Are radiomic spleen features useful for assessing the differentiation status of advanced gastric cancer?

Dongbo Lyu; Pan Liang; Chencui Huang; Xingzhi Chen; Ming Cheng; Bingbing Zhu; Mengru Liu; Songwei Yue; Jianbo Gao

doi:10.3389/fonc.2023.1167602

Are radiomic spleen features useful for assessing the differentiation status of advanced gastric cancer?

Front Oncol. 2023 May 5:13:1167602. doi: 10.3389/fonc.2023.1167602. eCollection 2023.

Authors

Dongbo Lyu¹, Pan Liang¹, Chencui Huang², Xingzhi Chen², Ming Cheng³, Bingbing Zhu¹, Mengru Liu¹, Songwei Yue¹, Jianbo Gao¹

Affiliations

¹ The Departments of Radiology, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
² The Department of Research Collaboration, R&D Center, Beijing Deepwise & League of PHD Technology Co., Ltd, Beijing, China.
³ The Departments of Information Department, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.

Abstract

Background: The differentiation status of gastric cancer is related to clinical stage, treatment and prognosis. It is expected to establish a radiomic model based on the combination of gastric cancer and spleen to predict the differentiation degree of gastric cancer. Thus, we aim to determine whether radiomic spleen features can be used to distinguish advanced gastric cancer with varying states of differentiation.

Materials and methods: January 2019 to January 2021, we retrospectively analyzed 147 patients with advanced gastric cancer confirmed by pathology. The clinical data were reviewed and analyzed. Three radiomics predictive models were built from radiomics features based on gastric cancer (GC), spleen (SP) and combination of two organ position (GC+SP) images. Then, three Radscores (GC, SP and GC+SP) were obtained. A nomogram was developed to predict differentiation statue by incorporating GC+SP Radscore and clinical risk factors. The area under the curve (AUC) of operating characteristics (ROC) and calibration curves were assessed to evaluate the differential performance of radiomic models based on gastric cancer and spleen for advanced gastric cancer with different states of differentiation (poorly differentiated group and non- poorly differentiated group).

Results: There were 147 patients evaluated (mean age, 60 years ± 11SD, 111 men). Univariate and multivariate logistic analysis identified three clinical features (age, cTNM stage and CT attenuation of spleen arterial phase) were independent risk factors for the degree of differentiation of GC (p =0.004,0.000,0.020, respectively). The clinical radiomics (namely, GC+SP+Clin) model showed powerful prognostic ability in the training and test cohorts with AUCs of 0.97 and 0.91, respectively. The established model has the best clinical benefit in diagnosing GC differentiation.

Conclusion: By combining radiomic features (GC and spleen) with clinical risk factors, we develop a radiomic nomogram to predict differentiation status in patients with AGC, which can be used to guide treatment decisions.

Keywords: differentiation; gastric cancer; radiomics; spleen; tomography; x-ray computed.