CN111583175A - Erythrocyte image detection method, erythrocyte image detection equipment and erythrocyte image detection medium - Google Patents
Erythrocyte image detection method, erythrocyte image detection equipment and erythrocyte image detection medium Download PDFInfo
- Publication number
- CN111583175A CN111583175A CN202010236853.0A CN202010236853A CN111583175A CN 111583175 A CN111583175 A CN 111583175A CN 202010236853 A CN202010236853 A CN 202010236853A CN 111583175 A CN111583175 A CN 111583175A
- Authority
- CN
- China
- Prior art keywords
- image
- red blood
- blood cell
- erythrocyte
- segmentation
- 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
- 210000003743 erythrocyte Anatomy 0.000 title claims abstract description 375
- 238000001514 detection method Methods 0.000 title claims abstract description 41
- 230000011218 segmentation Effects 0.000 claims abstract description 54
- 230000004927 fusion Effects 0.000 claims abstract description 32
- 238000003708 edge detection Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims description 47
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 239000006002 Pepper Substances 0.000 claims description 9
- 235000002566 Capsicum Nutrition 0.000 claims description 8
- 235000016761 Piper aduncum Nutrition 0.000 claims description 8
- 235000017804 Piper guineense Nutrition 0.000 claims description 8
- 235000008184 Piper nigrum Nutrition 0.000 claims description 8
- 150000003839 salts Chemical class 0.000 claims description 8
- 230000010261 cell growth Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 244000203593 Piper nigrum Species 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 11
- 241000722363 Piper Species 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000000877 morphologic effect Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 3
- 239000008280 blood Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 210000002506 abnormal erythrocyte Anatomy 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011895 specific detection Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 210000000601 blood cell Anatomy 0.000 description 1
- 238000004820 blood count Methods 0.000 description 1
- 210000001772 blood platelet Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000001351 cycling effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 208000032839 leukemia Diseases 0.000 description 1
- 210000000265 leukocyte Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000001000 micrograph Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 210000004180 plasmocyte Anatomy 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The embodiment of the application provides a red blood cell image detection method, a device and a medium, which are used for obtaining a corresponding red blood cell image and obtaining a corresponding red blood cell gray image according to the red blood cell image; carrying out edge detection on the red blood cell gray level image to obtain a corresponding red blood cell edge information image; processing the erythrocyte edge information image based on expansion operation to obtain a corresponding erythrocyte expansion fusion image; carrying out closed operation processing on the erythrocyte expansion fusion image to obtain an erythrocyte segmentation image; determining a plurality of connected components in the red blood cell segmentation image; and counting the number of red blood cells in the red blood cell image according to a plurality of connected domains in the red blood cell segmentation image. By the scheme, the erythrocyte detection efficiency can be improved to a great extent, the erythrocyte counting accuracy is improved, and the influence of the detection environment is reduced.
Description
Technical Field
The present application relates to the field of biological detection technologies, and in particular, to a method, an apparatus, and a medium for detecting an image of red blood cells.
Background
The erythrocyte is a transport carrier of oxygen molecules of a human body, the content and morphological characteristics of the erythrocyte are main parameters of human health, and the erythrocyte detection is important content of clinical pathological change inspection.
At present, the main mode of erythrocyte detection is an impedance-based erythrocyte quantitative detection method for counting the number of erythrocytes, but the method is greatly influenced by environment and has low accuracy, the counting precision of the number of erythrocytes is low, and the morphological structure of erythrocytes cannot be effectively obtained.
Therefore, how to improve the accuracy of red blood cell detection and the accuracy of red blood cell count becomes an important technical problem.
Disclosure of Invention
The embodiment of the specification provides a red blood cell image detection method, a device and a medium, which are used for solving the following technical problems in the prior art: the erythrocyte detection accuracy is low, the influence of the environment is large, and the erythrocyte quantity counting precision is low.
The embodiment of the specification adopts the following technical scheme:
a method of red blood cell image detection, the method comprising:
obtaining a corresponding erythrocyte image, and obtaining a corresponding erythrocyte graying image according to the erythrocyte image;
carrying out edge detection on the red blood cell gray level image to obtain a corresponding red blood cell edge information image;
processing the erythrocyte edge information image based on expansion operation to obtain a corresponding erythrocyte expansion fusion image;
performing closed operation processing on the erythrocyte expansion fusion image to obtain an erythrocyte segmentation image;
determining a plurality of connected components in the red blood cell segmentation image;
and counting the number of red blood cells in the red blood cell image according to a plurality of connected domains in the red blood cell segmentation image.
In a possible implementation manner, the obtaining a corresponding grayscale image of red blood cells according to the red blood cell image specifically includes:
decomposing the red blood cell image into a green single-channel image;
and carrying out graying processing on the green single-channel image to obtain a corresponding red blood cell grayed image.
In one possible implementation manner, before obtaining the corresponding red blood cell edge information image, the method further includes:
and carrying out filtering processing on the red blood cell gray-scale image so as to eliminate salt and pepper noise of the red blood cell gray-scale image.
In one possible implementation, before obtaining the corresponding erythrocyte expansion fusion image, the method further includes:
according to a preset threshold value, performing threshold value segmentation on the red blood cell gray image to obtain a red blood cell gray image with a reserved red blood cell body; or
And performing threshold segmentation on the erythrocyte marginal information image according to a preset threshold to obtain the erythrocyte marginal information image with the reserved erythrocyte body.
In one possible implementation, before obtaining the red blood cell segmentation image, the method further includes:
performing corresponding calculation according to the erythrocyte expansion fusion image, and determining a plurality of connected domains in the erythrocyte expansion fusion image;
determining whether the area of each connected domain is smaller than a corresponding preset threshold value;
and filling the connected domain under the condition that the area of the connected domain is smaller than a corresponding preset threshold value.
In one possible implementation, the red blood cells include normal state red blood cells, abnormal state red blood cells;
the counting the number of red blood cells in the red blood cell image according to the plurality of connected domains in the red blood cell segmentation image specifically includes:
calculating the circularity of each connected domain in the red blood cell segmentation image;
under the condition that the circularity of the connected domain is smaller than a preset threshold value, determining that the connected domain is abnormal red blood cells, and accumulating the number of the abnormal red blood cells;
and under the condition that the circularity of the connected domain is greater than or equal to a preset threshold value, determining that the connected domain is red blood cells in a normal state, and accumulating the number of the red blood cells in the normal state.
In one possible implementation manner, the abnormal state red blood cells include at least one of the following: crushed red blood cells, and variant red blood cells.
In a possible implementation manner, performing edge detection on the red blood cell grayscale image to obtain a corresponding red blood cell edge information image, specifically including:
and based on a preset direction controllable filter, carrying out edge detection on the red blood cell gray image to obtain a corresponding red blood cell edge information image.
A red blood cell image detection apparatus, the apparatus comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to:
obtaining a corresponding erythrocyte image, and obtaining a corresponding erythrocyte graying image according to the erythrocyte image;
carrying out edge detection on the red blood cell gray level image to obtain a corresponding red blood cell edge information image;
processing the erythrocyte edge information image based on expansion operation to obtain a corresponding erythrocyte expansion fusion image;
performing closed operation processing on the erythrocyte expansion fusion image to obtain an erythrocyte segmentation image;
determining a plurality of connected components in the red blood cell segmentation image;
and counting the number of red blood cells in the red blood cell image according to a plurality of connected domains in the red blood cell segmentation image.
A non-transitory computer storage medium for red blood cell image detection, storing computer-executable instructions configured to:
obtaining a corresponding erythrocyte image, and obtaining a corresponding erythrocyte graying image according to the erythrocyte image;
carrying out edge detection on the red blood cell gray level image to obtain a corresponding red blood cell edge information image;
processing the erythrocyte edge information image based on expansion operation to obtain a corresponding erythrocyte expansion fusion image;
performing closed operation processing on the erythrocyte expansion fusion image to obtain an erythrocyte segmentation image;
determining a plurality of connected components in the red blood cell segmentation image;
and counting the number of red blood cells in the red blood cell image according to a plurality of connected domains in the red blood cell segmentation image.
