Copenhagen, Denmark
Onsite/Online

ESTRO 2022

Session Item

Monday
May 09
10:30 - 11:30
Room D5
Deep learning for image analysis
Andre Dekker, The Netherlands;
Catarina Veiga, United Kingdom
Proffered Papers
Physics
11:00 - 11:10
Deep learning-based 4D synthetic CT for lung radiotherapy
Matteo Maspero, The Netherlands
OC-0772

Abstract

Deep learning-based 4D synthetic CT for lung radiotherapy
Authors:

Matteo Maspero1, Katrinus Keijnemans1, Sara L Hackett1, Bas W Raaymakers1, Joost J C Verhoeff1, Martin F Fast1, Cornelis A T van den Berg1

1UMC Utrecht, Radiotherapy, Utrecht, The Netherlands

Show Affiliations
Purpose or Objective

Synthetic-computed tomography (sCT) generation is crucial to enable MR-only radiotherapy (RT) and accurate MR-based dose calculations[1]. To date, sCT generation was scarcely performed in the thoracic area[2,3]. Obtaining sCT in a region strongly affected by breathing motion is crucial to facilitate adaptive MR-guided radiotherapy (MRgRT), possibly reducing the time from patient positioning to irradiation and enabling dose accumulation based on 4D MRI. Also, dose accumulation requires fast respiratory-sorted sCT generation (<1min)[4,5]. Recently, convolutional neural networks (CNNs) were able to generate sCTs (< 20 s) quickly[6,7]. However, no previous work focused on the generations of sCT for anatomies affected by respiratory motion.

This work aims to assess the feasibility of sCT generation for patients with thoracic cancer using 4D MRI sorted according to the respiratory phase and investigate the dosimetric accuracy of MR-based calculation with these sCTs.

Material and Methods

Thirteen patients undergoing lung radiotherapy were considered in this study. Patients underwent a planning 4D-CT, and a 4D-MRI was acquired with a simultaneous multi-slice (SMS) sequence obtaining ten respiratory phases and a midposition. Additional 98 thoracic patients imaged with 3D CT and a 2D turbo spin-echo MRI were considered to enlarge the training set.  Patients were split in train (4D/3D=7/70)/validation (2/7) /test (4/11) sets. A 2D reversible adversarial network (revGAN) was used to learn paired mapping from MRI to CT. Before training, CT images were rigidly registered to MR images (Fig1). Training of revGAN was performed in the three orthogonal planes and over ten respiratory phases and midposition for 30 epochs. After hyperparameter optimisation on the validation set, the network was inferred in the three orthogonal directions to the four patients (test), producing three sCTs per patient. A voxel-wise median was calculated for each patient, obtaining a combined sCT [8]. The midposition sCTs in the test were evaluated against the midposition planning CT after matching body contours. Dose recalculation of clinical plans was performed on sCTs in Monaco (Elekta AB, 3mm grid) with 1.5 T magnetic field. Dose distributions were analysed through voxel-based dose differences and gamma-analysis.

Results


Applying the trained revGAN to the three planes of a single patient (Fig1) required about 10s. A mean absolute error of 71±14HU (mean±std) was obtained in the body contours intersection between CT and sCT (Tab1). A dose difference of 0.8±1.0% was obtained on the D>90% of the prescribed dose, with a mean γ-2%,2mm pass rate of 97.8±1.0% (Tab1).

Conclusion

Accurate MR-based dose calculation from MR-based sCT is feasible for lung cancer patients, enabling MRI-only radiotherapy in an anatomical area affected by respiratory motion. This study motivates the development of MR-only RT for lung advocating for a clinical study on a larger cohort.