CN117152745A - Mycoplasma recognition and input method and system based on image processing technology - Google Patents
Mycoplasma recognition and input method and system based on image processing technology Download PDFInfo
- Publication number
- CN117152745A CN117152745A CN202311372618.6A CN202311372618A CN117152745A CN 117152745 A CN117152745 A CN 117152745A CN 202311372618 A CN202311372618 A CN 202311372618A CN 117152745 A CN117152745 A CN 117152745A
- Authority
- CN
- China
- Prior art keywords
- result
- image
- report
- sample
- identification
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012545 processing Methods 0.000 title claims abstract description 34
- 241000204031 Mycoplasma Species 0.000 title claims abstract description 31
- 238000005516 engineering process Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 143
- 238000012549 training Methods 0.000 claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims description 37
- 239000003086 colorant Substances 0.000 claims description 21
- 241000204003 Mycoplasmatales Species 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 12
- 238000012550 audit Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000000813 microbial effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 239000003153 chemical reaction reagent Substances 0.000 description 5
- 230000035945 sensitivity Effects 0.000 description 5
- 206010059866 Drug resistance Diseases 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 239000013642 negative control Substances 0.000 description 3
- ULGZDMOVFRHVEP-RWJQBGPGSA-N Erythromycin Chemical compound O([C@@H]1[C@@H](C)C(=O)O[C@@H]([C@@]([C@H](O)[C@@H](C)C(=O)[C@H](C)C[C@@](C)(O)[C@H](O[C@H]2[C@@H]([C@H](C[C@@H](C)O2)N(C)C)O)[C@H]1C)(C)O)CC)[C@H]1C[C@@](C)(OC)[C@@H](O)[C@H](C)O1 ULGZDMOVFRHVEP-RWJQBGPGSA-N 0.000 description 2
- 238000012258 culturing Methods 0.000 description 2
- SGKRLCUYIXIAHR-AKNGSSGZSA-N (4s,4ar,5s,5ar,6r,12ar)-4-(dimethylamino)-1,5,10,11,12a-pentahydroxy-6-methyl-3,12-dioxo-4a,5,5a,6-tetrahydro-4h-tetracene-2-carboxamide Chemical compound C1=CC=C2[C@H](C)[C@@H]([C@H](O)[C@@H]3[C@](C(O)=C(C(N)=O)C(=O)[C@H]3N(C)C)(O)C3=O)C3=C(O)C2=C1O SGKRLCUYIXIAHR-AKNGSSGZSA-N 0.000 description 1
- GSDSWSVVBLHKDQ-JTQLQIEISA-N Levofloxacin Chemical compound C([C@@H](N1C2=C(C(C(C(O)=O)=C1)=O)C=C1F)C)OC2=C1N1CCN(C)CC1 GSDSWSVVBLHKDQ-JTQLQIEISA-N 0.000 description 1
- 239000004098 Tetracycline Substances 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 229960003722 doxycycline Drugs 0.000 description 1
- 229960003276 erythromycin Drugs 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229960003376 levofloxacin Drugs 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 239000013641 positive control Substances 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 229960002180 tetracycline Drugs 0.000 description 1
- 229930101283 tetracycline Natural products 0.000 description 1
- 235000019364 tetracycline Nutrition 0.000 description 1
- 150000003522 tetracyclines Chemical class 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the technical field of image recognition, solves the problems that in the prior art, the efficiency of microbial mycoplasma is low when manual detection is carried out, and a great deal of manpower and time cost are required to be consumed for inputting an electronic system, and discloses a mycoplasma recognition and input method and system based on an image processing technology, wherein the method comprises the following steps: acquiring a detection box image to be identified containing sample information; constructing and training a target detection and recognition model; constructing a first database of the corresponding relation between the hole position coordinate information and the report item and a second database of the corresponding relation between the color and the report item result; acquiring an image recognition result and a report item result; the image of the detection box to be identified, the image identification result and the report result are stored, and the report result is uploaded to the appointed electronic system, so that the identification efficiency and the identification accuracy of the detection result can be greatly improved, and a large amount of manpower and time cost can be saved.
Description
Technical Field
The application relates to the technical field of image recognition, in particular to a mycoplasma recognition and input method and system based on an image processing technology.
Background
Detection of mycoplasma, in which a detection staff manually inserts an acquired specimen swab into a culture flask, writes sample numbers on a detection box, and cultures the specimen swab in a incubator at 35-37 ℃ for 24h and 48h for respectively observing results. The detection box has 30 hole sites, and every hole site presents different results after the detection, and the colour is discerned to the manual work, judges mycoplasma negative positive result: yellow or orange- & gt negative (-), clear transparent red- & gt positive (+), cloudy red- & gt pollution. After judging the result, the user converts the yin-yang result correspondence into a text report result (sensitive, drug resistant, intermediary, <10≡4, > 10≡4, etc.), and transcribes the text report result to a paper report form or enters an electronic system, and the text report result is released as a final report result after secondary auditing.
The prior art has the following defects: on the one hand, the detection personnel need to write the sample number manually, and when the result is recorded last, the number on the detection box corresponds to the number in the recording system, and extra labor is required to be consumed. On the other hand, the artificial identification color is unstable, and has individual difference, and the judgment speed is limited and influenced by artificial experience. Meanwhile, the results of the different report items corresponding to 30 hole sites on the detection box correspondingly convert the yin-yang results, and the results are transcribed to a paper report form or recorded into an electronic system, so that huge labor and time cost can be consumed.
Disclosure of Invention
The application aims to solve the problems that in the prior art, the efficiency of microbial mycoplasma is low when manual detection is carried out, and a great deal of manpower and time cost are required to be consumed for inputting an electronic system, and provides a mycoplasma identification and input method and system based on an image processing technology.
In a first aspect, a mycoplasma identification and recording method based on an image processing technology is provided, including:
acquiring a to-be-identified detection box image containing sample information, wherein the sample information comprises a sample hole site image and a sample label two-dimensional code;
constructing and training a target detection and identification model, wherein the target detection and identification model is used for identifying sample tag two-dimensional codes, sample hole site colors and hole site coordinate information;
constructing a first database of the corresponding relation between the hole position coordinate information and the report item and a second database of the corresponding relation between the color and the report item result;
identifying the to-be-identified detection box image through the target detection identification model to obtain sample numbers, sample hole site colors and hole site coordinate information;
matching the image recognition result with a first database and a second database to obtain a report result, wherein the report result comprises a sample tag two-dimensional code, a report item and a corresponding report item result;
and storing the detection box image to be identified, the image identification result and the report result, and uploading the report result to a specified electronic system.
Further, the method further comprises the following steps: performing abnormal judgment on the report result according to a preset abnormal result judgment rule, and marking the sample with a completion label if the judgment result is normal; and if the judgment result is abnormal, marking the sample with an abnormal label, and auditing and editing the report result through manual intervention.
Further, the method further comprises the following steps: providing an interface for checking the to-be-identified detection box image, the image identification result and the report result for the human, and checking the to-be-identified detection box image, the image identification result and the report result through the human;
in response to the passing of the audit, uploading the report result to a specified electronic system;
and if the verification is not passed, modifying the image recognition result and the report result according to the manual detection result, saving the modified image recognition result and the modified report result again, and uploading the modified report result to the appointed electronic system.
Further, the audit includes at least one of: whether the detection box image to be identified is blocked, whether the detection box image to be identified is clear, whether the image identification result is correct and whether the report item result is correct.
Further, constructing and training a target detection recognition model, including:
acquiring a sample detection box image containing sample information and constructing an image set;
taking the deep-learning convolutional neural network model as a target detection and identification model;
dividing the image set into a training set and a testing set, and training and testing the target detection recognition model by using the training set and the testing set to obtain the target detection recognition model with the target recognition precision reaching a preset threshold.
In a second aspect, there is provided a mycoplasma identification and typing system based on image processing technology, comprising:
the image acquisition module is used for acquiring a to-be-identified detection box image containing sample information, wherein the sample information comprises a sample hole site image and a sample label two-dimensional code;
the model construction module is used for constructing and training a target detection and identification model, wherein the target detection and identification model is used for identifying sample tag two-dimensional codes, sample hole site colors and hole site coordinate information;
the database construction module is used for constructing a first database of the corresponding relation between the hole position coordinate information and the report item and a second database of the corresponding relation between the color and the report item result;
the identification module is used for identifying the to-be-identified detection box image through the target detection identification model so as to obtain sample numbers, sample hole site colors and hole site coordinate information;
the result matching module is used for matching the image recognition result with the first database and the second database to obtain a report result, and the report result comprises a sample tag two-dimensional code, a report item and a corresponding report item result;
and the output module is used for storing the detection box image to be identified, the image identification result and the report result and uploading the report result to a specified electronic system.
Further, the method further comprises the following steps: the abnormal marking module is used for carrying out abnormal judgment on the report result according to a preset abnormal result judgment rule, and marking the sample with a completion label if the judgment result is normal; and if the judgment result is abnormal, marking the sample with an abnormal label, and auditing and editing the report result through manual intervention.
Further, the method further comprises the following steps: the manual auditing and recording module is used for providing an interface for checking the to-be-identified detection box image, the image identification result and the report result for the manual, and auditing the to-be-identified detection box image, the image identification result and the report result through the manual;
in response to the passing of the audit, uploading the report result to a specified electronic system;
and if the verification is not passed, modifying the image recognition result and the report result according to the manual detection result, saving the modified image recognition result and the modified report result again, and uploading the modified report result to the appointed electronic system.
In a third aspect, a computer readable storage medium is provided, the computer readable medium storing program code for execution by a device, the program code comprising steps for performing the method as in any one of the implementations of the first aspect.
In a fourth aspect, there is provided an electronic device comprising a processor, a memory and a program or instruction stored on the memory and executable on the processor, which when executed by the processor implements a method as in any of the implementations of the first aspect.
The application has the following beneficial effects:
1. according to the method, through an image processing technology, colors and coordinates of all hole sites of the mycoplasma detection box can be identified simultaneously, and two-dimensional codes and numbers of sample labels can be automatically identified simultaneously, so that the numbers on the detection box and the numbers in an input appointed electronic system can be automatically subjected to one-to-one correspondence, the accuracy of result input is ensured, meanwhile, color results of the sample detection box are identified, the colors of different identified hole sites are correspondingly converted into report results of a plurality of report items of mycoplasma detection according to the corresponding relation between a first database and a second database, and images, image identification results and report results of the detection box to be identified are automatically stored in a data background for storage, so that the identification efficiency and identification accuracy of the detection results can be greatly improved, and a large amount of manpower and time cost can be saved;
2. the method provides a checking electronic interface for a detection personnel, and can check the stored image of the detection box to be identified, the image identification result and the report result, so that the detection personnel can check, edit, store, input the image identification result and the report result by the electronic system, and the like, thereby realizing the closed loop of the result input;
3. according to the method, a set of perfect abnormal result judging rules are preset, abnormal marks are provided for automatic identification according with the abnormal result judging rules, and detection personnel are prompted when a sample is marked with the abnormal marks, so that the result of manual intervention processing is input, and the accuracy of the result processing is improved.
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 specification, illustrate embodiments of the application and together with the description serve to explain the application.
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a mycoplasma identification and typing method based on image processing technology of embodiment 1 of the present application;
fig. 2 is a schematic structural diagram of a detection box in a mycoplasma identification and recording method based on an image processing technology in embodiment 1 of the present application;
fig. 3 is an example diagram of correspondence between hole site coordinate information and report items in the mycoplasma identification and recording method based on image processing technology according to embodiment 1 of the present application;
fig. 4 is an exemplary diagram of the correspondence between the color and the report result in the mycoplasma identification and recording method based on the image processing technology according to embodiment 1 of the present application;
FIG. 5 is a block diagram showing the structure of a Mycoplasma recognition and entry system based on image processing technique according to embodiment 2 of the present application;
fig. 6 is a schematic diagram of the internal structure of the electronic device of embodiment 4 of the present application.
Reference numerals:
100. an image acquisition module; 200. a model building module; 300. a database construction module; 400. an identification module; 500. a result matching module; 600. an output module; 700. a detection box; 701. a sample reagent bottle placement tank; 702. sample hole sites; 703. sample label two-dimensional code; 704. a dropper placing groove.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Example 1
The application relates to a mycoplasma identification and input method based on an image processing technology, which comprises the following steps: acquiring a to-be-identified detection box image containing sample information, wherein the sample information comprises a sample hole site image and a sample label two-dimensional code; constructing and training a target detection and identification model, wherein the target detection and identification model is used for identifying sample tag two-dimensional codes, sample hole site colors and hole site coordinate information; constructing a first database of the corresponding relation between the hole position coordinate information and the report item and a second database of the corresponding relation between the color and the report item result; identifying the to-be-identified detection box image through the target detection identification model to obtain sample numbers, sample hole site colors and hole site coordinate information; matching the image recognition result with a first database and a second database to obtain a report result, wherein the report result comprises a sample tag two-dimensional code, a report item and a corresponding report item result; the method can simultaneously identify all hole site colors and coordinates of the mycoplasma detection box through an image processing technology, and simultaneously automatically identify sample tag two-dimensional codes and numbers, so that the numbers on the detection box and the numbers in the input appointed electronic system can be automatically subjected to one-to-one correspondence, the accuracy of result input is ensured, meanwhile, the color results of the sample detection box are identified, the colors of the identified different hole sites are correspondingly converted into the report results of a plurality of report items of mycoplasma detection according to the corresponding relation between the first database and the second database, and the image, the image identification results and the report results of the mycoplasma detection box are automatically stored in a data background for storage, thereby greatly improving the identification efficiency and the identification accuracy of the detection results, and further saving a large amount of manpower and time cost.
