AUTHOR=Feng Bao , Huang Liebin , Liu Yu , Chen Yehang , Zhou Haoyang , Yu Tianyou , Xue Huimin , Chen Qinxian , Zhou Tao , Kuang Qionglian , Yang Zhiqi , Chen Xiangguang , Chen Xiaofeng , Peng Zhenpeng , Long Wansheng 

TITLE=A Transfer Learning Radiomics Nomogram for Preoperative Prediction of Borrmann Type IV Gastric Cancer From Primary Gastric Lymphoma

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.802205

DOI=10.3389/fonc.2021.802205

ISSN=2234-943X

ABSTRACT=Objective: This study aims to differentiate preoperative Borrmann type IV gastric cancer (GC) from primary gastric lymphoma (PGL) by transfer learning radiomics nomogram (TLRN), combining computed tomography (CT) images and whole slide images (WSIs) of gastric cancer.
Materials and Methods: This study retrospectively enrolled 438 patients with histopathologic diagnoses of Borrmann type IV GC and PGL. They received RCECT examinations from three hospitals. Quantitative transfer learning features were extracted by the proposed transfer learning radiopathomic network and used to construct transfer learning radiomics signatures (TLRS). A TLRN, which integrates TLRS, clinical factors, and CT subjective findings, was developed by multivariate logistic regression. The diagnostic TLRN performance was assessed by clinical usefulness in the independent validation set.
Results: The TLRN was built by TLRS and a high enhanced serosa sign, which showed good agreement by the calibration curve. The TLRN performance was superior to the clinical model and TLRS. Its areas under the curve (AUC) were 0.958 (95% confidence interval [CI], 0.883–0.991), 0.867 (95% CI, 0.794–0.922), and 0.921 (95% CI, 0.860–0.960) in the internal and two external validation cohorts, respectively. Decision curve analysis (DCA) showed that the TLRN was better than any other model. TLRN has potential generalization ability, as shown in the stratification analysis.
Conclusions: The proposed TLRN based on gastric WSIs may help preoperatively differentiate PGL from Borrmann type IV GC.
Keywords: Borrmann type IV gastric cancer, primary gastric lymphoma, transfer learning, whole slide image, deep learning