ESTRO 2024 - Abstract Book

S3788

Physics - Image acquisition and processing

ESTRO 2024

(~15 image pairs) to account for CBCT quality changes. The proposed methodology greatly increases the viability of clinical integration of sCT-generating deep learning models.

Keywords: synthetic ct, adaptive radiotherapy, deep learning

References:

[1] Thummerer A, Seller Oria C, Zaffino P, et al. Clinical suitability of deep learning-based synthetic CTs for adaptive proton therapy of lung cancer. Med Phys. 2021;48(12):7673-7684. doi:10.1002/mp.15333

[2] Spadea MF, Pileggi G, Zaffino P, et al. Deep Convolution Neural Network (DCNN) Multiplane Approach to Synthetic CT Generation From MR images-Application in Brain Proton Therapy. Int J Radiat Oncol Biol Phys. 2019;105(3):495 503. doi:10.1016/j.ijrobp.2019.06.2535 [3] de Koster, RJC, Thummerer, A, Scandurra, D, Langendijk, JA, Both, S. Technical note: Evaluation of deep learning based synthetic CTs clinical readiness for dose and NTCP driven head and neck adaptive proton therapy. Med Phys. 2023; 1-11. https://doi.org/10.1002/mp.16782

679

Digital Poster

Image quantified method for digital tomosynthesis technology of different gantry rotation for IGRT.

Fang-Jing Li, Meng-Wei Ho, Jen-Yu Cheng

Kaohsiung Chang Gung Memorial Hospital, Department of Radiation Oncology and Proton & Radiation Therapy Center, Kaohsiung, Taiwan

Purpose/Objective:

Previous studies have indicated that the digital tomosynthesis (DTS) images serve as a simpler alternative for image guided radiation therapy, offering the potential to significantly increase the temporal resolution while reducing mechanical constrains and imaging dose [1-3]. DTS technology can be employed in respiratory-gated liver treatment to acquire breath-hold (BH) images during a single BH, thus avoiding out-of-plane blurring caused by multiple BH segments [1]. It can also improve the effective in identifying pulmonary nodules [2]. Furthermore, DTS technology can be used for edge detection of breast lesion in the oblique DTS scans [3]. Since the DTS is a limited angle image tomography, the trajectory of image acquisition rotation is a crucial imaging parameter. This study aims to provide quantified image methods to identify the optimal gantry rotation trajectory for DTS image acquisition in our system.

Material/Methods: