Nikulin Pavel, Hofheinz Frank, Maus Jens, Li Yimin, Bütof Rebecca, Lange Catharina, Furth Christian, Zschaeck Sebastian, Kreissl Michael C, Kotzerke Jörg, van den Hoff Jörg
Helmholtz-Zentrum Dresden-Rossendorf, PET Center, Institute of Radiopharmaceutical Cancer Research, Bautzner Landstrasse 400, 01328, Dresden, Germany.
Department of Radiation Oncology, Xiamen Cancer Center, The First Affiliated Hospital of Xiamen University, Xiamen, China.
Eur J Nucl Med Mol Imaging. 2021 Apr;48(4):995-1004. doi: 10.1007/s00259-020-04991-9. Epub 2020 Oct 1.
The standardized uptake value (SUV) is widely used for quantitative evaluation in oncological FDG-PET but has well-known shortcomings as a measure of the tumor's glucose consumption. The standard uptake ratio (SUR) of tumor SUV and arterial blood SUV (BSUV) possesses an increased prognostic value but requires image-based BSUV determination, typically in the aortic lumen. However, accurate manual ROI delineation requires care and imposes an additional workload, which makes the SUR approach less attractive for clinical routine. The goal of the present work was the development of a fully automated method for BSUV determination in whole-body PET/CT.
Automatic delineation of the aortic lumen was performed with a convolutional neural network (CNN), using the U-Net architecture. A total of 946 FDG PET/CT scans from several sites were used for network training (N = 366) and testing (N = 580). For all scans, the aortic lumen was manually delineated, avoiding areas affected by motion-induced attenuation artifacts or potential spillover from adjacent FDG-avid regions. Performance of the network was assessed using the fractional deviations of automatically and manually derived BSUVs in the test data.
The trained U-Net yields BSUVs in close agreement with those obtained from manual delineation. Comparison of manually and automatically derived BSUVs shows excellent concordance: the mean relative BSUV difference was (mean ± SD) = (- 0.5 ± 2.2)% with a 95% confidence interval of [- 5.1,3.8]% and a total range of [- 10.0, 12.0]%. For four test cases, the derived ROIs were unusable (< 1 ml).
CNNs are capable of performing robust automatic image-based BSUV determination. Integrating automatic BSUV derivation into PET data processing workflows will significantly facilitate SUR computation without increasing the workload in the clinical setting.
标准化摄取值（SUV）在肿瘤学FDG-PET定量评估中被广泛应用，但作为肿瘤葡萄糖消耗的测量指标存在众所周知的缺点。肿瘤SUV与动脉血SUV（BSUV）的标准摄取比（SUR）具有更高的预后价值，但需要基于图像确定BSUV，通常是在主动脉腔内。然而，准确的手动感兴趣区（ROI）勾画需要小心操作且会增加额外工作量，这使得SUR方法在临床常规应用中吸引力降低。本研究的目的是开发一种用于全身PET/CT中BSUV自动测定的方法。
使用U-Net架构的卷积神经网络（CNN）对主动脉腔进行自动勾画。来自多个站点的946例FDG PET/CT扫描用于网络训练（N = 366）和测试（N = 580）。对于所有扫描，手动勾画主动脉腔，避免受运动诱导的衰减伪影或相邻FDG摄取区域潜在溢出影响的区域。使用测试数据中自动和手动得出的BSUV的分数偏差评估网络性能。
训练后的U-Net得出的BSUV与手动勾画获得的结果高度一致。手动和自动得出的BSUV比较显示出极佳的一致性：平均相对BSUV差异为（平均值±标准差）=（-0.5±2.2）%，95%置信区间为[-5.1,3.8]%，总范围为[-10.0,12.0]%。对于四个测试病例，得出的ROI不可用（<1 ml）。
CNNs能够进行基于图像的稳健自动BSUV测定。将自动BSUV推导集成到PET数据处理工作流程中将显著促进SUR计算，而不会增加临床环境中的工作量。
