A CT-based deep learning model: visceral pleural invasion and survival prediction in clinical stage IA lung adenocarcinoma
Xiaofeng Lin,
Kunfeng Liu,
Kunwei Li,
Xiaojuan Chen,
Biyun Chen,
Sheng Li,
Huai Chen,
Li Li
Affiliations
Xiaofeng Lin
Department of Medical Imaging, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P.R. China
Kunfeng Liu
Department of Medical Imaging, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P.R. China
Kunwei Li
Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai 519000, P.R. China
Xiaojuan Chen
Department of Radiology, First Affiliated Hospital of Guangzhou Medical University, Guangzhou 510260, P.R. China
Biyun Chen
Department of Medical Imaging, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P.R. China
Sheng Li
Department of Medical Imaging, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P.R. China; Corresponding author
Huai Chen
Department of Radiology, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou 510260, P.R. China; Corresponding author
Li Li
Department of Medical Imaging, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P.R. China; Corresponding author
Summary: Pathologic visceral pleural invasion (VPI) in patients with early-stage lung cancer can result in the upstaging of T1 to T2, in addition to having implications for surgical resection and prognostic outcomes. This study was designed with the goal of establishing and validating a CT-based deep learning (DL) model capable of predicting VPI status and stratifying patients based on their prognostic outcomes. In total, 2077 patients from three centers with pathologically confirmed clinical stage IA lung adenocarcinoma were enrolled. DL signatures were extracted with a 3D residual neural network. DL model was able to effectively predict VPI status. VPI predicted by the DL models, as well as pathologic VPI, was associated with shorter disease-free survival. The established deep learning signature provides a tool capable of aiding the accurate prediction of VPI in patients with clinical stage IA lung adenocarcinoma, thus enabling prognostic stratification.