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects: the red blood cell image is subjected to graying, edge detection, expansion operation, closing operation and other processing in sequence to obtain a red blood cell segmentation image, a plurality of connected domains in the red blood cell segmentation image are determined, and the number of red blood cells in the red blood cell image is counted according to the connected domains. Compared with the existing red blood cell image detection method, the method is not limited to a specific detection environment, has strong adaptability to the detection environment and is not easily influenced by the environment; on the other hand, the technical scheme that this application embodiment provided, the statistical accuracy of erythrocyte quantity is high, the rate of accuracy is high to compare in current erythrocyte detection technology, it is simple more convenient, thereby improve erythrocyte detection efficiency, reinforcing user uses and experiences.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flowchart of a method for red blood cell image detection according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of structural elements provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram of an erythrocyte image detecting device provided in an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more apparent, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person skilled in the art without making any inventive step based on the embodiments in the description belong to the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
The detection of red blood cells is an important matter in clinical lesion examination, and is also an important matter for the detection of the number of red blood cells. The number of red blood cells exceeding the normal level can be regarded as an increase in the amount of red blood cells, and of course, the value or range of values corresponding to the normal level is different for people of different ages and sexes. When the number of erythrocytes is lower than the normal level, it can be considered that erythrocytes are decreased, and symptoms such as leukemia and synthesis disorder may be present.
Fig. 1 is a flowchart of a red blood cell image detection method according to an embodiment of the present disclosure. As shown in fig. 1, the method comprises the steps of:
s101, acquiring a corresponding erythrocyte image.
The image of the red blood cell referred to herein may be a microscope image containing red blood cells.
As will be appreciated by those skilled in the art, the composition of blood includes plasma and blood cells, including red blood cells, white blood cells, and platelets. Generally, when detecting red blood cells, it is necessary to collect corresponding blood first, then make a blood smear, observe the smear through a microscope, and collect an image to obtain the image of red blood cells. The red blood cell image may be an image in an RGB color mode or an image in an HSV color mode, and the color mode of the red blood cell image is not limited in the embodiment of the present application.
And S102, obtaining a corresponding red blood cell gray image according to the red blood cell image.
The red blood cell image mentioned above may be a color image in an RGB color mode, and the RGB color mode obtains various colors by the variation of three color channels of red (R), green (G) and blue (B) and their superposition with each other. That is, the red blood cell image may be composed of three color channels of red, green and blue.
Thus, in some embodiments of the present application, the above-described red blood cell image may be obtained by: the red blood cell image can be decomposed into a green single-channel image, and the green single-channel image is subjected to graying processing to obtain a corresponding single-channel grayscale image, namely the red blood cell grayed image.
Since the red blood cells in the red blood cell image are red, the green channel has the highest contrast to red with respect to the red channel and the blue channel. Therefore, the erythrocyte image is decomposed into a green single-channel image, and then graying is carried out, so that the erythrocyte in the image can be more highlighted, and the image error after graying is smaller, thereby reducing the error of erythrocyte quantity statistics during later detection and improving the accuracy.
In the embodiment of the present application, the red blood cell image may be decomposed into a red single-channel image or a blue single-channel image, but the contrast is smaller and the error is larger than that of the red blood cell image or the blue single-channel image. Furthermore, if the red blood cell image is the red blood cell image in the HSV color mode or the other color mode, the red blood cell image in the other color mode can be converted into the red blood cell image in the RGB color mode by a corresponding algorithm, and then the step S102 is performed.
And S103, filtering the red blood cell gray-scale image to eliminate salt and pepper noise of the red blood cell gray-scale image.
Salt and pepper noise is an image noise often seen in images, and is a randomly occurring white and black dot, which may be a bright area with black pixels or a dark area with white pixels, or both. Therefore, in order to avoid the interference of salt-pepper noise in the red blood cell grayscale image, the red blood cell grayscale image may be subjected to filtering processing to denoise the red blood cell grayscale image. Through step S103, the influence of salt and pepper noise on the red blood cell detection can be reduced, and the accuracy of red blood cell detection can be further improved.
The filtering process for the red blood cell grayscale image may be performed by using, for example, a 5 × 5 mean filter. Other methods of removing salt and pepper noise may also be used, as will be appreciated by those skilled in the art. In the embodiment of the present application, the technical means for filtering the red blood cell grayscale image is not limited, as long as the function of eliminating salt and pepper noise can be achieved.
And S104, carrying out edge detection on the red blood cell gray image to obtain a corresponding red blood cell edge information image.
The red blood cell grayscale image in step S104 may be the red blood cell image from which the salt and pepper noise is removed in step S103, or may be the red blood cell grayscale image in step S102.
Specifically, the red blood cell image may be subjected to edge detection based on a preset direction controllable filter, so as to obtain a corresponding red blood cell edge image. The direction controllable filter is composed of a plurality of basic filters, the basic filters can form any direction of the direction controllable filter, the direction controllable filter is adopted to carry out filtering enhancement on the gray level image, and the erythrocyte edge information can be effectively segmented out, so that the erythrocyte edge information image is obtained.
In the present specification, other edge detection algorithms, such as an edge detection algorithm based on Canny operator, and an edge detection algorithm based on Log operator, may also be used. The present specification does not limit a specific embodiment of edge detection for a red blood cell grayscale image.
In step S104, the boundary of the red blood cell in the image can be detected, that is, the contour of the red blood cell can be obtained.
And S105, performing threshold segmentation on the erythrocyte edge information image according to a preset threshold to obtain the erythrocyte edge information image with reserved erythrocyte bodies.
And performing threshold segmentation on the red blood cell edge information image through a corresponding preset threshold to remove other noises except the red blood cell body in the red blood cell edge information image so as to obtain the red blood cell edge information image retaining the red blood cell body.
Other boundaries than the red blood cell boundary may exist in the red blood cell edge information image, which may interfere with the detection of the red blood cells. In general, the pixel values of other boundaries are obviously different from the pixel values of the red blood cell boundaries, so that the red blood cell edge information image can be segmented by setting corresponding threshold values. The interference can be eliminated through the step S105, and the accuracy of the red blood cell detection is further improved.
In the embodiment of the application, a global thresholding method may be adopted to perform thresholding on the red blood cell edge information image, that is, only one fixed threshold T is selected for thresholding the red blood cell edge information image, and typical thresholding methods include an Ostu method, a maximum entropy method, a gray scale expectation method, and the like.
In some embodiments of the present application, except that step S105 may be performed after step S104, the red blood cell edge information image is subjected to threshold segmentation; before step S104, the red blood cell grayscale image filtered in step S103 may be subjected to threshold segmentation.
And S106, processing the erythrocyte edge information image based on an expansion algorithm to obtain a corresponding erythrocyte expansion fusion image.
Specifically, a structural element (as shown in fig. 2) is used to perform expansion operation on the red blood cell edge information image, and during the expansion operation, if the pixel point of the structural element overlaps with the red blood cell edge information image, the structural element is retained, and the red blood cell expansion fusion image is obtained by cycling and traversing.
Through the step S106, some cavities in the red blood cells in the red blood cell edge information image can be filled and small particle noise can be eliminated, so that the shapes of the red blood cells in the red blood cell edge information image are more real, the difference between the red blood cells and the real red blood cells is further reduced, and the use experience of a user is improved.
The red blood cell edge information image mentioned here may be obtained after step S105 is executed, or may be obtained after step S104 is executed, and is not limited to the red blood cell edge image subjected to the threshold segmentation processing.
And S107, performing closed-loop operation processing on the erythrocyte expansion fusion image to obtain an erythrocyte segmentation image.