Specifically, fig. 1 shows a flowchart of a mycoplasma identification and recording method based on an image processing technology in application example 1, including:
s100, acquiring a to-be-identified detection box image containing sample information, wherein the sample information comprises a sample hole site image and a sample label two-dimensional code;
specifically, the user uses the printing and pasting device of the automatic sample label two-dimensional code to paste the sample label two-dimensional code at the non-result position of the detection box of the microbial mycoplasma, wherein the sample label two-dimensional code comprises a sample number consisting of a number, a letter or a combination of the number and the letter, the sample number is a unique identification of the sample, and the result of the detection box and the result recorded in the system are associated and correspond through the sample number.
The detection box of the mycoplasma is placed in a incubator at the temperature of 35-37 ℃ for 48 hours, the cultured sample is placed in a device system capable of containing a plurality of detection boxes of the mycoplasma for shooting, one or more groups of detection boxes of the mycoplasma can be contained in standard positions, standard scattered light sources meet the brightness requirement of shooting the detection boxes, standard digital camera devices shoot images of the detection boxes to be identified with stable quality, a user can connect a terminal web interface of the digital camera devices after logging in the shooting device system, after the sample is automatically identified, the interface automatically uploads picture data, the user can click a shooting button or a shortcut key on the interface, the interface displays the shot picture in real time, the user can select one piece of picture to upload from the shot pictures, and the uploaded picture data is stored in a storage device, namely the images of the detection boxes to be identified.
It should be noted that, when the to-be-identified detection box image is acquired, the auxiliary information may also be acquired at the same time, where the auxiliary information includes the item number, the item name, the detection box picture id, and the storage path of the to-be-identified detection box image.
S200, constructing and training a target detection and identification model, wherein the target detection and identification model is used for identifying sample tag two-dimensional codes, sample hole site colors and hole site coordinate information;
wherein, the construction and training of target detection recognition model includes:
s201, acquiring a sample detection box image containing sample information and constructing an image set;
s202, taking a deep-learning convolutional neural network model as a target detection recognition model;
s203, dividing the image set into a training set and a testing set, and training and testing the target detection recognition model by using the training set and the testing set to obtain the target detection recognition model with the target recognition precision reaching a preset threshold.
Specifically, the pictures for training are acquired according to the service scene, the deep-learning convolutional neural network model is used as the target detection model, the positions and the categories of a plurality of targets can be predicted in a single neural network at the same time, and the color results of a plurality of hole sites on the mycoplasma detection box and the two-dimensional code patterns of the sample labels are all identified.
The convolutional neural network model comprises model series of yolov5s, yolov5l, yolov5x, yolov5m and the like, and can be selected according to speed and precision in practical application. The establishment of the model uses actual mycoplasma detection kit pictures (shown in fig. 2) of a detection laboratory as a training set and a test set, in fig. 2, one end of a detection kit 700 (i.e. mycoplasma detection kit) is provided with a sample reagent bottle placing groove 701 for placing a sample reagent bottle, a sample tag two-dimensional code 703 is arranged below the sample reagent bottle placing groove 701, one side of the sample reagent bottle placing groove 701 is provided with a plurality of sample hole sites 702 marked with numbers (i.e. position information, positions of the hole sites can be identified by the numbers), and a placing groove 704 for placing a dropper is also arranged below the sample hole sites 702.
