Can peritumoral regions increase the efficiency of machine-learning prediction of pathological invasiveness in lung adenocarcinoma manifesting as ground-glass nodules?

Xiang Wang; Kaili Chen; Wei Wang; Qingchu Li; Kai Liu; Qianyun Li; Xing Cui; Wenting Tu; Hongbiao Sun; Shaochun Xu; Rongguo Zhang; Yi Xiao; Li Fan; Shiyuan Liu

doi:10.21037/jtd-20-2981

Can peritumoral regions increase the efficiency of machine-learning prediction of pathological invasiveness in lung adenocarcinoma manifesting as ground-glass nodules?

J Thorac Dis. 2021 Mar;13(3):1327-1337. doi: 10.21037/jtd-20-2981.

Authors

Xiang Wang¹, Kaili Chen², Wei Wang^{1

3}, Qingchu Li¹, Kai Liu¹, Qianyun Li⁴, Xing Cui⁵, Wenting Tu¹, Hongbiao Sun¹, Shaochun Xu¹, Rongguo Zhang⁵, Yi Xiao¹, Li Fan¹, Shiyuan Liu¹

Affiliations

¹ Department of Radiology, Changzheng Hospital, Naval Medical University, Shanghai, China.
² Department of Hematology, The Myeloma & Lymphoma Center, Changzheng Hospital, Naval Medical University, Shanghai, China.
³ 71282 Hospital, Baoding, China.
⁴ Department of Radiology, Taizhou Hospital of Zhejiang Province, Linhai, China.
⁵ Beijing Infervision Technology Co. Ltd., Beijing, China.

Abstract

Background: The peri-tumor microenvironment plays an important role in the occurrence, growth and metastasis of cancer. The aim of this study is to explore the value and application of a CT image-based deep learning model of tumors and peri-tumors in predicting the invasiveness of ground-glass nodules (GGNs).

Methods: Preoperative thin-section chest CT images were reviewed retrospectively in 622 patients with a total of 687 pulmonary GGNs. GGNs are classified according to clinical management strategies as invasive lesions (IAC) and non-invasive lesions (AAH, AIS and MIA). The two volumes of interest (VOIs) identified on CT were the gross tumor volume (GTV) and the gross volume of tumor incorporating peritumoral region (GPTV). Three dimensional (3D) DenseNet was used to model and predict GGN invasiveness, and five-fold cross validation was performed. We used GTV and GPTV as inputs for the comparison model. Prediction performance was evaluated by sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).

Results: The GTV-based model was able to successfully predict GGN invasiveness, with an AUC of 0.921 (95% CI, 0.896-0.937). Using GPTV, the AUC of the model increased to 0.955 (95% CI, 0.939-0.971).

Conclusions: The deep learning method performed well in predicting GGN invasiveness. The predictive ability of the GPTV-based model was more effective than that of the GTV-based model.

Keywords: Pulmonary adenocarcinoma; X-ray computed tomography (X-ray CT); deep learning; peritumoral region; tumor invasiveness.