深度学习辅助开发和验证一种预测持续性纯磨玻璃结节生长的算法。

Deep learning-assisted development and validation of an algorithm for predicting the growth of persistent pure ground-glass nodules.

作者信息

Tang Yanhua, Li Minzhen, Lin Benke, Tao Xuemin, Shi Zhongyue, Jin Xin, Bongiolatti Stefano, Ricciardi Sara, Divisi Duilio, Durand Marion, Youness Houssein A, Shinohara Shuichi, Zhu Chuang, Liu Yi

机构信息

Department of Radiology, Beijing Chaoyang Hospital, Beijing, China.

School of Artificial Intelligence, Beijing University of Posts and Telecommunications (BUPT), Beijing, China.

出版信息

Transl Lung Cancer Res. 2023 Dec 26;12(12):2494-2504. doi: 10.21037/tlcr-23-666. Epub 2023 Dec 22.

DOI:10.21037/tlcr-23-666

PMID:38205216

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10775010/

Abstract

BACKGROUND

The prediction of the persistent pure ground-glass nodule (pGGN) growth is challenging and limited by subjective assessment and variation across radiologists. A chest computed tomography (CT) image-based deep learning classification model (DLCM) may provide a more accurate growth prediction.

METHODS

This retrospective study enrolled consecutive patients with pGGNs from January 2010 to December 2020 from two independent medical institutions. Four DLCM algorithms were built to predict the growth of pGGNs, which were extracted from the nodule areas of chest CT images annotated by two radiologists. All nodules were assigned to either the study, the inner validation, or the external validation cohort. Accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and areas under the ROC curve (AUROCs) were analyzed to evaluate our models.

RESULTS

A total of 286 patients were included, with 419 pGGN. In total, 197 (68.9%) of the patients were female and the average age was 59.5±12.0 years. The number of pGGN assigned to the study, the inner validation, and the external validation cohort were 193, 130, and 96, respectively. The follow-up time of stable pGGNs for the primary and external validation cohorts were 3.66 (range, 2.01-10.08) and 4.63 (range, 2.00-9.91) years, respectively. Growth of the pGGN occurred in 166 nodules [83 (43%), 39 (30%), and 44 (45%) in the study, inner and external validation cohorts respectively]. The best-performing DLCM algorithm was DenseNet_DR, which achieved AUROCs of 0.79 [95% confidence interval (CI): 0.70, 0.86] in predicting pGGN growth in the inner validation cohort and 0.70 (95% CI: 0.60, 0.79) in the external validation cohort.

CONCLUSIONS

DLCM algorithms that use chest CT images can help predict the growth of pGGNs.

摘要

背景

持续性纯磨玻璃结节（pGGN）生长的预测具有挑战性，且受主观评估和放射科医生之间差异的限制。基于胸部计算机断层扫描（CT）图像的深度学习分类模型（DLCM）可能提供更准确的生长预测。

方法

这项回顾性研究纳入了2010年1月至2020年12月期间来自两个独立医疗机构的连续pGGN患者。构建了四种DLCM算法来预测pGGN的生长，这些算法是从两名放射科医生标注的胸部CT图像结节区域中提取的。所有结节被分配到研究队列、内部验证队列或外部验证队列。分析准确性、敏感性、特异性、受试者工作特征（ROC）曲线和ROC曲线下面积（AUROC）以评估我们的模型。

结果

共纳入286例患者，有419个pGGN。总共197例（68.9%）患者为女性，平均年龄为59.5±12.0岁。分配到研究队列、内部验证队列和外部验证队列的pGGN数量分别为193个、130个和96个。主要验证队列和外部验证队列中稳定pGGN的随访时间分别为3.66年（范围2.01 - 10.08年）和4.63年（范围2.00 - 9.91年）。166个结节出现了pGGN生长[研究队列、内部验证队列和外部验证队列中分别为83个（43%）、39个（30%）和44个（45%）]。表现最佳的DLCM算法是DenseNet_DR，其在内部验证队列中预测pGGN生长的AUROC为0.79[95%置信区间（CI）：0.70，0.86]，在外部验证队列中为0.70（95%CI：0.60，0.79）。