WO2014206376A1 - Method of classifying and counting white blood cells on basis of morphology - Google Patents
Method of classifying and counting white blood cells on basis of morphology Download PDFInfo
- Publication number
- WO2014206376A1 WO2014206376A1 PCT/CN2014/082868 CN2014082868W WO2014206376A1 WO 2014206376 A1 WO2014206376 A1 WO 2014206376A1 CN 2014082868 W CN2014082868 W CN 2014082868W WO 2014206376 A1 WO2014206376 A1 WO 2014206376A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- cells
- counting
- white blood
- regions
- image
- Prior art date
Links
- 210000000265 leukocyte Anatomy 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 title claims abstract description 15
- 210000004027 cell Anatomy 0.000 claims abstract description 59
- 210000004698 lymphocyte Anatomy 0.000 claims abstract description 20
- 210000003714 granulocyte Anatomy 0.000 claims abstract description 15
- 210000001616 monocyte Anatomy 0.000 claims abstract description 12
- 210000003979 eosinophil Anatomy 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 210000000440 neutrophil Anatomy 0.000 claims abstract description 5
- 210000005259 peripheral blood Anatomy 0.000 claims abstract description 5
- 239000011886 peripheral blood Substances 0.000 claims abstract description 5
- 230000008033 biological extinction Effects 0.000 claims abstract 2
- 230000000877 morphologic effect Effects 0.000 claims description 18
- 230000001086 cytosolic effect Effects 0.000 claims description 5
- 238000001000 micrograph Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 abstract description 3
- 238000010186 staining Methods 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 abstract 1
- 210000004940 nucleus Anatomy 0.000 description 11
- 230000004907 flux Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 210000005087 mononuclear cell Anatomy 0.000 description 3
- 238000003909 pattern recognition Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 210000003855 cell nucleus Anatomy 0.000 description 2
- 210000000805 cytoplasm Anatomy 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 210000003651 basophil Anatomy 0.000 description 1
- 210000000227 basophil cell of anterior lobe of hypophysis Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000000601 blood cell Anatomy 0.000 description 1
- 238000004820 blood count Methods 0.000 description 1
- 238000009534 blood test Methods 0.000 description 1
- 230000012292 cell migration Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000012303 cytoplasmic staining Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 210000003743 erythrocyte Anatomy 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010339 medical test Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012758 nuclear staining Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 210000004976 peripheral blood cell Anatomy 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/53—Immunoassay; Biospecific binding assay; Materials therefor
- G01N33/569—Immunoassay; Biospecific binding assay; Materials therefor for microorganisms, e.g. protozoa, bacteria, viruses
- G01N33/56966—Animal cells
- G01N33/56972—White blood cells
-
- G01N15/1433—
Definitions
- the invention belongs to the field of image processing, and particularly relates to a method for classifying and counting ⁇ ⁇ cells.
- the number of cells is only red blood cells] /, 800, in a cell image collection field of view, there will be about 1-5 cells, ⁇ cells are an important part of the body's defense system, according to the nuclear and The granules in the original form are divided into granulocytes, nucleated cells and lymphocytes. The granulocytes are further divided into eosinophils, basophils and neutrophils depending on the nature of the particles. The percentage of components of all types of cells and the total number of cells is an important item for blood tests. After Wright's staining, the types of 0 cells are distinguished according to the morphology of various mature cells under the microscope, such as nuclear staining, cytoplasmic staining, and karyotyping.
- the blood cell migration analyzer can quickly perform cell classification and counting, it has the following insurmountable shortcomings: 1 The cells have to pass through very small pores, which easily cause clogging; 2 The ability to identify abnormal cells is not conducive to clinical diagnosis; 3 The original physiological state of the sample cannot be saved. So it is necessary to find a way to effectively replace it.
- Pattern recognition is the most mature application of computational vision. It has been used in medical testing for the classification and counting of peripheral blood cells. By establishing a standard cell morphology library, the cells of the sample to be tested are compared with standard cells, and then classified. , to achieve the purpose of counting and counting cells.
- pattern recognition is a limitation in medical applications. Medical detection mainly detects abnormal conditions (abnormalities in the case of catastrophic conditions), and these abnormal states vary widely and are extremely diverse, while pattern recognition is Based on the comparison with the normal sample - the non-measurement comparison algorithm of the towel, it is impossible to judge or recognize the abnormality of diversity.
- micro-computer as the main body, using the relevant techniques of image processing and analysis, determining the cells through various characteristics of cells, and realizing the dynamic recognition and quantitative analysis of white blood cell microscopic images have important research significance.
