肺癌CT图像特征的ISODATA模糊聚类分析  被引量:1

Fuzzy Cluster Analysis Based on CT Image Features of Lung Cancer

在线阅读下载全文

作  者:金剑[1,3] 宋长钰 张峰 顾燃 JIN Jian;SONG Chang-yu;ZHANG Feng;GU Ran(School of Economics,Hebei University,Baoding 071002,China;Health Science Center,Hebei University,Baoding 071002,China;Institute for Advanced Study of Yanzhao Culture,Hebei University,Baoding 071002,China;China Statistics Press,Beijing 100073,China)

机构地区:[1]河北大学经济学院,河北保定071002 [2]河北大学医学部,河北保定071002 [3]河北大学燕赵文化高等研究院,河北保定071002 [4]中国统计出版社,北京100073

出  处:《数理统计与管理》2021年第4期625-633,共9页Journal of Applied Statistics and Management

基  金:国家社科基金项目(19BTJ029)。

摘  要:针对肺癌早期所表现的医学征象,根据其特征进行分类,使医生在病变初期就能够对可疑病变做出分类。使用由56名肺癌患者组成的样本集,在MATLAB编程环境下,采用ISODATA模糊聚类方法,对关键的医学征象进行分析,将患者分类,反复迭代得到理想的聚类结果。结果显示,ISODATA模糊聚类算法可将孤立性肺结节肺癌CT图像特征相似的归为一类;样本集中的全部患者可分为3类。并进一步研究了肺部CT图像特征与肺癌诊断之间的关系,辅助医生更深刻地理解孤立性肺结节肺癌CT图像的医学特征,对肺癌的早期诊断及临床治疗具有十分重要的意义。According to the medical signs in the early stage of lung cancer,the classification is made according to its characteristics,so that the doctors can classify the suspicious lesions at the early stage.In the MATLAB programming environment,the method of ISODATA fuzzy clustering was adopted to analyze the key medical signs,56 lung cancer patients were composed into a sample set and classified,and the ideal clustering results were obtained through repeated iteration.The results show that ISODATA fuzzy clustering algorithm classifies the CT images of solitary pulmonary nodules lung cancer with similar features into one category,and the clustering results are 3 categories,which accord with the expected results.The relationship between CT features of lung and diagnosis of lung cancer was further studied,to assist doctors to better understand the medical characteristics of isolated lung nodules of lung cancer in the CT images,which is of great significance for the early diagnosis and clinical treatment of lung cancer.

关 键 词:图像识别 ISODATA算法 模糊聚类 肺癌 

分 类 号:O212[理学—概率论与数理统计]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象