Feasibility of artificial-intelligence-based synthetic computed tomography in a magnetic resonance-only radiotherapy workflow for brain radiotherapy: Two-way dose validation and 2D/2D kV-image-based positioning

被引:13
|
作者
Masitho, Siti [1 ,2 ,3 ]
Szkitsak, Juliane [1 ,3 ]
Grigo, Johanna [1 ,3 ]
Fietkau, Rainer [1 ,3 ]
Putz, Florian [1 ,3 ]
Bert, Christoph [1 ,3 ]
机构
[1] Univtsklinikum Erlangen, Friedrich Alexander Univ Erlangen Nurnberg FAU, Dept Radiat Oncol, Erlangen, Germany
[2] Univtsklinikum Erlangen, Strahlenklin, Univtsstrass 27, D-91054 Erlangen, Germany
[3] Comprehens Canc Ctr Erlangen EMN CCC EREMN, Erlangen, Germany
来源
PHYSICS & IMAGING IN RADIATION ONCOLOGY | 2022年 / 24卷
关键词
Brain radiotherapy; Synthetic CT; MRI-only workflow; Artificial intelligence; kV -image -based positioning; CT IMAGES; ELECTRON-DENSITY; MRI; VERIFICATION; DISTORTION; ACCURACY; TUMORS;
D O I
10.1016/j.phro.2022.10.002
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Background and purpose: Magnetic Resonance Imaging (MRI)-only workflow eliminates the MRI-computed to-mography (CT) registration inaccuracy, which degrades radiotherapy (RT) treatment accuracy. For an MRI-only workflow MRI sequences need to be converted to synthetic-CT (sCT). The purpose of this study was to evaluate a commercially available artificial intelligence (AI)-based sCT generation for dose calculation and 2D/2D kV -image daily positioning for brain RT workflow. Materials and methods: T1-VIBE DIXON was acquired at the 1.5 T MRI for 26 patients in RT setup for sCTs generation. For each patient, a volumetric modulated arc therapy (VMAT) plan was optimized on the CT, then recalculated on the sCT; and vice versa. sCT-based digitally reconstructed radiographs (DRRs) were fused with stereoscopic X-ray images recorded as image guidance for clinical treatments. Dosimetric differences between planned/recalculated doses and the differences between the calculated and recorded clinical couch shift/rotation were evaluated. Results: Mean Delta D50 between planned/recalculated doses for target volumes ranged between -0.2 % and 0.2 %; mean Delta D50 and Delta D0.01ccm were-0.6 % and 1.6 % and-1.4 % and 1.0 % for organ-at-risks, respectively. Dif-ferences were tested for clinical equivalence using intervals +/- 2 % (dose), +/- 1mm (translation), and +/- 1 degrees (rota-tion). Dose equivalence was found using +/- 2 % interval (p < 0.001). The median differences between lat./long./ vert. couch shift between CT-based/sCT-based DRRs were 0.3 mm/0.2 mm/0.3 mm (p < 0.05); median differ-ences between lat./long./vert. couch rotation were -1.5 degrees/0.1 degrees/0.1 degrees (after improvement of RT setup: - 0.4 degrees/ -0.1 degrees/- 0.4 degrees , p < 0.05). Conclusions: This in-silico study showed that the AI-based sCT provided equivalent results to the CT for dose calculation and daily stereoscopic X-ray positioning when using an optimal RT setup during MRI acquisition.
引用
收藏
页码:111 / 117
页数:7
相关论文
共 1 条
  • [1] Challenges and opportunities in the development and clinical implementation of artificial intelligence based synthetic computed tomography for magnetic resonance only radiotherapy
    Villegas, Fernanda
    Dal Bello, Riccardo
    Alvarez-Andres, Emilie
    Dhont, Jennifer
    Janssen, Tomas
    Milan, Lisa
    Robert, Charlotte
    Salagean, Ghizela-Ana-Maria
    Tejedor, Natalia
    Trnkova, Petra
    Fusella, Marco
    Placidi, Lorenzo
    Cusumano, Davide
    RADIOTHERAPY AND ONCOLOGY, 2024, 198