- the present invention has been made to solve the above technical problems, and provides an image analysis based on a morphological parameter using a microcomputer as a processing core to quickly and efficiently quantify white blood cells.
- step (3) further analyzing the morphological parameters of the regional cells divided by the step (2), and accurately distinguishing the cells from the cells, lymphocytes, eosinophils and neutrophils;
- the nucleus pulp ratio is the abscissa
- the nucleus roundness is the ordinate
- the two morphological parameters of the 1 cell are two-dimensional scattergrams, which are divided into four regions.
- the regional cells are identified as lymphocyte regions, monocytes
- the total nucleus brightness is the abscissa
- the nucleus roundness is the ordinate
- the two morphological parameters of the lymphocyte region and the monocyte region are: two-dimensional scatter Figure, further distinguishing between lymphocyte nuclei and monocytes based on the corresponding microscopic images of the regions.
- step (3) the cell chromaticity is divided into red flux and blue flux, with red flux as abscissa, blue flux as ordinate to construct two-dimensional scattergram, and cells with more red component are acidophilic Granulocytes, therefore, further differentiate the granulocyte region into eosinophils and i ⁇ ' granulocytes.
- Nuclear area ⁇ The sum of pixels in the cell nucleus area.
- Cytoplasmic area Cytoplasmic IX: The sum of the pixels of the domain.
- Cell nucleoplasmic ratio nuclear area (nuclear area of pixel area) / cytoplasmic area (pixel area of cytoplasmic area).
- Roundness of the nucleus The roundness of the nucleus 3 ⁇ 4 characterizes the important characteristic parameters of the nucleus close to the circle.
- the roundness of the cell nucleus according to the present invention means the degree of variation (CV) or variance (Var) of the nuclear radius (the length of the line connecting the center of gravity to the boundary point) to indicate the roundness of the nucleus.
- Blue component (B) The amount of blue component in the cytoplasm.
- Red component (R) The amount of red component in the cytoplasm.
- the computer system analyzes and processes the image, and uses several simple morphological parameters to make a two-dimensional scatter plot. All the cells are presented in the form of a statistical graph. According to the corresponding microscopic image features of the region, the rapid and accurate classification of white blood cells is realized. Compared with the manual counting method, the white blood cell count overcomes the subjective factors, the steps are simple and rapid, and the diagnostic speed and accuracy are greatly improved.
- Fig. 1 is a two-dimensional scattergram of cell morphology parameters of leukocyte regions of the present invention.
- Figure 2 is a two-dimensional scattergram of the cell morphology parameters of the lymphocyte region of the present invention.
- Figure 4 is a two-dimensional scattergram of the morphological parameters of the granulocyte region of the present invention.
- Figure 5 is a microscopic image of lymphoid mononuclear cells of the present invention.
- Figure 6 is a microscopic image of lymphocytes of the present invention.
- Figure 7 is a microscopic image of a nuclear cell of the present invention.
- Figure 8 is a microscopic image of a large nuclear lymphocyte of the present invention.
- Figure 9 is a microscopic image of cells of the granulocyte region of the present invention.
- the total nuclear brightness is plotted on the abscissa, and the nuclear roundness (core radius variance) is plotted on the ordinate.
- a two-dimensional scattergram is constructed. According to the corresponding microscopic image of the regional cells, the lymphocyte region R1 and the single The nuclear cell region R2 is further accurately distinguished into lymphoid mononuclear cells R5, lymphocytes R7, monocytes R6, and large nuclear lymphocytes R8;
- the red component (R) is plotted on the abscissa and the blue component (B) is plotted on the ordinate.
- a two-dimensional scatter plot is constructed.
- the cells with more red components are eosinophils, and the granulocyte region R3 is further accurately distinguished.
- Figure 5 Figure 6, Figure 7, Figure 8, and Figure 9 correspond to microscopic images of lymphoid mononuclear cells R5, lymphocytes R7, monocytes R6, large nuclear lymphocytes R8, and granulocyte region R3 regions, respectively.
- the characteristics of the microscope image, ⁇ to identify the white blood cell species.
