Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (17): 22-34.DOI: 10.3778/j.issn.1002-8331.2210-0435

• Research Hotspots and Reviews • Previous Articles     Next Articles

Review of Application of Machine Learning in Radiomics Analysis

LU Huimin, XUE Han1, WANG Yilong, WANG Guizeng, SANG Pengcheng   

  1. 1.College of Computer Science and Engineering, Changchun University of Technology, Changchun 130102, China
    2.College of Mathematics and Statistics, Changchun University of Technology, Changchun 130012, China
    3.The First Hospital of Jilin University, Changchun 130061, China
  • Online:2023-09-01 Published:2023-09-01

机器学习在影像组学分析中的应用综述

鲁慧民,薛涵,王奕龙,王贵增,桑鹏程   

  1. 1.长春工业大学 计算机科学与工程学院,长春 130102
    2.长春工业大学 数学与统计学院,长春 130012
    3.吉林大学第一医院,长春 130061

Abstract: Radiomics is a technique for quantitatively extracting features from standard medical images. The construction of predictive or diagnostic models with the assistance of machine learning enables data to be extracted and applied in clinical decision support systems to improve diagnostic accuracy, which has been widely used in tumor staging, cancer detection, survival analysis and other tasks. The application and research progress of machine learning in radiomics analysis are reviewed. The applicability and limitations of machine learning algorithms in each stage of radiomics analysis are emphatically discussed, and the representative algorithms are thoroughly sorted out and analyzed in terms of principles and application effects. The evaluation methods to the work of each stage in the radiomics analysis are comprehensively introduced. The publicly available medical image datasets and software toolkits for radiomics feature extraction are organized. Finally, the future development of machine learning in radiomics is discussed.

Key words: machine learning, radiomics, feature engineering, deep learning, medical images

摘要: 影像组学(radiomics)是一种从标准医学影像中定量地提取特征的技术。借助机器学习构建预测或诊断模型,能够在临床决策支持系统中提取和应用数据,以提高诊断的准确性,该技术在肿瘤分期、癌症检测、生存分析等任务中得到了广泛的应用。回顾了机器学习在影像组学分析中的相关应用和研究进展;重点论述了机器学习算法在影像组学分析中各阶段的适用性和局限性,在原理和应用效果上对代表性算法进行了深入梳理与分析;综合介绍了在影像组学分析中对各阶段工作的评估方法;整理了公开的医学影像数据集以及用于影像组学特征提取的软件与工具包;最后讨论了机器学习在影像组学中的未来发展。

关键词: 机器学习, 影像组学, 特征工程, 深度学习, 医学影像