Synthetic Megavoltage Cone Beam Computed Tomography Image Generation for Improved Contouring Accuracy of Cardiac Pacemakers.

Autor:	Baroudi H; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Chen X; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Cao W; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., El Basha MD; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Gay S; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Gronberg MP; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Hernandez S; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Huang K; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Kaffey Z; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Melancon AD; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Mumme RP; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Sjogreen C; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Tsai JY; Department of Anesthesiology and Perioperative Medicine, Division of Anesthesiology, Critical Care Medicine and Pain Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Yu C; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Court LE; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA., Pino R; Department of Radiation Oncology, Houston Methodist Hospital, Houston, TX 77030, USA., Zhao Y; MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas, Houston, TX 77030, USA.; Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA.
Jazyk:	angličtina
Zdroj:	Journal of imaging [J Imaging] 2023 Nov 08; Vol. 9 (11). Date of Electronic Publication: 2023 Nov 08.
DOI:	10.3390/jimaging9110245
Abstrakt:	In this study, we aimed to enhance the contouring accuracy of cardiac pacemakers by improving their visualization using deep learning models to predict MV CBCT images based on kV CT or CBCT images. Ten pacemakers and four thorax phantoms were included, creating a total of 35 combinations. Each combination was imaged on a Varian Halcyon (kV/MV CBCT images) and Siemens SOMATOM CT scanner (kV CT images). Two generative adversarial network (GAN)-based models, cycleGAN and conditional GAN (cGAN), were trained to generate synthetic MV (sMV) CBCT images from kV CT/CBCT images using twenty-eight datasets (80%). The pacemakers in the sMV CBCT images and original MV CBCT images were manually delineated and reviewed by three users. The Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and mean surface distance (MSD) were used to compare contour accuracy. Visual inspection showed the improved visualization of pacemakers on sMV CBCT images compared to original kV CT/CBCT images. Moreover, cGAN demonstrated superior performance in enhancing pacemaker visualization compared to cycleGAN. The mean DSC, HD95, and MSD for contours on sMV CBCT images generated from kV CT/CBCT images were 0.91 ± 0.02/0.92 ± 0.01, 1.38 ± 0.31 mm/1.18 ± 0.20 mm, and 0.42 ± 0.07 mm/0.36 ± 0.06 mm using the cGAN model. Deep learning-based methods, specifically cycleGAN and cGAN, can effectively enhance the visualization of pacemakers in thorax kV CT/CBCT images, therefore improving the contouring precision of these devices.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu