Page 72 - 南京医科大学自然版

南京医科大学学报（自然科学版） 第45卷第5期
·658 · Journal of Nanjing Medical University（Natural Sciences） 2025年5月

·临床研究·

CT 影像组学联合临床病理特征模型预测非转移性 2~3 级肾透

明细胞癌术后无病生存期的研究

马传贤，陈 晨，杨雅雯，柴 顺，马占龙 *

南京医科大学第一附属医院放射科，江苏 南京 210029

［摘 要］ 目的：对比术前增强CT影像组学特征模型与临床病理特征模型预测非转移性2~3级肾透明细胞癌（clear cell renal
cell carcinoma，ccRCC）患者术后无病生存期（disease⁃free survival，DFS）的价值。方法：回顾性分析2013年1月—2020年12月
行手术治疗且术后病理分级为2~3级的315例非转移性ccRCC患者，收集患者术前增强CT图像、临床病理资料以及随访信息，
勾画病灶感兴趣区并使用Python提取组学特征，利用最小绝对收缩和选择算子以及Cox回归分析计算患者影像组学评分，分
别构建临床病理特征模型、影像组学模型（皮髓质期、实质期、皮髓质期+实质期）以及影像组学与临床病理特征联合模型预测
患者DFS。结果：在预测非转移性2~3级ccRCC患者DFS时，皮髓质期+实质期组学模型预测效能（C⁃index：训练组0.848，验证
组 0.754）高于单一时期影像组学模型（皮髓质期 C⁃index：训练组 0.832，验证组 0.701；实质期 C⁃index：训练组 0.842，验证组
0.720），而组学特征与临床病理特征构建的联合模型拥有最高的预测效能（C⁃index：训练组0.857，验证组0.832）。结论：基于
术前增强CT皮髓质期+实质期图像提取的影像组学特征结合临床病理特征构建的模型有助于预测非转移性2~3级ccRCC患
者术后DFS。
［关键词］ 肾透明细胞癌；影像组学；计算机断层扫描；无病生存期
［中图分类号］ R814.42 ［文献标志码］ A ［文章编号］ 1007⁃4368（2025）05⁃658⁃07
doi：10.7655/NYDXBNSN240864

CT radiomics combined with clinical⁃pathological features predict disease⁃free survival in

non⁃metastatic grades 2-3 clear cell renal cell carcinoma
MA Chuanxian，CHEN Chen，YANG Yawen，CHAI Shun，MA Zhanlong *
Department of Radiology，the First Affiliated Hospital of Nanjing Medical University，Nanjing 210029，China

［Abstract］ Objective：To evaluate the predictive value of preoperative enhanced CT radiomic feature models in comparison with
clinical⁃pathological feature models for disease⁃free survival（DFS）in patients with non⁃metastatic grades 2-3 clear cell renal cell
carcinoma（ccRCC）after surgery. Methods：A retrospective analysis was conducted on 315 patients with non⁃metastatic ccRCC who
underwent surgical treatment and were pathologically graded as grades 2-3 between January 2013 and December 2020. Preoperative
enhanced CT images，clinical⁃pathological data，and follow⁃up information were collected. The region of interest（ROI）of the lesion
was delineated，and radiomic features were extracted using Python. Patients’radiomic scores were calculated using the least absolute
shrinkage and selection operator（LASSO）and Cox regression analysis. Clinical ⁃ pathological feature models，radiomic models
（corticomedullary phase，parenchymal phase，corticomedullary+parenchymal phase），and combined radiomic and clinical⁃pathological
feature models were constructed to predict DFS. Results：When predicting DFS in non⁃metastatic grades 2-3 ccRCC patients，the
combined radiomic model of corticomedullary + parenchymal phase demonstrated superior predictive efficacy（C ⁃ index：training set
0.848，validation set 0.754）compared to single⁃phase radiomic models（corticomedullary phase C⁃index：training set 0.832，validation
set 0.701；parenchymal phase C⁃index：training set 0.842，validation set 0.720）. However，the combined model incorporating both
radiomic and clinical⁃pathological features exhibited the highest predictive efficacy（C⁃index：training set 0.857，validation set 0.832）.
Conclusion：The model constructed based on radiomics features extracted from preoperative enhanced CT corticomedullary phase+

［基金项目］ 国家自然科学基金（81971669）
通信作者（Corresponding author），E⁃mail：mazhanlong@126.com（ORCID：0009⁃0009⁃3713⁃8015）
∗