Yang Jaewon, Sohn Jae Ho, Behr Spencer C, Gullberg Grant T, Seo Youngho
Department of Radiology and Biomedical Imaging (J.Y., J.H.S., S.C.B., G.TG., Y.S.) and Physics Research Laboratory (J.Y., G.T.G., Y.S.), University of California, San Francisco, 185 Berry St, Suite 350, San Francisco, CA 94143-0946.
Radiol Artif Intell. 2020 Dec 2;3(2):e200137. doi: 10.1148/ryai.2020200137. eCollection 2021 Mar.
To demonstrate the feasibility of CT-less attenuation and scatter correction (ASC) in the image space using deep learning for whole-body PET, with a focus on the potential benefits and pitfalls.
In this retrospective study, 110 whole-body fluorodeoxyglucose (FDG) PET/CT studies acquired in 107 patients (mean age ± standard deviation, 58 years ± 18; age range, 11-92 years; 72 females) from February 2016 through January 2018 were randomly collected. A total of 37.3% (41 of 110) of the studies showed metastases, with diverse FDG PET findings throughout the whole body. A U-Net-based network was developed for directly transforming noncorrected PET (PET) into attenuation- and scatter-corrected PET (PET). Deep learning-corrected PET (PET) images were quantitatively evaluated by using the standardized uptake value (SUV) of the normalized root mean square error, the peak signal-to-noise ratio, and the structural similarity index, in addition to a joint histogram for statistical analysis. Qualitative reviews by radiologists revealed the potential benefits and pitfalls of this correction method.
The normalized root mean square error (0.21 ± 0.05 [mean SUV ± standard deviation]), mean peak signal-to-noise ratio (36.3 ± 3.0), mean structural similarity index (0.98 ± 0.01), and voxelwise correlation (97.62%) of PET demonstrated quantitatively high similarity with PET. Radiologist reviews revealed the overall quality of PET. The potential benefits of PET include a radiation dose reduction on follow-up scans and artifact removal in the regions with attenuation correction- and scatter correction-based artifacts. The pitfalls involve potential false-negative results due to blurring or missing lesions or false-positive results due to pseudo-low-uptake patterns.
Deep learning-based direct ASC at whole-body PET is feasible and potentially can be used to overcome the current limitations of CT-based approaches, benefiting patients who are sensitive to radiation from CT.© RSNA, 2020.
证明在图像空间中使用深度学习对全身PET进行无CT衰减和散射校正（ASC）的可行性，重点关注其潜在的益处和缺陷。
在这项回顾性研究中，随机收集了2016年2月至2018年1月期间107例患者（平均年龄±标准差，58岁±18岁；年龄范围，11 - 92岁；72名女性）的110例全身氟脱氧葡萄糖（FDG）PET/CT研究。共有37.3%（110例中的41例）的研究显示有转移，全身FDG PET表现多样。开发了一种基于U-Net的网络，用于直接将未校正的PET（PET）转换为经衰减和散射校正的PET（PET）。除了用于统计分析的联合直方图外，还通过归一化均方根误差的标准化摄取值（SUV）、峰值信噪比和结构相似性指数对深度学习校正的PET（PET）图像进行了定量评估。放射科医生的定性评估揭示了这种校正方法的潜在益处和缺陷。
PET的归一化均方根误差（0.21±0.05[平均SUV±标准差]）、平均峰值信噪比（36.3±3.0）、平均结构相似性指数（0.98±0.01）和体素相关性（97.62%）在定量上与PET具有高度相似性。放射科医生的评估揭示了PET的整体质量。PET的潜在益处包括随访扫描时辐射剂量降低以及基于衰减校正和散射校正的伪影区域中的伪影消除。缺陷包括由于模糊或遗漏病变导致的潜在假阴性结果或由于伪低摄取模式导致的假阳性结果。
基于深度学习的全身PET直接ASC是可行的，并且有可能用于克服基于CT方法的当前局限性，使对CT辐射敏感的患者受益。©RSNA，2020。
