The value of CT radiomics in predicting treatment outcomes in patients with nasal polyps
10.3760/cma.j.cn115330-20240120-00038
- VernacularTitle:CT影像组学在预测鼻息肉术后疗效中的价值
- Author:
Kanghua WANG
1
;
Yueming CUI
;
Jianbo SHI
;
Yueqi SUN
Author Information
1. 中山大学附属第七医院耳鼻咽喉科，深圳 518107
- Keywords:
Nasal polyp;
Refractory;
Sinus CT;
Radiomics;
Prediction
- From:
Chinese Journal of Otorhinolaryngology Head and Neck Surgery
2024;59(6):582-589
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To evaluate the predictive efficacy of sinus CT radiomics for treatment outcomes in nasal polyp patients undergoing endoscopic sinus surgery.Methods:A retrospective cohort study was conducted at the First Affiliated Hospital of Sun Yat-sen University, including 194 patients with nasal polyps treated between January 2015 and December 2019. The cohort comprised 132 males and 62 females, aged 16 to 75 years. Patients were divided into a training set ( n=135) and an internal validation set ( n=59). An external validation set ( n=34), consisting of 22 males and 12 females aged 16 to 59 years, was included from January 2020 to December 2021. Disease control was evaluated using the criteria from the European Position Paper on Rhinosinusitis and Nasal Polyps 2020 (EPOS 2020). Radiomic features were extracted from sinus CT images and analyzed using the least absolute shrinkage and selection operator (LASSO) regression. Models combining radiomic and clinical features were developed to predict treatment efficacy. Results:The radiomics and combined models, based on four selected features, outperformed the clinical feature model in the training set, with AUC values of 0.901 and 0.915, versus 0.874, respectively. In the internal validation set, AUCs were 0.839, 0.832, and 0.716. Despite reduced AUCs in the external set, the radiomics model maintained good generalizability (0.748, 0.764, 0.620). Decision curve analysis showed significant clinical benefits in both radiomics and combined models.Conclusion:The CT-based radiomics model demonstrates significant predictive power in identifying refractory nasal polyps, suggesting its potential for clinical application in treatment outcome prediction.
