MRI-based habitat radiomics for evaluating lymph node metastasis in renal cell carcinoma
10.3760/cma.j.cn112149-20241105-00657
- VernacularTitle:基于MRI生境影像组学预测肾细胞癌区域淋巴结转移的研究
- Author:
Xu BAI
1
;
Xu FU
;
Honghao XU
;
Shaopeng ZHOU
;
Tongyu JIA
;
Sicheng YI
;
Houming ZHAO
;
Bo LIU
;
Xin LIU
;
Haili LIU
;
Xuetao MU
;
Mengmeng ZHANG
;
Lixia QI
;
Huiyi YE
;
Xin MA
;
Haiyi WANG
Author Information
1. 解放军总医院第一医学中心放射诊断科，北京 100853
- Publication Type:Journal Article
- Keywords:
Magnetic resonance imaging;
Renal cell carcinoma;
Lymph node metastasis;
Radiomics;
Habitat analysis
- From:
Chinese Journal of Radiology
2025;59(4):384-392
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To evaluate the efficacy of preoperative prediction of regional lymph node (RLN) metastasis in renal cell carcinoma (RCC) using a machine learning model based on habitat imaging radiomics from renal MRI.Methods:This cross-sectional study retrospectively analyzed 220 patients with RCC who underwent nephrectomy and RLN dissection at four medical centers of Chinese PLA General Hospital from January 2010 to August 2023. The cohort included 65 patients with RLN metastasis and 155 without. A stratified random sampling method was used to divide 175 patients from the first medical center into a training set ( n=140) and an internal test set ( n=35) in an 8∶2 ratio, while 45 patients from the third, fourth, and fifth medical centers constituted the external test set. The primary RCC lesions were categorized into 15 habitat subregions based on corticomedullary-phase enhancement and T 2WI signal intensity on MRI, and the volume fractions of different subregions were analyzed. In the training cohort, radiomics features derived from the habitat subregions were used to construct a radiomics model employing various machine learning algorithms, including extremely random trees (ET), gradient boosting decision trees (GBDT), random forest (RF), and support vector machine (SVM). The optimal model was selected and combined with RLN short-axis diameter to develop a combined model. The efficacy of each model in predicting RLN metastasis was evaluated using the receiver operating characteristic (ROC) curve. Results:The volume fraction of hyper-enhanced hyper-intense regions in the non-metastatic group was significantly higher than that in the metastatic group (0.05±0.09 vs. 0.02±0.03; t=3.00, P=0.003). Among the machine learning models constructed using 15 optimal habitat radiomics features, the SVM model demonstrated the best performance, with area under the ROC curve (AUC) values of 0.85 (95% CI 0.72-0.98) in the internal test set and 0.82 (95% CI 0.67-0.98) in the external test set, surpassing those of the ET, GBDT, and RF models. The combined model, integrating the SVM model with RLN short-axis diameter, achieved AUC values of 0.94 (95% CI 0.85-1.00) in the internal test set and 0.89 (95% CI 0.78-1.00) in the external test set, with RLN short-axis diameter contributing AUC values of 0.81 (95% CI 0.66-0.96) and 0.81 (95% CI 0.68-0.94), respectively. The diagnostic sensitivity of the combined model was 91.7% in the internal test set and 85.7% in the external test set, with specificities of 78.3% and 67.7%, respectively. Conclusion:The combined model based on MRI habitat imaging radiomics and RLN short-axis diameter demonstrates excellent preoperative assessment capability for RLN metastasis in RCC.
