基于增强CT图像纹理分析鉴别局灶性结节性增生与肝细胞腺瘤的价值评估
回顾性单中心研究纳入48例70个肝细胞腺瘤和50例62个局灶性结节性增生,利用增强CT动脉期和门静脉期图像行纹理分析,发现两组多个纹理参数有显著差异;基于动脉期中、粗滤波图像的均值、mpp和熵构建的模型鉴别肝细胞腺瘤的AUROC最大,为0.824。
要点
- 动脉期中、粗滤波图像的均值、mpp和熵是诊断肝细胞腺瘤的独立预测因子。
- 基于上述动脉期纹理参数的模型鉴别肝细胞腺瘤与局灶性结节性增生的AUROC为0.824。
- 动脉期未滤波图像中局灶性结节性增生的均值、mpp和偏度显著高于肝细胞腺瘤。
核心结论
- 增强CT纹理分析中多个参数在局灶性结节性增生与肝细胞腺瘤间存在显著差异,基于动脉期中、粗滤波图像均值、mpp和熵的模型鉴别肝细胞腺瘤的AUROC最大,为0.824。
研究设计与样本
- 回顾性、经IRB批准的单中心研究,2008年至2017年病历检索纳入48例患者70个肝细胞腺瘤和50例患者62个局灶性结节性增生,所有病灶经组织学证实并有术前增强CT图像;采用肝脏动脉期和门静脉期图像,使用商用研究软件TexRAD提取纹理特征。
诊断标准与关键数值
- 动脉期未滤波图像中局灶性结节性增生的均值、mpp和偏度显著高于肝细胞腺瘤(p≤0.007);动脉期滤波分析中标准差、熵和mpp在两组间有显著差异(p≤0.006);门静脉期未滤波图像中局灶性结节性增生的均值、mpp和偏度与肝细胞腺瘤有显著差异(p≤0.001),滤波图像中局灶性结节性增生的熵和峰度显著更高(p≤0.018);基于动脉期中、粗滤波图像均值、mpp和熵的模型鉴别肝细胞腺瘤的AUROC为0.824。
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 explore the value of CT texture analysis (CTTA) for differentiation of focal nodular hyperplasia (FNH) from hepatocellular adenoma (HCA) on contrast-enhanced CT (CECT).
METHODS: This is a retrospective, IRB-approved study conducted in a single institution. A search of the medical records between 2008 and 2017 revealed 48 patients with 70 HCA and 50 patients with 62 FNH. All lesions were histologically proven and with available pre-operative CECT imaging. Hepatic arterial phase (HAP) and portal venous phase (PVP) were used for CTTA. Textural features were extracted using a commercially available research software (TexRAD). The differences between textural parameters of FNH and HCA were assessed using the Mann-Whitney U test and the AUROC were calculated. CTTA parameters showing significant difference in rank sum test were used for binary logistic regression analysis. A p value < 0.05 was considered statistically significant.
RESULTS: On HAP images, mean, mpp, and skewness were significantly higher in FNH than in HCA on unfiltered images (p ≤ 0.007); SD, entropy, and mpp on filtered analysis (p ≤ 0.006). On PVP, mean, mpp, and skewness in FNH were significantly different from HCA (p ≤ 0.001) on unfiltered images, while entropy and kurtosis were significantly higher in FNH on filtered images (p ≤ 0.018). The multivariate logistic regression analysis indicated that the mean, mpp, and entropy of medium-level and coarse-level filtered images on HAP were independent predictors for the diagnosis of HCA and a model based on all these parameters showed the largest AUROC (0.824).
CONCLUSIONS: Multiple explored CTTA parameters are significantly different between FNH and HCA on CECT.
引用
- Cannella R, Borhani AA, Minervini MI, et al. Evaluation of texture analysis for the differential diagnosis of focal nodular hyperplasia from hepatocellular adenoma on contrast-enhanced CT images. Abdom Radiol (NY). 2019. PMID: 30267107. doi:10.1007/s00261-018-1788-5
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。