CN110930345B - Sperm tail identification method - Google Patents
Sperm tail identification method Download PDFInfo
- Publication number
- CN110930345B CN110930345B CN201811009206.5A CN201811009206A CN110930345B CN 110930345 B CN110930345 B CN 110930345B CN 201811009206 A CN201811009206 A CN 201811009206A CN 110930345 B CN110930345 B CN 110930345B
- Authority
- CN
- China
- Prior art keywords
- image
- tail
- area
- sperm
- filtering
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 210000000582 semen Anatomy 0.000 claims abstract description 47
- 238000001914 filtration Methods 0.000 claims abstract description 33
- 238000012935 Averaging Methods 0.000 claims description 7
- 230000003321 amplification Effects 0.000 claims description 6
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 239000012535 impurity Substances 0.000 abstract description 12
- 238000011160 research Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000010186 staining Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011496 digital image analysis Methods 0.000 description 1
- 238000004043 dyeing Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000009027 insemination Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009612 semen analysis Methods 0.000 description 1
- 238000012360 testing method 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
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G06T5/90—
-
- 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
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10056—Microscopic 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
A method for identifying the tail of sperm, comprising the steps of: step 1: acquiring an image, and step 2: obtaining a difference image: step 3: acquiring a tail image; step 4: acquiring a sperm head region image; step 5: combining the tail image and the sperm head region image; step 6: and filtering a bright spot area in which a long tail area does not appear within a preset distance to obtain a sperm area image. The difference image is obtained, the bright spot area in the semen sample image is filtered, the non-long tail area is conveniently filtered, and the image of impurities or cells with large difference from the sperm structure in the semen is realized. The method can be used for filtering bright spot images without long tail areas nearby the filtering, so that the bright spot areas of the non-sperm cells are filtered. The method realizes the accurate filtration of impurities in semen, and is convenient for researchers to count and research semen.
Description
Technical Field
The invention relates to the field of sperm detection, in particular to a tail identification method of sperms.
Background
Computer aided analysis technology (CASA) based on sperm quality was rapidly developed at the end of the last 80 th century. It has been found that the automatic measurement and evaluation of various data of sperm by using a computer image analysis technology has many advantages, such as simple operation, high analysis speed, high calculation accuracy, good repeatability, providing accurate reference data for artificial insemination, improving the inspection level of inspection doctors, reducing the workload of the inspection doctors, and overcoming the defects of the traditional measurement method, such as time consumption, poor measurement accuracy, strong artificial subjectivity, etc.
In the prior art, most of the analysis methods for semen are as follows: firstly, staining a semen sample, amplifying and collecting dynamic images under a microscope through the microscope and a camera system, and counting or identifying sperms in the images. But this approach has the following problems:
1. after the semen sample is dyed, the activity of sperms can be influenced to a certain extent, so that the analysis of the semen quality by the answer is influenced;
2. since semen contains many non-sperm components (such as round cells and impurities), the judgment of the number of sperm is affected.
To above problem, the staining procedure to the semen sample has been saved to current semen analysis process, directly detects the semen sample through the microscope of high power, in the testing process, utilizes phase contrast microscope to acquire the cell image in the semen, and the sperm cell in the semen can show into bright spot under the microscope, thereby the inspector obtains the quantity of sperm through the automatic bright spot count of CASA system.
Although the method can avoid the influence of the dyeing process on the semen activity, a plurality of impurities can be displayed as bright spots under a microscope, and the method has a display effect similar to that of sperms, so that the calculation of the number of sperms by a CASA system is influenced.
Disclosure of Invention
The invention aims to provide a sperm tail recognition method which has the advantages that non-sperm cells or impurities in semen can be filtered out through the structure of the sperm with the tail, and the number of the sperm in the semen can be clearly presented.
The technical aim of the invention is realized by the following technical scheme:
a method for identifying the tail of a sperm, comprising the steps of:
step 1: acquiring an image, and acquiring a semen sample image by using an image amplifying device;
step 2: obtaining a difference image, and filtering a bright spot area in the semen sample image to obtain the difference image;
step 3: acquiring a tail image, and filtering a non-long tail region in the difference image to acquire the tail image;
step 4: acquiring a sperm head area image, and filtering a non-bright spot area in the sperm sample image to acquire a sperm head area image;
step 5: combining the tail image and the sperm head region image;
step 6: and acquiring a sperm area image, and filtering a bright spot area in which a long tail area does not appear within a preset distance to acquire the sperm area image.
