北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (4): 51-57.doi: 10.13190/j.jbupt.2022-069

• 智慧医疗 • 上一篇    下一篇

一种放射组学分析的海马硬化自动诊断方法

欧阳莫微1, 康桂霞1, 王开亮2, 王亚明2   

  1. 1. 北京邮电大学 信息与通信工程学院, 北京 100876;
    2. 首都医科大学 宣武医院, 北京 100053
  • 收稿日期:2022-03-28 出版日期:2022-08-28 发布日期:2022-06-26
  • 通讯作者: 康桂霞(1972—),女,教授,博士生导师,邮箱:gxkang@bupt.edu.cn。 E-mail:gxkang@bupt.edu.cn
  • 作者简介:欧阳莫微(1997—),女,硕士生。
  • 基金资助:
    国家自然科学基金项目(82030037);北京邮电大学校行动计划项目(2020XD-A06-1)

Automated Hippocampal Sclerosis Detection Method with Radiomics Analysis

OUYANG Mowei1, KANG Guixia1, WANG Kailiang2, WANG Yaming2   

  1. 1. School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China;
    2. Xuanwu Hospital, Capital Medical University, Beijing 100053, China
  • Received:2022-03-28 Online:2022-08-28 Published:2022-06-26

摘要: 为深入挖掘具有海马硬化病变表征能力的放射组学特征,提升海马硬化检测的精度,提出了一种结合放射组学分析的自动诊断方法,通过将放射组学特征与小波变换、高斯拉普拉斯算子滤波算法相结合,提取不同滤波图像中海马体感兴趣区域的放射组学特征并用于识别海马硬化,挖掘敏感度较高的放射组学特征。首先对受试样本的T1图像进行预处理和多种滤波处理,基于原始图像和滤波图像提取放射组学特征;然后依次使用双样本T检验、特征相关性分析法对放射组学特征降维;最后利用这些特征构建海马硬化的检测模型。实验结果显示,基于放射组学特征构建的海马硬化检测模型可以有效地辅助识别海马硬化病灶;用基于小波变换的方法提取放射组学特征能够使自动诊断模型的检测效果最优,在实际数据集上硬化海马的检出率可达到97.7%。

关键词: 放射组学, 海马硬化, 机器学习, 小波变换

Abstract: Based on radiomics analysis, an automatic diagnosis method of hippocampal sclerosis is proposed to find radiomics features to characterize hippocampal sclerosis lesions and improve the detection accuracy of hippocampal sclerosis. Combined with the wavelet transform and Laplacian of Gaussian filtering algorithm, the radiomics features in the region of hippocampus were extracted from several filtered images to obtain highly sensitive features and identify hippocampal sclerosis. First, pre-processing and filtering processes are applied to T1 image of tested samples, and radiomic features are extracted from the original image and the filtered image. Then, the student-T test and feature correlation analysis are used to reduce the dimension of the radiomic features. Finaly, hippocampal sclerosis detection models are built based on these features. The experimental results show that the hippocampal sclerosis detection model based on radiomics features can effectively assist the identification of hippocampal sclerosis lesions, and the radiomics features extracted from wavelet transform image have the best detection performance onthe automatic diagnosis model with a detection accuracy of 97.7% for the actual dataset.

Key words: radiomics, hippocampal sclerosis, machine learning, wavelet transform

中图分类号: