Chen Zhihui, Zhu Hongqing, Shu Hongmin, Zhang Jianbo, Gu Kangchen, Yao Wenjun
Department of Radiology, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, China.
Medical Imaging Research Center, Anhui Medical University, Hefei, Anhui, China.
Cancer Imaging. 2025 May 3;25(1):59. doi: 10.1186/s40644-025-00875-z.
The World Health Organization/International Society of Urological Pathology (WHO/ISUP) grading of clear cell renal cell carcinoma (ccRCC) is crucial for prognosis and treatment planning. This study aims to predict the grade using intratumoral and peritumoral subregional CT radiomics analysis for better clinical interventions.
Data from two hospitals included 513 ccRCC patients, who were divided into training (70%), validation (30%), and an external validation set (testing) of 67 patients. Using ITK-SNAP, two radiologists annotated tumor regions of interest (ROI) and extended surrounding areas by 1 mm, 3 mm, and 5 mm. The K-means clustering algorithm divided the tumor region into three sub-regions, and the Least Absolute Shrinkage and Selection Operator (LASSO) regression identified the most predictive features. Various machine learning models were established, including radiomics models, peritumoral radiomics models, models based on intratumoral heterogeneity (ITH) score, clinical models, and comprehensive models. Predictive ability was evaluated using receiver operating characteristic (ROC) curves, area under the curve (AUC) values, DeLong tests, calibration curves, and decision curves.
The combined model showed strong predictive power with an AUC of 0.852 (95% CI: 0.725-0.979) on the test data, outperforming individual models. The ITH score model was highly precise, with AUCs of 0.891 (95% CI: 0.854-0.927) in training, 0.877 (95% CI: 0.814-0.941) in validation, and 0.847 (95% CI: 0.725-0.969) in testing, proving its superior predictive ability across datasets.
A comprehensive model combining Habitat, Peri1mm, and salient clinical features was significantly more accurate in predicting ccRCC pathologic grading.
Question: Characterize tumor heterogeneity to non-invasively predict WHO/ISUP pathological grading preoperatively.
An integrated model combining subregion characterization, peritumoral characteristics, and clinical features can predict ccRCC grade preoperatively.
Subregion tumor characterization outperforms the single-entity approach. The integrated model, compared with the radiomics model, boosts grading and prognostic accuracy for more targeted clinical actions.
世界卫生组织/国际泌尿病理学会（WHO/ISUP）对透明细胞肾细胞癌（ccRCC）的分级对于预后和治疗规划至关重要。本研究旨在通过瘤内和瘤周亚区域CT放射组学分析预测分级，以实现更好的临床干预。
来自两家医院的数据包括513例ccRCC患者，他们被分为训练组（70%）、验证组（30%）和一个包含67例患者的外部验证集（测试组）。使用ITK-SNAP，两名放射科医生标注肿瘤感兴趣区域（ROI），并将周围区域分别扩展1毫米、3毫米和5毫米。K均值聚类算法将肿瘤区域分为三个子区域，最小绝对收缩和选择算子（LASSO）回归确定最具预测性的特征。建立了各种机器学习模型，包括放射组学模型、瘤周放射组学模型、基于瘤内异质性（ITH）评分的模型、临床模型和综合模型。使用受试者操作特征（ROC）曲线、曲线下面积（AUC）值、德龙检验、校准曲线和决策曲线评估预测能力。
联合模型在测试数据上显示出强大的预测能力，AUC为0.852（95%CI：0.725 - 0.979），优于单个模型。ITH评分模型非常精确，在训练组中的AUC为0.891（95%CI：0.854 - 0.927），在验证组中为0.877（95%CI：0.814 - 0.941），在测试组中为0.847（95%CI：0.725 - 0.969），证明其在各个数据集中具有卓越的预测能力。
结合Habitat、Peri1mm和显著临床特征的综合模型在预测ccRCC病理分级方面明显更准确。
问题：表征肿瘤异质性以术前无创预测WHO/ISUP病理分级。
结合子区域表征、瘤周特征和临床特征的综合模型可术前预测ccRCC分级。
子区域肿瘤表征优于单一实体方法。与放射组学模型相比，综合模型提高了分级和预后准确性，可采取更具针对性的临床行动。
