ESTRO 2025 - Abstract Book

S2995

Physics - Image acquisition and processing

ESTRO 2025

Conclusion: In this work, we devised a prior knowledge-induced deep learning model to accelerate CBCT imaging. Qualitative and quantitative results have shown that the proposed model can achieve the desired 3D volumetric CBCT image reconstruction. Moreover, the proposed model only needs one projection data and can be easily integrated into the existing image-guided radiotherapy procedures, showing the potential for realizing real-time imaging in ART.

Keywords: CBCT, Adaptive Radiotherapy, Deep Learning

References: [1] H. Liu, D. Schaal, H. Curry, R. Clark, A. Magliari, P. Kupelian, D. Khuntia, and S. Beriwal, “Review of cone beam computed tomography based online adaptive radiotherapy: Current trend and future direction”, Radiation Oncology, vol. 18, np. 1, p. 144, 2023.

1936

Digital Poster Spectral CT for Stopping-Power-Ratio prediction in particle therapy: Comparing Virtual Contrast Removal in Dual-Energy and Photon-Counting CT Julian Schwengfelder 1,2 , Patrick Wohlfahrt 3 , Christian Richter 1,2,4 1 OncoRay – National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany. 2 Helmholtz-Zentrum Dresden-Rossendorf, Institute of Radiooncology – OncoRay, Dresden, Germany. 3 Siemens, Healthineers, Forchheim, Germany. 4 Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany Purpose/Objective: Spectral CT imaging methods, specifically dual-energy CT (DECT) and photon-counting CT (PCCT), enable material differentiation, allowing for virtual removal of contrast agents (CA) from contrast-enhanced scans. Previous studies explored the accuracy of CA removal and showed suitability for application scenarios in radiology [1] and dose calculation in photon therapy [2]. This study investigates the CA influence on relative electron density (RED) and