, a MAE of 54.9 & PLUSMN; 10.5 HU and a ME of 4.4 & PLUSMN; 7.4 HU was obtained. Mean gamma passing rates for 2%/2mm, and 3%/3mm tolerance criteria were 95.5 & PLUSMN; 5.9% and 98.2 & PLUSMN; 4.1% for pure sCT, 96.1 & PLUSMN; 5.1% and 98.5 & PLUSMN; 3.9% for hybrid sCT: the difference between the two approaches was significant (p = 0.01). As regards DVH analysis, differences in target parameters estima-tion were found to be within 5% using hybrid approach and 20% using pure sCT.Conclusion: The DL algorithm here presented can generate sCT images in the thorax with good image and dose accuracy, especially when the hybrid approach is used. The algorithm does not suffer from inter -scanner variability, making feasible the implementation of MR-only workflows for palliative treatments.(c) 2022 Elsevier B.V. All rights reserved. Radiotherapy and Oncology 176 (2022) 31-38
Lingua originaleEnglish
pagine (da-a)31-38
Numero di pagine8
RivistaRadiotherapy and Oncology
Stato di pubblicazionePubblicato - 2022


  • Artificial Intelligence
  • Deep Learning
  • Synthetic CT
  • MR-only Radiotherapy
  • MR-guided Radiotherapy


Entra nei temi di ricerca di 'A deep learning approach to generate synthetic CT in low field MR-guided radiotherapy for lung cases'. Insieme formano una fingerprint unica.

Cita questo