摘要
随着人工智能技术与精准医学概念的兴起,传统影像学诊断模式逐渐难以满足个性化医疗活动的需要。通过高通量定量特征提取方法,将图像转换为可挖掘的数据,利用机器学习算法对数据进行分析以提供临床决策支持的影像组学受到了广泛关注。现有不少研究尝试将影像组学应用于骨肿瘤临床诊疗中。笔者将着重从应用角度对影像组学技术方法作简要概述,详细介绍影像组学在骨肿瘤诊断鉴别诊断、分级分型、预后预测及基因分析方面的研究进展,并提出目前所面临的挑战及未来发展方向。
With the development of artificial intelligence technology and the concept of precision medicine,the traditional imaging diagnosis model is gradually difficult to meet the needs of personalized medical activities.Radiomics,which uses high-throughput quantitative feature extraction methods to convert images into minable data and analyzes the data using machine learning algorithms to provide clinical decision support,has received widespread attention.Many existing studies have tried to apply radiomics to the clinical diagnosis and treatment of bone tumors.This article will focus on a brief overview of radiomics techniques from an application perspective,detailing the progress of radiomics studies in diagnosis and differential diagnosis,typing and stage,prognosis prediction and genetic analysis of bone tumor,and presenting the current challenges and future development direction.
作者
刘珂
张恩龙
王奇政
陈永晔
张家慧
郎宁
LIU Ke;ZHANG Enlong;WANG Qizheng;CHEN Yongye;ZHANG Jiahui;LANG Ning(Department of Radiology,Peking University Third Hospital,Beijing 100191,China;Department of Radiology,Peking University International Hospital,Beijing 102206,China)
出处
《磁共振成像》
CAS
2020年第10期957-960,共4页
Chinese Journal of Magnetic Resonance Imaging
基金
国家自然科学基金(编号:81971578,81701648)
北京市自然科学基金(编号:Z190020)。
关键词
骨肿瘤
影像组学
特征提取
机器学习
bone tumor
radiomics
feature extraction
machine learning