CN103745210A - Method and device for classifying white blood cells - Google Patents
Method and device for classifying white blood cells Download PDFInfo
- Publication number
- CN103745210A CN103745210A CN201410041995.6A CN201410041995A CN103745210A CN 103745210 A CN103745210 A CN 103745210A CN 201410041995 A CN201410041995 A CN 201410041995A CN 103745210 A CN103745210 A CN 103745210A
- Authority
- CN
- China
- Prior art keywords
- image
- blood sample
- leucocyte
- dyeing
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention provides a method and a device for classifying white blood cells. The method comprises the following steps: dyeing the white blood cells in a blood sample to obtain a blood sample containing the dyed white blood cells; performing image acquisition on the white blood cell blood sample to obtain a white blood cell blood sample image; segmenting various cells of the white blood cell blood sample image, and respectively extracting cell morphology characteristic parameters of various cells; performing re-segmentation on various segmented cells to obtain a cell nucleus image and a cytoplasm and particle image; extracting color characteristic parameters of the cell nucleus image; extracting particle distribution characteristic parameters and color characteristic parameters of the cytoplasm and particle image; performing normalization on extracted characteristics; sending the normalized characteristics into a neural network classifier, identifying five types of cells in the white blood cells, and respectively working out the number of the five types of cells and the percentage of total white blood cell count. According to the method and the device for classifying the white blood cells provided by the invention, the white blood cells can be accurately classified.
Description
Technical field
The present invention relates to cell classification field, relate in particular a kind of leukocyte differential count method and device.
Background technology
Leukocyte differential count is when carrying out the procuratorial work of blood microscope, by a kind of medical science detection method of Arneth's count.Leucocyte in blood comprises neutrophil cell, eosinophil, basophilic granulocyte, lymphocyte and monocyte.In addition, myeloblast is progenitor cell or the juvenile cell that granulocyte is grown, and there will be in certain patient's blood, and as occurred in the blood of leukemia patient, myeloblast is not classified as general classification cell, and its composition basophilla can au bleu after dyeing.They respectively have its physiological function separately above-mentioned various types of cells, and in environmental medicine research, leukocyte differential count is an important index.
Current leukocyte differential count method is normally hived off according to leukocytic volume, be less than 90FL person for lymphocyte, be greater than 160FL person for maxicell district, it is monocyte, what be positioned at 90FL and 160FL centre is granulocyte, granulocyte comprises eosinophil, basophilic granulocyte, neutrophil cell, this scheme has just simply been divided into three classes according to the large young pathbreaker's leucocyte of leucocyte volume, therefore, this kind of sorting technique makes neutrophil cell, eosinophil, basophilic granulocyte, the magnitude range of this five classes cell of lymphocyte and monocyte has overlapping, sorting technique is not accurate enough, and the eosinophil in granulocyte, neutrophil cell, basophilic granulocyte also cannot specifically be distinguished.
Therefore,, according to existing leukocyte differential count method, can accurately not classify by dialogue cell.
Summary of the invention
In view of this, the problem of can accurately dialogue cell not classifying in order to solve existing leukocyte differential count method, technical scheme is as follows:
A kind of leukocyte differential count method, comprising:
Leucocyte in blood sample is dyeed, obtain comprising the leucocyte blood sample sample after dyeing;
Described leucocyte blood sample sample is carried out to image acquisition, obtain leucocyte blood sample image;
The various types of cells image of described leucocyte blood sample image is split, extract respectively the cytomorphology characteristic parameter of described various types of cells image;
Described various types of cells image after cutting apart is carried out to secondary splitting, obtain respectively nuclei picture, tenuigenin and particle image;
Extract the Color characteristics parameters of described nuclei picture;
Extract particle distribution characteristics parameter and the Color characteristics parameters of described tenuigenin and particle image;
Particle distribution characteristics parameter and the Color characteristics parameters of the Color characteristics parameters to described cytomorphology characteristic parameter, described nuclei picture, described tenuigenin and particle image are normalized;
Particle distribution characteristics parameter and the Color characteristics parameters of the Color characteristics parameters of the described cytomorphology characteristic parameter after normalization, described nuclei picture, described tenuigenin and particle image are sent into neural network classifier, identify eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast in described leucocyte, and obtain respectively the number of described eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and account for the number percent of total leukocyte number.
Preferably, in above-mentioned leukocyte differential count method, described described leucocyte blood sample sample is carried out to image acquisition, obtains leucocyte blood sample image, comprising:
Leucocyte blood sample sample after utilizing microscope to the dyeing of setting area amplifies;
Utilize video camera or CCD element to carry out image information collecting to the image after amplifying, obtain the first image.
Preferably, in above-mentioned leukocyte differential count method, also comprise:
The number of described eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and the number percent that accounts for total leukocyte number are shown on output unit.
Preferably, in above-mentioned leukocyte differential count method, described leucocyte in blood sample is dyeed, obtains all kinds of leukocytic blood sample sample that comprises dyeing, comprising:
Utilize staining reagent to carry out erythrocyte hemolysis processing to blood sample, and dialogue cell dyeing obtain all kinds of leukocytic blood sample sample that comprises dyeing.
Preferably, in above-mentioned leukocyte differential count method, described morphological feature parameter comprises: parameters for shape characteristic, size characteristic parameter, textural characteristics parameter and Color characteristics parameters.
The embodiment of the present invention also provides a kind of leukocyte differential count device, comprising:
Dyeing unit, described dyeing unit dyes to the leucocyte in blood sample, obtains comprising the leucocyte blood sample sample after dyeing;
Graphics processing unit, described graphics processing unit carries out image acquisition to described leucocyte blood sample sample, obtain leucocyte blood sample image, the various types of cells image of described leucocyte blood sample image is split, extract respectively the cytomorphology characteristic parameter of described various types of cells image, described various types of cells image after cutting apart is carried out to secondary splitting, obtain respectively nuclei picture, tenuigenin and particle image, extract the Color characteristics parameters of described nuclei picture, extract particle distribution characteristics parameter and the Color characteristics parameters of described tenuigenin and particle image, to described cytomorphology characteristic parameter, the Color characteristics parameters of described nuclei picture, particle distribution characteristics parameter and the Color characteristics parameters of described tenuigenin and particle image are normalized,
Be based upon the sorter on neural net base, by the described morphological feature parameter after normalization, the Color characteristics parameters of described nuclei picture, particle distribution characteristics parameter and the Color characteristics parameters of described tenuigenin and particle image are sent into described sorter, identify the eosinophil in described leucocyte, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast, and obtain respectively described eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, the number of myeloblast and account for the number percent of total leukocyte number.
Preferably, in above-mentioned leukocyte differential count device, described graphics processing unit, comprising:
Microscope, the leucocyte blood sample sample after utilizing described microscope to the dyeing of setting area amplifies;
Video camera or CCD element, utilize described video camera or CCD element to carry out image information collecting to the image after amplifying, and obtains the first image;
Preferably, in above-mentioned leukocyte differential count device, also comprise:
Output unit shows the number of described eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and the number percent that accounts for total leukocyte number on described output unit.
Preferably, in above-mentioned leukocyte differential count device, described dyeing unit, comprising:
Reagent dyeing unit, described reagent dyeing unit by using staining reagent carries out erythrocyte hemolysis processing to blood sample, and dialogue cell dyeing obtains all kinds of leukocytic blood sample sample that comprises dyeing.
Preferably, in above-mentioned leukocyte differential count device, described cell characteristic comprises: shape facility, textural characteristics and color characteristic.
In technique scheme, there is following beneficial effect:
Known via above-mentioned technical scheme, compared with prior art, leukocyte differential count method provided by the invention is carried out secondary splitting to all kinds of leucocytes after cutting apart, and the image after secondary splitting is carried out to feature extraction, thereby can to leucocyte, classify accurately, identify the eosinophil in all kinds of leucocytes, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast, and obtain respectively eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, the number of myeloblast and account for the number percent of total leukocyte number, the clinical data reference that provides is provided.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only embodiments of the invention, for those of ordinary skills, do not paying under the prerequisite of creative work, other accompanying drawing can also be provided according to the accompanying drawing providing.
A kind of schematic flow sheet of the leukocyte differential count method that Fig. 1 provides for the embodiment of the present invention;
A kind of schematic flow sheet of the leukocyte differential count method that Fig. 2 provides for the embodiment of the present invention;
A kind of structural representation of the leukocyte differential count device that Fig. 3 provides for the embodiment of the present invention;
A kind of structural representation of graphics processing unit in the leukocyte differential count device that Fig. 4 provides for the embodiment of the present invention;
A kind of structural representation of the leukocyte differential count device that Fig. 5 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, rather than whole embodiment.Based on the embodiment in the present invention, those of ordinary skills, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
Referring to Fig. 1, the embodiment of the present invention provides a kind of leukocyte differential count method, comprising:
Step 110: the leucocyte in blood sample is dyeed, obtain comprising the leucocyte blood sample sample after dyeing.
Step 120: leucocyte blood sample sample is carried out to image acquisition, obtain leucocyte blood sample image.
Step 130: the various types of cells of leucocyte blood sample image is split, extract respectively the cytomorphology characteristic parameter of various types of cells.
Step 140: the various types of cells after cutting apart is carried out to secondary splitting, obtain respectively nuclei picture, tenuigenin and particle image.
Step 150: the Color characteristics parameters that extracts nuclei picture.
Step 160: the particle distribution characteristics parameter and the Color characteristics parameters that extract tenuigenin and particle image.
Step 170: particle distribution characteristics parameter and the Color characteristics parameters of Color characteristics parameters, tenuigenin and particle image to morphological feature parameter, nuclei picture are normalized.
Step 180: particle distribution characteristics parameter and the Color characteristics parameters of Color characteristics parameters, tenuigenin and the particle image of the morphological feature parameter after normalization, nuclei picture are sent into neural network classifier, identify eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast in all kinds of leucocytes, and obtain respectively the number of eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and account for the number percent of total leukocyte number.
The embodiment of the present invention is carried out secondary splitting to all kinds of leucocytes after cutting apart, and the image after secondary splitting is carried out to feature extraction, thereby can to leucocyte, classify accurately, identify eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast in all kinds of leucocytes, and obtain respectively the number of eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and account for the number percent of total leukocyte number, the clinical data reference that provides is provided.
Referring to Fig. 2, the embodiment of the present invention, provide a kind of leukocyte differential count method, comprising:
Step 210: the leucocyte in blood sample is dyeed, obtain comprising the leucocyte blood sample sample after dyeing.
Can utilize staining reagent to carry out erythrocyte hemolysis processing to blood sample, and dialogue cell dyeing obtain all kinds of leukocytic blood sample sample that comprises dyeing; Or, can utilize fluorescent staining method to dye to leucocyte, obtain all kinds of leukocytic blood sample sample that comprises dyeing.
Utilize staining reagent to the red blood cell in blood sample cell fast, up hill and dale destroy; lysed erythrocyte fragment effectively; and punching enters in leucocyte endochylema dyestuff fast on leucocyte film; variable grain is combined and is presented different colours in leucocyte endochylema; in staining reagent, can comprise stabilizing agent, stabilizing agent can be protected leucocyte film and keep leukocytic integrality.
