文献速递妇产影像腹部CT

瘤内与瘤周影像组学预测高级别浆液性卵巢癌早期复发

Intra- and peritumoral radiomics for predicting early recurrence in patients with high-grade serous ovarian cancer.
PubMed 文献 · Abdom Radiol (NY) · 2022-11-29

本研究纳入110例高级别浆液性卵巢癌患者,基于治疗前增强CT提取瘤内和瘤周影像组学特征,构建联合影像组学标签及列线图预测复发。联合模型在训练集和验证集AUC分别为0.899和0.815,列线图预测能力最佳(训练集AUC 0.901,验证集0.818)。

要点

  • 瘤内联合瘤周CT影像组学可预测HGSOC复发,联合模型优于单一区域。
  • 结合FIGO分期、月经状态和肿瘤位置的列线图预测效能最佳。
  • 列线图在训练集和验证集AUC分别为0.901和0.818,校准和决策曲线支持其临床价值。

核心结论

  • 瘤内与瘤周联合的CT影像组学对预测HGSOC复发具有价值,所构建列线图可能有助于临床应用。

研究设计与样本

  • 单中心回顾性研究,纳入2017年8月至2021年4月本院110例HGSOC患者,均于治疗前接受增强CT扫描。
  • 采用LASSO回归从瘤内和瘤周区域筛选影像组学特征,分别构建Intra-RS、Peri-RS和Com-RS。
  • 结合影像组学标签与有预测潜力的临床参数构建列线图,以ROC、校准曲线和DCA评估效能。

诊断标准与关键数值

  • Com-RS预测复发的AUC在训练集为0.899(Intra-RS 0.861,Peri-RS 0.836),验证集为0.815(Intra-RS 0.788,Peri-RS 0.762)。
  • 列线图预测复发的AUC在训练集为0.901(Com-RS 0.899,临床模型0.648),验证集为0.818(Com-RS 0.815,临床模型0.666)。
  • FIGO分期、月经状态和肿瘤位置与肿瘤复发强相关。

临床应用与阅片要点

  • 治疗前增强CT可同时提取瘤内和瘤周影像组学特征,联合模型比单一区域模型预测复发更准。
  • 列线图整合影像组学与临床参数(FIGO分期、月经状态、肿瘤位置),可辅助个体化复发风险评估。

局限性

  • 单中心回顾性研究,样本量110例,外部验证不足。

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 explore values of intra- and peritumoral CT-based radiomics for predicting recurrence in high-grade serous ovarian cancer (HGSOC) patients.

METHODS: This study enrolled 110 HGSOC patients from our hospital between Aug 2017 and Apr 2021. All patients underwent contrast-enhanced CT scans before treatment. The least absolute shrinkage and selection operator (LASSO) regression was used to select radiomics features from intra- and peritumoral areas. Radiomics signatures were built based on selected features from Intra-RS, Peri-RS, and in Com-RS. A nomogram was constructed by combining radiomics signatures and clinical parameters with predictive potential. Receiver operating characteristics (ROC), calibration, and decision curve analyses (DCA) curves were used to evaluate performance of the nomogram.

RESULTS: The intra- and peritumoral combined Com-RS showed effective ability in predicting recurrent HGSOC in the training (AUCs, Intra-RS vs. Peri-RS vs. Com-RS, 0.861 vs. 0.836 vs. 899) and validation (AUCs, Intra-RS vs. Peri-RS vs. Com-RS, 0.788 vs. 0.762 vs. 815) cohort. The Federation of International of FIGO stage, menstruation, and location were found to be strongly associated with tumor recurrence. The nomogram has the best predictive ability in the training (AUCs, Com-RS vs. clinical model vs. nomogram, 0.899 vs. 0.648 vs. 0.901) and validation (AUCs, Com-RS vs. clinical model vs. nomogram, 0.815 vs. 0.666 vs. 0.818) cohort.

CONCLUSION: Our findings suggested values of intra- and peritumoral-based radiomics for predicting recurrent HGSOC. The constructed nomogram may be of importance in clinical application.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Wu, Jiang, Fu, et al. Intra- and peritumoral radiomics for predicting early recurrence in patients with high-grade serous ovarian cancer. Abdom Radiol (NY). 2022. PMID: 36445408. doi:10.1007/s00261-022-03717-9

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。