ESTRO 2023 - Abstract Book

S1374

Digital Posters

ESTRO 2023

Conclusion Our initial assessment of the A3i platform demonstrates large reductions in TIRT, achieved through the enhanced efficiency of the parallel workflow, and reduced TAT while TDT has not changed. Knowing that these initially reported A3i treatment times are inclusive of our initial learning curve, we anticipate further efficiency gains as our experience on the A3i platform matures.

PO-1671 3D patch cycle-GAN-based MR-to-CT synthesis from monocenter and multicenter training

P. Lekieffre 1 , E. Collot 1 , B. Texier 1 , C. Hémon 1 , S. Tahri 1 , H. Chourak 1,2 , I. Bessieres 3 , P. Greer 2 , J. Dowling 2 , A. Barateau 1 , C. Lafond 1 , R. de Crevoisier 1 , J. Nunes 1 1 LTSI, INSERM, UMR 1099, Univ Rennes 1, CHU Rennes, CLCC Eugène Marquis, Rennes, France; 2 CSIRO Australian e-Health Research Centre, Herston, Queensland, Australia; 3 Centre Georges-François Leclerc, Departement of Medical Physics, Dijon, France Purpose or Objective To increase the accuracy of cancer radiation therapy, many MR-to-CT deep-learning methods have been developed, including the 3D cycle-GAN architecture. The aim of this study is to compare a monocentric and a multicentric training of this architecture to generalize the model for use in all cancer centers. Materials and Methods For this study, prostate CT and MR images were acquired in treatment position for 79 patients from two centers. The first center is composed of 39 patients. CT scans have been acquired with a GE LightSpeedRT large-bore scanner or a Toshiba Aquilion. MR acquisitions, using 3D T2-weighted SPACE sequences, were performed with a 3T Siemens Skyra MRI scanner. The other 40 patients are from a second center where the CT scans were acquired with a GE Medical Systems LightSpeed RT16 (2.5 mm slice thickness) and the 3DT2/T1-weighted SPACE MRI with a 0.35T ViewRay Inc. Linac MRIdian. The cycle