MRI及影像组学评估不同分子亚型乳腺癌新辅助治疗疗效的研究进展  

Progress of MRI and Radiomics in predicting the response to neoadjuvant therapy for breast cancer in different molecular subtypes

作　　者：陈淑銮 车树楠 李静 CHEN Shuluan;CHE Shu'nan;LI Jing(Department of Diagnostic Radiology,National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital,Chinese Academy of Medical Sciences and Peking Union Medical College,Beijing 100021,China)

机构地区：[1]国家癌症中心/国家肿瘤临床医学研究中心/中国医学科学院北京协和医学院肿瘤医院影像诊断科,北京100021

出　　处：《磁共振成像》2023年第6期156-160,共5页Chinese Journal of Magnetic Resonance Imaging

基　　金：中国癌症基金会北京希望马拉松专项基金(编号:LC2018B08)。

摘　　要：新辅助治疗(neoadjuvant therapy, NAT)是乳腺癌综合治疗的重要组成部分。磁共振成像(magnetic resonance imaging, MRI)是NAT疗效评估的重要方法,但仍存在一定局限性,对不同分子亚型乳腺癌疗效评估的准确性亦存在差异,现有研究显示基于MRI的影像组学模型能够提高其预测效能。针对不同分子亚型乳腺癌,建立联合多参数MRI的影像组学及深度学习模型,可进一步提高预测效能,精准指导临床决策。本文将对MRI评估不同分子亚型乳腺癌NAT疗效的价值、联合影像组学及深度学习模型的预测效能以及面临的问题和挑战进行综述,旨在为下一步研究及临床实践提供参考。Neoadjuvant therapy(NAT)is an important part of comprehensive treatment in breast cancer.Magnetic resonance imaging(MRI)is a major method in predicting the response to NAT,but still has certain limitations and some differences in the accuracy of efficacy evaluation of different molecular subtypes of breast cancer.Existing researches show that the radiomics model based on MRI can improve prediction performance.Aiming at different molecular subtypes of breast cancer,the establishment of image omics and deep learning models combined with multi-parameter MRI can further improve the prediction efficiency and accurately guide clinical decision-making.In this paper,the value of MRI in evaluating NAT efficacy of different molecular subtypes of breast cancer,the predictive efficacy of combined imagomics and deep learning models,as well as the problems and challenges faced were reviewed,aiming to provide references for further research and clinical practice.

关 键 词：乳腺癌 分子亚型 新辅助治疗 疗效评价 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] R737.9[医药卫生—诊断学]