Abstract
A method of classifying and counting white blood cells on the basis of morphology is disclosed: Wright's staining a peripheral blood smear, then obtaining an image by means of a microscope; processing the image by means of a computer system, performing morphology parameter analysis on white blood cells, and differentiating said cells into four areas, i.e. a lymphocyte area, a monocyte area, a granulocyte area and a cell extinction area; performing morphology parameter analysis on the cells differentiated into said areas in step 1 to further differentiate said cells into monocytes, lymphocytes, eosinophil granulocytes and neutrophil granulocytes; and creating statistics on classification and count of differentiated white blood cell types. Use of a computer system to analyze and process an image, and utilization of several simple morphology parameters to generate a two-dimensional scatter plot, so as to represent the cells in the form of a statistical graph, allow for the accurate and rapid classification of white blood cells and for the automated counting of said cells. Compared to manual counting, the steps of the present invention are simple and quick and markedly increase the speed and accuracy of diagnosis.
Description
技术领域 Technical field
本发明属于图像处理领域, 具体涉及一种 ι ι细胞分类计数方法。 The invention belongs to the field of image processing, and particularly relates to a method for classifying and counting ι ι cells.
背景技术 Background technique
在血液样本中, 细胞数量只有红细胞的 ]/,800, 在一个细胞图像采集视野中, 会出现 1-5个左右的 |细胞, ^细胞是人体防御系统的重要组成部分, 根据包含在核与原形质中的 颗粒不同, 分为粒细胞, 核细胞和淋巴细胞, 粒细胞又根据颗粒的性质不同分为嗜酸性 粒细胞, 嗜碱性粒细胞和中性粒细胞。 各类 细胞与全体 细胞总数的成分百分比是血液 检查的重要项目, 经瑞氏染色后, 根据各种成熟 细胞在显微镜下核染色、 胞浆染色、 核 形等形态来区分 0细胞的种类。 In blood samples, the number of cells is only red blood cells] /, 800, in a cell image collection field of view, there will be about 1-5 cells, ^ cells are an important part of the body's defense system, according to the nuclear and The granules in the original form are divided into granulocytes, nucleated cells and lymphocytes. The granulocytes are further divided into eosinophils, basophils and neutrophils depending on the nature of the particles. The percentage of components of all types of cells and the total number of cells is an important item for blood tests. After Wright's staining, the types of 0 cells are distinguished according to the morphology of various mature cells under the microscope, such as nuclear staining, cytoplasmic staining, and karyotyping.
外周血血涂片瑞氏染色后对其中的 β细胞进行人工分类计数是目前临床检验中的常规 工作, 由于这些检测工作量大, 化验时间长, 过程繁琐, 工作效率低, 对细胞的分析受检 验医师经验和视觉分辨率的限制, 掺杂过多的主观因素, 缺少客观标准。 The manual classification and counting of β-cells in peripheral blood smears after Wright's staining is a routine work in clinical trials. Due to the large workload, long test time, cumbersome process and low work efficiency, the analysis of cells is affected. Test physician experience and limitations in visual resolution, excessive subjective factors, and lack of objective criteria.
血细胞向动分析仪虽然能快速地进行 细胞分类计数, 但是它存在以下难以克服的缺 点: ①细胞要通过很细的小孔, 容易造成堵塞; ②对于异常细胞没有能力识别, 不利于临 床诊断; ③不能保存样本的原始生理状态。 所以很有必要找一种有效替代它的方法。 Although the blood cell migration analyzer can quickly perform cell classification and counting, it has the following insurmountable shortcomings: 1 The cells have to pass through very small pores, which easily cause clogging; 2 The ability to identify abnormal cells is not conducive to clinical diagnosis; 3 The original physiological state of the sample cannot be saved. So it is necessary to find a way to effectively replace it.
模式识别作为计算视觉最成熟的应用, 目前已经运用于医学检测中的为外周血血细胞 分类计数, 通过建立标准的细胞形态库, 将待检样本的细胞与标准细胞进行比对, 然后进 行归类, 而达到对细胞进行分类计数的目的。 但模式识别在医学应用中, 宵其局限性, 医 学检测主要检测的是不正常状态(疾变情况下出现的异常情况),且这些异常状态千差成别, 极其多样性, 而模式识别是基于与正常样本比对 - 巾非测量性比较算法, 无法对多样性的 异常作为判断或识别。 Pattern recognition is the most mature application of computational vision. It has been used in medical testing for the classification and counting of peripheral blood cells. By establishing a standard cell morphology library, the cells of the sample to be tested are compared with standard cells, and then classified. , to achieve the purpose of counting and counting cells. However, pattern recognition is a limitation in medical applications. Medical detection mainly detects abnormal conditions (abnormalities in the case of catastrophic conditions), and these abnormal states vary widely and are extremely diverse, while pattern recognition is Based on the comparison with the normal sample - the non-measurement comparison algorithm of the towel, it is impossible to judge or recognize the abnormality of diversity.
