...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>The Analyst >Cluster analysis of infrared spectra of rabbit cortical bone samples during maturation and growth
【24h】

Cluster analysis of infrared spectra of rabbit cortical bone samples during maturation and growth

机译：兔皮质骨样品成熟和生长过程中红外光谱的聚类分析

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Bone consists of an organic and an inorganic matrix. During development, bone undergoes changes innits composition and structure. In this study we apply three different cluster analysis algorithmsn[K-means (KM), fuzzy C-means (FCM) and hierarchical clustering (HCA)], and discriminant analysisn(DA) on infrared spectroscopic data from developing cortical bone with the aim of comparing theirnability to correctly classify the samples into different age groups. Cortical bone samples from thenmid-diaphysis of the humerus of New Zealand white rabbits from three different maturation stagesn(newborn (NB), immature (11 days–1 month old), mature (3–6 months old)) were used. Three clustersnwere obtained by KM, FCM and HCA methods on different spectral regions (amide I, phosphate andncarbonate). The newborn samples were well separated (71–100% correct classifications) from the othernage groups by all bone components. The mature samples (3–6 months old) were well separated (100%)nfrom those of other age groups by the carbonate spectral region, while by the phosphate and amidenI regions some samples were assigned to another group (43–71% correct classifications). The greatestnvariance in the results for all algorithms was observed in the amide I region. In general, FCM clusteringnperformed better than the other methods, and the overall error was lower. The discriminate analysisnresults showed that by combining the clustering results from all three spectral regions, the ability tonpredict the correct age group for all samples increased (from 29–86% to 77–91%). This study is the firstnto compare several clustering methods on infrared spectra of bone. Fuzzy C-means clusteringnperformed best, and its ability to study the degree of memberships of samples to each cluster might benbeneficial in future studies of medical diagnostics.
机译：骨骼由有机和无机基质组成。在发育过程中，骨骼发生变化，从而编织出成分和结构。在这项研究中，我们应用了三种不同的聚类分析算法n [K-均值（KM），模糊C均值（FCM）和层次聚类（HCA）]，以及判别分析n（DA），以开发皮质骨为目标的红外光谱数据比较其正确分类样本的能力。使用了来自三个不同成熟阶段（新生（NB），未成熟（11天至1个月大），成熟（3至6个月大））的新西兰白兔肱骨中骨干的皮质骨样本。通过KM，FCM和HCA方法在不同的光谱区域（酰胺I，磷酸盐和碳酸盐）获得了三个簇。新生儿样品的所有骨成分与其他组的分离良好（正确分类率为71-100％）。成熟样本（3–6个月大）通过碳酸盐光谱区域与其他年龄组的样本相距很远（100％）n，而通过磷酸盐和甲酰胺I区域则将一些样本分配到另一组（正确分类为43–71％） ）。在酰胺I区中观察到所有算法结果的最大方差。通常，FCM聚类的性能优于其他方法，并且总体误差较低。区分分析结果表明，通过结合所有三个光谱区域的聚类结果，该能力可以正确预测所有样品的正确年龄组（从29-86％增至77-91％）。这项研究是首次比较几种在骨骼红外光谱上的聚类方法。模糊C均值聚类的表现最佳，其研究样本对每个聚类的隶属度的能力可能会在未来的医学诊断研究中受益。

著录项

  • 来源
    《The Analyst》 |2010年第12期|p.3147-3155|共9页
  • 作者

    Yevgeniya Kobrina Mikael J. Turunen Simo Saarakkala Jukka S. Jurvelin Markku Hauta-Kasari and Hanna Isaksson;

  • 作者单位

    aDepartment of Physics and Mathematics, University of Eastern Finland,PO Box 1627, 70211 Kuopio, Finland. E-mail: hanna.isaksson@uef.fi;

    Tel: +358 40 355 2079bDepartment of Diagnostic Radiology, Institute of Diagnostics, Universityof Oulu, FinlandcSchool of Computing, University of Eastern Finland, Joensuu, Finland† This article is part of a themed issue on Optical Diagnosis. This issueincludes work presented at SPEC 2010 Shedding Light on Disease:Optical Diagnosis for the New Millennium, which was held inManchester, UK June 26th–July 1st 2010.;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号