CN109259965A - Adaptive medical POCT system and detection method - Google Patents
Adaptive medical POCT system and detection method Download PDFInfo
- Publication number
- CN109259965A CN109259965A CN201811151325.4A CN201811151325A CN109259965A CN 109259965 A CN109259965 A CN 109259965A CN 201811151325 A CN201811151325 A CN 201811151325A CN 109259965 A CN109259965 A CN 109259965A
- Authority
- CN
- China
- Prior art keywords
- test card
- detection
- database
- project
- detection project
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61G—TRANSPORT, PERSONAL CONVEYANCES, OR ACCOMMODATION SPECIALLY ADAPTED FOR PATIENTS OR DISABLED PERSONS; OPERATING TABLES OR CHAIRS; CHAIRS FOR DENTISTRY; FUNERAL DEVICES
- A61G12/00—Accommodation for nursing, e.g. in hospitals, not covered by groups A61G1/00 - A61G11/00, e.g. trolleys for transport of medicaments or food; Prescription lists
Landscapes
- Health & Medical Sciences (AREA)
- Nursing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a kind of adaptive medical POCT system and detection methods, scanning means including the image for scanning test card, for receiving the processing unit of described image, and the display device shown for will test result, the processing unit is programmed to execute following steps: identifying detection project corresponding to the test card and characteristic value from described image, the project in the detection project and database of the test card is compared;If there is no the detection project in database, carries out test card training and obtain the fitting formula of the detection project and be stored in the database;If having the detection project in database, fitting formula corresponding to the detection project is called from database, and the characteristic value of described image is updated in fitting formula and calculates testing result.The present invention need not upgrade system software after new detection project generates, and only be detected by detection project that can be new to this after test paper training.
Description
Technical field
The invention belongs to medical auxiliary equipment technical fields, and in particular to a kind of adaptively medical POCT system and detection side
Method.
Background technique
POCT, real-time test (point-of-care testing), refers to the clinical detection carried out beside patient and bedside
It detects (bedside testing), is not necessarily clinical examination teacher usually to carry out.It is to be analyzed at once in sampling location,
Complex process program of the sample in laboratory inspection is saved, a kind of new method of inspection result is quickly obtained.
Currently, on the market existing POCT detector be mainly done after passing through purchase instrument using specified test paper it is specified
Project must just can be carried out detection by the new instrument of software upgrading or purchase when the type of detection project increases.For
Have to put into improvement of a large amount of manpower and material resources on software developing a kind of new project test paper every time for the producer
And upgrading.Must timely update just for the consumer group can be carried out corresponding test paper and detects to obtain item detection result.It is no
Then it cannot get corresponding testing result having bought the test paper project of corresponding instrument.
Therefore, it is necessary to develop a kind of adaptively medical POCT system and detection method.
Summary of the invention
The object of the present invention is to provide a kind of adaptive medical POCT system and detection methods, generate in new detection project
System software need not be upgraded afterwards, only be detected by detection project that can be new to this after test paper training, with very
High adaptivity.
Adaptive medical POCT system of the present invention, the scanning means including the image for scanning test card are used
In the processing unit for receiving described image, and the display device shown for will test result, the processing unit quilt
Programming is to execute following steps:
Detection project corresponding to the test card and characteristic value are identified from described image, by the detection project of the test card
It is compared with the project in database;If there is no the detection project in database, carries out test card training and obtain the detection
The fitting formula of project is simultaneously stored in the database;If having the detection project in database, called from database
Fitting formula corresponding to the detection project, and the characteristic value of described image is updated in fitting formula and calculates detection knot
Fruit.
Further, the detailed process for being trained to obtain the fitting formula of detection project to test card includes:
The image of test card after chromogenic reaction known to one group of concentration is subjected to image procossing and obtains one group of characteristic value, by the group
Characteristic value and standard value compare and fit the fitting formula of the detection project;
The fitting formula P are as follows: p=ax^5+bx^4+cx^3+dx^2+ex^2+fx+g;
Wherein: a, b, c, d, e, f, g are constant, and x indicates the characteristic value of test card.
