[1]潘子妍,邢素霞,逄键梁,等.基于多特征融合与XGBoost的肺结节检测[J].中国医学物理学杂志,2021,38(11):1371-1376.[doi:DOI:10.3969/j.issn.1005-202X.2021.11.010]
　PAN Ziyan,XING Suxia,PANG Jianliang,et al.Lung nodule detection based on multi-feature fusion and XGBoost[J].Chinese Journal of Medical Physics,2021,38(11):1371-1376.[doi:DOI:10.3969/j.issn.1005-202X.2021.11.010]
点击复制

基于多特征融合与XGBoost的肺结节检测()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
38卷
期数:
2021年第11期
页码:
1371-1376
栏目:
医学影像物理
出版日期:
2021-11-26

文章信息/Info

Title:
Lung nodule detection based on multi-feature fusion and XGBoost
文章编号:
1005-202X（2021）11-1371-06
作者:
潘子妍1; 邢素霞1; 逄键梁2; 申楠1; 王瑜1; 刘子骄1; 鞠子涵1
1.北京工商大学人工智能学院， 北京 100048； 2.空军特色医学中心， 北京 100048
Author(s):
PAN Ziyan1;  XING Suxia1;  PANG Jianliang2;  SHEN Nan1;  WANG Yu1;  LIU Zijiao1;  JU Zihan1
1. School of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China 2. Air Force Medical Center, Beijing 100048, China
关键词:
肺结节检测; 基于超分辨率重建的卷积神经网络; 特征融合; 词袋模型; XGBoost
Keywords:
Keywords: lung nodule detection super-resolution convolutional neural network feature fusion bag-of-words model XGBoost
分类号:
R318；TP301.6
DOI:
DOI:10.3969/j.issn.1005-202X.2021.11.010
文献标志码:
A
摘要:
为了提高肺结节检测的精确度和效率，提出一种基于多特征融合和XGBoost的肺结节检测模型。首先采用阈值分割与形态学运算，获得候选结节区域；然后通过基于超分辨率重建的卷积神经网络进行候选结节的特征增强；其次采用快速鲁棒特征、灰度共生矩阵、灰度不变矩的提取方法获得候选结节的局部与全局的多种特征，采用词袋模型进行降维并融合；最后利用XGBoost-决策树分类模型去除假阳性结节，完成肺结节的检测。在LIDC-IDRI数据上进行的实验表明该模型能达到97.87%的准确率和97.92%的召回率。该模型可用于辅助医生进行肺结节诊断，具有一定的临床应用价值。
Abstract:
Abstract: A lung nodule detection model based on multi-feature fusion and XGBoost is proposed for improving the accuracy and efficiency of lung nodule detection. After candidate nodule regions are obtained by threshold segmentation and morphological operations, the features of candidate nodules are enhanced by super-resolution convolutional neural network. Then several methods including speeded up robust features, gray-level co-occurrence matrix and gray-level invariant moments are used to extract various local and global features of candidate nodules, and bag-of-words model is utilized for dimensionality reduction and fusion. Finally, XGBoost-decision tree classification model is used to remove false positive nodules and complete the detection of lung nodules. The experiments on LIDC-IDRI data show that the model can achieve an accuracy of 97.87% and a recall rate of 97.92%. The proposed model can be used to assist doctors in the diagnosis of lung nodules and has certain clinical application value.

相似文献/References:

[1]田吉,杨萍,刘佳,等.改进YOLOv5的肺结节检测算法[J].中国医学物理学杂志,2025,42(1):43.[doi:DOI:10.3969/j.issn.1005-202X.2025.01.007]
　TIAN Ji,YANG Ping,LIU Jia,et al.Lung nodule detection algorithm based on improved YOLOv5[J].Chinese Journal of Medical Physics,2025,42(11):43.[doi:DOI:10.3969/j.issn.1005-202X.2025.01.007]

备注/Memo

备注/Memo:
【收稿日期】2021-06-10 【基金项目】国家自然科学基金（61671028）；首都卫生发展科研专项（首发2018-2-5122）；北京市自然科学基金-北京市教育委员会科技计划重点项目（KZ202110011015） 【作者简介】潘子妍，在读研究生，主要从事图像处理、机器学习方面的研究，E-mail: panzy11751@163.com 【通信作者】邢素霞，博士，副教授，主要从事图像处理与嵌入式系统的研究，E-mail: xingsuxia@163.com
更新日期/Last Update: 2021-11-27