By adopting the technical scheme, as the impurity species in the semen is too many, and impurities can be displayed as bright point images identical to those of spermatids under a microscope, the spermatids are counted or the images are sampled to generate interference. The difference image is obtained, the bright spot area in the semen sample image is filtered, the non-long tail area is conveniently filtered, and the image of impurities or cells with large difference from the sperm structure in the semen is realized. Because the bright spot image of the non-sperm does not have a long tail-shaped area nearby, the bright spot image of the non-sperm can be filtered nearby by a distance selecting method, and the bright spot area of the non-sperm cells can be filtered. Therefore, the method realizes the accurate filtration of impurities in the semen, and is convenient for researchers to count and research the semen.
As an improvement of the present invention, the step 2 includes:
step 2-1: carrying out averaging treatment on the semen sample image to obtain an average value image;
step 2-2: and carrying out difference on the mean value image and the semen sample image to generate the difference image.
As an improvement of the invention, the method for the averaging treatment comprises the following steps:
wherein Sxy represents that the center point is at (x, y), a filter window with the size of m×n is selected, g (s, t) represents an original image, and f (x, y) represents an image obtained after mean filtering.
As an improvement of the present invention, the step 2-2 further includes: and performing brightness amplification after the difference between the mean value image and the semen sample image to generate the difference image.
As an improvement of the present invention, the method for amplifying brightness is as follows:
g’=(g1-g2)*Mult+Add
wherein g1 is a semen sample image, g2 is a mean image, mult is an amplification factor, add is an offset, and g' is the difference image.
As an improvement of the present invention, the step 3 includes:
step 3-1: performing binarization processing on the difference image to generate a binarized image;
step 3-2: and filtering non-long tail regions in the binarized image to obtain the tail image.
As an improvement of the present invention, the step 3-2 includes:
step 3-2-1: selecting a roundness range and a convexity range;
step 3-2-2: and filtering the image area which can not meet the roundness range and the convexity range simultaneously to obtain the tail image.
As an improvement of the present invention, a method of filtering an image region that cannot satisfy both a roundness range and a convexity range includes:
wherein p is the center point of the selected image area, pi is any point on the contour of the selected image area, and round is the Roundness of the selected image area;
where Fo is the total area circled by all the salient points in the selected image area and Fc is the actual area of the selected image area;
n={f(R-<Roundness<R+)andf(C-<C<C+)}
wherein n is the tail image, the roundness range is the convexity range.
In summary, the invention has the following beneficial effects:
1. the filtering precision is high, the filtering of impurities, cells and non-sperm bright spot areas in the semen can be respectively realized by adopting the method of filtering the non-long tail area and selecting the distance, and the obtained sperm area image can clearly show the number of sperms in the semen.
2. The long tail region is selected in a roundness and convexity selection mode, so that the complexity of data calculation processing is reduced while the selection of the long tail region is realized.
Drawings
A flow chart of a method of tail recognition of sperm of figure 1;
FIG. 2 is a schematic diagram of a semen sample image;
FIG. 3 is a schematic representation of a mean image;
FIG. 4 is a schematic diagram of a difference image;
FIG. 5 is a schematic diagram of a tail image;
FIG. 6 is a schematic view of a sperm head region image;
fig. 7 is a schematic diagram of a blended image.
Detailed Description
The present invention will be described in further detail below with reference to the drawings, wherein like parts are designated by like reference numerals. It should be noted that the words "front", "rear", "left", "right", "upper" and "lower", "bottom" and "top" used in the following description refer to directions in the drawings, and the words "inner" and "outer" refer to directions toward or away from, respectively, the geometric center of a particular component.
A method for identifying the tail of a sperm, as shown in fig. 1, comprising the steps of:
step 1: an image is acquired and an image of the semen sample as shown in fig. 2 is acquired using an image magnification device, preferably a phase contrast microscope.
Step 2: and obtaining a difference image, and filtering a bright spot area in the semen sample image to obtain the difference image.
Step 2-1: and (3) carrying out averaging treatment on the semen sample image to obtain an average value image shown in fig. 3.
Step 2-2: the difference between the mean image and the semen sample image is made to generate a difference image as shown in fig. 4.
Step 2-1: and (3) carrying out averaging treatment on the semen sample image to obtain an average value image shown in fig. 3.
The method for the averaging treatment comprises the following steps:
wherein Sxy represents that the center point is at (x, y), a filter window with the size of m×n is selected, g (s, t) represents an original image, and f (x, y) represents an image obtained after mean filtering.
Step 2-2: and performing difference between the mean value image and the semen sample image to perform brightness amplification, and generating a difference image. The brightness amplifying method comprises the following steps:
g’=(g1-g2)*Mult+Add
wherein g1 is a semen sample image, g2 is a mean image, mult is an amplification factor, add is an offset, and g' is a difference image.
Step 3: and acquiring a tail image, and filtering a non-long tail region in the difference image to acquire the tail image.