Further, the characteristic value of the test card is identified from described image, specifically:
Image is split first, the image after segmentation is subjected to the conversion of hsv color space, to being used for after S component binaryzation
Border detection carries out column summation to the data after binaryzation, and calculates the mean value after column summation, to the left and right range number of test card
Value is compared the left and right range for determining test card with mean value, if the difference of the left and right of test card is greater than 40 column, then it represents that
Test card detection failure, cannot get testing result, when being less than or equal to 40 column, then increase left margin length and the right of 10 column
Boundary reduces the length of 10 column, the right boundary as test card processing;
Diversity factor and the summation for calculating every a line of image after right boundary processing R component and G component, by the data after summation
It seeks mean value and is made the difference with each of image data with mean value;At it after data progress smothing filtering after making the difference
Middle searching detection zone, and obtain the characteristic value of the control zone of detection zone.
Further, the method for finding detection zone are as follows:
It first passes through maximum value and finds check plot, check plot and near zone and too far region are rejected, after rejecting hash
Image relay it is continuous find maximum wave crest, then with a window searching maximum region in the wave crest near zone, this is most
Big region is required detection zone;
Wherein, the near zone includes the range of check plot upward 50 row and downward 50 row, and too far region refers to from control zone
More than upward 250 row and more than downward 250 row.
Further, detection project corresponding to the test card is identified from described image, specifically:
The test card is equipped with two dimensional code, and the packet of the two dimensional code contains the information of detection project;
The two dimensional code on test card is scanned by scanning means, obtains detection project corresponding to the test card.
A kind of adaptive medical POCT system detection method of the present invention, using of the present invention adaptive medical
POCT system, test method the following steps are included:
Using the image of scanning means scanning test card, and it is sent to processing unit;
The processing unit identifies detection project corresponding to the test card and characteristic value from described image, by the test paper
Project in the detection project and database of card compares;If there is no the detection project in database, test card instruction is carried out
Practice, obtains the fitting formula of the detection project and be stored in the database;
If having the detection project in database, fitting formula corresponding to the detection project is called from database, and will
The characteristic value of described image is updated in the fitting formula, calculates testing result, be will test result and is carried out by display device
It is displayed and stored in database.
The invention has the following advantages that
(1) system software need not be upgraded after new detection project generates, only by can be to this after test paper training
New detection project is detected, therefore has very high adaptivity;
(2) image processing algorithm used can identify the lower test paper of concentration, higher than the detection accuracy of the prior art.
Detailed description of the invention
Fig. 1 is the principle of the present invention frame diagram;
Fig. 2 is the flow chart of image procossing of the present invention;
Fig. 3 is the flow chart of test paper training process of the invention;
Fig. 4 is flow chart of the invention;
In figure: 1, test card, 2, scanning means, 3, processing unit, 4, display device.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings.
Adaptive medical POCT system as shown in Figure 1 and Figure 4, the scanning dress including the image for scanning test card 1
2 are set, for receiving the processing unit 3 of described image, and the display device 4 shown for will test result, the place
Reason device 3 be programmed to execute following steps: identified from described image detection project corresponding to the test card and
Characteristic value compares the project in the detection project and database of the test card;If there is no the detection project in database,
Test card training is then carried out to obtain the fitting formula of the detection project and be stored in the database;If having this in database
Detection project then calls fitting formula corresponding to the detection project from database, and the characteristic value of described image is substituted into
Testing result is calculated into fitting formula.
As shown in figure 3, being trained to obtain the detailed process of the fitting formula of detection project to test card in the present embodiment
Include:
The image of test card after chromogenic reaction known to one group of concentration is subjected to image procossing and obtains one group of characteristic value, by the group
Characteristic value and standard value, which compare and pass through the highest power of default, fits the fitting formula of the detection project;
The fitting formula P are as follows: p=ax^5+bx^4+cx^3+dx^2+ex^2+fx+g;
Wherein: a, b, c, d, e, f, g are constant, and x indicates the characteristic value of test card.This fitting formula is a general formula, for
Different detection projects, the numerical value of a, b, c, d, e, f, g are different in fitting formula.
