Shao Xiaonan, Niu Rong, Shao Xiaoliang, Gao Jianxiong, Shi Yunmei, Jiang Zhenxing, Wang Yuetao
Department of Nuclear Medicine, The Third Affiliated Hospital of Soochow University, Changzhou, 213003, China.
Changzhou Key Laboratory of Molecular Imaging, Changzhou, 213003, China.
EJNMMI Phys. 2021 Nov 2;8(1):74. doi: 10.1186/s40658-021-00423-1.
This work aims to train, validate, and test a dual-stream three-dimensional convolutional neural network (3D-CNN) based on fluorine 18 (F)-fluorodeoxyglucose (FDG) PET/CT to distinguish benign lesions and invasive adenocarcinoma (IAC) in ground-glass nodules (GGNs).
We retrospectively analyzed patients with suspicious GGNs who underwent F-FDG PET/CT in our hospital from November 2011 to November 2020. The patients with benign lesions or IAC were selected for this study. According to the ratio of 7:3, the data were randomly divided into training data and testing data. Partial image feature extraction software was used to segment PET and CT images, and the training data after using the data augmentation were used for the training and validation (fivefold cross-validation) of the three CNNs (PET, CT, and PET/CT networks).
A total of 23 benign nodules and 92 IAC nodules from 106 patients were included in this study. In the training set, the performance of PET network (accuracy, sensitivity, and specificity of 0.92 ± 0.02, 0.97 ± 0.03, and 0.76 ± 0.15) was better than the CT network (accuracy, sensitivity, and specificity of 0.84 ± 0.03, 0.90 ± 0.07, and 0.62 ± 0.16) (especially accuracy was significant, P-value was 0.001); in the testing set, the performance of both networks declined. However, the accuracy and sensitivity of PET network were still higher than that of CT network (0.76 vs. 0.67; 0.85 vs. 0.70). For dual-stream PET/CT network, its performance was almost the same as PET network in the training set (P-value was 0.372-1.000), while in the testing set, although its performance decreased, the accuracy and sensitivity (0.85 and 0.96) were still higher than both CT and PET networks. Moreover, the accuracy of PET/CT network was higher than two nuclear medicine physicians [physician 1 (3-year experience): 0.70 and physician 2 (10-year experience): 0.73].
The 3D-CNN based on F-FDG PET/CT can be used to distinguish benign lesions and IAC in GGNs, and the performance is better when both CT and PET images are used together.
本研究旨在训练、验证和测试基于氟18（F）-氟脱氧葡萄糖（FDG）PET/CT的双流三维卷积神经网络（3D-CNN），以区分磨玻璃结节（GGN）中的良性病变和浸润性腺癌（IAC）。
我们回顾性分析了2011年11月至2020年11月在我院接受F-FDG PET/CT检查的可疑GGN患者。选择患有良性病变或IAC的患者进行本研究。按照7:3的比例，将数据随机分为训练数据和测试数据。使用部分图像特征提取软件对PET和CT图像进行分割，并将使用数据增强后的训练数据用于三个CNN（PET、CT和PET/CT网络）的训练和验证（五重交叉验证）。
本研究共纳入106例患者的23个良性结节和92个IAC结节。在训练集中，PET网络的性能（准确率、灵敏度和特异度分别为0.92±0.02、0.97±0.03和0.76±0.15）优于CT网络（准确率、灵敏度和特异度分别为0.84±0.03、0.90±0.07和0.62±0.16）（尤其是准确率差异显著，P值为0.001）；在测试集中，两个网络的性能均有所下降。然而，PET网络的准确率和灵敏度仍高于CT网络（0.76对0.67；0.85对0.70）。对于双流PET/CT网络，其在训练集中的性能与PET网络几乎相同（P值为0.372 - 1.000），而在测试集中，尽管其性能下降，但其准确率和灵敏度（0.85和0.96）仍高于CT和PET网络。此外，PET/CT网络的准确率高于两名核医学医师[医师1（3年经验）：0.70和医师2（10年经验）：0.73]。
基于F-FDG PET/CT的3D-CNN可用于区分GGN中的良性病变和IAC，同时使用CT和PET图像时性能更佳。
