CN109767450A - A kind of mask method for sperm morphology intelligence diagosis system - Google Patents
A kind of mask method for sperm morphology intelligence diagosis system Download PDFInfo
- Publication number
- CN109767450A CN109767450A CN201811529506.6A CN201811529506A CN109767450A CN 109767450 A CN109767450 A CN 109767450A CN 201811529506 A CN201811529506 A CN 201811529506A CN 109767450 A CN109767450 A CN 109767450A
- Authority
- CN
- China
- Prior art keywords
- image
- diagosis
- sperm
- intelligence
- profile
- 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.)
- Pending
Links
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The present invention provides a kind of mask method for sperm morphology intelligence diagosis system, includes the following steps: S1) HSV image conversion process is carried out to dyeing glass slide image；S2) image binaryzation is handled；S3 the structural element for) constructing 5 × 5 unit matrixs, the operation of corrosion treatment again is first expanded to image, extracts image outline；S4) all profiles are judged, the profile deletion of threshold value will be less than comprising counting；S5 all undesirable profiles) are excluded, profile list is updated, complete the drafting of profile mark.Advantages of the present invention are as follows: provide the solution from the human-computer interaction for generating sperm picture, marking to single sperm, generating diagosis conclusion, a whole set of diagosis process of more people intersection diagosis；The present invention is directed to improve the intelligent and unmanned of medicine diagosis, can spread out the working environment stretched and be labeled applied to all kinds of needs to a large amount of targets, such as bone detection, CT film field.
Description
Technical field
The present invention relates to field of artificial intelligence, and in particular to a kind of mark for sperm morphology intelligence diagosis system
Method.
Background technique
Sperm morphological is
Reflect an important indicator of male fecundity.With the development of medical science, the rapid emergence of andrology and sterility
Patient increase, simple Sperm recovery is no longer satisfied the needs of clinical development, can not comprehensively, objectively reflect trouble
The truth of person can not evaluate testicular function.Guzick DS etc. suggests the inspection diagnosis of medical field modification male sterility
Standard proposes the fertility that reflect male in the form of sperm.
Existing sperm morphology diagosis mode has the following problems: slide diagosis is watched under microscope, eyes fatiguability is long
Phase work harm health；Single diagosis, as a result subjectivity is too strong, and conclusion is unstable；If slide is not retained, data are abandoned, conclusion
It can not recall.
Summary of the invention
The object of the present invention is to provide it is a kind of reduction human cost, improve mark effect be used for sperm morphology intelligence diagosis
The mask method of system.
In order to achieve the above object, the present invention is achieved through the following technical solutions:
A kind of mask method for sperm morphology intelligence diagosis system, includes the following steps:
S1) under based on Python and openCV environment, HSV image conversion process is carried out to dyeing glass slide image；
S2 after) obtaining initialization HSV data, white (255) are set as by the part in threshold range for given staining conditions,
Black (0) is set as lower than bottom threshold or higher than the part of upper threshold；
S3 the structural element for) constructing 5 × 5 unit matrixs carries out the image after binary conversion treatment according to the structural element of construction
The chamfered shape of sperm in image is extracted in the operation of first expansion process corrosion treatment again；
S4) to the coordinate points number given threshold of profile, all profiles are judged, the profile of threshold value will be less than comprising counting
It deletes；
S5 all undesirable profiles) are excluded, profile list is updated, complete the drafting of profile mark.
Further, step S2) in, the lower limit that the threshold range of given staining conditions is arranged is [50,10,10], the upper limit
For [120,255,255].
Further, step S3) in, expansion process is used to merge same sperm adjacent area in image.
Further, step S3) in, corrosion treatment is used to remove the noise spot in image.
Compared with prior art, the present invention having the advantage that
A kind of mask method for sperm morphology intelligence diagosis system of the present invention, provide from generate sperm picture, to single
Sperm marks, generates the solution of the human-computer interaction of diagosis conclusion, a whole set of diagosis process of more people intersection diagosis.The present invention
It is demarcated by area of computer aided, promotes diagosis efficiency, unified diagosis standard；More people intersect diagosis, improve conclusion accuracy, are promoted
Confidence level；Diagosis System information retains morphological data, forms data assets.
The present invention is directed to improve the intelligent and unmanned of medicine diagosis, it can spread out and stretch applied to all kinds of needs to a large amount of targets
The working environment being labeled, such as bone detection, CT film field.
The present invention is converted by using HSV, is realized in the case where color of object and background color are closer to, to mesh
Profile is marked more completely capture and extract.
The present invention is realized the secondary removal for ambient noise point, preferably ensure that by design removal noise module
Ideal output result.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the mask method for sperm morphology intelligence diagosis system of the present invention.
Fig. 2 is a kind of HSV conversion effect figure of the mask method for sperm morphology intelligence diagosis system of the present invention.