因此, 以微型机为主体, 运用图像处理与分析的相关技术, 通过 细胞的各种特征确 定细胞, 实现白细胞显微图像的 ^动识别和定量分析, 具有重要的研究意义。 Therefore, using micro-computer as the main body, using the relevant techniques of image processing and analysis, determining the cells through various characteristics of cells, and realizing the dynamic recognition and quantitative analysis of white blood cell microscopic images have important research significance.
发明内容 Summary of the invention
发明 的: 本发明的 的是为了解决上述技术问题, 提供 · ·种以微型计算机为处理核 心, 基于形态 参数的图像分析, 做到快速高效准确定量分类白细胞。 SUMMARY OF THE INVENTION The present invention has been made to solve the above technical problems, and provides an image analysis based on a morphological parameter using a microcomputer as a processing core to quickly and efficiently quantify white blood cells.
技术方案: 本发明所述的 ·'种基于形态学分类计数白细胞的方法, 所述方法包括以下 步骤: Technical Solution: The method for counting white blood cells based on morphological classification according to the present invention, the method comprising the following steps:
( 1 ) 外周血涂片经瑞氏染色后, 利用显微镜采集图像;
为淋巴细胞 [x:、 单核细胞区、 粒细胞区及消亡细胞区四个区域; (1) After the peripheral blood smear is stained by Wright, the image is collected using a microscope; It is the four regions of lymphocytes [x:, monocyte region, granulocyte region and extinct cell region;
( 3 ) 进一步将歩骤 (2 ) 所划分出的区域细胞进行形态学参数分析, 将细胞进一歩精 确区分出準.核细胞、 淋巴细胞、 嗜酸性粒细胞和中性粒细胞; (3) further analyzing the morphological parameters of the regional cells divided by the step (2), and accurately distinguishing the cells from the cells, lymphocytes, eosinophils and neutrophils;
( 1 ) 将区分 来的 细胞种类进行分类计数统计。 (1) Sort and count the differentiated cell types.
步骤 (2 ) 中, 以细胞核浆比为横坐标, 细胞核圆度 (核半径变异系数) 为纵坐标, 对 1细胞的这两个形态学参数作二维散点图, 划分为四个区域, 根据区域相对应的显微镜图 像, 将区域细胞识别为淋巴细胞区、 单核细胞 |x:、 粒细胞区及消亡细胞区。 In step (2), the nucleus pulp ratio is the abscissa, the nucleus roundness (nuclear radius variation coefficient) is the ordinate, and the two morphological parameters of the 1 cell are two-dimensional scattergrams, which are divided into four regions. The regional cells are identified as lymphocyte regions, monocytes |x:, granulocyte regions, and extinct cell regions according to the corresponding microscopic images of the regions.
步骤 (3 ) 中, 以细胞核亮度总量为横坐标, 细胞核圆度 (核半径方差) 为纵坐标, 对 淋巴细胞区和单核细胞区细胞的这两个形态学参数作:二维散点图, 根据区域相对应的显微 镜图像, 进一步区分出淋巴细胞核和单核细胞。 In step (3), the total nucleus brightness is the abscissa, the nucleus roundness (the kernel radius variance) is the ordinate, and the two morphological parameters of the lymphocyte region and the monocyte region are: two-dimensional scatter Figure, further distinguishing between lymphocyte nuclei and monocytes based on the corresponding microscopic images of the regions.
步骤 (3 ) 中, 细胞色度分为红色通量和蓝色通量, 以红色通量为横坐标, 蓝色通量为 纵坐标构建二维散点图, 红色分量多的细胞为嗜酸粒细胞, 因此将粒细胞区进一步精确区 分为嗜酸粒细胞和 i†'性粒细胞。 In step (3), the cell chromaticity is divided into red flux and blue flux, with red flux as abscissa, blue flux as ordinate to construct two-dimensional scattergram, and cells with more red component are acidophilic Granulocytes, therefore, further differentiate the granulocyte region into eosinophils and i†' granulocytes.
形态学参数的含义, The meaning of morphological parameters,
细胞核面积: ^细胞胞核区域的像素总和。 Nuclear area: ^ The sum of pixels in the cell nucleus area.
细胞浆面积: 细胞胞浆 IX:域的像素总和。 Cytoplasmic area: Cytoplasmic IX: The sum of the pixels of the domain.
细胞核浆比: 细胞核面积(细胞核 域像素组成面积) /细胞浆面积 (细胞浆区域像素组 成面积)。 Cell nucleoplasmic ratio: nuclear area (nuclear area of pixel area) / cytoplasmic area (pixel area of cytoplasmic area).