Because the red blood cell expansion fusion image has the burr noise, the burr noise needs to be removed according to the morphological characteristics of the actual red blood cells, and therefore the closed operation is carried out on the red blood cell expansion fusion image to obtain the red blood cell segmentation image with the burr noise removed.
As known to those skilled in the art, the red blood cells are in the form of round cakes with convexities on both sides and concavities on the middle, i.e., the centers of the red blood cells are concave. Therefore, some of the red blood cells in the red blood cell expansion fusion image obtained after step S106 may appear in a ring shape, and the real morphological features of the red blood cells cannot be effectively displayed.
Therefore, in some embodiments of the present application, a plurality of connected components in the red blood cell expansion fusion image can be determined by performing corresponding calculation according to the red blood cell expansion fusion image. And determining whether the area editing of each connected domain is smaller than a corresponding preset threshold, and filling the connected domain under the condition that the area of the connected domain is smaller than the corresponding preset threshold.
Through the scheme, the red blood cells can be expanded and fused with the part of the red blood cells in the image, which are annular in the image, so that the real morphological characteristics of the red blood cells can be effectively displayed.
And S108, processing the red blood cell segmentation image and determining a plurality of connected domains in the red blood cell segmentation image.
And calculating connected domains in the red blood cell segmentation image, and counting the number of the connected domains.
S109, counting the number of red blood cells in the red blood cell image according to the plurality of connected domains in the red blood cell segmentation image.
In the present specification, it can be considered that one connected domain corresponds to one red blood cell, and the number of connected domains in the red blood cell segmentation image is counted, that is, the number of red blood cells in the red blood cell image is counted
Furthermore, in addition to normal erythrocytes, erythrocytes may also contain abnormal erythrocytes, such as fragmented erythrocytes, altered erythrocytes, etc. The abnormal state red blood cells mentioned herein include at least one of: crushed red blood cells, and variant red blood cells. Abnormal erythrocytes such as numbers of fragmented erythrocytes and numbers of mutated erythrocytes are also important for clinical lesion examination.
Therefore, in some embodiments of the present application, the number of red blood cells in normal state and red blood cells in abnormal state can be further detected by the following methods:
calculating the circularity of each connected domain in the red blood cell segmentation image;
under the condition that the circularity of the connected domain is smaller than a preset threshold value, determining that the connected domain is the red blood cells in the abnormal state, and accumulating the number of the red blood cells in the abnormal state;
and under the condition that the circularity of the connected domain is greater than or equal to a preset threshold value, determining that the connected domain is red blood cells in a normal state, and accumulating the number of the red blood cells in a long state.
Because the crushed red blood cells generally refer to red blood cell fragments or incomplete red blood cells, the size is different, the appearance is irregular, and the crushed red blood cells have various shapes such as thorn shape, helmet shape, triangle shape and the like. The altered red blood cells can be red blood cells with altered shapes. That is, the normal state red blood cells and the abnormal state red blood cells are greatly different in shape, so that the circularity of each connected domain can be calculated, and compared with the circularity of each connected domain according to a corresponding preset threshold value, thereby determining whether the connected domain is the abnormal state red blood cells or the normal state red blood cells.
The embodiment of the application provides a red blood cell image detection method, which is characterized in that a red blood cell segmentation image is obtained by sequentially carrying out graying, edge detection, expansion operation, closing operation and other processing on the red blood cell image, a plurality of connected domains in the red blood cell segmentation image are determined, and the number of red blood cells in the red blood cell image is counted according to the connected domains. Compared with the existing red blood cell image detection method, the method is not limited to a specific detection environment, has strong adaptability to the detection environment and is not easily influenced by the environment; on the other hand, the erythrocyte image detection method provided by the embodiment of the application has high statistical accuracy and high accuracy, and is simpler and more convenient compared with the method adopted in the prior art, so that the erythrocyte detection efficiency is improved, and the user experience is enhanced.