Fig. 3 is effect picture after a kind of expansion of the mask method for sperm morphology intelligence diagosis system of the present invention.
Fig. 4 is effect picture after a kind of corrosion of the mask method for sperm morphology intelligence diagosis system of the present invention.
Fig. 5 is a kind of final mark outline effect of the mask method for sperm morphology intelligence diagosis system of the present invention
Figure.
Specific embodiment
With reference to the accompanying drawing, the embodiment of the present invention is described in further detail.
A kind of mask method for sperm morphology intelligence diagosis system, using the dividing method based on hsv color feature,
Target mark is carried out to an image untreated, that ambient noise is biggish, target object is more, ensure that in dyeing face
In the case that color is identical, realization system is automatically labeled sperm profile, adapts to future medicine intelligent diagnosis to reach
Change, unmanned needs.
As shown in Figure 1, specifically comprising the following steps:
S1) under based on Python and openCV environment, HSV image conversion process is carried out to dyeing glass slide image.
S2 after) obtaining initialization HSV data, white is set as by the part in threshold range for given staining conditions
(255), be set as black (0) lower than bottom threshold or higher than the part of upper threshold, the lower limit of threshold range be [50,10,
10], the upper limit is [120,255,255].HSV image conversion method is converted different from traditional image RGB, and HSV can be for close
RGB color carry out it is more apparent distinguish, more will can completely extract objective contour, the processing point for subsequent step
It cuts.
S3) construct 5 × 5 unit matrixs structural element (core), according to the structural element of construction to binary conversion treatment after
Image carries out expansion process operation, and expansion process is used to merge same sperm adjacent area in image；Corrosion treatment behaviour is carried out again
Make, corrosion treatment is used to remove more apparent noise spot in image, extracts the chamfered shape of sperm in image.
S4) to the coordinate points number given threshold of profile, all profiles are judged, threshold value will be less than comprising counting
Profile is deleted, and is realized the secondary removal to ambient noise point, is guaranteed comparatively ideal output result.
S5 all undesirable profiles) are excluded, profile list is updated, complete the drafting of profile mark.
To support mask method of the invention to realize, devise image processing system, including image outline constructing module and
Remove noise module.
The image outline constructing module is converted by HSV image and expansion process and corrosion treatment, realize for
The extraction of sperm chamfered shape in given image.
The removal noise module is realized by the coordinate points number given threshold to given profile for given figure
As the elimination of most noises.
The above is only the preferred embodiment for the present invention, it is noted that for those skilled in the art,
Without departing from the inventive concept of the premise, several improvements and modifications can also be made, these improvements and modifications also should be regarded as this
In invention protection scope.
Claims (4)
1. a kind of mask method for sperm morphology intelligence diagosis system, it is characterised in that include the following steps:
S1) under based on Python and openCV environment, HSV image conversion process is carried out to dyeing glass slide image；
S2 after) obtaining initialization HSV data, white (255) are set as by the part in threshold range for given staining conditions,
Black (0) is set as lower than bottom threshold or higher than the part of upper threshold；
S3 the structural element for) constructing 5 × 5 unit matrixs carries out the image after binary conversion treatment according to the structural element of construction
The chamfered shape of sperm in image is extracted in the operation of first expansion process corrosion treatment again；
S4) to the coordinate points number given threshold of profile, all profiles are judged, the profile of threshold value will be less than comprising counting
It deletes；
S5 all undesirable profiles) are excluded, profile list is updated, complete the drafting of profile mark.
2. a kind of mask method for sperm morphology intelligence diagosis system according to claim 1, it is characterised in that:
Step S2) in, the lower limit that the threshold range of given staining conditions is arranged is [50,10,10], the upper limit be [120,255,
255]。
3. a kind of mask method for sperm morphology intelligence diagosis system according to claim 1, it is characterised in that:
Step S3) in, expansion process is used to merge same sperm adjacent area in image.
