ESTRO 2022 - Abstract Book

S288

Abstract book

ESTRO 2022

Results We deploy the trained model on the held-out testing set for few-view 3D image reconstruction. The reconstructed results are compared with ground truth qualitatively and quantitatively. For single-/two-/three-view reconstruction, the average NRMSE / SSIM / PSNR values over all testing data are 0.368 / 0.734 / 20.770, 0.300 / 0.807 / 22.687 and 0.274 / 0.838 / 23.669, respectively. By visualizing the reconstructed CT images, we observe the proposed model can generate images closely to the targets although the anatomic structures of different patients have a large variance, indicating the potential of the proposed model for volumetric imaging even with few views. Moreover, experiments also show the proposed model can also be generalized to multi-view 3D image reconstruction and outperform deep models without geometry priors.

Conclusion We present a novel geometry-integrated deep learning model for volumetric imaging with ultra-sparse sampling. The study opens new avenues for data-driven biomedical imaging and promises to provide substantially improved imaging tools for various clinical imaging and image-guided interventions.

Poster Discussion: 08: Advances in radiotherapy planning & techniques

PD-0325 Feasibility and safety of MR-guided stereotactic ablative body radiotherapy for Prostate Cancer

L. Geddes 1 , D. Crawford 1 , V. Batumalai 1 , C. Pagulayan 1 , L. Hogan 1 , U. Jelen 1 , C. Loo 1 , N. Dunkerley 1 , M. Picton 1 , S. Alvares 1 , S. Sampaio 1 , M. Heinke 1 , T. Twentyman 1 , M. Jameson 1 , J. De Leon 1

1 GenesisCare, Radiation Oncology, Sydney, Australia

Purpose or Objective