术前MRI预测肝细胞癌微血管侵犯研究进展  

Research progress of preoperative prediction of microvascular invasion of hepatocellular carcinoma based on magnetic resonance imaging

作　　者：胡光超 张倩倩[2] 毛宁[2] 李乃选 HU Guangchao;ZHANG Qianqian;MAO Ning;LI Naixuan(School of Medical Imaging,Binzhou Medical University,Yantai 264000,China;Department of Radiology,Yantai Yuhuangding Hospital,Affiliated Hospital of Qingdao University,Yantai 264000,China;Department of Vascular Interventional Surgery,Yantai Affiliated Hospital of Binzhou Medical University,Yantai 264000,China)

机构地区：[1]滨州医学院医学影像学院,烟台264000 [2]青岛大学附属烟台毓璜顶医院影像科,烟台264000 [3]滨州医学院烟台附属医院介入血管外科,烟台264000

出　　处：《磁共振成像》2022年第2期159-162,共4页Chinese Journal of Magnetic Resonance Imaging

基　　金：山东省中医药科技发展计划项目(编号:2019-0501)。

摘　　要：肝细胞癌是全球常见的恶性肿瘤,最主要的治疗方法是手术切除肿瘤,但经常复发,很大一部分原因与微血管侵犯相关。因此,寻找一种无创的术前预测微血管侵犯的方法对于指导手术治疗、改善患者预后、提高患者生存率等具有重要意义。磁共振成像(magnetic resonance imaging,MRI)技术的多序列、多模态成像以及基于MRI的影像组学、深度学习技术的快速发展使得术前无创性地预测肝细胞癌的微血管侵犯成为可能并极具发展前景,本文将主要就此方面展开综述。Hepatocellular carcinoma(HCC)is a common malignant tumor in the world,the primary treatment of HCC is surgical resection,but recurrence after surgical treatment is common,a large part of the reason is related to microvascular invasion.Therefore,looking for a non-invasive method to predict microvascular invasion before operation is of great significance for guiding surgical treatment,improving the prognosis and improving the survival rate of patients.Multi-sequence,multimodal magnetic resonance imaging(MRI)and MRI-based radiomics and deep learning technology are developing rapidly,which makes preoperative non-invasive prediction of microvascular invasion in hepatocellular carcinoma possible and highly promising.This paper mainly reviewed in this respect.

关 键 词：肝细胞癌 微血管侵犯 磁共振成像 影像组学 深度学习 

分 类 号：R445.2[医药卫生—影像医学与核医学] R735.7[医药卫生—诊断学]