Prediction of Pathological Subtypes of Lung Adenocarcinoma with Pure Ground Glass Nodules by Deep Learning Model.
10.3881/j.issn.1000-503X.11693
- Author:
Xue-Min TAO
1
;
Rui FANG
2
;
Chong-Chong WU
2
;
Chi ZHANG
3
;
Rong-Guo ZHANG
3
;
Peng-Xin YU
3
;
Shao-Hong ZHAO
2
Author Information
1. Medical School of Chinese PLA,Beijing 100853,China.
2. Department of Radiology,the First Medical Center,Chinese PLA General Hospital,Beijing 100853,China.
3. Institute of Advanced Research,Infervision,Beijing 100025,China.
- Publication Type:Journal Article
- Keywords:
artificial intelligence;
convolutional neural network;
deep learning;
lung adenocarcinoma;
tomography,X ray computed
- MeSH:
Adenocarcinoma of Lung;
Deep Learning;
Humans;
Lung Neoplasms;
Retrospective Studies;
Tomography, X-Ray Computed
- From:
Acta Academiae Medicinae Sinicae
2020;42(4):477-484
- CountryChina
- Language:Chinese
-
Abstract:
To make a preliminary pathological classification of lung adenocarcinoma with pure ground glass nodules(pGGN)on CT by using a deep learning model. 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. 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% =0.7016-0.9157)for of deep learning model,0.5000(95% =0.3639-0.6361)for expert 1,0.5625(95% =0.4227-0.6931)for expert 2,and 0.5417(95% =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(=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)(=0.000). The deep learning model showed better performance in predicting the pathological types of pGGN lung adenocarcinoma compared with experienced radiologists.
