AUTHOR=Zeng Qingwen , Li Hong , Zhu Yanyan , Feng Zongfeng , Shu Xufeng , Wu Ahao , Luo Lianghua , Cao Yi , Tu Yi , Xiong Jianbo , Zhou Fuqing , Li Zhengrong 

TITLE=Development and validation of a predictive model combining clinical, radiomics, and deep transfer learning features for lymph node metastasis in early gastric cancer

JOURNAL=Frontiers in Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2022.986437

DOI=10.3389/fmed.2022.986437

ISSN=2296-858X

ABSTRACT=Background: This study aims to develop and validation of a predictive model combining deep transfer learning, radiomics and clinical features for lymph node metastasis (LNM) in early gastric cancer (EGC).
Methods: This study retrospectively collected 555 patients of EGC, randomly divided into two cohorts with a ratio of 7:3 (training cohort, n=388; internal validation cohort, n=167). 79 EGC patients collected from the Second Affiliated Hospital of Soochow University were used as external validation cohort. The pre-trained deep learning networks were used to extract deep transfer learning features (DTL) and radiomics features were extracted based on hand-crafted features. We employed the Spearman rank correlation test and least absolute shrinkage and selection operator regression for features selection from the combined features of clinical, radiomics and DTL features, then, the machine learning classification models including support vector machine, K-nearest neighbor, random decision forests (RF) and XGBoost were trained and compared their performance by determining the area under the curve (AUC).
Results: We constructed 8 pre-trained transfer learning networks and extracted DTL features respectively. The results showed that the 1,048 DTL features extracted based on the pre-trained Resnet152 network combined in the predictive model had the best performance in discriminating LNM status in EGC with an AUC of 0.901 (95%CI: 0.847-0.956) and 0.915 (95%CI: 0.850-0.981) in the internal validation and external validation cohorts, respectively.
Conclusions: We firstly utilized a comprehensive multidimensional data based on deep transfer learning, radiomics and clinical features, a good predictive ability for discriminating LNM status in EGC, which could provide favorable information when choosing therapy options for individuals with EGC.