All kinds of leukocytic concrete form features after dyeing: neutrophil cell particle empurple, nucleus blueness, and between particle, gap is high-visible; Nucleus bending is sausage sample, the blunt circle in two ends; Or be divided into 2～5 leaves, take 3 leaves as many.Though eosinophil particle empurple is more gorgeous than neutrophil cell grain color, and almost very close to each other between particle, nucleus blueness, is almost had a liking for acid; Nucleus is divided into 2 leaves, is glasses-type.The equal purple of basophilic granulocyte endochylema, particle and nucleus, but have obvious depth difference, endochylema is painted shallow, and each form is high-visible; Nuclear structure is unclear, and leaflet is not obvious.Lymphocyte and monocyte karyon, endochylema levelling au bleu, but lymphocyte individuality is little, and nuclear staining is even, and slightly dark; Lymphocyte nuclear is rounded or oval, limit.Monocyte nucleus is irregular shape, kidney shape, and the shape of a hoof or distortion are folding.Myeloblast color depth, individual large, karyon, endochylema levelling au bleu and easily distinguish with normal cell.Wherein, myeloblast is progenitor cell or the juvenile cell that granulocyte is grown, and only in the blood of leukemia patient, occurs, be not classified as general classification cell, its composition basophilla is dyed blueness.
Step 220: the leucocyte blood sample sample after utilizing microscope to the dyeing of setting area amplifies; Utilizing video camera or CCD element to carry out image information collecting to the image after amplifying, obtain the first image, is also leucocyte blood sample image.
Step 230: the various types of cells image of leucocyte blood sample image is split, extract respectively the morphological feature parameter of various types of cells.Morphological feature parameter comprises: parameters for shape characteristic, textural characteristics parameter and the Color characteristics parameters of cell.
From all kinds of leukocytic concrete form features after above-mentioned dyeing, leucocyte after dyeing has different color characteristics, there is larger difference with the gray scale of background picture, therefore adopting the Threshold Segmentation Algorithm based on neural network cuts apart leucocyte after dyeing, leucocyte picture after being cut apart, and the Leukocyte Image after cutting apart is carried out to the extraction of parameters for shape characteristic, textural characteristics parameter and Color characteristics parameters.
Step 240: the various types of cells image after cutting apart is carried out to secondary splitting, obtain respectively nuclei picture, tenuigenin and particle image.
Because the nucleus after dyeing is different with cytoplasmic color, and obscurity boundary, therefore can utilize the image segmentation algorithm based on fuzzy clustering, can accurately Leukocyte Image be divided into nuclei picture, tenuigenin and particle image.
Further, as follows according to the above-mentioned dividing method based on fuzzy clustering image segmentation algorithm:
(1) by the data of cutting apart rear various types of cells image by RGB color space conversion to hsv color space, using H as image cutting room, the pixel characteristic value of cutting apart as fuzzy clustering image.The tone of H presentation video.
Because the Leukocyte Image color characteristic after dyeing is widely different, therefore, when it being carried out to image cutting according to the color distortion of leucocyte various piece in picture, need to be by it from RGB color space conversion to hsv color space, wherein, H is tone; S is saturation degree; V is brightness.
(2) setting cluster centre is 2, is respectively the cluster centre v of nuclei picture
1and the cluster centre v of tenuigenin and particle image
2, and set v
1, v
2initial value.
(3) threshold value of setting iterations L is T, and cluster centre difference threshold ε.
(4) according to formula
And formula
Carry out iteration;
When meeting iterations L>T or max
i|| v
i (L+1)-v
i (L)|| during < ε, stop iteration, obtain suitable membership function and cluster centre value.
In above-mentioned formula,
Wherein:
Image is comprised of c region, and the cluster centre in region is expressed as { v
1, v
2, v
n, v
ibe i class cluster centre, i.e. cluster centre v={v
1, v
2, v
nin one;
L represents iterations;
U
ikrepresent x
ibelong to the degree of membership in k class region;
D
ikrepresent x
karrive i class cluster centre v
idistance;
X
krepresent x={x
1, x
2..., x
nin a value, x={x
1, x
2..., x
nthe gray-scale value of image pixel or the eigenwert of pixel, corresponding, in this programme, the value of x is H;
J (U, V) represents that the pixel in region is to the quadratic sum of the center Weighted distance of birdsing of the same feather flock together, the compactness of the size reflection image-region of J (U, V), and the possibility that the less expression pixel of value is a region is larger, and Clustering Effect is better;
Parameter m is the weighted index of degree of membership, it is the contrast that belongs to zones of different in order to strengthen pixel characteristic value, the fog-level of its decision classification results, m ∈ [1, ∞), get different m values can produce different fog-levels data divide, according to the optimal choice interval of experimental study m, be (1.5,2.5), in general select 2 can obtain preferably fuzzy clustering.
(5) according to maximum membership grade principle, and according to cluster centre value, image pixel is classified, the image after being cut apart.
Step 250: the Color characteristics parameters that extracts nuclei picture.
Step 260: the particle distribution characteristics parameter and the Color characteristics parameters that extract tenuigenin and particle image.Particle distribution characteristics parameter, extracts the color and vein characteristic parameter of tenuigenin and particle image, in order to embody the distribution situation of particle in tenuigenin.
Step 270: particle distribution characteristics parameter and the Color characteristics parameters of Color characteristics parameters, tenuigenin and particle image to morphological feature parameter, nuclei picture are normalized.
The characteristic parameter of the Color characteristics parameters of Color characteristics parameters, tenuigenin and the particle image of all kinds of leukocytic parameters for shape characteristic obtained above, Color characteristics parameters, textural characteristics parameter, nuclei picture, particle distribution characteristics parameter is calculated to a normalized eigenwert by the Feature Fusion Algorithm based on PCA weighting.Can to above-mentioned these features, be normalized by Fusion Features device.
Step 280: particle distribution characteristics parameter and the Color characteristics parameters of Color characteristics parameters, tenuigenin and the particle image of the morphological feature parameter after normalization, nuclei picture are sent into neural network classifier, identify eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast in all kinds of leucocytes, and obtain respectively the number of eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and account for the number percent of total leukocyte number.
Neural network classifier is the sorter being based upon on BP neural net base, this sorter adopts the multiple samples of artificial training, form a disaggregated model, according to step 210-270, obtain the normalized parameter of the each category feature of sample to be tested, in all kinds of normalized parameter input sorters, the disaggregated model in sorter is classified the each leucocyte in sample to be tested.Further, this sorter being based upon on BP neural net base also comprises a feedback procedure, this feedback procedure is that classification suspicious object and identification error target out carried out to refinement, classification, complementary features parameter, thereby the disaggregated model to original foundation improves, by neural network is trained, neural network automatic learning is also remembered those refinements, classification, supplementary characteristic parameter, those refinements, classification, supplementary characteristic parameter are entered to model database, then the sorter returning based on neural network carries out cell classification.
The embodiment of the present invention is carried out secondary splitting to the various types of cells after cutting apart, and the image after secondary splitting is carried out to feature extraction, thereby can to leucocyte, classify accurately, identify eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast in all kinds of leucocytes, and obtain respectively the number of eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and account for the number percent of total leukocyte number, the clinical data reference that provides is provided.Further, the feedback procedure of sorter can further improve the accuracy of leukocyte differential count.
In other embodiments of the invention, also comprise:
The number of eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and the number percent that accounts for total leukocyte number are shown on output unit.
The number of eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and the number percent that accounts for total leukocyte number can be shown on output unit with figure or data mode, for related personnel's reference, this output unit can be the display for remote medical consultation with specialists connected to the network, or printer, with mode output image or the data printed, so that medical personnel analyze.
Referring to Fig. 3, the embodiment of the present invention, provide a kind of leukocyte differential count device, comprising:
Color characteristic extraction unit 350, for extracting the Color characteristics parameters of nuclei picture;
Characteristic parameter extraction unit 360, for extracting particle distribution characteristics parameter and the Color characteristics parameters of tenuigenin and particle image;
Characteristic parameter normalization unit 370, is normalized for particle distribution characteristics parameter and the Color characteristics parameters of the Color characteristics parameters to cytomorphology characteristic parameter, nuclei picture, tenuigenin and particle image;
Be based upon the sorter 380 on neural net base;
Particle distribution characteristics parameter and the Color characteristics parameters of Color characteristics parameters, tenuigenin and the particle image of the morphological feature parameter after normalization, nuclei picture are sent into sorter, identify eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast in all kinds of leucocytes, and obtain respectively the number of eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and account for the number percent of total leukocyte number.
The embodiment of the present invention is carried out secondary splitting to the various types of cells after cutting apart, and the image after secondary splitting is carried out to feature extraction, thereby can to leucocyte, classify accurately, identify eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast in all kinds of leucocytes, and obtain respectively the number of eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and account for the number percent of total leukocyte number, the clinical data reference that provides is provided.
Further, referring to Fig. 4, in other embodiments of the invention, image acquisition units 320 comprises:
Video camera or CCD element 322, utilize video camera or CCD element to carry out image information collecting to the image after amplifying, and obtains the first image,
Further, referring to Fig. 5, in other embodiments of the invention, device also comprises:
Further, in other embodiments of the invention, dyeing unit comprises:
Reagent dyeing unit, reagent dyeing unit by using staining reagent carries out erythrocyte hemolysis processing to blood sample, and dialogue cell dyeing obtains all kinds of leukocytic blood sample sample that comprises dyeing;
Or,
Fluorescent dye unit, fluorescent dye utilizes fluorescent staining method to dye to leucocyte, obtains all kinds of leukocytic blood sample sample that comprises dyeing.
Further, in other embodiments of the invention, above-mentioned morphological feature parameter comprises: parameters for shape characteristic, textural characteristics parameter and Color characteristics parameters.
In this instructions, each embodiment adopts the mode of going forward one by one to describe, and each embodiment stresses is and the difference of other embodiment, between each embodiment identical similar part mutually referring to.For the disclosed device of embodiment, because it corresponds to the method disclosed in Example, so description is fairly simple, relevant part illustrates referring to method part.
Finally, also it should be noted that, in this article, relational terms such as first, second grade is only used for an entity or operation to separate with another entity or operational zone, and not necessarily requires or imply and between these entities or operation, have the relation of any this reality or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thereby the process, method, article or the equipment that make to comprise a series of key elements not only comprise those key elements, but also comprise other key elements of clearly not listing, or be also included as the intrinsic key element of this process, method, article or equipment.The in the situation that of more restrictions not, the key element being limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment that comprises described key element and also have other identical element.
While for convenience of description, describing above device, with function, being divided into various unit describes respectively.Certainly, when implementing the application, the function of each unit can be realized in same or multiple software and/or hardware.
To the above-mentioned explanation of the disclosed embodiments, make professional and technical personnel in the field can realize or use the present invention.To the multiple modification of these embodiment, will be apparent for those skilled in the art, General Principle as defined herein can, in the situation that not departing from the spirit or scope of the present invention, realize in other embodiments.Therefore, the present invention will can not be restricted to these embodiment shown in this article, but will meet the widest scope consistent with principle disclosed herein and features of novelty.
Claims (10)
1. a leukocyte differential count method, is characterized in that, comprising:
Leucocyte in blood sample is dyeed, obtain comprising the leucocyte blood sample sample after dyeing;
Described leucocyte blood sample sample is carried out to image acquisition, obtain leucocyte blood sample image;
The various types of cells image of described leucocyte blood sample image is split, extract respectively the cytomorphology characteristic parameter of described various types of cells image;
Described various types of cells image after cutting apart is carried out to secondary splitting, obtain respectively nuclei picture, tenuigenin and particle image;
Extract the Color characteristics parameters of described nuclei picture;
Extract particle distribution characteristics parameter and the Color characteristics parameters of described tenuigenin and particle image;
Particle distribution characteristics parameter and the Color characteristics parameters of the Color characteristics parameters to described cytomorphology characteristic parameter, described nuclei picture, described tenuigenin and particle image are normalized;
Particle distribution characteristics parameter and the Color characteristics parameters of the Color characteristics parameters of the described cytomorphology characteristic parameter after normalization, described nuclei picture, described tenuigenin and particle image are sent into neural network classifier, identify eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast in described leucocyte, and obtain respectively the number of described eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and account for the number percent of total leukocyte number.
2. method according to claim 1, is characterized in that, described described leucocyte blood sample sample is carried out to image acquisition, obtains leucocyte blood sample image, comprising:
Leucocyte blood sample sample after utilizing microscope to the dyeing of setting area amplifies;
Utilize video camera or CCD element to carry out image information collecting to the image after amplifying, obtain the first image.
3. method according to claim 1, is characterized in that, also comprises:
The number of described eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and the number percent that accounts for total leukocyte number are shown on output unit.
4. method according to claim 1, is characterized in that, described leucocyte in blood sample is dyeed, and obtains all kinds of leukocytic blood sample sample that comprises dyeing, comprising:
Utilize staining reagent to carry out erythrocyte hemolysis processing to blood sample, and dialogue cell dyeing obtain all kinds of leukocytic blood sample sample that comprises dyeing.
5. according to any one method described in claim 1-4, it is characterized in that, described morphological feature parameter comprises: parameters for shape characteristic, size characteristic parameter, textural characteristics parameter and Color characteristics parameters.
6. a leukocyte differential count device, is characterized in that, comprising:
Dyeing unit, described dyeing unit dyes to the leucocyte in blood sample, obtains comprising the leucocyte blood sample sample after dyeing;
Image acquisition units, for described leucocyte blood sample sample is carried out to image acquisition, obtains leucocyte blood sample image;
Feature extraction unit, for the various types of cells image of described leucocyte blood sample image is split, extracts respectively the cytomorphology characteristic parameter of described various types of cells image;
Secondary splitting unit, for the described various types of cells image after cutting apart is carried out to secondary splitting, obtains respectively nuclei picture, tenuigenin and particle image;
Color characteristic extraction unit, for extracting the Color characteristics parameters of described nuclei picture;
Characteristic parameter extraction unit, for extracting particle distribution characteristics parameter and the Color characteristics parameters of described tenuigenin and particle image;
Characteristic parameter normalization unit, is normalized for particle distribution characteristics parameter and the Color characteristics parameters of the Color characteristics parameters to described cytomorphology characteristic parameter, described nuclei picture, described tenuigenin and particle image;
Be based upon the sorter on neural net base;
The particle distribution characteristics parameter of the Color characteristics parameters of the described morphological feature parameter after normalization, described nuclei picture, described tenuigenin and particle image and Color characteristics parameters are sent into described sorter, identify eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast in described leucocyte, and obtain respectively the number of described eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and account for the number percent of total leukocyte number.
7. device according to claim 6, is characterized in that, described image acquisition units, comprising:
Microscope, the leucocyte blood sample sample after utilizing described microscope to the dyeing of setting area amplifies;
Video camera or CCD element, utilize described video camera or CCD element to carry out image information collecting to the image after amplifying, and obtains the first image.
8. device according to claim 6, is characterized in that, also comprises:
Output unit shows the number of described eosinophil, basophilic granulocyte, neutrophil cell, lymphocyte, monocyte, myeloblast and the number percent that accounts for total leukocyte number on described output unit.
9. device according to claim 6, is characterized in that, described dyeing unit, comprising:
Reagent dyeing unit, described reagent dyeing unit by using staining reagent carries out erythrocyte hemolysis processing to blood sample, and dialogue cell dyeing obtains all kinds of leukocytic blood sample sample that comprises dyeing.
10. according to the device described in claim 6-9 any one, it is characterized in that, described cell characteristic comprises: shape facility, textural characteristics and color characteristic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410041995.6A CN103745210B (en) | 2014-01-28 | 2014-01-28 | A kind of leucocyte classification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410041995.6A CN103745210B (en) | 2014-01-28 | 2014-01-28 | A kind of leucocyte classification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103745210A true CN103745210A (en) | 2014-04-23 |
| CN103745210B CN103745210B (en) | 2018-02-06 |
Family
ID=50502227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410041995.6A Active CN103745210B (en) | 2014-01-28 | 2014-01-28 | A kind of leucocyte classification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103745210B (en) |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103984939A (en) * | 2014-06-03 | 2014-08-13 | 爱威科技股份有限公司 | Sample visible component classification method and system |
| CN103985119A (en) * | 2014-05-08 | 2014-08-13 | 山东大学 | Method for partitioning cytoplasm and cell nucleuses of white blood cells in color blood cell image |
| CN104360050A (en) * | 2014-09-22 | 2015-02-18 | 重庆医科大学附属儿童医院 | Method for lymphocyte subsets and kit thereof |
| CN104732524A (en) * | 2015-02-07 | 2015-06-24 | 嘉善加斯戴克医疗器械有限公司 | Random weight network partitioning method for blood leukocyte microscopic image |
| CN105136795A (en) * | 2015-07-20 | 2015-12-09 | 爱威科技股份有限公司 | Blood sample detection device, blood sample detection method and blood sample detection system |
| CN105205054A (en) * | 2014-06-04 | 2015-12-30 | 阿里巴巴集团控股有限公司 | Method for displaying pictures and method and device for acquiring hue characteristic values of pictures |
| CN105404887A (en) * | 2015-07-05 | 2016-03-16 | 中国计量学院 | White blood count five-classification method based on random forest |
| CN106248559A (en) * | 2016-07-14 | 2016-12-21 | 中国计量大学 | A kind of leukocyte five sorting technique based on degree of depth study |
| CN106295588A (en) * | 2016-08-17 | 2017-01-04 | 电子科技大学 | The automatic identifying method of leukocyte in a kind of leucorrhea micro-image |
| CN106327490A (en) * | 2016-08-22 | 2017-01-11 | 中国计量大学 | Nucleus segmentation method based on white blood cell detection |
| CN107730499A (en) * | 2017-10-31 | 2018-02-23 | 河海大学 | A kind of leucocyte classification method based on nu SVMs |
| CN107977682A (en) * | 2017-12-19 | 2018-05-01 | 南京大学 | Lymph class cell sorting method and its device based on the enhancing of polar coordinate transform data |
| CN108139320A (en) * | 2015-02-17 | 2018-06-08 | 西门子医疗保健诊断公司 | For the method and apparatus based on model classified to the chaff interferent in sample |
| CN108376400A (en) * | 2018-02-12 | 2018-08-07 | 华南理工大学 | A kind of bone marrow cell automatic classification method |
| CN108593643A (en) * | 2018-03-13 | 2018-09-28 | 重庆交通大学 | Urine detection method based on intelligent mobile terminal |
| CN108693009A (en) * | 2017-03-31 | 2018-10-23 | 合度精密生物科技有限公司 | Candidate cell is identified using image analysis |
| CN108885682A (en) * | 2016-02-26 | 2018-11-23 | 谷歌有限责任公司 | Use Processing with Neural Network cell image |
| CN108885681A (en) * | 2015-12-18 | 2018-11-23 | 雅培实验室 | For assessing the method and system of cellular morphology |
| CN109034257A (en) * | 2018-08-02 | 2018-12-18 | 河北工程大学 | A kind of cell image record system and classification method |
| CN109636782A (en) * | 2018-11-30 | 2019-04-16 | 苏州深析智能科技有限公司 | A kind of cell type analysis model training method, device and analysis method |
| CN109754398A (en) * | 2019-01-14 | 2019-05-14 | 武汉兰丁医学高科技有限公司 | A kind of computer based myeloplast automark method and system |
| CN109952614A (en) * | 2016-08-22 | 2019-06-28 | 艾瑞斯国际有限公司 | The categorizing system and method for biomone |
| CN110119710A (en) * | 2019-05-13 | 2019-08-13 | 广州锟元方青医疗科技有限公司 | Cell sorting method, device, computer equipment and storage medium |
| JP2019195304A (en) * | 2018-05-10 | 2019-11-14 | 学校法人順天堂 | Image analysis method, device, computer program, and generation method of deep learning algorithm |
| CN111504885A (en) * | 2020-04-04 | 2020-08-07 | 电子科技大学 | Full-automatic blood smear morphological analysis device based on machine vision |
| CN111684281A (en) * | 2018-07-12 | 2020-09-18 | 细胞力学德累斯顿有限责任公司 | Method for obtaining an indicator of sepsis in a patient and device for use in the method |
| CN111868739A (en) * | 2018-03-15 | 2020-10-30 | 西门子医疗有限公司 | In vitro method for label-free determination of cell types of leukocytes |
| CN112070722A (en) * | 2020-08-14 | 2020-12-11 | 厦门骁科码生物科技有限公司 | Fluorescence in situ hybridization cell nucleus segmentation method and system |
| CN112329860A (en) * | 2020-11-05 | 2021-02-05 | 深圳市微埃智能科技有限公司 | Hybrid deep learning visual detection method, device, equipment and storage medium |
| CN112432902A (en) * | 2020-12-03 | 2021-03-02 | 中国人民解放军陆军军医大学第二附属医院 | Automatic detection system and method for judging cell number through peripheral blood cell morphology |
| CN112446427A (en) * | 2020-11-27 | 2021-03-05 | 王伟佳 | Method and device for identifying myeloid blood cells, storage medium and electronic equipment |
| 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 |
| CN112595655A (en) * | 2020-10-28 | 2021-04-02 | 宁夏医科大学总医院 | Automatic cerebrospinal fluid cell analysis system based on artificial intelligence |
| KR20230027365A (en) * | 2021-08-18 | 2023-02-28 | 주식회사 아폴론 | Method and apparatus for processing raman data of eosinophil based on artificial intelligence |
| CN116934742A (en) * | 2023-09-13 | 2023-10-24 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | Lymphatic structure image recognition method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6594586B1 (en) * | 1997-10-28 | 2003-07-15 | California Institute Of Technology | Incorporation of contextual information in object identification |
| US20040126008A1 (en) * | 2000-04-24 | 2004-07-01 | Eric Chapoulaud | Analyte recognition for urinalysis diagnostic system |
| EP1542008A1 (en) * | 2002-06-24 | 2005-06-15 | Sysmex Corporation | Method of classifying and counting leucocytes |
| US20100104169A1 (en) * | 2008-10-28 | 2010-04-29 | Sysmex Corporation | Specimen processing system and blood cell image classifying apparatus |
| CN103020639A (en) * | 2012-11-27 | 2013-04-03 | 河海大学 | Method for automatically identifying and counting white blood cells |
| CN103154732A (en) * | 2010-08-05 | 2013-06-12 | 艾博特健康公司 | Method and apparatus for automated whole blood sample analyses from microscopy images |
| 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 |
| CN103398935A (en) * | 2013-08-23 | 2013-11-20 | 爱威科技股份有限公司 | Method and kit for leukocyte differential count |
| CN103473739A (en) * | 2013-08-15 | 2013-12-25 | 华中科技大学 | White blood cell image accurate segmentation method and system based on support vector machine |
-
2014
- 2014-01-28 CN CN201410041995.6A patent/CN103745210B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6594586B1 (en) * | 1997-10-28 | 2003-07-15 | California Institute Of Technology | Incorporation of contextual information in object identification |
| US20040126008A1 (en) * | 2000-04-24 | 2004-07-01 | Eric Chapoulaud | Analyte recognition for urinalysis diagnostic system |
| EP1542008A1 (en) * | 2002-06-24 | 2005-06-15 | Sysmex Corporation | Method of classifying and counting leucocytes |
| US20100104169A1 (en) * | 2008-10-28 | 2010-04-29 | Sysmex Corporation | Specimen processing system and blood cell image classifying apparatus |
| CN103154732A (en) * | 2010-08-05 | 2013-06-12 | 艾博特健康公司 | Method and apparatus for automated whole blood sample analyses from microscopy images |
| 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 |
| CN103473739A (en) * | 2013-08-15 | 2013-12-25 | 华中科技大学 | White blood cell image accurate segmentation method and system based on support vector machine |
| CN103398935A (en) * | 2013-08-23 | 2013-11-20 | 爱威科技股份有限公司 | Method and kit for leukocyte differential count |
Cited By (58)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103985119A (en) * | 2014-05-08 | 2014-08-13 | 山东大学 | Method for partitioning cytoplasm and cell nucleuses of white blood cells in color blood cell image |
| CN103984939A (en) * | 2014-06-03 | 2014-08-13 | 爱威科技股份有限公司 | Sample visible component classification method and system |
| CN103984939B (en) * | 2014-06-03 | 2017-07-04 | 爱威科技股份有限公司 | A kind of sample visible component sorting technique and system |
| CN105205054A (en) * | 2014-06-04 | 2015-12-30 | 阿里巴巴集团控股有限公司 | Method for displaying pictures and method and device for acquiring hue characteristic values of pictures |
| CN104360050A (en) * | 2014-09-22 | 2015-02-18 | 重庆医科大学附属儿童医院 | Method for lymphocyte subsets and kit thereof |
| CN104732524A (en) * | 2015-02-07 | 2015-06-24 | 嘉善加斯戴克医疗器械有限公司 | Random weight network partitioning method for blood leukocyte microscopic image |
| CN104732524B (en) * | 2015-02-07 | 2018-12-14 | 迈克医疗电子有限公司 | The random weight network dividing method of blood leucocyte micro-image |
| CN108139320B (en) * | 2015-02-17 | 2023-12-22 | 西门子医疗保健诊断公司 | Model-based method and device for classifying interferents in a sample |
| CN108139320A (en) * | 2015-02-17 | 2018-06-08 | 西门子医疗保健诊断公司 | For the method and apparatus based on model classified to the chaff interferent in sample |
| CN105404887A (en) * | 2015-07-05 | 2016-03-16 | 中国计量学院 | White blood count five-classification method based on random forest |
| CN105404887B (en) * | 2015-07-05 | 2019-04-09 | 中国计量大学 | A kind of five classification method of leucocyte based on random forest |
| CN105136795A (en) * | 2015-07-20 | 2015-12-09 | 爱威科技股份有限公司 | Blood sample detection device, blood sample detection method and blood sample detection system |
| CN108885681A (en) * | 2015-12-18 | 2018-11-23 | 雅培实验室 | For assessing the method and system of cellular morphology |
| CN108885682B (en) * | 2016-02-26 | 2022-03-22 | 谷歌有限责任公司 | Processing cell images using neural networks |
| US11443190B2 (en) | 2016-02-26 | 2022-09-13 | Google Llc | Processing cell images using neural networks |
| US11915134B2 (en) | 2016-02-26 | 2024-02-27 | Google Llc | Processing cell images using neural networks |
| CN108885682A (en) * | 2016-02-26 | 2018-11-23 | 谷歌有限责任公司 | Use Processing with Neural Network cell image |
| CN106248559A (en) * | 2016-07-14 | 2016-12-21 | 中国计量大学 | A kind of leukocyte five sorting technique based on degree of depth study |
| 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 |
| CN106295588A (en) * | 2016-08-17 | 2017-01-04 | 电子科技大学 | The automatic identifying method of leukocyte in a kind of leucorrhea micro-image |
| CN106295588B (en) * | 2016-08-17 | 2019-10-01 | 电子科技大学 | The automatic identifying method of leucocyte in a kind of leukorrhea micro-image |
| CN109952614A (en) * | 2016-08-22 | 2019-06-28 | 艾瑞斯国际有限公司 | The categorizing system and method for biomone |
| CN109952614B (en) * | 2016-08-22 | 2023-11-10 | 艾瑞斯国际有限公司 | Biological particle classification system and method |
| CN106327490A (en) * | 2016-08-22 | 2017-01-11 | 中国计量大学 | Nucleus segmentation method based on white blood cell detection |
| CN108693009A (en) * | 2017-03-31 | 2018-10-23 | 合度精密生物科技有限公司 | Candidate cell is identified using image analysis |
| US11866791B2 (en) | 2017-03-31 | 2024-01-09 | Cellmax Ltd. | Identifying candidate cells using image analysis with intensity levels |
| US11866792B2 (en) | 2017-03-31 | 2024-01-09 | Cellmax Ltd. | Identifying candidate cells using image analysis with overlap thresholds |
| US11859253B2 (en) | 2017-03-31 | 2024-01-02 | Cellmax Ltd. | Identifying candidate cells using image analysis |
| CN108693009B (en) * | 2017-03-31 | 2021-02-19 | 合度精密生物科技有限公司 | Identifying candidate cells using image analysis |
| CN107730499A (en) * | 2017-10-31 | 2018-02-23 | 河海大学 | A kind of leucocyte classification method based on nu SVMs |
| CN107977682A (en) * | 2017-12-19 | 2018-05-01 | 南京大学 | Lymph class cell sorting method and its device based on the enhancing of polar coordinate transform data |
| CN107977682B (en) * | 2017-12-19 | 2021-09-28 | 南京大学 | Lymphocyte classification method and device based on polar coordinate transformation data enhancement |
| CN108376400B (en) * | 2018-02-12 | 2021-11-23 | 华南理工大学 | Automatic bone marrow cell classification method |
| CN108376400A (en) * | 2018-02-12 | 2018-08-07 | 华南理工大学 | A kind of bone marrow cell automatic classification method |
| CN108593643A (en) * | 2018-03-13 | 2018-09-28 | 重庆交通大学 | Urine detection method based on intelligent mobile terminal |
| CN111868739A (en) * | 2018-03-15 | 2020-10-30 | 西门子医疗有限公司 | In vitro method for label-free determination of cell types of leukocytes |
| US11830188B2 (en) | 2018-05-10 | 2023-11-28 | Sysmex Corporation | Image analysis method, apparatus, non-transitory computer readable medium, and deep learning algorithm generation method |
| JP2023061956A (en) * | 2018-05-10 | 2023-05-02 | 学校法人順天堂 | Image analysis method, device, computer program, and method for producing deep learning algorithms |
| JP2019195304A (en) * | 2018-05-10 | 2019-11-14 | 学校法人順天堂 | Image analysis method, device, computer program, and generation method of deep learning algorithm |
| CN111684281A (en) * | 2018-07-12 | 2020-09-18 | 细胞力学德累斯顿有限责任公司 | Method for obtaining an indicator of sepsis in a patient and device for use in the method |
| CN111684281B (en) * | 2018-07-12 | 2023-09-12 | 细胞力学德累斯顿有限责任公司 | Method for detecting an indicator of sepsis in a patient and device for carrying out said method |
| CN109034257A (en) * | 2018-08-02 | 2018-12-18 | 河北工程大学 | A kind of cell image record system and classification method |
| CN109636782A (en) * | 2018-11-30 | 2019-04-16 | 苏州深析智能科技有限公司 | A kind of cell type analysis model training method, device and analysis method |
| CN109754398A (en) * | 2019-01-14 | 2019-05-14 | 武汉兰丁医学高科技有限公司 | A kind of computer based myeloplast automark method and system |
| CN110119710A (en) * | 2019-05-13 | 2019-08-13 | 广州锟元方青医疗科技有限公司 | Cell sorting method, device, computer equipment and storage medium |
| CN111504885B (en) * | 2020-04-04 | 2022-03-15 | 电子科技大学 | Analysis method of full-automatic blood smear morphological analysis device based on machine vision |
| CN111504885A (en) * | 2020-04-04 | 2020-08-07 | 电子科技大学 | Full-automatic blood smear morphological analysis device based on machine vision |
| CN112070722A (en) * | 2020-08-14 | 2020-12-11 | 厦门骁科码生物科技有限公司 | Fluorescence in situ hybridization cell nucleus segmentation method and system |
| CN112595655A (en) * | 2020-10-28 | 2021-04-02 | 宁夏医科大学总医院 | Automatic cerebrospinal fluid cell analysis system based on artificial intelligence |
| 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 |
| CN112329860A (en) * | 2020-11-05 | 2021-02-05 | 深圳市微埃智能科技有限公司 | Hybrid deep learning visual detection method, device, equipment and storage medium |
| CN112329860B (en) * | 2020-11-05 | 2024-02-27 | 深圳市微埃智能科技有限公司 | Mixed deep learning visual detection method, device, equipment and storage medium |
| CN112446427B (en) * | 2020-11-27 | 2021-07-27 | 王伟佳 | Method and device for identifying myeloid blood cells, storage medium and electronic equipment |
| CN112446427A (en) * | 2020-11-27 | 2021-03-05 | 王伟佳 | Method and device for identifying myeloid blood cells, storage medium and electronic equipment |
| CN112432902A (en) * | 2020-12-03 | 2021-03-02 | 中国人民解放军陆军军医大学第二附属医院 | Automatic detection system and method for judging cell number through peripheral blood cell morphology |
| KR20230027365A (en) * | 2021-08-18 | 2023-02-28 | 주식회사 아폴론 | Method and apparatus for processing raman data of eosinophil based on artificial intelligence |
| CN116934742A (en) * | 2023-09-13 | 2023-10-24 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | Lymphatic structure image recognition method and system |
| CN116934742B (en) * | 2023-09-13 | 2024-02-27 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | Lymphatic structure image recognition method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103745210B (en) | 2018-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103745210A (en) | Method and device for classifying white blood cells | |
| CN106248559B (en) | A kind of five sorting technique of leucocyte based on deep learning | |
| CN102359938B (en) | Morphological analytical apparatus and method for erythrocytes | |
| Jayakody et al. | Microscope image based fully automated stomata detection and pore measurement method for grapevines | |
| CN103020639A (en) | Method for automatically identifying and counting white blood cells | |
| CN103996195A (en) | Image saliency detection method | |
| CN103985119A (en) | Method for partitioning cytoplasm and cell nucleuses of white blood cells in color blood cell image | |
| CN103984939B (en) | A kind of sample visible component sorting technique and system | |
| CN105205804A (en) | Caryon-cytolymph separation method and apparatus of white blood cells in blood cell image, and classification method and apparatus of white blood cells in blood cell image | |
| CN107292314A (en) | A kind of lepidopterous insects species automatic identification method based on CNN | |
| CN110458082A (en) | A kind of city management case classification recognition methods | |
| CN104156945A (en) | Method for segmenting gray scale image based on multi-objective particle swarm optimization algorithm | |
| Zheng et al. | Direct neural network application for automated cell recognition | |
| CN104732524B (en) | The random weight network dividing method of blood leucocyte micro-image | |
| CN103778443A (en) | Method for achieving scene analysis description based on theme model method and field rule library | |
| CN101655909A (en) | Device and method for calculating matching degree | |
| CN110059568A (en) | Multiclass leucocyte automatic identifying method based on deep layer convolutional neural networks | |
| CN104573701B (en) | A kind of automatic testing method of Tassel of Corn | |
| CN106570076A (en) | Computer text classification system | |
| CN112784767A (en) | Cell example segmentation algorithm based on leukocyte microscopic image | |
| CN110414317B (en) | Full-automatic leukocyte classification counting method based on capsule network | |
| Zhao et al. | The stress detection and segmentation strategy in tea plant at canopy level | |
| CN113435493A (en) | Deep migration learning-based label-free leukocyte classification system and method | |
| CN110110807B (en) | Leukocyte extraction and classification method based on improved K-means and convolutional neural network | |
| CN107392115A (en) | A kind of traffic sign recognition method based on layered characteristic extraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |