CT影像组学对肝细胞癌TACE术后生存预测的有限增量价值及跨队列可迁移性
该回顾性研究纳入221例WAW-TACE和98例HCC-TACE-SEG患者,评估治疗前CT影像组学(R1)在临床Cox模型(C0)基础上对总生存(OS)的增量价值,并在独立队列中验证冻结模型。结果显示R1未能在各队列内一致提升临床参考模型,冻结模型在HCC-TACE-SEG中区分度有限。
要点
- 在WAW-TACE队列中,R1(Top-K=15)的C-index为0.593±0.049,低于临床C0模型的0.646±0.043。
- 联合模型C0+R1在WAW-TACE的C-index为0.639±0.045,未超过C0的0.646±0.043。
- 冻结R1模型在HCC-TACE-SEG外部队列中C-index为0.463–0.535,区分度有限。
核心结论
- 评估的模型在这些TACE队列中对OS预测未显示一致增量价值,冻结模型在临床特征不同的HCC-TACE-SEG队列中区分度有限;这些发现不支持这些模型的临床使用,也不能确立CT影像组学的普遍局限性。
研究设计与样本
- 回顾性研究,纳入221例WAW-TACE和98例HCC-TACE-SEG患者,使用治疗前动脉期和门静脉期CT;在队列内采用5折交叉验证重复10次评估增量价值,外部验证仅对WAW训练冻结的R1模型(Top-K=5、10、15)在HCC-TACE-SEG中无重拟合应用,联合C0+R1模型未做外部验证。
诊断标准与关键数值
- WAW-TACE队列中,临床C0模型C-index为0.646±0.043,R1(Top-K=15)为0.593±0.049,C0+R1为0.639±0.045。
- HCC-TACE-SEG队列中,临床C0模型C-index为0.496±0.087,R1(Top-K=15)为0.530±0.072,C0+R1为0.495±0.094。
- 冻结外部应用时,Top-K=5的C-index为0.463(95%CI 0.397-0.532),Top-K=10为0.535(95%CI 0.468-0.608),Top-K=15为0.528(95%CI 0.460-0.598)。
临床应用与阅片要点
- 原文结论指出这些发现不支持这些模型的临床使用,也未确立CT影像组学的普遍局限性。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: To evaluate whether pretreatment CT radiomics adds information for overall survival (OS) prediction among patients with hepatocellular carcinoma (HCC) treated with transarterial chemoembolization (TACE), and assess frozen imaging-model performance in an independent cohort.
METHODS: This retrospective study included 221 WAW-TACE and 98 HCC-TACE-SEG patients with pretreatment arterial and portal venous CT. Incremental value of a tumor-radiomics Random Survival Forest score (R1) beyond cohort-specific clinical Cox models (C0) was evaluated within each cohort using 5-fold cross-validation repeated 10 times. External validation was restricted to frozen WAW-trained R1 models (Top-K = 5, 10, 15) applied to HCC-TACE-SEG without refitting; the combined C0 + R1 model was not externally validated.
RESULTS: WAW-TACE included 162 deaths and HCC-TACE-SEG 86 deaths. In WAW-TACE, C0, R1 Top-K = 15, and C0 + R1 achieved C-indices of 0.646 ± 0.043, 0.593 ± 0.049, and 0.639 ± 0.045, respectively. Corresponding HCC-TACE-SEG estimates were 0.496 ± 0.087, 0.530 ± 0.072, and 0.495 ± 0.094. Thus, R1 did not consistently improve cohort-specific clinical reference models. In frozen external application, Top-K = 5, 10, and 15 achieved C-indices of 0.463 (95% CI 0.397-0.532), 0.535 (0.468-0.608), and 0.528 (0.460-0.598), respectively.
CONCLUSION: The evaluated models showed no consistent incremental value for OS prediction within these TACE cohorts and limited frozen-model discrimination in the clinically distinct HCC-TACE-SEG cohort. These findings do not support clinical use of these models or establish a general limitation of CT radiomics.
引用
- Bartnik K, Tsevegmed B. Limited incremental value and cross-cohort transferability of CT radiomics for survival prediction after TACE in hepatocellular carcinoma. Abdom Radiol (NY). 2026. PMID: 42867540. doi:10.1007/s00261-026-05830-5
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。