Fig. 3 is a schematic structural diagram of an erythrocyte image detecting device according to an embodiment of the present application, and as shown in fig. 3, the device includes:
at least one processor; and
a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to:
obtaining a corresponding erythrocyte image, and obtaining a corresponding erythrocyte graying image according to the erythrocyte image;
carrying out edge detection on the red blood cell gray level image to obtain a corresponding red blood cell edge information image;
processing the erythrocyte edge information image based on expansion operation to obtain a corresponding erythrocyte expansion fusion image;
performing closed operation processing on the erythrocyte expansion fusion image to obtain an erythrocyte segmentation image;
determining a plurality of connected components in the red blood cell segmentation image;
and counting the number of red blood cells in the red blood cell image according to a plurality of connected domains in the red blood cell segmentation image.
The embodiment of the present application further provides a non-volatile computer storage medium for red blood cell image detection, which stores computer-executable instructions configured to:
obtaining a corresponding erythrocyte image, and obtaining a corresponding erythrocyte graying image according to the erythrocyte image;
carrying out edge detection on the red blood cell gray level image to obtain a corresponding red blood cell edge information image;
processing the erythrocyte edge information image based on expansion operation to obtain a corresponding erythrocyte expansion fusion image;
performing closed operation processing on the erythrocyte expansion fusion image to obtain an erythrocyte segmentation image;
determining a plurality of connected components in the red blood cell segmentation image;
and counting the number of red blood cells in the red blood cell image according to a plurality of connected domains in the red blood cell segmentation image.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device and media embodiments, the description is relatively simple as it is substantially similar to the method embodiments, and reference may be made to some descriptions of the method embodiments for relevant points.
The device and the medium provided by the embodiment of the application correspond to the method one to one, so the device and the medium also have the similar beneficial technical effects as the corresponding method, and the beneficial technical effects of the method are explained in detail above, so the beneficial technical effects of the device and the medium are not repeated herein.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method of red blood cell image detection, the method comprising:
obtaining a corresponding erythrocyte image, and obtaining a corresponding erythrocyte graying image according to the erythrocyte image;
carrying out edge detection on the red blood cell gray level image to obtain a corresponding red blood cell edge information image;
processing the erythrocyte edge information image based on expansion operation to obtain a corresponding erythrocyte expansion fusion image;
performing closed operation processing on the erythrocyte expansion fusion image to obtain an erythrocyte segmentation image;
determining a plurality of connected components in the red blood cell segmentation image;
and counting the number of red blood cells in the red blood cell image according to a plurality of connected domains in the red blood cell segmentation image.
2. The method according to claim 1, wherein obtaining the corresponding grayscale image of the red blood cell from the red blood cell image comprises:
decomposing the red blood cell image into a green single-channel image;
and carrying out graying processing on the green single-channel image to obtain a corresponding red blood cell grayed image.
3. The method of claim 1, wherein prior to obtaining the corresponding red blood cell edge information image, the method further comprises:
and carrying out filtering processing on the red blood cell gray-scale image so as to eliminate salt and pepper noise of the red blood cell gray-scale image.
4. The method of claim 1, wherein prior to obtaining the corresponding red blood cell expansion fusion image, the method further comprises:
according to a preset threshold value, performing threshold value segmentation on the red blood cell gray image to obtain a red blood cell gray image with a reserved red blood cell body; or
And performing threshold segmentation on the erythrocyte marginal information image according to a preset threshold to obtain the erythrocyte marginal information image with the reserved erythrocyte body.
5. The method of claim 1, wherein prior to obtaining the red blood cell segmentation image, the method further comprises:
performing corresponding calculation according to the erythrocyte expansion fusion image, and determining a plurality of connected domains in the erythrocyte expansion fusion image;
determining whether the area of each connected domain is smaller than a corresponding preset threshold value;
and filling the connected domain under the condition that the area of the connected domain is smaller than a corresponding preset threshold value.