细胞核圆度: 核圆度 ¾表征细胞核接近圆形的重要特征参数。 本发明所述细胞核圆度 是指用核半径 (重心点到边界点连线的长度) 的变异系数 (CV) 或者方差 (Var)的大小来表 示细胞核的圆度。 Roundness of the nucleus: The roundness of the nucleus 3⁄4 characterizes the important characteristic parameters of the nucleus close to the circle. The roundness of the cell nucleus according to the present invention means the degree of variation (CV) or variance (Var) of the nuclear radius (the length of the line connecting the center of gravity to the boundary point) to indicate the roundness of the nucleus.
蓝色分量 (B ) : 细胞浆内蓝色成分的量。 Blue component (B) : The amount of blue component in the cytoplasm.
红色分量 (R) : 细胞浆内红色成分的量。 Red component (R) : The amount of red component in the cytoplasm.
有益效果: 经计算机系统分析处理图像, 运用几种简单的形态 参数作出二维散点图, 将所有细胞以统计图的方式呈现, 根据区域相对应的显微镜图像特征, 实现了白细胞快速 精准分类, 白细胞计数 ^动化, 与人工计数方法相比, 克服了主观因素, 步骤简单快速, 诊断速度与准确性大幅提高。 Beneficial effects: The computer system analyzes and processes the image, and uses several simple morphological parameters to make a two-dimensional scatter plot. All the cells are presented in the form of a statistical graph. According to the corresponding microscopic image features of the region, the rapid and accurate classification of white blood cells is realized. Compared with the manual counting method, the white blood cell count overcomes the subjective factors, the steps are simple and rapid, and the diagnostic speed and accuracy are greatly improved.
附图说明 DRAWINGS
图 1是本发明的白细胞区域细胞形态学参数二维散点图。 BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a two-dimensional scattergram of cell morphology parameters of leukocyte regions of the present invention.
图 2是本发明的淋巴细胞区细胞形态学参数二维散点图。
。 图 4是本发明的粒细胞区细胞形态学参数二维散点图。 Figure 2 is a two-dimensional scattergram of the cell morphology parameters of the lymphocyte region of the present invention. . Figure 4 is a two-dimensional scattergram of the morphological parameters of the granulocyte region of the present invention.
图 5是本发明的淋巴样单核细胞的显微镜图像。 Figure 5 is a microscopic image of lymphoid mononuclear cells of the present invention.
图 6是本发明的淋巴细胞的显微镜图像。 Figure 6 is a microscopic image of lymphocytes of the present invention.
图 7是本发明的舉核细胞的显微镜图像。 Figure 7 is a microscopic image of a nuclear cell of the present invention.
图 8是本发明的大核淋巴细胞的显微镜图像。 Figure 8 is a microscopic image of a large nuclear lymphocyte of the present invention.
图 9是本发明的粒细胞区细胞的显微镜图像。 Figure 9 is a microscopic image of cells of the granulocyte region of the present invention.
具体实施方式 detailed description
为了加深对本发明的理解, 下面将结合实施例和附图对本发明作进一歩详述, 该实施 例仅用于解释本发明, 并不构成对本发明保护范围的限定。 The present invention will be described in detail with reference to the embodiments and the accompanying drawings, which are intended to be illustrative only, and not to limit the scope of the invention.
