基于Sonazoid超声造影库普弗期表现术前预测肝细胞癌Ki-67水平的影像组学研究

Preoperative prediction of Ki-67 level in hepatocellular carcinoma based on radiomics signatures during Kupffer phase of Sonazoid contrast enhanced ultrasound

目的基于Sonazoid超声造影(CEUS)库普弗期特征构建影像组学预测模型, 探讨其在术前预测肝细胞癌(HCC)的核增殖抗原蛋白67(Ki-67)水平中的价值。方法 2020年10月至2021年8月前瞻性地纳入复旦大学附属中山医院经手术及病理证实的HCC且术前1周进行过Sonazoid CEUS检查的患者, 分别从灰阶图像及库普弗期图像的肿瘤区域提取、筛选特征并分别构建影像组学预测模型, 以病理及免疫组化结果为金标准, 比较不同模型预测Ki-67水平的效能。结果共有50例经病理及免疫组化证实的HCC病灶纳入研究, 其中24例Ki-67高水平(>20%), 26例Ki-67低水平(≤20 %)。根据灰阶图像及库普弗期图像特征分别构建HCC病灶Ki-67水平影像组学预测模型, 发现基于库普弗期图像的影像组学模型较灰阶图像影像组学模型有着显著更高的ROC曲线下面积(0.753比0.535, P=0.017)、准确性(0.720比0.580, P=0.023)和敏感性(0.458比0.250, P=0.043)。校准曲线显示基于库普弗期影像组学特征评分较灰阶影像组学评分与实际观测的Ki-67指数有更好的一致性。结论基于Sonazoid CEUS库普弗期特征建立的影像组学模型, 是一种无创性术前预测HCC病灶Ki-67表达水平的潜在方法。

Objective To evaluate the value of Sonazoid contrast enhanced ultrasound(CEUS)in preoperative prediction of proliferating cell nuclear antigen 67(Ki-67)level of hepatocellular carcinoma(HCC)by establishing predictive model based on radiomics features of Kupffer phase.Methods From October 2020 to August 2021,patients with histologically confirmed HCC lesion and who underwent Sonazoid CEUS examination 1 week before surgery were prospectively enrolled.The radiomics signatures were extracted from the whole tumor region on gray scale images and Kupffer phase images.Two predictive radiomics models were constructed using radiomic method.The predictive performance of 2 models was compared.Results A total of 50 patients with histologically confirmed single HCC lesions were prospectively enrolled in this study.Among them,histological results revealed 24 HCC lesions with high level representation of Ki-67(>20%)and 26 HCC lesions with low level representation of Ki-67(≤20%).Two radiomics predictive models were established based on gray scale images and Kupffer phase images respectively.While compared with model based on B-mode ultrasound images,model based on Kupffer phase images showed significantly higher area under receiver operating characteristic curve(0.753 vs 0.535,P=0.017),accuracy(0.720 vs 0.580,P=0.023)and sensitivity(0.458 vs 0.250,P=0.043).Calibration plot indicated that Kupffer phase model showed better consistency with the actual Ki-67 level than gray scale model.Conclusions The radiomics model based on Kupffer phase features of Sonazoid CEUS is a preoperative and noninvasive prediction the presentation level of Ki-67 in HCC lesions.