6. The method of claim 1, wherein the red blood cells comprise normal state red blood cells, abnormal state red blood cells;
the counting the number of red blood cells in the red blood cell image according to the plurality of connected domains in the red blood cell segmentation image specifically includes:
calculating the circularity of each connected domain in the red blood cell segmentation image;
under the condition that the circularity of the connected domain is smaller than a preset threshold value, determining that the connected domain is abnormal red blood cells, and accumulating the number of the abnormal red blood cells;
and under the condition that the circularity of the connected domain is greater than or equal to a preset threshold value, determining that the connected domain is red blood cells in a normal state, and accumulating the number of the red blood cells in the normal state.
7. The method of claim 6, wherein the abnormal state of the red blood cells comprises at least one of: crushed red blood cells, and variant red blood cells.
8. The method according to claim 1, wherein performing edge detection on the red blood cell grayscale image to obtain a corresponding red blood cell edge information image specifically comprises:
and based on a preset direction controllable filter, carrying out edge detection on the red blood cell gray image to obtain a corresponding red blood cell edge information image.
9. An apparatus for red blood cell image detection, the apparatus comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to:
obtaining a corresponding erythrocyte image, and obtaining a corresponding erythrocyte graying image according to the erythrocyte image;
carrying out edge detection on the red blood cell gray level image to obtain a corresponding red blood cell edge information image;
processing the erythrocyte edge information image based on expansion operation to obtain a corresponding erythrocyte expansion fusion image;
performing closed operation processing on the erythrocyte expansion fusion image to obtain an erythrocyte segmentation image;
determining a plurality of connected components in the red blood cell segmentation image;
and counting the number of red blood cells in the red blood cell image according to a plurality of connected domains in the red blood cell segmentation image.
10. A non-transitory computer storage medium for red blood cell image detection, storing computer-executable instructions, the computer-executable instructions configured to:
obtaining a corresponding erythrocyte image, and obtaining a corresponding erythrocyte graying image according to the erythrocyte image;
carrying out edge detection on the red blood cell gray level image to obtain a corresponding red blood cell edge information image;
processing the erythrocyte edge information image based on expansion operation to obtain a corresponding erythrocyte expansion fusion image;
performing closed operation processing on the erythrocyte expansion fusion image to obtain an erythrocyte segmentation image;
determining a plurality of connected components in the red blood cell segmentation image;
and counting the number of red blood cells in the red blood cell image according to a plurality of connected domains in the red blood cell segmentation image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010236853.0A CN111583175B (en) | 2020-03-30 | 2020-03-30 | Erythrocyte image detection method, erythrocyte image detection equipment and erythrocyte image detection medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010236853.0A CN111583175B (en) | 2020-03-30 | 2020-03-30 | Erythrocyte image detection method, erythrocyte image detection equipment and erythrocyte image detection medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111583175A true CN111583175A (en) | 2020-08-25 |
| CN111583175B CN111583175B (en) | 2024-03-22 |
Family
ID=72112596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010236853.0A Active CN111583175B (en) | 2020-03-30 | 2020-03-30 | Erythrocyte image detection method, erythrocyte image detection equipment and erythrocyte image detection medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111583175B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669304A (en) * | 2021-01-05 | 2021-04-16 | 天津大学 | Pollen detection method based on digital image processing technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101826207A (en) * | 2010-04-09 | 2010-09-08 | 杭州电子科技大学 | Method for automatically searching region of interest in cell microscopic images |
| WO2012016242A2 (en) * | 2010-07-30 | 2012-02-02 | Aureon Biosciences, Inc. | Systems and methods for segmentation and processing of tissue images and feature extraction from same for treating, diagnosing, or predicting medical conditions |
