Akita Ryuji, Takauchi Komei, Ishibashi Mana, Kondo Shota, Ono Shogo, Yokomachi Kazushi, Ochi Yusuke, Kiguchi Masao, Mitani Hidenori, Nakamura Yuko, Awai Kazuo
Department of Diagnostic Radiology, Graduate School of Biomedical and Health Sciences, Hiroshima University, 1-2-3 Kasumi, Minami-ku, Hiroshima, 734-8551, Japan.
Department of Radiology, Hiroshima University Hospital, 1-2-3 Kasumi, Minami-ku, Hiroshima, 734-8551, Japan.
EJNMMI Res. 2025 Jul 1;15(1):78. doi: 10.1186/s13550-025-01269-9.
A deep learning-based image reconstruction (DLR) algorithm that can reduce the statistical noise has been developed for PET/CT imaging. It may reduce the administered dose of F-FDG and minimize radiation exposure while maintaining diagnostic quality. This retrospective study evaluated whether the injected F-FDG dose could be reduced by applying DLR to PET images. To this aim, we compared the quantitative image quality metrics and the false-positive rate between DLR with a reduced F-FDG dose and Ordered Subsets Expectation Maximization (OSEM) with a standard dose.
This study included 90 oncology patients who underwent F-FDG PET/CT. They were divided into 3 groups (30 patients each): group A (F-FDG dose per body weight [BW]: 2.00-2.99 MBq/kg; PET image reconstruction: DLR), group B (3.00-3.99 MBq/kg; DLR), and group C (standard dose group; 4.00-4.99 MBq/kg; OSEM). The evaluation was performed using the signal-to-noise ratio (SNR), target-to-background ratio (TBR), and false-positive rate. DLR yielded significantly higher SNRs in groups A and B than group C (p < 0.001). There was no significant difference in the TBR between groups A and C, and between groups B and C (p = 0.983 and 0.605, respectively). In group B, more than 80% of patients weighing less than 75 kg had at most one false positive result. In contrast, in group B patients weighing 75 kg or more, as well as in group A, less than 80% of patients had at most one false-positives.
Our findings suggest that the injected F-FDG dose can be reduced to 3.0 MBq/kg in patients weighing less than 75 kg by applying DLR. Compared to the recommended dose in the European Association of Nuclear Medicine (EANM) guidelines for 90 s per bed position (4.7 MBq/kg), this represents a dose reduction of 36%. Further optimization of DLR algorithms is required to maintain comparable diagnostic accuracy in patients weighing 75 kg or more.
已开发出一种基于深度学习的图像重建（DLR）算法，可减少PET/CT成像中的统计噪声。它可能在保持诊断质量的同时减少F-FDG的给药剂量，并将辐射暴露降至最低。这项回顾性研究评估了将DLR应用于PET图像是否可以降低F-FDG的注射剂量。为此，我们比较了降低F-FDG剂量的DLR与标准剂量的有序子集期望最大化（OSEM）之间的定量图像质量指标和假阳性率。
本研究纳入了90例接受F-FDG PET/CT检查的肿瘤患者。他们被分为3组（每组30例患者）：A组（每体重[BW]的F-FDG剂量：2.00-2.99 MBq/kg；PET图像重建：DLR），B组（3.00-3.99 MBq/kg；DLR），C组（标准剂量组；4.00-4.99 MBq/kg；OSEM）。使用信噪比（SNR）、靶本比（TBR）和假阳性率进行评估。DLR在A组和B组中产生的SNR显著高于C组（p<0.001）。A组和C组之间以及B组和C组之间的TBR没有显著差异（分别为p = 0.983和0.605）。在B组中，体重小于75 kg的患者中超过80%最多有一个假阳性结果。相比之下，在体重75 kg或以上的B组患者以及A组患者中，不到80%的患者最多有一个假阳性。
我们的研究结果表明，通过应用DLR，体重小于75 kg的患者的F-FDG注射剂量可降至3.0 MBq/kg。与欧洲核医学协会（EANM）指南中每个床位90秒的推荐剂量（4.7 MBq/kg）相比，这意味着剂量降低了36%。需要进一步优化DLR算法，以在体重75 kg或以上的患者中保持相当的诊断准确性。
