The investigation of the predictive effect of PET/CT radiomics model for Ki-67 expression status in non-small cell lung cancer
10.3969/j.issn.1002-1671.2024.09.008
- VernacularTitle:探究PET/CT影像组学模型对非小细胞肺癌Ki-67表达状态的预测作用
- Author:
Bo LI
1
;
Jie SU
;
Chen CHEN
;
Chunfeng HU
Author Information
1. 徐州医科大学附属医院放射科,江苏 徐州 221000
- Keywords:
non-small cell lung cancer;
Ki-67;
radiomics;
fusion model
- From:
Journal of Practical Radiology
2024;40(9):1429-1433
- CountryChina
- Language:Chinese
-
Abstract:
Objective To predict the Ki-67 expression status of non-small cell lung cancer(NSCLC)by constructing a fusion model based on PET/CT radiomics features combined with clinical indicators.Methods A total of 110 NSCLC patients were enrolled,and underwent PET/CT scans and Ki-67 detection.The Mann-Whitney U test,the least absolute shrinkage and selection operator(LASSO)method,and Spearman correlation analysis were used to identify the most significant features.The PET model,CT model,PET/CT model,and fusion model were established and their efficacies were compared by the area under the curve(AUC).Results The fusion model with PET/CT radiomics features and clinical indicators outperformed the other three models,with an AUC of 0.961[95％confidence interval(CI)0.922-0.999]in the training set and an AUC of 0.893(95％CI 0.772-1.000)in the test set.Conclusion The fusion model with PET/CT radiomics features and clinical indicators provides the most effective prediction of Ki-67 expression status in NSCLC patients,which is helpful for the assessment of patient prognosis and the formulation of personalized treat-ment plans.
