光学与光电技术, 2017, 15 (1): 13, 网络出版: 2017-02-23
血片自动扫描镜检中白细胞细胞核的快速分割方法
Quick Leukocyte Nucleus Segmentation Method in Blood Smear Automatic Scanning Microscopic Examination
白细胞核的快速分割 显微图像 彩色空间 分量差 白细胞计数 quick leukocyte nucleus segmentation microscopic images color space component difference leukocyte counting
摘要
血片镜检可以实现白细胞的分类计数,同时还能提供详细的白细胞形态等特征,有助于疾病的诊断。目前国内大多数医院白细胞检测的主要方法是人工镜检,但人工镜检依赖医务人员的工作经验,劳动强度大,检测效率低。因此提出一种基于RGB彩色空间分量差的白细胞细胞核的快速分割方法。通过显微镜分析人体外周血液涂片的显微图像,发现白细胞细胞核区域的B分量和G分量的差值明显比其他区域大,可以通过一个简单8 bit的B-G运算,来实现五类白细胞细胞核的快速分割,白细胞细胞核的平均分割时间为0.26 ms,体现了较好的鲁棒性和实时性。该方法成功应用到白细胞的实时在线自动扫描镜检中,提高了镜检的效率。
Abstract
Microscopic examination of the blood smear can realize the classification and counting of leukocyte, and it can provide leukocyte detailed features such as morphology feature, and so on. It is helpful for diagnosis. Presently, manual inspection is still regarded as the main leukocyte detection method in the most of hospitals. Manual inspection is low efficiency and labour-intensive, and its accuracy is impacted easily by experience of medical workers. A quick leukocyte nucleus segmentation method based on the component difference in RGB color space is proposed. By analyzing the captured microscopic images of the peripheral blood smears from the auto-scanning microscope, it is found that the difference values between B component and G component in the regions of the leukocyte nuclei are much bigger than those in the other regions, the 8 bit subtraction operation B-G can realize the nucleus segmentation for the five types of leukocyte with a quick speed. The average segmentation time consumption for each leukocyte is 0.26 ms. It has good robustness and real-time. The proposed method can be applied in the real-time peripheral blood smear auto-scanning microscopic examination successfully. It improves the microscopy examination efficiency.<收稿日期:>2016-06-20<收到修改稿日期:>2016-07-25
王朝霞, 曹益平. 血片自动扫描镜检中白细胞细胞核的快速分割方法[J]. 光学与光电技术, 2017, 15(1): 13. WANG Zhao-xia, CAO Yi-ping. Quick Leukocyte Nucleus Segmentation Method in Blood Smear Automatic Scanning Microscopic Examination[J]. OPTICS & OPTOELECTRONIC TECHNOLOGY, 2017, 15(1): 13.