Combining radiomics and deep learning to predict liver metastasis of gastric cancer on CT image

Yimin Guo; Haixiang Yin; Hanyue Zhang; Pan Liang; Jianbo Gao; Ming Cheng

doi:10.3389/fonc.2025.1613972

Combining radiomics and deep learning to predict liver metastasis of gastric cancer on CT image

Front Oncol. 2025 Jun 24:15:1613972. doi: 10.3389/fonc.2025.1613972. eCollection 2025.

Authors

Yimin Guo^#^{1

2}, Haixiang Yin^#^{2

3}, Hanyue Zhang^{1

2}, Pan Liang^{1

2}, Jianbo Gao^{1

2}, Ming Cheng^{3

4}

Affiliations

¹ Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.
² Henan Key Laboratory of Image Diagnosis and Treatment for Digestive System Tumor, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.
³ Department of Medical Information, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.
⁴ Institute of Interconnected Intelligent Health Management of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.

^# Contributed equally.

Abstract

Objective: Our study aimed to explore the potential of deep learning (DL) radiomics features from CT images of primary gastric cancer (GC) in predicting gastric cancer liver metastasis (GCLM) by establishing and verifying a prediction model based on clinical factors, classical radiomics and DL features.

Methods: We retrospectively analyzed 1001 pathologically confirmed GC patients from June 2014 to May 2024, divided into non-LM (n=689) and LM groups (n=312). CT-based classic radiomics and DL features were extracted and screened to construct a DL-radiomics score. This score, along with statistically significant clinical factors, was used to build a fused model which visualized as a nomogram. The model's predictive performance, calibration, and clinical utility were assessed and compared against a clinical model. Additionally, the DL-radiomics score's role in distinguishing between synchronous and metachronous GCLM was evaluated.

Results: The fused model showed good predictive performance [AUC: 0.796 (95% CI: 0.766-0.826) in training cohort and 0.787 (95% CI: 0.741-0.834) in test cohort], outperforming the clinical model, radiomics score and DL score (P<0.05). In addition, the decision curve confirmed that the model provided the largest clinical net benefit compared with all other models in the relevant threshold. DL-radiomics score showed moderate predictive performance in distinguishing between synchronous GCLM and metachronous GCLM, with an AUC of 0.665 (95% CI, 0.613-0.718).

Conclusion: The CT-based fused model has demonstrated significant value in predicting the occurrence of GCLM, and can provide a reference for the personalized follow-up and treatment of patients.

Keywords: computed tomography; deep learning; gastric cancer; liver metastasis; radiomics nomogram.