Page 100 - 南京医科大学自然版
P. 100
南京医科大学学报(自然科学版) 第46卷第7期
·1046 · Journal of Nanjing Medical University(Natural Sciences) 2026年7月
·临床研究·
时序影像组学预测肝癌免疫联合治疗疗效
王 添,许正刚,吴怀玉,操舒亚,季顾惟,王 科 *
南京医科大学第一附属医院肝胆外科,江苏省消化系统重大慢病重点实验室,江苏 南京 210029
[摘 要] 目的:构建融合多期相增强影像、肿瘤内异质性(imaging,intratumoral heterogeneity,ITH)、时间序列影像组学(time⁃
series radiomics,TSR)与Delta影像组学(delta⁃radiomics,DR)的预测模型,评估其在肝细胞癌(hepatocellular carcinoma,HCC)免
疫联合治疗疗效判定中的价值,并以该模型为核心建立临床决策支持系统(clinical decision support system,CDSS)。方法:回顾
性收集2021年1月—2024年12月在南京医科大学第一附属医院接受免疫联合治疗的62例HCC患者资料。围绕动脉期、门静
脉期与延迟期增强影像提取传统影像组学、ITH、TSR、DR以及临床检验指标密度(clinical test index density,CTId)特征,经由三
阶段筛选确定最优特征集,并借助多种机器学习算法训练融合预测模型;在此基础上搭建CDSS以考察其实际应用效能。结
果:融合模型对治疗进展预测的验证集曲线下面积(area under the curve,AUC)达到0.821(95%CI:0.629~0.987),显著优于单期
相影像组学模型(0.706~0.738)、ITH 单一模型(0.752)及传统临床模型(0.685),DeLong 检验均具统计学意义(P < 0.05);对≥Ⅱ
级、≥Ⅲ级并发症的预测,AUC 分别为 0.803 与 0.845。影像组学风险分层在无进展生存期(HR=4.36,95%CI:1.94~9.80,P <
0.001)与总生存期(HR=4.23,95%CI:1.78~10.08,P=0.001)层面均构成独立预后因子;在 Ⅰ~Ⅱ 期早期亚组内 PFS 判别效能保
持稳定(χ =14.60,P < 0.001),总生存期因事件数偏少未达统计学意义(P=0.341)。所搭建 CDSS 完成单例分层用时 ≤60 s,与
2
人工分析一致性达 100%。结论:融合多期相与纵向动态特征的影像组学模型能够较为准确地刻画 HCC 免疫联合治疗的疗效
及并发症风险,依托该模型搭建的 CDSS 可为个体化临床决策提供可量化的支持工具。
[关键词] 肝细胞癌;增强磁共振成像;影像组学;时间序列;临床决策支持系统
[中图分类号] R735.7 [文献标志码] A [文章编号] 1007⁃4368(2026)07⁃1046⁃10
doi:10.7655/NYDXBNSN260500
Temporal radiomics predicts response to immuno⁃combination therapy in hepatocellular
carcinoma
*
WANG Tian,XU Zhenggang,WU Huaiyu,CAO Shuya,JI Guwei,WANG Ke
Department of Hepatobiliary Surgery,the First Affiliated Hospital of Nanjing Medical University,Jiangsu Provincial
Key Laboratory of Chronic Digestive Diseases,Nanjing 210029,China
[Abstract] Objective:To develop a combined prediction model that integrates multi⁃phase contrast⁃enhanced imaging,intratumoral
heterogeneity(ITH),time ⁃ series radiomics(TSR)and delta ⁃ radiomics(DR)features for assessing the therapeutic response of
hepatocellular carcinoma(HCC)to immuno ⁃ combination therapy,and to build a clinical decision support system(CDSS)upon it.
Methods:Sixty ⁃ two HCC patients who received immuno ⁃ combination therapy at the First Affiliated Hospital of Nanjing Medical
University between January 2021 and December 2024 were retrospectively enrolled. Traditional radiomics,ITH,TSR,DR,and clinical
test index density(CTId)features were extracted from arterial,portal⁃venous and delayed⁃phase images. A three⁃stage feature selection
pipeline was employed to identify the optimal feature set,and multiple machine ⁃ learning classifiers were trained to construct the
combined model,based on which a CDSS was subsequently developed and evaluated. Results:The combined model yielded a
validation AUC of 0.821(95%CI:0.629-0.987)for predicting disease progression,significantly outperforming single⁃phase radiomics
models(0.706-0.738),the ITH⁃only model(0.752)and the clinical model(0.685),with all differences statistically significant via
Delong test(all P < 0.05). The AUC values for predicting grade ≥Ⅱ and ≥Ⅲ complications reached 0.803 and 0.845,respectively.
Radiomics⁃based risk stratification independently predicted both progression⁃free survival(HR=4.36,95%CI:1.94-9.80,P < 0.001)
[基金项目] 江苏省科技厅临床前沿技术(BF2024053)
通信作者(Corresponding author),E⁃mail:021a23@njmu.edu.cn(ORCID:0000⁃0002⁃5627⁃2537)
∗

