用于连续全身PET扫描中降低辐射剂量的人工智能变换器
AI Transformers for Radiation Dose Reduction in Serial Whole-Body PET Scans.
作者信息
Wang Yan-Ran Joyce, Qu Liangqiong, Sheybani Natasha Diba, Luo Xiaolong, Wang Jiangshan, Hawk Kristina Elizabeth, Theruvath Ashok Joseph, Gatidis Sergios, Xiao Xuerong, Pribnow Allison, Rubin Daniel, Daldrup-Link Heike E
机构信息
From the Departments of Biomedical Data Science (Y.R.J.W., L.Q., N.D.S., K.E.H., X.X., D.R., H.E.D.L.), Radiology (Y.R.J.W., A.J.T.), and Nuclear Medicine (K.E.H.), Stanford University, Stanford, CA 94304; Department of Diagnostic and Interventional Radiology, University Hospital Tübingen, Tübingen, Germany (S.G.); School of Engineering, University of Science and Technology of China, Hefei, China (X.L., J.W.); and Department of Pediatrics, Division of Pediatric Oncology, Lucile Packard Children's Hospital, Stanford University School of Medicine, Stanford, Calif (A.P., D.R., H.E.D.L.).
出版信息
Radiol Artif Intell. 2023 May 3;5(3):e220246. doi: 10.1148/ryai.220246. eCollection 2023 May.
PURPOSE
To develop a deep learning approach that enables ultra-low-dose, 1% of the standard clinical dosage (3 MBq/kg), ultrafast whole-body PET reconstruction in cancer imaging.
MATERIALS AND METHODS
In this Health Insurance Portability and Accountability Act-compliant study, serial fluorine 18-labeled fluorodeoxyglucose PET/MRI scans of pediatric patients with lymphoma were retrospectively collected from two cross-continental medical centers between July 2015 and March 2020. Global similarity between baseline and follow-up scans was used to develop Masked-LMCTrans, a longitudinal multimodality coattentional convolutional neural network (CNN) transformer that provides interaction and joint reasoning between serial PET/MRI scans from the same patient. Image quality of the reconstructed ultra-low-dose PET was evaluated in comparison with a simulated standard 1% PET image. The performance of Masked-LMCTrans was compared with that of CNNs with pure convolution operations (classic U-Net family), and the effect of different CNN encoders on feature representation was assessed. Statistical differences in the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and visual information fidelity (VIF) were assessed by two-sample testing with the Wilcoxon signed rank test.
RESULTS
The study included 21 patients (mean age, 15 years ± 7 [SD]; 12 female) in the primary cohort and 10 patients (mean age, 13 years ± 4; six female) in the external test cohort. Masked-LMCTrans-reconstructed follow-up PET images demonstrated significantly less noise and more detailed structure compared with simulated 1% extremely ultra-low-dose PET images. SSIM, PSNR, and VIF were significantly higher for Masked-LMCTrans-reconstructed PET ( < .001), with improvements of 15.8%, 23.4%, and 186%, respectively.
CONCLUSION
Masked-LMCTrans achieved high image quality reconstruction of 1% low-dose whole-body PET images. Pediatrics, PET, Convolutional Neural Network (CNN), Dose Reduction © RSNA, 2023.
目的
开发一种深度学习方法，以实现超低剂量（标准临床剂量的1%，即3 MBq/kg）、超快速全身PET重建，用于癌症成像。
材料与方法
在这项符合《健康保险流通与责任法案》的研究中，回顾性收集了2015年7月至2020年3月期间两个跨大陆医疗中心的淋巴瘤儿科患者的系列氟-18标记氟脱氧葡萄糖PET/MRI扫描图像。利用基线扫描和随访扫描之间的全局相似性，开发了Masked-LMCTrans，这是一种纵向多模态协同注意力卷积神经网络（CNN）变换器，可在同一患者的系列PET/MRI扫描之间提供交互和联合推理。将重建的超低剂量PET的图像质量与模拟的标准1%PET图像进行比较评估。将Masked-LMCTrans的性能与具有纯卷积操作的CNN（经典U-Net家族）的性能进行比较，并评估不同CNN编码器对特征表示的影响。通过Wilcoxon符号秩检验的双样本测试评估结构相似性指数测量（SSIM）、峰值信噪比（PSNR）和视觉信息保真度（VIF）的统计差异。
结果
主要队列包括21例患者（平均年龄15岁±7[标准差]；12例女性），外部测试队列包括10例患者（平均年龄13岁±4；6例女性）。与模拟的1%极低剂量PET图像相比，Masked-LMCTrans重建的随访PET图像显示噪声明显减少，结构更详细。Masked-LMCTrans重建的PET的SSIM、PSNR和VIF显著更高（<0.001），分别提高了15.8%、23.4%和186%。
结论
Masked-LMCTrans实现了1%低剂量全身PET图像的高图像质量重建。儿科学、PET、卷积神经网络（CNN）、剂量降低 ©RSNA，2023。
Zotero 插件