Integrative Radiogenomics Approach for Risk Assessment of Postoperative and Adjuvant Chemotherapy Benefits for Gastric Cancer Patients.

Yin Jin,Weiyang Cai,Yanyan Li,Renpin Chen,Yilun Xu

doi:10.3389/fonc.2021.755271

Abstract

Gastric cancer (GC) is a typical heterogeneous malignant tumor, whose insensitivity to chemotherapy is a common cause of tumor recurrence and metastasis. There is no doubt regarding the effectiveness of adjuvant chemotherapy (ACT) for GC, but the population for whom it is indicated and the selection of specific options remain the focus of present research. The conventional pathological TNM prediction focuses on cancer cells to predict prognosis, while they do not provide sufficient prediction. Enhanced computed tomography (CT) scanning is a validated tool that assesses the involvement of careful identification of the tumor, lymph node involvement, and metastatic spread. Using the radiomics approach, we selected the least absolute shrinkage and selection operator (LASSO) Cox regression model to build a radiomics signature for predicting the overall survival (OS) and disease-free survival (DFS) of patients with complete postoperative gastric cancer and further identifying candidate benefits from ACT. The radiomics trait-associated genes captured clinically relevant molecular pathways and potential chemotherapeutic drug metabolism mechanisms. Our results of precise surrogates using radiogenomics can lead to additional benefit from adjuvant chemotherapy and then survival prediction in postoperative GC patients.

Highlights

Gastric cancer (GC) is the third most common cancer and the second leading cause of cancerrelated mortality worldwide [1], of which nearly three-quarters occurred in Asia, and more than two-fifths occurred in China [2]
Metabolically active tumor volume (MATV) has been proven to be a prognostic factor in patients with GC [7]; Li et al constructed a radiomics signature of 18-F fluorodeoxyglucose PET/computed tomography (CT) for prediction of GC survival [8]; Jiang et al selected 19 potential predictors from the 269 features identified, which provided a neoteric angle for individualized diagnosis and prediction of malignancy potential for GC patients [9]; Jiang et al developed machine learning for predicting the pathological stage for GC [8]; and studies established a deep learning radiomics model for effectively predicting the lymph node metastasis of local GC [10]
There was no significant difference between the two cohorts in terms of clinicopathologic factors or follow-up time

Summary

Introduction

Gastric cancer (GC) is the third most common cancer and the second leading cause of cancerrelated mortality worldwide [1], of which nearly three-quarters occurred in Asia, and more than two-fifths occurred in China [2]. Metabolically active tumor volume (MATV) has been proven to be a prognostic factor in patients with GC [7]; Li et al constructed a radiomics signature of 18-F fluorodeoxyglucose PET/CT for prediction of GC survival [8]; Jiang et al selected 19 potential predictors from the 269 features identified, which provided a neoteric angle for individualized diagnosis and prediction of malignancy potential for GC patients [9]; Jiang et al developed machine learning for predicting the pathological stage for GC [8]; and studies established a deep learning radiomics model for effectively predicting the lymph node metastasis of local GC [10]. More contributing factors should be offered for choice in the intended population and ideal regimens before therapy selection

Methods

Results

Conclusion