Sato Mitsuru, Daisaki Hiromitsu, Watanabe Haruyuki, Isogai Saaya, Shiga Manami, Ikari Yasuhiko, Tsuda Keisuke, Hirata Kenji, Tateishi Ukihide, Mori Kazuaki, Hosono Makoto, Fujii Hirofumi
Department of Radiological Technology, Gunma Prefectural College of Health Sciences, 323-1, Kamioki-Machi, Maebashi, Gunma, Japan.
JSNM PET Imaging Site Qualification Program (J-PEQi), Tokyo, Japan.
Radiol Phys Technol. 2025 Jun 25. doi: 10.1007/s12194-025-00928-9.
The PET Imaging Site Qualification Program for amyloid positron emission tomography (PET) in Japan includes visual evaluation of the cylinder phantom. This visual evaluation requires observation of the entire image of the phantom and confirmation of the absence of apparent artifacts. Because the evaluation is visually performed, inter-observer differences might exist among evaluators for difficult cases. Therefore, the workload of the staff who perform approval tasks must be reduced, and objective evaluation methods are needed. Thus, we attempted to develop an artificial-intelligence-based objective method for anomaly detection. Three artificial intelligence methods for anomaly detection were developed, and their accuracy was evaluated using AutoEncoder, AnoGAN, and a method combining feature extraction using AlexNet and a one-class support vector machine. In total, 10,207 normal images from 128 facilities and 594 abnormal images from eight facilities, all of which were submitted as part of application for amyloid PET certification, were used. Group five-fold cross-validation was employed for artificial intelligence training and evaluation. In addition, the performance of each artificial intelligence method was assessed using receiver operating characteristic analysis. The areas under the curve for anomaly detection using AutoEncoder, AnoGAN, and the method combining feature extraction using AlexNet and a one-class support vector machine were 0.80 ± 0.04, 0.77 ± 0.03, and 0.99 ± 0.01, respectively. Artificial intelligence effectively distinguished between normal and abnormal images with high accuracy. In the future, its practical implementation is anticipated to reduce the workload in the approval work for the Japanese site qualification program for amyloid PET.
日本用于淀粉样蛋白正电子发射断层扫描（PET）的PET成像站点资格认证计划包括对圆柱模型的视觉评估。这种视觉评估需要观察模型的整个图像并确认没有明显的伪影。由于评估是通过视觉进行的，对于疑难病例，评估者之间可能存在观察者间差异。因此，必须减轻执行审批任务的工作人员的工作量，并且需要客观的评估方法。因此，我们尝试开发一种基于人工智能的异常检测客观方法。开发了三种用于异常检测的人工智能方法，并使用自动编码器、异常生成对抗网络（AnoGAN）以及一种结合使用AlexNet进行特征提取和一类支持向量机的方法对其准确性进行了评估。总共使用了来自128个机构的10207张正常图像和来自8个机构的594张异常图像，所有这些图像都是作为淀粉样蛋白PET认证申请的一部分提交的。采用五组交叉验证进行人工智能训练和评估。此外，使用接收器操作特征分析评估了每种人工智能方法的性能。使用自动编码器、异常生成对抗网络（AnoGAN）以及结合使用AlexNet进行特征提取和一类支持向量机的方法进行异常检测的曲线下面积分别为0.80±0.04、0.77±0.03和0.99±0.01。人工智能能够以高精度有效地区分正常图像和异常图像。未来，预计其实际应用将减少日本淀粉样蛋白PET站点资格认证计划审批工作的工作量。
