The application value of CT-enhanced imaging-based radiomics nomogram in preoperative assessment of microsatellite instability status in colon cancer
10.3969/j.issn.1002-1671.2024.07.016
- VernacularTitle:基于CT增强的影像组学诺模图在术前评估结肠癌微卫星不稳定状态的应用价值
- Author:
Wei WANG
1
;
Lu LI
;
Yuwen ZHANG
;
Changqing GU
;
Dongxue SUN
;
Junjie SHEN
Author Information
1. 蚌埠医学院第一附属医院放射科,安徽 蚌埠 233000
- Keywords:
colon cancer;
microsatellite instability;
computed tomography;
machine learning;
radiomics
- From:
Journal of Practical Radiology
2024;40(7):1105-1110
- CountryChina
- Language:Chinese
-
Abstract:
Objective To evaluate the predictive value of CT-enhanced imaging-based radiomics nomogram for the status of microsatel-lite instability(MSI)in colon cancer.Methods A retrospective analysis was conducted on 129 postoperative colon cancer patients with confirmed MSI status.They were randomly divided into a training group(n=90)and a validation group(n=39)at a ratio of 7:3.Radiomics features were extracted from preoperative CT-enhanced images of the patients.The predictive performance of various machine learning algorithms was evaluated using the area under the curve(AUC).A nomogram model was developed by incorporating clinical independent risk factors,and the model's overall performance was assessed using decision curve analysis(DCA).Results Age and lesion site were identified as prominent independent risk factors and utilized in the construction of a clinical model.The light gradient boosting machine(LightGBM)algorithm was chosen for building a radiomics model.As a joint model,the AUC of the nomogram model of 0.917 in the training group and 0.822 in the validation group.The DCA confirmed the substantial clinical applicability of the nomogram model.Conclusion The CT-enhanced imaging-based radiomics nomogram offers a pioneering and individualized predic-tive approach for determining the MSI status in colon cancer.
