Kang Hyejoo, Podgorsak Alexander R, Venkatesulu Bhanu Prasad, Saripalli Anjali L, Chou Brian, Solanki Abhishek A, Harkenrider Matthew, Shea Steven, Roeske John C, Abuhamad Mohammed
Department of Radiation Oncology, Stritch School of Medicine, Cardinal Bernadin Cancer Center, Loyola University Chicago, 2160 S. 1st Ave, Maywood, IL, United States of America.
Department of Radiology, Stritch School of Medicine, Cardinal Bernadin Cancer Center, Loyola University Chicago, 2160 S. 1st Ave, Maywood, IL, United States of America.
Phys Med Biol. 2023 Jul 28;68(15). doi: 10.1088/1361-6560/ace674.
. Both computed tomography (CT) and magnetic resonance imaging (MRI) images are acquired for high-dose-rate (HDR) prostate brachytherapy patients at our institution. CT is used to identify catheters and MRI is used to segment the prostate. To address scenarios of limited MRI access, we developed a novel generative adversarial network (GAN) to generate synthetic MRI (sMRI) from CT with sufficient soft-tissue contrast to provide accurate prostate segmentation without MRI (rMRI).. Our hybrid GAN, PxCGAN, was trained utilizing 58 paired CT-MRI datasets from our HDR prostate patients. Using 20 independent CT-MRI datasets, the image quality of sMRI was tested using mean absolute error (MAE), mean squared error (MSE), peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). These metrics were compared with the metrics of sMRI generated using Pix2Pix and CycleGAN. The accuracy of prostate segmentation on sMRI was evaluated using the Dice similarity coefficient (DSC), Hausdorff distance (HD) and mean surface distance (MSD) on the prostate delineated by three radiation oncologists (ROs) on sMRI versus rMRI. To estimate inter-observer variability (IOV), these metrics between prostate contours delineated by each RO on rMRI and the prostate delineated by treating RO on rMRI (gold standard) were calculated.. Qualitatively, sMRI images show enhanced soft-tissue contrast at the prostate boundary compared with CT scans. For MAE and MSE, PxCGAN and CycleGAN have similar results, while the MAE of PxCGAN is smaller than that of Pix2Pix. PSNR and SSIM of PxCGAN are significantly higher than Pix2Pix and CycleGAN (p < 0.01). The DSC for sMRI versus rMRI is within the range of the IOV, while the HD for sMRI versus rMRI is smaller than the HD for the IOV for all ROs (p ≤ 0.03).. PxCGAN generates sMRI images from treatment-planning CT scans that depict enhanced soft-tissue contrast at the prostate boundary. The accuracy of prostate segmentation on sMRI compared to rMRI is within the segmentation variation on rMRI between different ROs.
在我们机构，高剂量率（HDR）前列腺近距离放射治疗患者会同时获取计算机断层扫描（CT）和磁共振成像（MRI）图像。CT用于识别导管，MRI用于分割前列腺。为解决MRI获取受限的情况，我们开发了一种新型生成对抗网络（GAN），以从CT生成具有足够软组织对比度的合成MRI（sMRI），从而在没有MRI（rMRI）的情况下提供准确的前列腺分割。我们的混合GAN，即PxCGAN，利用来自我们HDR前列腺患者的58对CT-MRI数据集进行训练。使用20个独立的CT-MRI数据集，使用平均绝对误差（MAE）、均方误差（MSE）、峰值信噪比（PSNR）和结构相似性指数（SSIM）测试sMRI的图像质量。将这些指标与使用Pix2Pix和CycleGAN生成的sMRI的指标进行比较。在由三位放射肿瘤学家（ROs）在sMRI与rMRI上勾勒出的前列腺上，使用骰子相似系数（DSC）、豪斯多夫距离（HD）和平均表面距离（MSD）评估sMRI上前列腺分割的准确性。为估计观察者间变异性（IOV），计算了每个RO在rMRI上勾勒的前列腺轮廓与治疗RO在rMRI上勾勒的前列腺（金标准）之间的这些指标。定性地说，与CT扫描相比，sMRI图像在前列腺边界处显示出增强的软组织对比度。对于MAE和MSE，PxCGAN和CycleGAN有相似的结果，而PxCGAN的MAE小于Pix2Pix的MAE。PxCGAN的PSNR和SSIM显著高于Pix2Pix和CycleGAN（p < 0.01）。sMRI与rMRI的DSC在IOV范围内，而对于所有ROs而言，sMRI与rMRI的HD小于IOV的HD（p≤0.03）。PxCGAN从治疗计划CT扫描生成sMRI图像，这些图像在前列腺边界处描绘出增强的软组织对比度。与rMRI相比，sMRI上前列腺分割的准确性在不同ROs之间rMRI的分割变化范围内。
