|Table of Contents|

A radiomics model based on multi-phase contrast-enhanced CT for predicting HER2 expression in gastric cancer patients

Journal Of Modern Oncology[ISSN:1672-4992/CN:61-1415/R]

Issue:
2025 02
Page:
288-292
Research Field:
Publishing date:

Info

Title:
A radiomics model based on multi-phase contrast-enhanced CT for predicting HER2 expression in gastric cancer patients
Author(s):
SONG Tianjun1; 2; XUE Bing3; HU Chunfeng2; 4
1.Imaging Department,the Second Affiliated Hospital of Xuzhou Medical University,Jiangsu Xuzhou 221002,China;2.School of Medical Imaging,Xuzhou Medical University,Jiangsu Xuzhou 221002,China;3.Department of Radiology,the Affiliated Hospital of Xuzhou Medical University,Jiangsu Xuzhou 221002,China;4.Imaging Department,the Affiliated Hospital of Xuzhou Medical University,Jiangsu Xuzhou 221002,China.
Keywords:
gastric cancer; radiomics; human epidermal growth factor receptor; multi-phase contrast-enhanced computed tomography
PACS:
R735.2
DOI:
10.3969/j.issn.1672-4992.2025.02.018
Abstract:
Objective:To develop and validate a fusion model based on multi-phase contrast-enhanced computed tomography (CECT) combined with clinical features for preoperatively predicting the human epidermal growth factor receptor 2 (HER2) expression status in patients with gastric cancer.Methods:We retrospectively included 170 patients with gastric cancer who underwent surgery in our hospital from September 2015 to September 2023.They were randomly divided into a training set (n=118) and a test set (n=52).PyRadiomics was used to extract radiomics features from multi-phase CECT images.The Random Forest regression was used to construct models for clinical features，arterial phase radiomics,venous phase radiomics,delayed phase radiomics,multi-phase radiomics,and integrated models combining multi-phase radiomics features and clinical variables.The use of receiver operating characteristic (ROC) curves,their area under the curve (AUC),calibration curve analysis and decision curve analysis (DCA) was applied to evaluate,validate and compare the predictive power and the clinical utility of various models.Results:The fusion model demonstrated good discriminative performance in predicting HER2 expression status with an AUC of 0.895 in the training set and 0.874 in the test set,outperforming the other models (Delong test,P＜0.05 in the training set and test set).Calibration curves showed good model goodness-of-fit (Hosmer-Lemeshow test,P=0.346 in the training set,P=0.586 in the test set).DCA demonstrated that the net benefit of the fusion model in distinguishing between HER2-positive and HER2-negative cases was superior to that of the clinical feature model and the multi-phase radiomics model.Conclusion:The fusion model in the models established in this study has better performance and could be expected as a non-invasive tool for predicting HER2 expression status and guiding clinical treatment.

References:

［1］BRAY F,LAVERSANNE M,SUNG H,et al.Global cancer statistics 2022:GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries［J］.CA:A Cancer Journal for Clinicians,2024,74(3):229-263.
[2]ZHU Y,ZHU X,WEI X,et al.HER2-targeted therapies in gastric cancer［J］.Biochim Biophys Acta Rev Cancer,2021,1876(1):188549.
[3]CHARALAMPAKIS N,ECONOMOPOULOU P,KOTSANTIS I,et al.Medical management of gastric cancer:a 2017 update［J］.Cancer Med,2018,7(1):123-133.
[4]CIESIELSHI M,SZAJEWSKI M,PEKSA R,et al.The relationship between HER2 overexpression and angiogenesis in gastric cancer［J］.Medicine (Baltimore),2018,97(42):e12854.
[5]YAGI S,WAKATSUKI T,YAMAMOTO N,et al.Correction to:Clinical significance of intratumoral HER2 heterogeneity on trastuzumab efficacy using endoscopic biopsy specimens in patients with advanced HER2 positive gastric cancer［J］.Gastric Cancer,2019,22(3):526.
[6]IVONNE H,KATRIN S,ELBA R,et al.HER2 expression,test deviations,and their impact on survival in metastatic gastric cancer:results from the prospective multicenter VARIANZ study［J］.Journal of Clinical Oncology,2021,39(13):1468-1478.
[7]ZWANENBURG A,LEGER S,AGOLLI L,et al.Assessing robustness of radiomic features by image perturbation［J］.Sci Rep,2019,9(1):1-10.
[8]CHANG X,GUO X,LI X,et al.Potential value of radiomics in the identification of stage T3 and T4a esophagogastric junction adenocarcinoma based on contrast-enhanced CT images［J］.Front Oncol,2021,11:627947.
[9]KUBOTA K,SUZUKI A,SHIOZAKI H,et al.Accuracy of multidetector-row computed tomography in the preoperative diagnosis of lymph node metastasis in patients with gastric cancer［J］.Gastrointest Tumors,2017,3(3-4):163-170.
[10]LAMBIN P,LEI JENAAR RTH,DEIST TM,et al.Radiomics:the bridge between medical imaging and personalized medicine［J］.Nat Rev Clin Oncol,2017,14(12):749-762.
[11]CORREDOR G,BHARADWAJ S,PATHAK T,et al.A review of AI-based radiomics and computational pathology approaches in triple-negative breast cancer:current applications and perspectives［J］.Clin Breast Cancer,2023,23(8):800-812.
[12]WANG X,LI C,FANG M,et al.Integrating No.3 lymph nodes and primary tumor radiomics to predict lymph node metastasis in T1-2 gastric cancer［J］.BMC Med Imaging,2021,21(1):58.
[13]YANG J,SU H,CHEN T,et al.Development and validation of nomogram of peritoneal metastasis in gastric cancer based on simplified clinicopathological features and serum tumor markers［J］.BMC Cancer,2023,23(1):64.
[14]WANG Y,LIU W,YU Y,et al.CT radiomics nomogram for the preoperative prediction of lymph node metastasis in gastric cancer［J］.Eur Radiol,2020,30(2):976-986.
[15]LI Y,CHENG Z,GEVAERT O,et al.A CT-based radiomics nomogram for prediction of human epidermal growth factor receptor 2 status in patients with gastric cancer［J］.Chin J Cancer Res,2020,32(1):62-71.
[16]WANG Y,YU Y,HAN W,et al.CT radiomics for distinction of human epidermal growth factor receptor 2 negative gastric cancer［J］.Acad Radiol,2021,28(3):e86-e92.
[17]MEI D,LUO Y,WANG Y,et al.CT texture analysis of lung adenocarcinoma:can radiomic features be surrogate biomarkers for EGFR mutation statuses［J］.Cancer Imaging,2018,18(1):52.
[18]YING M,PAN J,LU G,et al.Development and validation of a radiomics-based nomogram for the preoperative prediction of microsatellite instability in colorectal cancer［J］.BMC Cancer,2022,22(1):524.
[19]NING Q,ZHAO X,MA Z.A novel method for identification of glutarylation sites combining Borderline-SMOTE with tomek links technique in imbalanced data［J］.IEEE/ACM Trans Comput Biol Bioinform,2022,19(5):2632-2641.

Memo

Memo:
-
Last Update: 1900-01-01