Division of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland.
Division of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland; Geneva Neuroscience Center, Geneva University, CH-1205 Geneva, Switzerland; Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, 9700 RB Groningen, Netherlands; Department of Nuclear Medicine, University of Southern Denmark, DK-500 Odense, Denmark.
Med Image Anal. 2020 Aug;64:101718. doi: 10.1016/j.media.2020.101718. Epub 2020 May 19.
Attenuation correction (AC) is essential for quantitative PET imaging. In the absence of concurrent CT scanning, for instance on hybrid PET/MRI systems or dedicated brain PET scanners, an accurate approach for synthetic CT generation is highly desired. In this work, a novel framework is proposed wherein attenuation correction factors (ACF) are estimated from time-of-flight (TOF) PET emission data using deep learning.
In this approach, referred to as called DL-EM), the different TOF sinogram bins pertinent to the same slice are fed into a multi-input channel deep convolutional network to estimate a single ACF sinogram associated with the same slice. The clinical evaluation of the proposed DL-EM approach consisted of 68 clinical brain TOF PET/CT studies, where CT-based attenuation correction (CTAC) served as reference. A two-tissue class consisting of background-air and soft-tissue segmentation of the TOF PET non-AC images (SEG) as a proxy of the technique used in the clinic was also included in the comparative evaluation. Qualitative and quantitative PET analysis was performed through SUV bias maps quantification in 63 different brain regions.
The DL-EM approach resulted in 6.1 ± 9.7% relative mean absolute error (RMAE) in bony structures compared to SEG AC method with RMAE of 16.1 ± 8.2% (p-value <0.001). Considering the entire head region, DL-EM led to a root mean square error (RMSE) of 0.3 ± 0.01 outperforming the SEG method with RMSE of 0.8 ± 0.02 SUV (p-value <0.001). The region-wise analysis of brain PET studies revealed less than 7% absolute SUV bias for the DL-EM approach, whereas the SEG method resulted in more than 14% absolute SUV bias (p-value <0.05).
Qualitative assessment and quantitative PET analysis demonstrated the superior performance of the DL-EM approach over the segmentation-based technique with clinically acceptable SUV bias. The results obtained using the DL-EM approach are comparable to state-of-the-art MRI-guided AC methods. Yet, this approach enables the extraction of interesting features about patient-specific attenuation which could be employed not only as a stand-alone AC approach but also as complementary/prior information in other AC algorithms.
衰减校正（AC）对于定量 PET 成像至关重要。例如，在没有 CT 扫描的情况下，在混合 PET/MRI 系统或专用脑 PET 扫描仪上，非常需要一种准确的合成 CT 生成方法。在这项工作中，提出了一种新的框架，其中使用深度学习从飞行时间（TOF）PET 发射数据中估计衰减校正因子（ACF）。
在这种方法中，称为 DL-EM），与同一切片相关的不同 TOF 正弦图箱被输入到多输入通道深度卷积网络中，以估计与同一切片相关的单个 ACF 正弦图。所提出的 DL-EM 方法的临床评估包括 68 项临床脑 TOF PET/CT 研究，其中 CT 衰减校正（CTAC）作为参考。在比较评估中，还包括由 TOF PET 非 AC 图像（SEG）的背景-空气和软组织分割组成的两组织类，作为该技术在临床中的替代物。通过在 63 个不同的脑区进行 SUV 偏差图定量进行定性和定量 PET 分析。
与 SEG AC 方法的 16.1±8.2%（p 值<0.001）相比，DL-EM 方法在骨结构中导致 6.1±9.7%的相对平均绝对误差（RMAE）。考虑整个头部区域，DL-EM 导致 0.3±0.01 的均方根误差（RMSE），优于 SEG 方法的 0.8±0.02 SUV（p 值<0.001）。脑 PET 研究的区域分析表明，DL-EM 方法的 SUV 偏差绝对值小于 7%，而 SEG 方法的 SUV 偏差绝对值大于 14%（p 值<0.05）。
定性评估和定量 PET 分析表明，DL-EM 方法优于基于分割的技术，具有可接受的 SUV 偏差。使用 DL-EM 方法获得的结果与最先进的 MRI 引导的 AC 方法相当。然而，该方法能够提取关于患者特定衰减的有趣特征，这些特征不仅可以作为独立的 AC 方法，还可以作为其他 AC 算法的补充/先验信息。