Below by detection project be β-HCG(human chorionic gonadotrophin) for be illustrated:
It is to obtain the test card of the β-HCG of eight groups of various concentrations first, this eight groups of concentration are known.It is used in the present embodiment
Test card known to eight groups is scanned, sweeps by concentration=[1/16,1/12,1/10,1/8,1/6,1/4,1/2,1]
Image after retouching is passed to respectively in the program of processing unit.First determine whether the detection project is new detection project, judges
The mode of new new projects is the two dimensional code scanned on test card, obtains the done project of test card, be will test in project and database
Stored project is compared, if not finding the fitting formula of the detection project, judges the detection project for new item
Otherwise mesh is existing project.Judge that this detection project is new projects by the above judgment mode, then it need to do is to test paper to instruct
Practice, the process of test paper training is that test card known to eight groups of concentration is passed through fac=tstsum (::, 2) to obtain the spy of data
(tstsum is averaged to the HSV space of entire tst to value indicative;Wherein tst indicates topography's square of the HSV space of detection zone
Battle array;Fac indicates to choose the mean value (the wherein space S that S indicates the second letter in HSV space) of S component in tstsum).It will
The characteristic value of above-mentioned data is stored in ret matrix, and wherein ret indicates the matrix for being used to store one group of characteristic value, will be above-mentioned
Data value ret and desired value y are fitted to formula, and medically corresponding numerical value is stored in one-dimension array y eight kinds of concentration, and y=
[8, 31, 62, 125, 250, 500, 1000, 2000];X=ret (2 :) wherein x be test paper characteristic value, we take quasi-
Close highest power n=5 of formula;A p=ax^5+bx^4 is obtained by function p=polyfit (x, y, n) in matlab
The multinomial of+cx^3+dx^2+ex^2+fx+g is exactly last fitting formula.Wherein a, b, c, d, e, f, g are exactly to pass through
The constant that polyfit (x, y, n) is obtained.Finally in the database by the multinomial storage of this p, the project is reused later
Test card can directly calculate testing result by obtained fitting formula.
As shown in Fig. 2, the characteristic value of the test card is identified from described image in the present embodiment, specifically: first
Image is split, the image after segmentation is subjected to HSV(H: tone, S: saturation degree, V: lightness) color space conversion, to S
It is used for border detection after component binaryzation, column summation is carried out to the data after binaryzation, and calculates the mean value after column summation, to examination
The left and right range values of paper card are compared the left and right range for determining test card with mean value, if the difference of the left and right of test card
Greater than 40 column, then it represents that test card detection failure cannot get testing result, when being less than or equal to 40 column, then increase left margin
The length and right margin of 10 column reduce the length of 10 column, the right boundary as test card processing.Scheme after handling right boundary
Every a line of picture calculates the diversity factor of R component and G component and summation, the data after summation is sought mean value and with every in image
One data makes the difference with mean value;Data after making the difference find detection zone after carrying out smothing filtering wherein, and obtain
The characteristic value of the control zone of detection zone.
In the present embodiment, the method for finding detection zone are as follows: first pass through maximum value and find check plot, by check plot and
Near zone and too far region are rejected, and the image relay after rejecting hash is continuous to find maximum wave crest, then in the wave crest
Maximum region is found with a window near zone, this maximum region is required detection zone.Wherein, described attached
Near field includes the range of check plot upward 50 row and downward 50 row, too far region refer to 250 row upward from control zone or more and
It is more than downward 250 row.
In the present embodiment, detection project corresponding to the test card is identified from described image, specifically: the examination
Paper card is equipped with two dimensional code, and the packet of the two dimensional code contains the information of detection project.It is scanned on test card by scanning means
Two dimensional code, obtain detection project corresponding to the test card.
A kind of adaptive medical POCT system detection method of the present invention, using of the present invention adaptive medical
POCT system, test method the following steps are included:
Using the image of scanning means scanning test card, and it is sent to processing unit;
The processing unit identifies detection project corresponding to the test card and characteristic value from described image, by the test paper
Project in the detection project and database of card compares;If there is no the detection project in database, test card instruction is carried out
Practice, obtains the fitting formula of the detection project and be stored in the database;
If having the detection project in database, fitting formula corresponding to the detection project is called from database, and will
The characteristic value of described image is updated in the fitting formula, calculates testing result, be will test result and is carried out by display device
It is displayed and stored in database.
Claims (6)
1. a kind of adaptive medical POCT system, which is characterized in that the scanning means including the image for scanning test card (1)
(2), for receiving the processing unit (3) of described image, and the display device (4) shown for will test result, institute
Processing unit (3) is stated to be programmed to execute following steps:
Detection project corresponding to the test card and characteristic value are identified from described image, by the detection project of the test card
It is compared with the project in database;If there is no the detection project in database, carries out test card training and obtain the detection
The fitting formula of project is simultaneously stored in the database;If having the detection project in database, called from database
Fitting formula corresponding to the detection project, and the characteristic value of described image is updated in fitting formula and calculates detection knot
Fruit.