Step 3-1: and carrying out binarization processing on the difference image to generate a binarized image.
Step 3-2: and filtering non-long tail-shaped areas in the binarized image to obtain a tail image.
Step 3-2-1: the roundness range and convexity range are selected, wherein the roundness range is [ R-, R+ ], and the convexity range is [ C-, C+ ].
Step 3-2-2: filtering the image area that cannot satisfy both the roundness range and convexity range, obtains the tail image as shown in fig. 5.
The method for filtering the image area which can not simultaneously meet the roundness range and the convexity range comprises the following steps:
wherein p is the center point of the selected image area, pi is any point on the contour of the selected image area, and round is the Roundness of the selected image area;
where Fo is the total area circled by all the salient points in the selected image area and Fc is the actual area of the selected image area; the tail image n is:
n={f(R-<Roundness<R+)andf(C-<C<C+)}
step 4: acquiring a sperm head region image, and filtering a non-bright spot region in the sperm sample image by adopting the method from the step 1 to the step 2 to obtain the sperm head region image shown in fig. 6.
Further, in the process of acquiring the sperm head region image, binarization processing is carried out on the image after the step 2, so that the bright spot region in the sperm head region image is displayed more clearly.
Step 5: the tail image and the sperm head region image were combined to obtain a blended image as shown in fig. 7.
Step 6: and acquiring a sperm area image, and filtering a bright spot area, in which a long tail area does not appear in a preset distance, in the mixed image to acquire the sperm area image.
From the above, it can be seen that the difference image is obtained, and the bright spot area in the semen sample image is filtered, so that the non-long tail area is conveniently filtered, and the image of the impurity or cell in the semen, which is greatly different from the sperm structure, is realized. Because the bright spot image of the non-sperm does not have a long tail-shaped area nearby, the bright spot image of the non-sperm can be filtered nearby by a distance selecting method, and the bright spot area of the non-sperm cells can be filtered. Therefore, the method realizes the accurate filtration of impurities in the semen, and is convenient for researchers to count and research the semen.
The present embodiment is only for explanation of the present invention and is not to be construed as limiting the present invention, and modifications to the present embodiment, which may not creatively contribute to the present invention as required by those skilled in the art after reading the present specification, are all protected by patent laws within the scope of claims of the present invention.
Claims (8)
1. A method for identifying the tail of a sperm, comprising the steps of:
step 1: acquiring an image, and acquiring a semen sample image by using an image amplifying device;
step 2: obtaining a difference image, and filtering a bright spot area in the semen sample image to obtain the difference image;
step 3: acquiring a tail image, and filtering a non-long tail region in the difference image to acquire the tail image;
step 4: acquiring a sperm head area image, and filtering a non-bright spot area in the sperm sample image to acquire a sperm head area image;
step 5: combining the tail image and the sperm head region image;
step 6: and acquiring a sperm area image, and filtering a bright spot area in which a long tail area does not appear within a preset distance to acquire the sperm area image.
2. A method of sperm tail identification as described in claim 1, wherein: the step 2 comprises the following steps:
step 2-1: carrying out averaging treatment on the semen sample image to obtain an average value image;
step 2-2: and carrying out difference on the mean value image and the semen sample image to generate the difference image.
3. A method of sperm tail identification as described in claim 2, wherein: the method for the averaging treatment comprises the following steps:
wherein Sxy represents that the center point is at (x, y), a filter window with the size of m×n is selected, g (s, t) represents an original image, and f (x, y) represents an image obtained after mean filtering.
4. A method of sperm tail recognition as described in claim 3, wherein: the step 2-2 further comprises: and performing brightness amplification after the difference between the mean value image and the semen sample image to generate the difference image.
5. The method for identifying the tail of a sperm cell as described in claim 4, wherein: the brightness amplifying method comprises the following steps: g' = (g 1-g 2) mult+add
Wherein g1 is a semen sample image, g2 is a mean image, mult is an amplification factor, add is an offset, and g' is the difference image.
6. The method for identifying the tail of a sperm cell as described in claim 5, wherein: the step 3 comprises the following steps:
step 3-1: performing binarization processing on the difference image to generate a binarized image;
step 3-2: and filtering non-long tail regions in the binarized image to obtain the tail image.
7. The method for identifying the tail of a sperm cell as described in claim 6, wherein: the step 3-2 comprises the following steps:
step 3-2-1: selecting a roundness range and a convexity range;
step 3-2-2: and filtering the image area which can not meet the roundness range and the convexity range simultaneously to obtain the tail image.
