深度学习模型对纯磨玻璃结节肺腺癌病理亚型的预测分析

目的 利用深度学习对CT上表现为纯磨玻璃密度结节(pGGN)的肺腺癌进行分型,并与手术病理结果对比,探讨其对病理亚型的预测价值。方法 收集219例(共240个病灶)经病理证实且胸部CT上表现为pGGN的肺腺癌患者的CT影像与病理资料,根据病理分型,将其分为非浸润性腺癌组包括浸润前病变(不典型腺瘤样增生和原位腺癌)以及微浸润腺癌]和浸润性腺癌组。首先对pGGN进行勾画与标记,然后将标记好的数据随机分为学习训练组(80%)及验证测试组(20%),其中验证测试组中的结果需与两位胸部影像专家的诊断结果进行对比。结果 深度学习模型对pGGN肺腺癌病理亚型的预测取得了较高的性能。深度学习模型对pGGN判断的准确率为0.8330,95%CI为0.7016~0.9157,专家1对pGGN诊断的准确率为0.5000,95%CI为0.3639~0.6361,专家2对pGGN诊断的准确率为0.5625,95%CI为0.4227~0.6931,两位专家联合对pGGN诊断的准确率为0.5417,95%CI为0.4029~0.6743,深度学习模型的准确率明显高于专家个人及专家组(P=0.002)。专家个人前后两次诊断的一致性Kappa值分别为0.939和0.799,专家个人前后两次的诊断一致性为良好;专家间的一致性Kappa值为0.667,专家间的诊断一致性为中等(P=0.000)。结论 深度学习模型能相对准确地判别pGGN的病理类型,诊断效能优于专家组判断。

Prediction of Pathological Subtypes of Lung Adenocarcinoma with Pure Ground Glass Nodules by Deep Learning Model

Objectiv To make a preliminary pathological classification of lung adenocarcinoma with pure ground glass nodules(pGGN)on CT by using a deep learning model. Methods CT images and pathological data of 219 patients(240 lesions in total)with pGGN on CT and pathologically confirmed adenocarcinoma were collected.According to pathological subtypes,the lesions were divided into non-invasive lung adenocarcinoma group(which included atypical adenomatous hyperplasia and adenocarcinoma in situ and micro-invasive adenocarcinoma)and invasive lung adenocarcinoma group.First,the lesions were outlined and labeled by two young radiologists,and then the labeled data were randomly divided into two datasets:the training set(80%)and the test set(20%).The prediction results of deep learning were compared with those of two experienced radiologists by using the test dataset. Results The deep learning model achieved high performance in predicting the pathological types(non-invasive and invasive)of pGGN lung adenocarcinoma.The accuracy rate in pGGN diagnosis was 0.8330(95% CI=0.7016-0.9157)for of deep learning model,0.5000(95% CI=0.3639-0.6361)for expert 1,0.5625(95% CI=0.4227-0.6931)for expert 2,and 0.5417(95% CI=0.4029-0.6743)for both two experts.Thus,the accuracy of the deep learning model was significantly higher than those of the experienced radiologists(P=0.002).The intra-observer agreements were good(Kappa values:0.939 and 0.799,respectively).The inter-observer agreement was general(Kappa value:0.667)(P=0.000). Conclusion The deep learning model showed better performance in predicting the pathological types of pGGN lung adenocarcinoma compared with experienced radiologists.