2. adaptive medical POCT system according to claim 1, it is characterised in that: be trained and examined to test card
The detailed process of the fitting formula of survey project includes:
The image of test card after chromogenic reaction known to one group of concentration is subjected to image procossing and obtains one group of characteristic value, by the group
Characteristic value and standard value compare and fit the fitting formula of the detection project;
The fitting formula P are as follows: p=ax^5+bx^4+cx^3+dx^2+ex^2+fx+g;
Wherein: a, b, c, d, e, f, g are constant, and x indicates the characteristic value of test card.
3. adaptive medical POCT system according to claim 1 or 2, it is characterised in that: identified from described image
The characteristic value of the test card, specifically:
Image is split first, the image after segmentation is subjected to the conversion of hsv color space, to being used for after S component binaryzation
Border detection carries out column summation to the data after binaryzation, and calculates the mean value after column summation, to the left and right range number of test card
Value is compared the left and right range for determining test card with mean value, if the difference of the left and right of test card is greater than 40 column, then it represents that
Test card detection failure, cannot get testing result, when being less than or equal to 40 column, then increase left margin length and the right of 10 column
Boundary reduces the length of 10 column, the right boundary as test card processing;
Diversity factor and the summation for calculating every a line of image after right boundary processing R component and G component, by the data after summation
It seeks mean value and is made the difference with each of image data with mean value;At it after data progress smothing filtering after making the difference
Middle searching detection zone, and obtain the characteristic value of the control zone of detection zone.
4. adaptive medical POCT system according to claim 3, it is characterised in that: the method for finding detection zone
Are as follows:
It first passes through maximum value and finds check plot, check plot and near zone and too far region are rejected, after rejecting hash
Image relay it is continuous find maximum wave crest, then with a window searching maximum region in the wave crest near zone, this is most
Big region is required detection zone;
Wherein, the near zone includes the range of check plot upward 50 row and downward 50 row, and too far region refers to from control zone
More than upward 250 row and more than downward 250 row.
5. adaptive medical POCT system according to claim 1 or 2 or 4, it is characterised in that: identified from described image
Detection project corresponding to the test card out, specifically:
The test card is equipped with two dimensional code, and the packet of the two dimensional code contains the information of detection project;
The two dimensional code on test card is scanned by scanning means, obtains detection project corresponding to the test card.
6. a kind of adaptive medical POCT system detection method, it is characterised in that: using as claimed in claim 1 to 5
Adaptive medical POCT system, test method the following steps are included:
Using the image of scanning means scanning test card, and it is sent to processing unit;
The processing unit identifies detection project corresponding to the test card and characteristic value from described image, by the test paper
Project in the detection project and database of card compares;If there is no the detection project in database, test card instruction is carried out
Practice, obtains the fitting formula of the detection project and be stored in the database;
If having the detection project in database, fitting formula corresponding to the detection project is called from database, and will
The characteristic value of described image is updated in the fitting formula, calculates testing result, be will test result and is carried out by display device
It is displayed and stored in database.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811151325.4A CN109259965A (en) | 2018-09-29 | 2018-09-29 | Adaptive medical POCT system and detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811151325.4A CN109259965A (en) | 2018-09-29 | 2018-09-29 | Adaptive medical POCT system and detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109259965A true CN109259965A (en) | 2019-01-25 |
Family
ID=65194901
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811151325.4A Pending CN109259965A (en) | 2018-09-29 | 2018-09-29 | Adaptive medical POCT system and detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109259965A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113486900A (en) * | 2021-05-28 | 2021-10-08 | 杭州微策生物技术股份有限公司 | Embedded real-time image acquisition and processing system for POCT |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6394952B1 (en) * | 1998-02-03 | 2002-05-28 | Adeza Biomedical Corporation | Point of care diagnostic systems |