8. The method for identifying the tail of a sperm cell as described in claim 7, wherein: the method for filtering the image area which can not simultaneously meet the roundness range and the convexity range comprises the following steps:
wherein p is the center point of the selected image area, pi is any point on the contour of the selected image area, and round is the Roundness of the selected image area;
where Fo is the total area circled by all the salient points in the selected image area and Fc is the actual area of the selected image area;
n={f(R-<Roundness<R+)andf(C-<C<C+)}
wherein n is a tail image, the roundness range is [ R-, R+ ], and the convexity range is [ C-, C+ ].
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811009206.5A CN110930345B (en) | 2018-08-31 | 2018-08-31 | Sperm tail identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811009206.5A CN110930345B (en) | 2018-08-31 | 2018-08-31 | Sperm tail identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110930345A CN110930345A (en) | 2020-03-27 |
CN110930345B true CN110930345B (en) | 2023-05-30 |
Family
ID=69854957
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811009206.5A Active CN110930345B (en) | 2018-08-31 | 2018-08-31 | Sperm tail identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110930345B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111563550B (en) * | 2020-04-30 | 2023-08-25 | 北京百度网讯科技有限公司 | Sperm morphology detection method and device based on image technology |
CN112330660B (en) * | 2020-11-24 | 2024-02-02 | 成都朴华科技有限公司 | Sperm tail detection method and system based on neural network |
CN113221860B (en) * | 2021-07-07 | 2021-10-22 | 深圳市瑞图生物技术有限公司 | DNA fragment recognition method, device, computer equipment and storage medium |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150031019A1 (en) * | 2013-03-14 | 2015-01-29 | Cellcura As | Computer Assisted Sperm Profile Analysis and Recognition |
WO2015137466A1 (en) * | 2014-03-12 | 2015-09-17 | 一般社団法人家畜改良事業団 | Sperm inspection method and device |
-
2018
- 2018-08-31 CN CN201811009206.5A patent/CN110930345B/en active Active
Non-Patent Citations (4)
Title |
---|
宋继清等.改进的动物精子图像分割算法.计算机工程与设计.2012,第33卷(第11期),4259-4263. * |
林玉狮.人类精子细胞图像的检测和追踪.中国优秀硕士学位论文全文数据库 信息科技辑.2016,(第4期),I138-995. * |
汪创.基于计算机视觉的动物精子形态分析系统.电子世界.2018,28-30. * |
谭征等.一种密度聚类的染色精子医学图像识别算法.烟台大学学报(自然科学与工程版).2014,第27卷(第4期),279-283. * |
Also Published As
Publication number | Publication date |
---|---|
CN110930345A (en) | 2020-03-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110930345B (en) | Sperm tail identification method | |
US7796815B2 (en) | Image analysis of biological objects | |
AU2003248207B2 (en) | Color Space Transformations for Use in Identifying Objects of Interest in Biological Specimens | |
US8135203B2 (en) | Cell image processor and cell image processing method | |
US20150187077A1 (en) | Image processing device, program, image processing method, computer-readable medium, and image processing system | |
WO2005080944A1 (en) | Analysis of cell morphology and motility | |
CN103984939B (en) | A kind of sample visible component sorting technique and system | |
US9607372B2 (en) | Automated bone marrow cellularity determination | |
CN110736748A (en) | Immunohistochemical nuclear plasma staining section diagnosis method and system | |
CN107678192A (en) | A kind of Mura defects detection method and system based on machine vision | |
CN109182081A (en) | A kind of unicellular separation system based on image processing model | |
CN111583185A (en) | Ki67 cell nucleus counting method and system based on pathological immunohistochemistry | |
CN107525768A (en) | A kind of method of quality control of DNA ploidy body analytical equipment | |
US8467590B2 (en) | Microscopy analysis technique | |
CN106767467A (en) | A kind of indexable insert tip, throw away tip blunt circle detecting system based on machine vision | |
CN109540890A (en) | A kind of DNA quantitative analysis method based on microcytoscope image | |
CN109948544A (en) | A kind of automatic positioning of target bacterium colony and recognition methods | |
CN113552126A (en) | Reticulocyte detection method and system | |
CN111583186A (en) | Pathological ER/PR (ER/PR) cell nucleus counting method and system for clinical application | |
CN112750118B (en) | Novel method and system for identifying cell number in single cell pore plate sequencing based on automatic visual detection | |
Sreelatha et al. | Automatic detection of comets in silver stained comet assay images for DNA damage analysis | |
CN114332027A (en) | Cell uniformity obtaining method and system based on image analysis | |
CN111832481B (en) | Edible vegetable oil processing quality detection method, equipment, storage medium and device | |
CN114627308A (en) | Extraction method and system of bone marrow cell morphological characteristics | |
CN110458042B (en) | Method for detecting number of probes in fluorescent CTC |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |