基于多参数MRI的影像组学列线图鉴别原发性黏液性卵巢癌与转移性卵巢癌
本研究纳入194例经组织学证实的原发性黏液性卵巢癌(72例)与转移性卵巢癌(122例)患者,随机分为训练队列(137例)与验证队列(57例),从轴位FS-T2WI、DWI及CE-T1WI序列提取影像组学特征构建列线图。列线图在训练队列与验证队列的AUC分别为0.931和0.934,显著优于影像组学模型、临床模型及放射科医师,决策曲线分析显示可提供更高净获益。
要点
- 联合mpMRI影像组学特征与临床特征的列线图鉴别PMOC与MOC的AUC在训练队列为0.931、验证队列为0.934。
- 列线图预测效能显著优于单纯影像组学模型与临床模型,且优于放射科医师(均P<0.05)。
- 决策曲线分析显示列线图可为患者提供更高净获益。
核心结论
- 基于mpMRI的影像组学列线图在鉴别PMOC与MOC方面表现出显著的预测效能,可作为无创的术前影像学方法。
研究设计与样本
- 回顾性研究,共纳入194例经组织学证实的PMOC(n=72)与MOC(n=122)患者,随机分为训练队列(n=137)与验证队列(n=57),从轴位FS-T2WI、DWI及CE-T1WI序列提取影像组学特征。
诊断标准与关键数值
- 列线图训练队列AUC为0.931,验证队列AUC为0.934。
- 影像组学模型训练队列AUC为0.870,验证队列AUC为0.844。
- 临床模型训练队列AUC为0.858,验证队列AUC为0.847。
- 列线图训练队列AUC 0.931 vs 影像组学模型0.870,P=0.004;验证队列AUC 0.934 vs 0.844,P=0.032。
- 列线图训练队列AUC 0.931 vs 临床模型0.858,P=0.005;验证队列AUC 0.934 vs 0.847,P=0.030。
临床应用与阅片要点
- 列线图可用于术前无创鉴别PMOC与MOC,辅助临床决策。
- 决策曲线分析显示列线图可为患者提供更高净获益。
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
OBJECTIVE: To develop a multiparametric magnetic resonance imaging (mpMRI)-based radiomics nomogram and evaluate its performance in differentiating primary mucinous ovarian cancer (PMOC) from metastatic ovarian cancer (MOC).
METHODS: A total of 194 patients with PMOC (n = 72) and MOC (n = 122) confirmed by histology were randomly divided into the primary cohort (n = 137) and validation cohort (n = 57). Radiomics features were extracted from axial fat-saturated T2-weighted imaging (FS-T2WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1-weighted imaging (CE-T1WI) sequences of each lesion. The effective features were selected by minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) regression to develop a radiomics model. Combined with clinical features, multivariate logistic regression analysis was employed to develop a radiomics nomogram. The efficiency of nomogram was evaluated using the receiver operating characteristic (ROC) curve analysis and compared using DeLong test. Finally, the goodness of fit and clinical benefit of nomogram were assessed by calibration curves and decision curve analysis, respectively.
RESULTS: The radiomics nomogram, by combining the mpMRI radiomics features with clinical features, yielded area under the curve (AUC) values of 0.931 and 0.934 in the primary and validation cohorts, respectively. The predictive performance of the radiomics nomogram was significantly superior to the radiomics model (0.931 vs. 0.870, P = 0.004; 0.934 vs. 0.844, P = 0.032), the clinical model (0.931 vs. 0.858, P = 0.005; 0.934 vs. 0.847, P = 0.030), and radiologists (all P < 0.05) in the primary and validation cohorts, respectively. The decision curve analysis revealed that the nomogram could provide higher net benefit to patients.
CONCLUSION: The mpMRI-based radiomics nomogram exhibited notable predictive performance in differentiating PMOC from MOC, emerging as a non-invasive preoperative imaging approach.
引用
- Shi SY, Li YA, Qiang JW, et al. Multiparametric MRI-based radiomics nomogram for differentiation of primary mucinous ovarian cancer from metastatic ovarian cancer. Abdom Radiol (NY). 2024. PMID: 39215773. doi:10.1007/s00261-024-04542-y
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。