CN103995108A (en) * | 2014-05-19 | 2014-08-20 | 智锐达仪器科技南通有限公司 | Colloidal gold detection system and corresponding colloidal gold chart reader |
CN104714009A (en) * | 2015-03-17 | 2015-06-17 | 深圳市海王英特龙生物技术股份有限公司 | Immunoassay detection system and detection method |
CN204557507U (en) * | 2014-12-30 | 2015-08-12 | 亚洲基因科技股份有限公司 | The real-time identification system of fast sieve test paper |
CN104964973A (en) * | 2015-07-08 | 2015-10-07 | 邓双胜 | Test paper reading and analyzing method and system based on mobile terminal camera |
CN106338596A (en) * | 2016-08-24 | 2017-01-18 | 四川长虹通信科技有限公司 | Health monitoring method, health monitoring apparatus, and electronic equipment |
CN107958073A (en) * | 2017-12-07 | 2018-04-24 | 电子科技大学 | A kind of Color Image Retrieval based on particle swarm optimization algorithm optimization |
-
2018
- 2018-09-29 CN CN201811151325.4A patent/CN109259965A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6394952B1 (en) * | 1998-02-03 | 2002-05-28 | Adeza Biomedical Corporation | Point of care diagnostic systems |
CN103995108A (en) * | 2014-05-19 | 2014-08-20 | 智锐达仪器科技南通有限公司 | Colloidal gold detection system and corresponding colloidal gold chart reader |
CN204557507U (en) * | 2014-12-30 | 2015-08-12 | 亚洲基因科技股份有限公司 | The real-time identification system of fast sieve test paper |
CN104714009A (en) * | 2015-03-17 | 2015-06-17 | 深圳市海王英特龙生物技术股份有限公司 | Immunoassay detection system and detection method |
CN104964973A (en) * | 2015-07-08 | 2015-10-07 | 邓双胜 | Test paper reading and analyzing method and system based on mobile terminal camera |
CN106338596A (en) * | 2016-08-24 | 2017-01-18 | 四川长虹通信科技有限公司 | Health monitoring method, health monitoring apparatus, and electronic equipment |
CN107958073A (en) * | 2017-12-07 | 2018-04-24 | 电子科技大学 | A kind of Color Image Retrieval based on particle swarm optimization algorithm optimization |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113486900A (en) * | 2021-05-28 | 2021-10-08 | 杭州微策生物技术股份有限公司 | Embedded real-time image acquisition and processing system for POCT |
CN113486900B (en) * | 2021-05-28 | 2024-06-07 | 杭州微策生物技术股份有限公司 | Embedded real-time image acquisition and processing system for POCT |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6110992B2 (en) | Image-adaptive physiologically relevant color separation | |
JP6767978B2 (en) | Analysis and screening of cell secretion profiles | |
US8129990B2 (en) | Image processing apparatus and computer program product | |
KR101989202B1 (en) | Method and software for analysing microbial growth | |
CN103528617B (en) | A kind of cockpit instrument identifies and detection method and device automatically | |
US20230177341A1 (en) | Using a First Stain to Train a Model to Predict the Region Stained by a Second Stain | |
Vostatek et al. | Performance comparison of publicly available retinal blood vessel segmentation methods | |
US11501545B2 (en) | Smart microscope system for radiation biodosimetry | |
US11756677B2 (en) | System and method for interactively and iteratively developing algorithms for detection of biological structures in biological samples | |
CN106526177A (en) | Biomarker detection system and method based on colloidal gold test strip | |
CN104680185B (en) | Hyperspectral image classification method based on boundary point reclassification | |
CN113095444B (en) | Image labeling method, device and storage medium | |
US7630534B2 (en) | Method for radiological image processing | |
CN111656393A (en) | Histological image analysis | |
CN109259965A (en) | Adaptive medical POCT system and detection method | |
Xu et al. | Fiber-image analysis part I: Fiber-image enhancement | |
CN110619621A (en) | Method and device for identifying rib region in image, electronic equipment and storage medium | |
US9519822B2 (en) | Determination method, determination device, determination system, and computer program | |
CN109478230A (en) | The method for checking distributed objects by segmentation general view image | |
US8433112B2 (en) | Method and apparatus for processing chest X-ray images | |
CN110555850A (en) | method and device for identifying rib region in image, electronic equipment and storage medium | |
US20080304721A1 (en) | Image detection method for diagnostic plates | |
CN112200803B (en) | Sperm nucleoprotein maturity detection method and device | |
CN113435444A (en) | Immunochromatography detection method, immunochromatography detection device, storage medium and computer equipment | |
CN112184708B (en) | Sperm survival rate detection method and device |
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 |
Application publication date: 20190125 |
|
RJ01 | Rejection of invention patent application after publication |