Prediction of hematologic toxicity in patients with locally advanced cervical cancer based on radiomics and dosiomics
10.3760/cma.j.cn112271-20240516-00179
- VernacularTitle:基于影像组学和剂量组学预测局部晚期宫颈癌患者的血液学不良反应
- Author:
Qionghui ZHOU
1
;
Luqiao CHEN
;
Qianxi NI
;
Jing LAN
;
Li ZHANG
;
Xizi LONG
;
Jun ZHU
Author Information
1. 湖南省肿瘤医院 中南大学湘雅医学院附属肿瘤医院放疗科，长沙 410013
- Publication Type:Journal Article
- Keywords:
Machine learning;
Radiomics;
Dosiomics;
Cervical cancer;
Hematologic toxicity
- From:
Chinese Journal of Radiological Medicine and Protection
2025;45(3):188-193
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To explore the application of machine learning (ML) models based on radiomics and dosiomics to the assessment of hematologic toxicity (HT) in patients with locally advanced cervical cancer, and to preliminarily explore the comprehensive application of multi-omics features.Methods:A retrospective study was conducted on the clinical data, planning computed tomography (CT) images, and dose files of 205 patients with locally advanced cervical cancer who received concurrent chemoradiotherapy at the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, from January 2022 to June 2023. Patients were categorized according to the severity of HT. Radiomics and dosiomics features were extracted from the same regions of interest (ROIs), followed by feature selection utilizing a random forest algorithm. Then, radiomics, dosiomics, and hybrid models were established based on extreme gradient boosting (XGBoost). The classification performance of these models was assessed by calculating their sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).Results:The radiomics model yielded sensitivity, specificity, and AUC of 0.42, 0.86, and 0.78, respectively. The dosiomics model exhibited sensitivity, specificity, and AUC of 0.50, 0.90, and 0.74, respectively. In contrast, the hybrid model achieved sensitivity, specificity, and AUC of 0.50, 0.83, and 0.83, respectively. These findings suggest that the hybrid model possessed an enhanced classification capability compared to the individual radiomics and dosiomics models.Conclusions:It is feasible to use ML models based on radiomics and dosiomics to conduct the classification and prediction of HT in patients with locally advanced cervical cancer treated with concurrent chemoradiotherapy. Furthermore, integrating both radiomics features and dosiomics features can improve the classification performance of relevant prediction models, thus holding application potentials to optimize treatment strategies for patients with locally advanced cervical cancer.
