Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (5): 1485-1489.DOI: 10.11772/j.issn.1001-9081.2018102205

• Virtual reality and multimedia computing • Previous Articles     Next Articles

Segmentation of nasopharyngeal neoplasms based on random forest feature selection algorithm

LI Xian1, WANG Yan2, LUO Yong3, ZHOU Jiliu2   

  1. 1. College of Electronics and Information Engineering, Sichuan University, Chengdu Sichuan 610065, China;
    2. College of Computer Science, Sichuan University, Chengdu Sichuan 610065, China;
    3. Department of Oncology, West China Hospital of Sichuan University, Chengdu Sichuan 610041, China
  • Received:2018-11-02 Revised:2018-12-17 Online:2019-05-10 Published:2019-05-14
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61701324).

基于随机森林特征选择算法的鼻咽肿瘤分割

李鲜1, 王艳2, 罗勇3, 周激流2   

  1. 1. 四川大学 电子信息学院, 成都 610065;
    2. 四川大学 计算机学院, 成都 610065;
    3. 四川大学华西医院 肿瘤科, 成都 610041
  • 通讯作者: 王艳
  • 作者简介:李鲜(1994-),男,江西萍乡人,硕士研究生,主要研究方向:医学图像处理;王艳(1986-),女,宁夏平罗人,讲师,博士,主要研究方向:医学图像处理、模式识别;罗勇(1980-),男,四川成都人,主治医师,博士,主要研究方向:医学影像分析、肿瘤诊断;周激流(1963-),男,四川成都人,教授,博士生导师,博士,主要研究方向:数字图像处理、无线传感网络、分数阶微积分。
  • 基金资助:
    国家自然科学基金资助项目(61701324)。

Abstract: Due to the low grey-level contrast and blurred boundaries of organs in medical images, a Random Forest (RF) feature selection algorithm was proposed to segment nasopharyngeal neoplasms MR images. Firstly, gray-level, texture and geometry information was extracted from nasopharyngeal neoplasms images to construct a random forest classifier. Then, feature importances were measured by the random forest, and the proposed feature selection method was applied to the original handcrafted feature set. Finally, the optimal feature subset obtained from the feature selection process was used to construct a new random forest classifier to make the final segmentation of the images. Experimental results show that the performances of the proposed algorithm are:dice coefficient 79.197%, accuracy 97.702%, sensitivity 72.191%, and specificity 99.502%. By comparing with the conventional random forest based and Deep Convolution Neural Network (DCNN) based segmentation algorithms, it is clearly that the proposed feature selection algorithm can effectively extract useful information from the nasopharyngeal neoplasms MR images and improve the segmentation accuracy of nasopharyngeal neoplasms under small sample circumstance.

Key words: nasopharyngeal neoplasms, random forest, feature importance, feature selection, optimal feature subset

摘要: 针对医学图像中存在的灰度对比度低、器官组织边界模糊等问题,提出一种新的随机森林(RF)特征选择算法用于鼻咽肿瘤MR图像的分割。首先,充分提取图像的灰度、纹理、几何等特征信息用于构建一个初始的随机森林分类器;随后,结合随机森林特征重要性度量,将改进的特征选择方法应用于原始手工特征集;最终,以得到的最优特征子集构建新的随机森林分类器对测试图像进行分割。实验结果表明,该算法对鼻咽肿瘤的分割精度为:Dice系数79.197%,Acc准确率97.702%,Sen敏感度72.191%,Sp特异性99.502%。通过与基于传统随机森林和基于深度卷积神经网络(DCNN)的分割算法对比可知,所提特征选择算法能有效提取鼻咽肿瘤MR图像中的有用信息,并较大程度地提升小样本情况下鼻咽肿瘤的分割精度。

关键词: 鼻咽肿瘤, 随机森林, 特征重要性, 特征选择, 最优特征子集

CLC Number: