Kang Jian, Liu Xing, Yang Xuwen, Xiong Yijia, Sheng Kai, Xiao Fan, Jiang Jingxuan
Department of Radiology, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China.
Oriental Pan-Vascular Devices Innovation College, University of Shanghai for Science and Technology, Shanghai, China.
Jpn J Radiol. 2025 Aug 18. doi: 10.1007/s11604-025-01854-x.
The purpose of this research was to evaluate the effectiveness of contrast-enhanced computed tomography (CECT)-based habitat radiomics in differentiating low-risk thymomas from high-risk thymomas prior to surgery.
A retrospective study was conducted involving patients with thymomas who had undergone CECT at three medical centers. The patients were divided into two cohorts: a training cohort comprising 134 patients from Centers A and B, and a validation cohort consisting of 41 patients from Center C. The k-means clustering algorithm was employed to segment the CECT images into distinct tumor habitats. Radiomic features were extracted from the entire tumor and the specific habitats identified. After feature selection, logistic regression (LR) model was developed to distinguish between low-risk and high-risk thymomas.
A total of 175 patients were enrolled in the study, with 106 diagnosed with low-risk thymomas and 69 with high-risk thymomas. In the validation cohort, the area under the receiver operating characteristic curve (AUC) values for the models derived from the whole tumor, habitat_1, habitat_2, and habitat_3 were 0.806 (95% CI 0.675-0.938), 0.946 (95% CI 0.861-1.000), 0.620 (95% CI 0.446-0.794), and 0.946 (95% CI 0.885-1.000), respectively. The habitats model demonstrated superior predictive performance compared to the whole tumor model.
CECT-based habitat radiomics represents a promising diagnostic approach for distinguishing between low-risk and high-risk thymomas in the preoperative setting, highlighting its potential for enhanced diagnostic accuracy.
本研究旨在评估基于对比增强计算机断层扫描（CECT）的瘤灶放射组学在术前鉴别低风险胸腺瘤与高风险胸腺瘤方面的有效性。
对三个医疗中心接受CECT检查的胸腺瘤患者进行回顾性研究。患者分为两个队列：一个训练队列，由来自A中心和B中心的134例患者组成；一个验证队列，由来自C中心的41例患者组成。采用k均值聚类算法将CECT图像分割为不同的肿瘤瘤灶。从整个肿瘤及识别出的特定瘤灶中提取放射组学特征。经过特征选择后，建立逻辑回归（LR）模型以区分低风险和高风险胸腺瘤。
本研究共纳入175例患者，其中106例诊断为低风险胸腺瘤，69例为高风险胸腺瘤。在验证队列中，基于整个肿瘤、瘤灶_1、瘤灶_2和瘤灶_3得出的模型的受试者操作特征曲线（AUC）值分别为0.806（95%CI 0.675 - 0.938）、0.946（95%CI 0.861 - 1.000）、0.62（95%CI 0.446 - 0.794）和0.946（95%CI 0.885 - 1.000）。瘤灶模型显示出比整个肿瘤模型更优的预测性能。
基于CECT的瘤灶放射组学是术前鉴别低风险和高风险胸腺瘤的一种有前景的诊断方法，凸显了其提高诊断准确性的潜力。
