• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International ISA biomedical sciences instrumentation symposium;International Society of Automation;Annual Rocky Mountain bioengineering symposium >DIAGNOSIS OF AUTOIMMUNE DISEASES USING HEP-2 STAINING PATTERN AND LOCAL DERIVATIVE PATTERN FEATURES
【24h】

DIAGNOSIS OF AUTOIMMUNE DISEASES USING HEP-2 STAINING PATTERN AND LOCAL DERIVATIVE PATTERN FEATURES

机译：利用HEP-2染色模式和局部衍生模式特征诊断自身免疫性疾病

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Indirect Immunofluorescence (IIF) of Human Epithelial Type-2 (HEp-2) cells treated with blood serum can determine thepresence of various antinuclear antibodies. This leads to diagnosis of autoimmune diseases such as systemic lupuserythematosus, Sjogren’s syndrome, and rheumatoid arthritis. Although it is reliable, the subjective nature of interpretation inmanual IIF method gives rise to significant inter-observer variances. Hence, a computer aided system is necessary. In thiswork, an attempt has been made to classify HEp-2 staining patterns using Local Derivative pattern (LDP) features. Standardimages from a public domain database are used in this study. It consists of 1500 HEp-2 cell images belonging to five classesof staining patterns, namely centromere, coarse speckled, fine speckled, homogenous, and nucleolar. The images arepreprocessed to improve contrast using contrast stretching technique. Subsequently, nuclear particles are segmented usingOtsu thresholding and validated against ground truth provided in the dataset. LDP features along with global features such asarea, entropy and mean intensity are extracted from the segmented images. Subsequently, these features are used for thedifferentiation of texture patterns using SVM classifier with a polynomial kernel. The obtained results indicate that Otsubased thresholding after contrast stretching is able to segment nuclear particles in all the images. The extracted featuresincluding the LDP features prove to be useful in classifying HEp-2 staining pattern with an accuracy of 73.73%. As IIFmicroscopy using HEp-2 cells is the gold standard for autoimmune disease diagnosis, the proposed work seems to be highlyrelevant in a clinical setting.
机译：血清处理的人类2型上皮细胞（HEp-2）的间接免疫荧光（IIF）可以确定 存在各种抗核抗体。这导致诊断出自身免疫性疾病，例如系统性狼疮 红斑，干燥综合征，类风湿关节炎。尽管它是可靠的，但解释的主观性 手动IIF方法会导致观察者之间的显着差异。因此，计算机辅助系统是必要的。在这个 在这项工作中，已经尝试使用局部衍生特征码（LDP）功能对HEp-2染色特征码进行分类。标准 本研究使用来自公共领域数据库的图像。它由1500个属于五个类别的HEp-2细胞图像组成 染色模式，即着丝粒，粗斑点，细斑点，均质和核仁。图像是 使用对比度拉伸技术进行预处理以提高对比度。随后，使用 Otsu阈值化并针对数据集中提供的基本事实进行了验证。 LDP功能以及诸如以下的全局功能 从分割的图像中提取面积，熵和平均强度。随后，这些功能将用于 使用带有多项式核的SVM分类器区分纹理图案。获得的结果表明大津 对比拉伸后基于阈值的阈值处理能够分割所有图像中的核粒子。提取的特征 包括LDP特征在内的事实证明以73.73％的准确性对HEp-2染色模式进行分类是有用的。作为IIF 使用HEp-2细胞进行显微镜检查是诊断自身免疫性疾病的金标准，拟议的工作似乎非常 与临床环境有关。

著录项

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