实施例 Example
( 1 ) 外周血涂片经瑞氏染色后, 利用显微镜采集图像; (1) After the peripheral blood smear is stained by Wright, the image is collected using a microscope;
( 2 ) 将图像输入计算机系统处理, 参见图 1, 对白细胞进行形态学参数分析, 以细胞 核浆比为横坐标, 构建 :维散点图, 细胞核圆度 (核半径变异系数) 为纵坐标, 构建二维 散点图, 根据区域细胞相对应的显微镜图像, 将 1: 细胞划区分为淋巴细胞区 Rl、 单核细胞 区 R2、 粒细胞区 R3及消亡细胞区 R4四个区域; (2) Input the image into the computer system for processing, see Figure 1, analyze the morphological parameters of the white blood cells, and construct the scatter plot with the nucleus pulp ratio as the abscissa. The nucleus roundness (nuclear radius variation coefficient) is the ordinate. Constructing a two-dimensional scattergram, according to the corresponding microscopic image of the regional cells, the 1: cell is divided into four regions: the lymphocyte region R1, the monocyte region R2, the granulocyte region R3, and the extinct cell region R4;
( 3 ) 进一步将步骤 (2 ) 所划分出的区域细胞淋巴细胞区 Rl、 单核细胞区 R2、 粒细胞 区 R3进行形态学参数分析; (3) further analyzing the morphological parameters of the regional lymphocyte region R1, the monocyte region R2, and the granulocyte region R3 divided by the step (2);
参见图 2和 3, 以细胞核亮度总量为横坐标, 细胞核圆度 (核半径方差) 为纵坐标,构 建二维散点图, 根据区域细胞相对应的显微镜图像, 将淋巴细胞区 R1和单核细胞区 R2进 一步精确区分为淋巴样单核细胞 R5、 淋巴细胞 R7、 单核细胞 R6、 大核淋巴细胞 R8; Referring to Figures 2 and 3, the total nuclear brightness is plotted on the abscissa, and the nuclear roundness (core radius variance) is plotted on the ordinate. A two-dimensional scattergram is constructed. According to the corresponding microscopic image of the regional cells, the lymphocyte region R1 and the single The nuclear cell region R2 is further accurately distinguished into lymphoid mononuclear cells R5, lymphocytes R7, monocytes R6, and large nuclear lymphocytes R8;
参见图 4, 以红色分量 (R ) 为横坐标, 蓝色分量 (B) 纵坐标, 构建二维散点图, 红色 分量多的细胞为嗜酸粒细胞, 将粒细胞区 R3进一步精确区分为嗜酸性粒细胞 R9和中性粒 细胞 RiO ; Referring to Figure 4, the red component (R) is plotted on the abscissa and the blue component (B) is plotted on the ordinate. A two-dimensional scatter plot is constructed. The cells with more red components are eosinophils, and the granulocyte region R3 is further accurately distinguished. Eosinophil R9 and neutrophil RiO;
图 5、 图 6、 图 7、 图 8、 图 9分别对应于淋巴样单核细胞 R5、 淋巴细胞 R7、 单核细胞 R6、 大核淋巴细胞 R8、 粒细胞区 R3区域细胞的显微镜图像,根据显微镜图像的特点, ^以 识别出白细胞种类。 Figure 5, Figure 6, Figure 7, Figure 8, and Figure 9 correspond to microscopic images of lymphoid mononuclear cells R5, lymphocytes R7, monocytes R6, large nuclear lymphocytes R8, and granulocyte region R3 regions, respectively. The characteristics of the microscope image, ^ to identify the white blood cell species.
( 4 ) 将区分出来的白细胞种类进行分类计数统计。 (4) Sort and count the differentiated white blood cell types.
以上所述仅为本发明的较佳实施例而已, 并不用以限制本发明, 凡在本发明的精祌和 原则之内, 所作的任何修改、 等同替换、 改进等, 均应包含在本发明的保护范围之内。
The above is only the preferred embodiment of the present invention, and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., which are included in the present invention, should be included in the present invention. Within the scope of protection.
Claims
1. 一种基于形态学分类计数 细胞的方法, 其特征在于, 包括以下歩骤: A method for counting cells based on morphological classification, comprising the following steps:
(1) 外周血涂片经瑞氏染色后, 禾 ij用显微镜采集图像; (1) After the peripheral blood smear is stained by Wright, ij ij collects the image with a microscope;
(2) 将歩骤 (1) 所采集的图像输入计算机系统, 对 1^细胞进行形态学参数分析, 将 ί'::【细胞划分为淋巴细胞区、 单核细胞区、 粒细胞区及消亡细胞区四个区域; (2) Input the image collected in step (1) into the computer system, analyze the morphological parameters of 1^ cells, and divide ί'::[ cells into lymphocyte regions, monocyte regions, granulocyte regions, and extinction. Four regions of the cell area;
(3) 将步骤 (2.) 所划分出的区域细胞进行形态学参数分析, 将细胞进一歩精确区分 出单核细胞、 淋巴细胞、 嗜酸性粒细胞和中性粒细胞; (3) Perform morphological parameter analysis on the regional cells divided in step (2.), and accurately distinguish cells from monocytes, lymphocytes, eosinophils and neutrophils;
( 4 ) 将区分出来的 1^1细胞种类进行分类计数统计。 (4) Sort and count the 1^1 cell types that are distinguished.
2. 根据权利要求 1所述的一种基于形态学分类计数 Ι ΐ细胞的方法, 其特征在于, 歩骤 2. A method for counting Ι cells based on morphological classification according to claim 1, wherein:
(2) 中所述的形态学参数为细胞核浆比和细胞核圆度。 The morphological parameters described in (2) are the nuclear to cytoplasmic ratio and the roundness of the nucleus.
