Deep learning for predicting subtype classification and survival of lung adenocarcinoma on computed tomography

Chengdi Wang; Jun Shao; Junwei Lv; Yidi Cao; Chaonan Zhu; Jingwei Li; Wei Shen; Lei Shi; Dan Liu; Weimin Li

doi:10.1016/j.tranon.2021.101141

Deep learning for predicting subtype classification and survival of lung adenocarcinoma on computed tomography

Transl Oncol. 2021 Aug;14(8):101141. doi: 10.1016/j.tranon.2021.101141. Epub 2021 Jun 1.

Authors

Chengdi Wang¹, Jun Shao¹, Junwei Lv², Yidi Cao², Chaonan Zhu², Jingwei Li¹, Wei Shen², Lei Shi², Dan Liu³, Weimin Li⁴

Affiliations

¹ Department of Respiratory and Critical Care Medicine, West China Hospital, West China Medical School, Sichuan University, No. 37 Guo Xue Alley, Chengdu 610041, China.
² Hangzhou YITU Healthcare Technology Co., Ltd. Hangzhou, China; Shanghai Key Laboratory of Artificial Intelligence for Medical Image and Knowledge Graph, Shanghai, China.
³ Department of Respiratory and Critical Care Medicine, West China Hospital, West China Medical School, Sichuan University, No. 37 Guo Xue Alley, Chengdu 610041, China. Electronic address: liudanscu@qq.com.
⁴ Department of Respiratory and Critical Care Medicine, West China Hospital, West China Medical School, Sichuan University, No. 37 Guo Xue Alley, Chengdu 610041, China. Electronic address: weimi003@scu.edu.cn.

Abstract

Objectives: The subtype classification of lung adenocarcinoma is important for treatment decision. This study aimed to investigate the deep learning and radiomics networks for predicting histologic subtype classification and survival of lung adenocarcinoma diagnosed through computed tomography (CT) images.

Methods: A dataset of 1222 patients with lung adenocarcinoma were retrospectively enrolled from three medical institutions. The anonymised preoperative CT images and pathological labels of atypical adenomatous hyperplasia, adenocarcinoma in situ, minimally invasive adenocarcinoma, invasive adenocarcinoma (IAC) with five predominant components were obtained. These pathological labels were divided into 2-category classification (IAC; non-IAC), 3-category and 8-category. We modeled the classification task of histological subtypes based on modified ResNet-34 deep learning network, radiomics strategies and deep radiomics combined algorithm. Then we established the prognostic models in lung adenocarcinoma patients with survival outcomes. The accuracy (ACC), area under ROC curves (AUCs) and C-index were primarily performed to evaluate the algorithms.

Results: This study included a training set (n = 802) and two validation cohorts (internal, n = 196; external, n = 224). The ACC of deep radiomics algorithm in internal validation achieved 0.8776, 0.8061 in the 2-category, 3-category classification, respectively. Even in 8 classifications, the AUC ranged from 0.739 to 0.940 in internal set. Further, we constructed a prognosis model that C-index was 0.892(95% CI: 0.846-0.937) in internal validation set.

Conclusions: The automated deep radiomics based triage system has achieved the great performance in the subtype classification and survival predictability in patients with CT-detected lung adenocarcinoma nodules, providing the clinical guide for treatment strategies.

Keywords: Computed tomography; Deep learning; Lung adenocarcinoma; Subtype.