Author: Jiayi Chen, Manju Liu, Ning Wen, Haoran Zhang, Yibin Zhang 👨🔬
Affiliation: Department of Radiation Oncology, Ruijin Hospital, Department of Radiology, Ruijin Hospital Shanghai Jiaotong University School of Medicine, Duke Kunshan University, Department of Radiation Oncology,Ruijin Hospital, Shanghai Jiao Tong University School of Medicine 🌍
Purpose: This study introduces a novel Dual Energy CT (DECT)-Guided Intelligent Radiation Therapy (DEIT) platform designed to streamline and optimize the radiotherapy process. The DEIT system combines DECT, a newly designed dual-layer multi-leaf collimator, deep learning algorithms for auto-segmentation, automated planning and QA capabilities.
Methods: The DEIT system integrates an 80-slice CT scanner with an 87 cm bore size, a linear accelerator delivering four photon and five electron energies, and a flat panel imager optimized for MV Cone Beam CT acquisition. A comprehensive evaluation of the system’s accuracy was conducted using end-to-end tests. Virtual monoenergetic CT images and electron density images of the DECT were generated and compared on both phantom and patient. The system’s auto-segmentation algorithms were tested on five cases for each of the 99 organs at risk. Automated optimization and planning capabilities were validated using 10 clinical cases, including 5 brain cases and 5 non-brain cases.
Results: The DEIT system demonstrated systematic errors of less than 1 mm for target localization. DECT reconstruction showed electron density mapping deviations ranging from -0.052 to 0.001, with stable HU consistency across monoenergetic levels above 60 keV, except for high-Z materials at lower energies. Auto-segmentation achieved dice similarity coefficients above 0.9 for most organs with inference time less than 2 seconds. Dose-volume histogram (DVH) comparisons showed improved dose conformity indices and reduced doses to critical structures in Auto-plans across various clinical cases. Additionally, gamma passing rates at 2%/2mm exceeded 97% in 2D and 99% in 3D in vivo QA analyses, further confirming the accuracy and reliability of the treatment plans.
Conclusion: The DEIT system represents an advancement in radiotherapy, integrating high-resolution imaging, AI-driven auto-segmentation, and automated treatment planning and QA capability to provide personalized, adaptive treatment.