Tao Guangyu, Zhu Li, Chen Qunhui, Yin Lekang, Li Yamin, Yang Jiancheng, Ni Bingbing, Zhang Zheng, Koo Chi Wan, Patil Pradnya D, Chen Yinan, Yu Hong, Xu Yi, Ye Xiaodan
Department of Radiology, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, China.
Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University, Shanghai, China.
Transl Lung Cancer Res. 2022 Feb;11(2):250-262. doi: 10.21037/tlcr-22-59.
Risk prediction models of lung nodules have been built to alleviate the heavy interpretative burden on clinicians. However, the malignancy scores output by those models can be difficult to interpret in a clinically meaningful manner. In contrast, the modeling of lung nodule growth may be more readily useful. This study developed a CT-based visual forecasting system that can visualize and quantify a nodule in three dimensions (3D) in any future time point using follow-up CT scans.
We retrospectively included 246 patients with 313 lung nodules with at least 1 follow-up CT scan. For the manually segmented nodules, we calculated geometric properties including CT value, diameter, volume, and mass, as well as growth properties including volume doubling time (VDT), and consolidation-to-tumor ratio (CTR) at follow-ups. These nodules were divided into growth and non-growth groups by thresholding their VDTs. We then developed a convolutional neural network (CNN) to model the imagery change of the nodules from baseline CT image (combined with the nodule mask) to follow-up CT image with a particular time interval. The model was evaluated on the geometric and radiological properties using either logistic regression or receiver operating characteristic (ROC) curve.
The lung nodules consisted of 115 ground glass nodules (GGN) and 198 solid nodules and were followed up for an average of 354 days with 2 to 11 scans. The 2 groups differed significantly in most properties. The prediction of our forecasting system was highly correlated with the ground truth with small relative errors regarding the four geometric properties. The prediction-derived VDTs had an area under the curve (AUC) of 0.857 and 0.843 in differentiating growth and non-growth nodules for GGN and solid nodules, respectively. The prediction-derived CTRs had an AUC of 0.892 in classifying high- and low-risk nodules.
This proof-of-concept study demonstrated that the deep learning-based model can accurately forecast the imagery of a nodule in a given future for both GGNs and solid nodules and is worthy of further investigation. With a larger dataset and more validation, such a system has the potential to become a prognostication tool for assessing lung nodules.
已构建肺结节风险预测模型以减轻临床医生繁重的解读负担。然而，这些模型输出的恶性肿瘤评分可能难以以具有临床意义的方式进行解读。相比之下，肺结节生长建模可能更具实用性。本研究开发了一种基于CT的视觉预测系统，该系统可以使用后续CT扫描在任何未来时间点以三维（3D）方式可视化和量化结节。
我们回顾性纳入了246例患有313个肺结节且至少有1次后续CT扫描的患者。对于手动分割的结节，我们计算了包括CT值、直径、体积和质量在内的几何属性，以及包括随访时的体积倍增时间（VDT）和实变与肿瘤比值（CTR）在内的生长属性。通过对VDT进行阈值划分，将这些结节分为生长组和非生长组。然后，我们开发了一个卷积神经网络（CNN），以模拟结节从基线CT图像（结合结节掩码）到具有特定时间间隔的后续CT图像的图像变化。使用逻辑回归或受试者操作特征（ROC）曲线对该模型的几何和放射学属性进行评估。
肺结节包括115个磨玻璃结节（GGN）和198个实性结节，平均随访354天，进行了2至11次扫描。两组在大多数属性上存在显著差异。我们的预测系统的预测与真实情况高度相关，在四个几何属性方面相对误差较小。预测得出的VDT在区分GGN和实性结节的生长和非生长结节方面，曲线下面积（AUC）分别为0.857和0.843。预测得出的CTR在对高风险和低风险结节进行分类时，AUC为0.892。
这项概念验证研究表明，基于深度学习的模型可以准确预测给定未来GGN和实性结节的图像，值得进一步研究。通过更大的数据集和更多验证，这样的系统有可能成为评估肺结节的预后工具。
