基于多模态MRI影像组学与深度学习的脑胶质瘤诊断及预后预测研究进展  

Diagnosis and prognosis prediction of glioma based on multimodal MRI radiomics and deep learning

作　　者：魏焕焕 杨燕 付芳芳[2] 高海燕 陈丽娟 吴亚平 白岩[2] 余璇 王梅云[2] WEI Huanhuan;YANG Yan;FU Fangfang;GAO Haiyan;CHEN Lijuan;WU Yaping;BAI Yan;YU Xuan;WANG Meiyun(Department of Imagingy,People's Hospital of Zhengzhou University,Zhengzhou 450003,China;Department of Imagingy,Henan Provincial People's Hospital,Zhengzhou 450003,China)

机构地区：[1]郑州大学人民医院影像科,郑州450003 [2]河南省人民医院影像科,郑州450003

出　　处：《磁共振成像》2023年第5期175-180,共6页Chinese Journal of Magnetic Resonance Imaging

基　　金：河南省自然科学基金青年项目(编号:212300410240);河南省科技攻关项目(编号:SBGJ202101002)。

摘　　要：脑胶质瘤是中枢神经系统最常见的原发性恶性肿瘤,其病程进展快、预后差,组织病理学分类/分级和分子表型信息的不同导致了胶质瘤的多样性及难治性。磁共振波谱成像(magnetic resonance spectroscopy, MRS)、磁共振指纹成像(magnetic resonance fingerprinting, MRF)、化学交换饱和转移(amide proton transfer, APT)、扩散加权成像(diffusion weighted imaging, DWI)、扩散张量成像(diffusion tensor imaging, DTI)、扩散峰度成像(diffusion kurtosis imaging,DKI)等多模态MRI技术能从多种角度为脑胶质瘤的鉴别诊断及治疗效果提供重要信息。此外,影像组学与深度学习技术的蓬勃发展为深入挖掘影像学数据提供了强有力的工具。联合影像组学与深度学习计算机辅助诊断技术可实现对脑胶质瘤更客观准确地评估分析,拓展MRI技术的临床应用价值。本文探讨了基于MRS、MRF、APT、DWI、DTI、DKI等多模态MRI技术影像组学与深度学习的脑胶质瘤诊断及预后预测研究现状,以期为临床术前评估脑胶质瘤提供参考和借鉴。Glioma is the most common primary malignant tumor of the central nervous system,which has a rapid progression and poor prognosis.Different histopathological classification/grading and molecular phenotype information lead to the diversity and refractory of glioma.Multimodality MRI techniques such as magnetic resonance spectroscopy(MRS),magnetic resonance fingerprint imaging(MRF),chemical exchange saturation transfer(APT),diffusion-weighted imaging(DWI),diffusion tensor imaging(DTI),and diffusion kurtosis imaging(DKI)can provide information for glioma assessment from a variety of perspectives,and combined artificial intelligence computer-assisted diagnostic techniques can achieve more objective and accurate evaluation and analysis of gliomas and expand the clinical application value of MR techniques.In this paper,the research status of the diagnosis and prognosis prediction of glioma based on multimodal magnetic resonance techniques such as MRS,MRF,APT,DWI,DTI,DKI and radiomics and deep learning were discussed,in order to provide reference for the preoperative evaluation of glioma.

关 键 词：脑胶质瘤 磁共振成像 多模态磁共振成像 影像组学 深度学习 诊断 预后预测 

分 类 号：R445.2[医药卫生—影像医学与核医学] R730.264[医药卫生—诊断学]