3. 根据权利要求 1所述的一种基于形态学分类计数 细胞的方法, 其特征在于, 步骤 3. A method for counting cells based on morphological classification according to claim 1, wherein:
(3) 中所述的形态学参数为细胞核亮度总量、 细胞核圆度、 红色分量、 蓝色分量。 The morphological parameters described in (3) are the total amount of nuclear nucleus, the roundness of the nucleus, the red component, and the blue component.
4. 根据权利要求 1 3所述的一种旌于形态学分类计数 细胞的方法, 其特征在于, 以 所述形态学参数为横、 纵坐标对白细胞进行二维散点图的绘制, 根据散点图区域相对应的 显微镜图像特征, 从图中判断划分出不同种类的细胞区。
4. A method for morphologically classifying and counting cells according to claim 13, wherein the morphological parameters are used to draw a two-dimensional scattergram of white blood cells on the horizontal and vertical coordinates, according to the scatter. The characteristics of the microscope image corresponding to the dot pattern area are determined from the figure to distinguish different types of cell regions.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310254872.6A CN103345654B (en) | 2013-06-25 | 2013-06-25 | Method for differential counting of white blood cells based on morphology |
CN201310254872.6 | 2013-06-25 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014206376A1 true WO2014206376A1 (en) | 2014-12-31 |
Family
ID=49280449
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2014/082868 WO2014206376A1 (en) | 2013-06-25 | 2014-07-24 | Method of classifying and counting white blood cells on basis of morphology |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN103345654B (en) |
WO (1) | WO2014206376A1 (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103345654B (en) * | 2013-06-25 | 2017-02-08 | 苏州创继生物科技有限公司 | Method for differential counting of white blood cells based on morphology |
CN103745210B (en) * | 2014-01-28 | 2018-02-06 | 爱威科技股份有限公司 | A kind of leucocyte classification method and device |
CN104408738B (en) * | 2014-12-15 | 2018-08-17 | 爱威科技股份有限公司 | A kind of image processing method and system |
US9971966B2 (en) | 2016-02-26 | 2018-05-15 | Google Llc | Processing cell images using neural networks |
CN107492088B (en) * | 2016-06-11 | 2020-12-04 | 青岛华晶生物技术有限公司 | Automatic identification and statistics method for white blood cells in gynecological microscopic image |
CN106248559B (en) * | 2016-07-14 | 2018-10-23 | 中国计量大学 | A kind of five sorting technique of leucocyte based on deep learning |
CN107686859B (en) * | 2017-07-18 | 2021-07-30 | 天津师范大学 | Method suitable for rapid classified counting of fish blood cells and application |
CN114729924A (en) * | 2019-12-04 | 2022-07-08 | 深圳迈瑞生物医疗电子股份有限公司 | Target cell counting method, device, system and storage medium |
CN111047577B (en) * | 2019-12-12 | 2021-02-26 | 太原理工大学 | Abnormal urine red blood cell classification statistical method and system |
CN112595654A (en) * | 2020-10-28 | 2021-04-02 | 宁夏医科大学总医院 | Cerebrospinal fluid cell image feature library and establishing method thereof |
CN112150466B (en) * | 2020-11-26 | 2021-03-09 | 北京小蝇科技有限责任公司 | Method and system for detecting abnormality of white blood cell scatter diagram |
CN112508909B (en) * | 2020-12-03 | 2023-08-25 | 中国人民解放军陆军军医大学第二附属医院 | Disease association method of peripheral blood cell morphology automatic detection system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0584544B2 (en) * | 1984-04-05 | 1993-12-02 | Hitachi Ltd | |
CN103020639A (en) * | 2012-11-27 | 2013-04-03 | 河海大学 | Method for automatically identifying and counting white blood cells |
CN103345654A (en) * | 2013-06-25 | 2013-10-09 | 苏州创继生物科技有限公司 | Method for differential counting of white blood cells based on morphology |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA1311404C (en) * | 1987-03-13 | 1992-12-15 | Kenneth H. Kortright | Automated analyzer and method for screening cells or formed bodies for enumeration of populations expressing selected characteristics |
CN101464245B (en) * | 2007-12-19 | 2012-08-29 | 深圳迈瑞生物医疗电子股份有限公司 | Method for recognizing erythrocyte chips |
-
2013
- 2013-06-25 CN CN201310254872.6A patent/CN103345654B/en not_active Expired - Fee Related
-
2014
- 2014-07-24 WO PCT/CN2014/082868 patent/WO2014206376A1/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0584544B2 (en) * | 1984-04-05 | 1993-12-02 | Hitachi Ltd | |
