A cross-modal 3D deep learning for accurate lymph node metastasis prediction in clinical stage T1 lung adenocarcinoma. (July 2020)

• Record Type: Journal Article
• Authors: Zhao, Xingyu; Wang, Xiang; Xia, Wei; Li, Qiong; Zhou, Liu; Li, Qingchu; Zhang, Rui; Cai, Jiali; Jian, Junming; Fan, Li; Wang, Wei; Bai, Honglin; Li, Zhen; Xiao, Yi; Tang, Yuguo; Gao, Xin; Liu, Shiyuan
• Is Part Of: Lung cancer. Volume 145(2020)
• Page Start: 10
• Page End: 17
• Publication Date: 2020-07
• Subjects: Lung adenocarcinoma -- Lymph node -- Metastasis -- CT -- Deep learning -- Knowledge; Lungs -- Cancer -- Periodicals; Lung Neoplasms -- Abstracts; Lung Neoplasms -- Periodicals; Poumons -- Cancer -- Périodiques; Lungs -- Cancer; Periodicals; Electronic journals; Electronic journals; 616.99424
• DOI: 10.1016/j.lungcan.2020.04.014
• Languages: English
• ISSNs: 0169-5002

Abstract

Highlights: Preoperative lymph node status evaluation is lack of high precision. Automatically predict lymph node status based on preoperative computed tomography. Develop a cross-modal 3D neural network based on images and prior clinical knowledge. The performance of the method we proposed is significantly higher than others. Integration of prior knowledge could enhance the diagnostic precision. Abstract: Objectives: The evaluation of lymph node (LN) status by radiologists based on preoperative computed tomography (CT) lacks high precision for early lung cancer patients; erroneous evaluations result in inappropriate therapeutic plans and increase the risk of complications. This study aims to develop a cross-modal 3D neural network based on CT images and prior clinical knowledge for accurate prediction of LN metastasis in clinical stage T1 lung adenocarcinoma. Patients and methods: Five hundred one lung adenocarcinoma patients with clinical stage T1 were enrolled. Data including: corresponding 3D nodule-centered patches of CT; prior clinical features; and pathological labels of LN status were obtained. We proposed a cross-modal deep learning system, which can successfully incorporate prior clinical knowledge and CT images into a 3D neural network to predict LN metastasis. We trained and validated our system with 401 cases and tested its performance with 100 cases. The result was compared with that of the logistic regression integration model, the single deep learning model without prior clinical knowledge integration, radiomics method, and manual evaluation by radiologists. Results: The model proposed DensePriNet achieved an AUC of 0.926, which is significantly higher than the logistic regression integration model (0.904) single deep learning model (0.880), and radiomics method (0.891). The Matthews Correlation Coefficient (MCC) of DensePriNet (0.705) was significantly higher than manual classification by one senior radiologist (0.534) and one junior radiologist (0.416), respectively. Conclusion: The performance of the single deep learning method is significantly higher than the radiomics method and the radiologists, and integration of prior clinical knowledge into the deep learning model enhance the diagnostic precision of LN status and facilitate the application of precision medicine.