A convolutional neural network-based system to classify patients using FDG PET/CT examinations
A convolutional neural network-based system to classify patients using FDG PET/CT examinations
复制标题
DOI：
10.1186/s12885-020-6694-x
复制
发表时间：
2020-03-17
期刊：
影响因子：
3.8
通讯作者：
Shiga, Tohru
中科院分区：
文献类型：
--
作者：
Kawauchi, Keisuke;Furuya, Sho;Shiga, Tohru
随着PET/CT扫描仪数量的增加以及FDG PET/CT成为肿瘤学常用的成像方式，对人工智能（AI）自动检测系统以防止人为疏忽和误诊的需求正在迅速增长。我们的目标是开发一个基于卷积神经网络（CNN）的系统，该系统可以将全身FDG PET分类为1)良性，2)恶性或3)模棱两可。方法回顾性研究3485例恶性或疑似恶性疾病患者，均在我院行全身FDG PET/CT检查。所有病例均由核医学医师分为3类。构建基于残差网络（ResNet）的CNN架构，将患者分为三类。此外，我们对CNN进行了基于区域的分析（头颈部、胸部、腹部和骨盆区域）。结果良性1280例（37%），恶性1450例（42%），模棱两可755例（22%）。在基于患者的分析中，CNN预测良性、恶性和模糊图像的准确率分别为99.4%、99.4%和87.5%。在基于区域的分析中，预测的正确率分别为97.3%（头颈部）、96.6%（胸部）、92.8%（腹部）和99.6%（骨盆）。结论基于cnn的系统可靠地将FDG PET图像分为3类，可作为医生的双重检查系统，防止疏忽和误诊。
Background As the number of PET/CT scanners increases and FDG PET/CT becomes a common imaging modality for oncology, the demands for automated detection systems on artificial intelligence (AI) to prevent human oversight and misdiagnosis are rapidly growing. We aimed to develop a convolutional neural network (CNN)-based system that can classify whole-body FDG PET as 1) benign, 2) malignant or 3) equivocal. Methods This retrospective study investigated 3485 sequential patients with malignant or suspected malignant disease, who underwent whole-body FDG PET/CT at our institute. All the cases were classified into the 3 categories by a nuclear medicine physician. A residual network (ResNet)-based CNN architecture was built for classifying patients into the 3 categories. In addition, we performed a region-based analysis of CNN (head-and-neck, chest, abdomen, and pelvic region). Results There were 1280 (37%), 1450 (42%), and 755 (22%) patients classified as benign, malignant and equivocal, respectively. In the patient-based analysis, CNN predicted benign, malignant and equivocal images with 99.4, 99.4, and 87.5% accuracy, respectively. In region-based analysis, the prediction was correct with the probability of 97.3% (head-and-neck), 96.6% (chest), 92.8% (abdomen) and 99.6% (pelvic region), respectively. Conclusion The CNN-based system reliably classified FDG PET images into 3 categories, indicating that it could be helpful for physicians as a double-checking system to prevent oversight and misdiagnosis.