CN103020639A (en) * | 2012-11-27 | 2013-04-03 | 河海大学 | Method for automatically identifying and counting white blood cells |
CN103345654A (en) * | 2013-06-25 | 2013-10-09 | 苏州创继生物科技有限公司 | Method for differential counting of white blood cells based on morphology |
Non-Patent Citations (4)
Title |
---|
QIN, SHUWEI;: "Studies on Classification and Recognition of Leukocyte Microscope-images", ELECTRONIC TECHNOLOGY & INFORMATION SCIENCE , CHINA MASTER'S THESES FULL-TEXT, no. 4, 15 April 2008 (2008-04-15), pages 4 - 6 * |
YU , JIE;: "Automatic Recognition System for Leukocyte Based On Computer Image Processing", MEDICINE & PUBLIC HEALTH, CHINESE SELECTED DOCTORAL DISSERTATIONS AND MASTER'S THESES FULL-TEXT DATABASES, no. 8, 15 December 2005 (2005-12-15), pages 13 - 14 * |
ZHANG, LIWEI;: "Studies on Classification of Leukocyte Microscope-images", ELECTRONIC TECHNOLOGY & INFORMATION SCIENCE , CHINA MASTER'S THESES FULL-TEXT DATABASE, no. 6, 15 June 2010 (2010-06-15) * |
ZHANG, SHIMIN;: "The Determination Principles and Scattergram Characters of Leukocyte 5-part Differential Hematology Analyzer", CHINA MEDICAL DEVICE INFORMATION, vol. 14, no. 12, 31 December 2008 (2008-12-31), pages 1 - 9 AND 44 * |
Also Published As
Publication number | Publication date |
---|---|
CN103345654A (en) | 2013-10-09 |
CN103345654B (en) | 2017-02-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2014206376A1 (en) | Method of classifying and counting white blood cells on basis of morphology | |
US10222320B2 (en) | Identifying and enumerating early granulated cells (EGCs) | |
Cornet et al. | Performance evaluation and relevance of the CellaVisionTM DM96 system in routine analysis and in patients with malignant hematological diseases | |
Labati et al. | All-IDB: The acute lymphoblastic leukemia image database for image processing | |
US10337975B2 (en) | Method and system for characterizing particles using a flow cytometer | |
Swolin et al. | Differential counting of blood leukocytes using automated microscopy and a decision support system based on artificial neural networks–evaluation of DiffMasterTM Octavia | |
JP2010506175A (en) | Analysis method of 5 fraction whole blood cells based on visual image | |
WO2016106688A1 (en) | Nucleated red blood cell warning method and device, and flow cytometer | |
JP2012519848A (en) | Device-to-device method and system for cell population identification | |
Hortinela et al. | Identification of abnormal red blood cells and diagnosing specific types of anemia using image processing and support vector machine | |
CN107389536B (en) | Flow cell particle classification counting method based on density-distance center algorithm | |
CN102662048B (en) | Method and device for analyzing urine | |
Beksaç et al. | An artificial intelligent diagnostic system on differential recognition of hematopoietic cells from microscopic images | |
CN102331393A (en) | Method for carrying out automatic classified counting on cells in human blood | |
WO2019206310A1 (en) | Blood analysis method, blood analysis system, and storage medium | |
Jo et al. | Reliable, accurate determination of the leukocyte differential of leukopenic samples by using Hematoflow method | |
AU2010348992A1 (en) | Method and system for analyzing a blood sample | |
CN112432902A (en) | Automatic detection system and method for judging cell number through peripheral blood cell morphology | |
CN111274949B (en) | Blood disease white blood cell scatter diagram similarity analysis method based on structural analysis | |
Priyankara et al. | An extensible computer vision application for blood cell recognition and analysis | |
US8512977B2 (en) | Analyzing reticulocytes | |
EP3244191A1 (en) | Method and system for characterizing particles using a flow cytometer | |
EP2920573B1 (en) | Particle data segmentation result evaluation methods and flow cytometer | |
CN112481346B (en) | Automatic early warning system and method for detecting abnormal cells in peripheral blood cell morphology | |
CN111868739A (en) | In vitro method for label-free determination of cell types of leukocytes |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14818784 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14818784 Country of ref document: EP Kind code of ref document: A1 |