4. a kind of mask method for sperm morphology intelligence diagosis system according to claim 1, it is characterised in that:
Step S3) in, corrosion treatment is used to remove the noise spot in image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811529506.6A CN109767450A (en) | 2018-12-14 | 2018-12-14 | A kind of mask method for sperm morphology intelligence diagosis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811529506.6A CN109767450A (en) | 2018-12-14 | 2018-12-14 | A kind of mask method for sperm morphology intelligence diagosis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109767450A true CN109767450A (en) | 2019-05-17 |
Family
ID=66450705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811529506.6A Pending CN109767450A (en) | 2018-12-14 | 2018-12-14 | A kind of mask method for sperm morphology intelligence diagosis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109767450A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111579466A (en) * | 2020-05-25 | 2020-08-25 | 上海师范大学 | Household sperm detection device and detection method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2287306Y (en) * | 1996-09-06 | 1998-08-05 | 清华大学 | Visualization and management apparatus for seeds and microorgans dyanmic (static) image inspection and case picture |
| CN1385700A (en) * | 2001-05-10 | 2002-12-18 | 华中科技大学同济医学院 | Sperm fluorescent staining computer detection system |
| CN104077773A (en) * | 2014-06-23 | 2014-10-01 | 北京京东方视讯科技有限公司 | Image edge detection method, and image target identification method and device |
| CN104268515A (en) * | 2014-09-18 | 2015-01-07 | 山东大学 | Sperm morphology anomaly detection method |
| WO2015153691A2 (en) * | 2014-04-03 | 2015-10-08 | Drexel University | Computer-implemented methods, computer-readable media, and systems for tracking a plurality of spermatozoa |
| CN107527028A (en) * | 2017-08-18 | 2017-12-29 | 深圳乐普智能医疗器械有限公司 | Target cell recognition methods, device and terminal |
-
2018
- 2018-12-14 CN CN201811529506.6A patent/CN109767450A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2287306Y (en) * | 1996-09-06 | 1998-08-05 | 清华大学 | Visualization and management apparatus for seeds and microorgans dyanmic (static) image inspection and case picture |
| CN1385700A (en) * | 2001-05-10 | 2002-12-18 | 华中科技大学同济医学院 | Sperm fluorescent staining computer detection system |
| WO2015153691A2 (en) * | 2014-04-03 | 2015-10-08 | Drexel University | Computer-implemented methods, computer-readable media, and systems for tracking a plurality of spermatozoa |
| CN104077773A (en) * | 2014-06-23 | 2014-10-01 | 北京京东方视讯科技有限公司 | Image edge detection method, and image target identification method and device |
| CN104268515A (en) * | 2014-09-18 | 2015-01-07 | 山东大学 | Sperm morphology anomaly detection method |
| CN107527028A (en) * | 2017-08-18 | 2017-12-29 | 深圳乐普智能医疗器械有限公司 | Target cell recognition methods, device and terminal |
Non-Patent Citations (1)
| Title |
|---|
| RAFAEL HUANG，MEGAN HARDY: "如何使用Python和OpenCV实现良好的边缘检测，以校准一些非常小的东西", 《HTTPS://XBUBA.COM/QUESTIONS/51491771》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111579466A (en) * | 2020-05-25 | 2020-08-25 | 上海师范大学 | Household sperm detection device and detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rahane et al. | Lung cancer detection using image processing and machine learning healthcare | |
| AU2018102232A4 (en) | Bone marrow cell marking method and system | |
| WO2020151307A1 (en) | Automatic lesion recognition method and device, and computer-readable storage medium | |
| CN104992445B (en) | A kind of automatic division method of CT images pulmonary parenchyma | |
| WO2020125319A1 (en) | Glaucoma image recognition method and device and screening system | |
| CN111062947B (en) | X-ray chest radiography focus positioning method and system based on deep learning | |
| CN101201893A (en) | Iris recognizing preprocessing method based on grey level information | |
| Vezzetti et al. | 3D Landmarking in multiexpression face analysis: a preliminary study on eyebrows and mouth | |
| Fan et al. | Principal component analysis based cataract grading and classification | |
| Saleh et al. | An efficient algorithm for retinal blood vessel segmentation using h-maxima transform and multilevel thresholding | |
| WO2020125318A1 (en) | Glaucoma image recognition method and device and diagnosis system | |
| CN112785591B (en) | Method and device for detecting and segmenting rib fracture in CT image | |
| CN107424167A (en) | A kind of method and apparatus of pore fixation and recognition | |
| Mussi et al. | A novel ear elements segmentation algorithm on depth map images | |
| Pushparaj et al. | Dental radiographs and photographs in human forensic identification | |
| Albawi et al. | Robust skin diseases detection and classification using deep neural networks | |
| CN109767450A (en) | A kind of mask method for sperm morphology intelligence diagosis system | |
| CN113963199A (en) | Medical waste identification method based on multiple sensor feature fusion and machine learning | |
| CN102663728A (en) | Dictionary learning-based medical image interactive joint segmentation | |
| CN112288697A (en) | Method and device for quantifying degree of abnormality, electronic equipment and readable storage medium | |
| bin Keram et al. | Covid-19 Detection from Chest X-Ray Images using Convolutional Neural Network | |
| Dey et al. | Chest X-ray analysis to detect mass tissue in lung | |
| Thamilarasi et al. | Lung segmentation in chest X-ray images using Canny with morphology and thresholding techniques | |
| Frants et al. | Dermoscopic image segmentation based on modified GrabCut with octree color quantization | |
| Rakesh et al. | Bone fracture detection using morphological and comparing the accuracy with genetic algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190517 |