| CN105631456A (en) * | 2015-12-15 | 2016-06-01 | 安徽工业大学 | Particle swarm optimization ITTI model-based white cell region extraction method |
| CN110110709A (en) * | 2019-05-27 | 2019-08-09 | 湖南开启时代智能科技有限公司 | A kind of red white corpuscle differential counting method, system and equipment based on image procossing |
-
2020
- 2020-03-30 CN CN202010236853.0A patent/CN111583175B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101826207A (en) * | 2010-04-09 | 2010-09-08 | 杭州电子科技大学 | Method for automatically searching region of interest in cell microscopic images |
| WO2012016242A2 (en) * | 2010-07-30 | 2012-02-02 | Aureon Biosciences, Inc. | Systems and methods for segmentation and processing of tissue images and feature extraction from same for treating, diagnosing, or predicting medical conditions |
| CN105631456A (en) * | 2015-12-15 | 2016-06-01 | 安徽工业大学 | Particle swarm optimization ITTI model-based white cell region extraction method |
| CN110110709A (en) * | 2019-05-27 | 2019-08-09 | 湖南开启时代智能科技有限公司 | A kind of red white corpuscle differential counting method, system and equipment based on image procossing |
Non-Patent Citations (4)
| Title |
|---|
| 刘伯强;尹聪;刘忠国;徐凯;张振旺;: "融合灰度和梯度信息的彩色细胞图像自动分割" * |
| 刘肖肖;孔德友;刘广宇;刘伯强;: "基于融合算法的尿沉渣显微图像有形成分外边缘检测方法研究" * |
| 范卫华;冯念伦;苏本华;尹聪;: "尿沉渣中红细胞影像分析研究" * |
| 蒋先刚;何晓岭;范自柱;: "粪便镜检图像中红白细胞的分割与识别方法" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669304A (en) * | 2021-01-05 | 2021-04-16 | 天津大学 | Pollen detection method based on digital image processing technology |
| CN112669304B (en) * | 2021-01-05 | 2023-02-28 | 天津大学 | Pollen detection method based on digital image processing technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111583175B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5941674B2 (en) | Cell contour forming apparatus and method, and cell contour forming program | |
| Oberholzer et al. | Methods in quantitative image analysis | |
| Toh et al. | Automated fish counting using image processing | |
| CN104063848B (en) | A kind of enhancement method of low-illumination image and device | |
| Angulo et al. | Automated detection of working area of peripheral blood smears using mathematical morphology | |
| CN115018844B (en) | Plastic film quality evaluation method based on artificial intelligence | |
| CN111027546B (en) | Character segmentation method, device and computer readable storage medium | |
| CN104732510B (en) | A kind of camera lens blackspot detection method and device | |
| US20080144898A1 (en) | Method for forming an optimally exposed image of cytological specimen | |
| CN111046862B (en) | Character segmentation method, device and computer readable storage medium | |
| CN110223305A (en) | Cell segmentation method, apparatus and readable storage medium storing program for executing | |
| CN110110667B (en) | Processing method and system of diatom image and related components | |
| JP6714273B2 (en) | Corneal endothelial cell quality evaluation support system | |
| CN111192241A (en) | Quality evaluation method and device of face image and computer storage medium | |
| CN111583175A (en) | Erythrocyte image detection method, erythrocyte image detection equipment and erythrocyte image detection medium | |
| Devi et al. | Analysis & evaluation of Image filtering Noise reduction technique for Microscopic Images | |
| CN109060830B (en) | Method and device for detecting impurities of display screen | |
| EP3293672A1 (en) | Particle boundary identification | |
| GB2485209A (en) | Curve fitting to histogram data for identification of chromatin types in nuclei | |
| CN106910172A (en) | A kind of image processing method and device | |
| JP3653804B2 (en) | Particle image region segmentation method and apparatus | |
| CN115423861A (en) | Gas leakage detection method and device, equipment and storage medium | |
| CN114494098A (en) | Lithium battery X-ray image enhancement method and device and storage medium | |
| JP4452624B2 (en) | Automatic histological categorization of tubules | |
| Amitha et al. | Developement of computer aided system for detection and classification of mitosis using SVM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240227 Address after: 250000 Langchao Science Park, No. 1036, Langchao Road, high tech Zone, Jinan, Shandong Applicant after: Inspur Genersoft Co.,Ltd. Country or region after: China Address before: 250101 Inspur science and Technology Park, 1036 Inspur Road, hi tech Zone, Jinan City, Shandong Province Applicant before: SHANDONG INSPUR GENESOFT INFORMATION TECHNOLOGY Co.,Ltd. Country or region before: China |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |