Pixel-Classification-Based Reticulocyte Detection in Blood-Smear Microscopy Images
Pixel-Classification-Based Reticulocyte Detection in Blood-Smear Microscopy Images
复制标题
血涂片显微镜图像中基于像素分类的网织红细胞检测
DOI：
10.1115/1.4043919
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Yuanlong Deng
中科院分区：
文献类型：
--
作者：
Xiaopin Zhong;Junjia Guo;Yuanlong Deng
基于数字图像处理技术的网织红细胞识别和计数方法很少。本文提出了一种基于像素的血液显微图像网织红细胞识别方法。这种方法不仅解决了手动方法的缓慢性，而且在很大程度上消除了基于流动的方法对核酸的敏感性。关键是提取像素级特征。从RGB、HSI和LUV三个颜色空间中提取一个颜色特征。从YCbCr颜色空间的Cr通道中提取三个纹理特征，称为Gabor特征，灰度共生矩阵和局部对比度模式，形成六个特征。随后，比较了颜色和纹理的各种组合的识别效果，最终选择了Gabor纹理特征和LUV颜色特征的组合。然后，使用支持向量机（SVM）分类器对像素级特征进行分类，并检测RNA染色区域。基于该区域的位置、数量和面积，可以确定靶细胞是否是网织红细胞。该方法对网织红细胞的准确率为98.4%，召回率为98.0%，F1测量值为0.982，表明其对自动化设备的有用性。
Methods for reticulocyte identification and counting based on digital image processing technology are rare. In this paper, we proposed a pixel-based reticulocyte identification method for blood micrographs. This approach not only addresses slowness of manual methods but also largely alleviates the susceptibility of flow-based methods to nucleic acid. The key is to extract pixel-level features. One color feature is extracted from three color spaces, namely RGB, HSI, and LUV. Three texture features called Gabor features, the gray-level co-occurrence matrix, and local contrast pattern are extracted from the Cr channel of the YCbCr color space, forming six features. Subsequently, the recognition effects of each combination of color and texture were compared, and the combination of Gabor texture features and LUV color features was selected. Then, a support vector machine (SVM) classifier was used to classify the pixel-level features, and the RNA-staining area was detected. Based on the location, number, and area of the region, whether the target cell is reticulocyte can be determined. The precision of this method for reticulocytes was 98.4%, recall was 98.0%, and the F1 measure was 0.982, indicating its usefulness for automation equipment.
登录
查看更多内容
DOI：
--
发表时间：
2007-10
期刊：
Klinicheskaia laboratornaia diagnostika
影响因子：
--
作者：
Piatnitskiĭ Am;Medovyĭ Vs;Parpara Aa
通讯作者：
Piatnitskiĭ Am;Medovyĭ Vs;Parpara Aa
DOI：
--
发表时间：
2008
期刊：
--
影响因子：
--
作者：
Chih-Wei Hsu;Chih-Chung Chang-;Chih-Jen Lin
通讯作者：
Chih-Wei Hsu;Chih-Chung Chang-;Chih-Jen Lin
DOI：
10.1109/tsmc.1973.5408578
发表时间：
1970-12
期刊：
IEEE Trans. Syst. Man Cybern.
影响因子：
--
作者：
R. Gran
通讯作者：
R. Gran
DOI：
10.1109/grc.2006.1635839
发表时间：
2006-05
期刊：
2006 IEEE International Conference on Granular Computing
影响因子：
--
作者：
Yuchun Tang;Yanqing Zhang
通讯作者：
Yuchun Tang;Yanqing Zhang
DOI：
10.1016/j.neunet.2012.04.012
发表时间：
2012-09
期刊：
Neural networks : the official journal of the International Neural Network Society
影响因子：
--
作者：
Xiang-yang Wang;Xian-Jin Zhang;Hongying Yang;Juan Bu
通讯作者：
Xiang-yang Wang;Xian-Jin Zhang;Hongying Yang;Juan Bu