According to the target detection requirement, the bottle at the leftmost side of the detection box is taken as a reference object in each picture, the bottle is firstly identified, then the two-dimensional code right below the bottle is identified, then the colors of all the holes representing the drug sensitivity result of the mycoplasma culture box at the right side of the bottle are identified, and finally the positions of the bottle, the positions of the holes, the colors corresponding to the positions of the holes and sample number information contained in the two-dimensional code are obtained.
Taking 157 mycoplasma detection box pictures collected by a clinical laboratory as an example, taking the pictures as a training set, marking bottles and colors of all hole sites by the training set, and dividing data into 4 categories which are {0: yellow, 1: red, 2:cap, 3:brown }, experiments were performed using the yolov5s target detection model in the protocol, and finally 100epoch was trained with a batch-size of 2 and an img-size of 640. And verifying by using the test set pictures collected by a clinical test laboratory to obtain the identification precision mAP50 index=0.972 of each detection target, and meeting the requirements of overall image identification, subsequent report result matching and input of a specified electronic system.
S300, constructing a first database of the corresponding relation between the hole position coordinate information and the report item and a second database of the corresponding relation between the color and the report item result;
exemplary, as shown in fig. 3, a correspondence example between hole position coordinate information and report items is shown, wherein the hole position coordinate information is a predefined number of the hole position, and is identified in a (x, y) coordinate form, and the hole position coordinate of the leftmost upper corner position is set to be (0, 0). Referring to the schematic diagram of the detection box, x corresponds to the longitudinal hole site sequence, and two positions of 0 and 1 can be selected; y corresponds to the sequence of the transverse hole sites, and is respectively: 0. 1,2, 3, 4 & gt14, i.e. by the 15 numerical numbers corresponding one to 15 transverse holes, it can be seen from the configuration of fig. 3: the report item of the negative control requires a hole site identification result, and the corresponding hole site coordinates are (0, 0), namely, the report result of the negative control is judged by judging the color of the hole site cultured for 48 hours; the hole position coordinates corresponding to the report item of mh48 are (1, 1) and (1, 2), namely the colors of the two hole positions need to be judged, and the report result of mh48 is judged by culturing the hole position color with the coordinate of (1, 1) for 48 hours and culturing the hole position color with the coordinate of (1, 2) for 48 hours; hole site coordinate information corresponding to the report of the croscarmycin is (0, 6) and (1, 6), namely, the result of the report of the croscarmycin is judged by judging the hole site color of which the coordinate is (0, 6) when the culture is 48 hours and the hole site color of which the coordinate is (1, 6) when the culture is 48 hours.
As shown in fig. 4, the correspondence between the color and the report result may be configured according to the requirements of different mycoplasma detection boxes.
S400, identifying the to-be-identified detection box image through the target detection identification model to obtain sample numbers, sample hole site colors and hole site coordinate information;
it should be noted that, in this step, an external interface may also be provided to provide the recognized image recognition result data to the subsequent step in a certain standardized data structure. The data structure needs to contain the following information: item number, item name, cartridge picture id, cartridge picture address, sample tag number, set of recognition results (hole location coordinates: 0,1, color chinese: red, yellow, brown, confidence: confidence of detection target recognition), and recognition completion time.
S500, matching the image recognition result with a first database and a second database to obtain a report result, wherein the report result comprises a sample tag two-dimensional code, a report item and a corresponding report item result;
specifically, in this step, the sample numbers identified by the sample tag two-dimensional code are used, the converted result text is automatically stored under the corresponding sample, and as shown in table 1, exemplary, the upper left corner of table 1 is the sample number read by scanning the two-dimensional code, the fourth behavior corresponds to the color interpretation result of the hole site, the third behavior is based on the color interpretation result and the original report result matched by the first database and the second database, and the second behavior is the final report result after verification and correction by manual work.
Table 1:
| microorganism number: 202309200003 | Uu count (24 h) | Mh count | Uu count (48 h) | Tetracycline | Levofloxacin | Erythromycin | Saccharomycin | Doxycycline |
| Final interpretation result | ≥10^4 | ≥10^4 | ≥10^4 | Intermediary(s) | Drug resistance | Drug resistance | Sensitivity to | Sensitivity to |
| Original interpretation | ≥10^4 | Intermediary(s) | Drug resistance | Drug resistance | Sensitivity to | Sensitivity to | ||
| Color interpretation | Red and red | Huang Hong | Red and red | Red and red | Huang Huang | Huang Huang |
And S600, storing the detection box image to be identified, the image identification result and the report result, and uploading the report result to a specified electronic system.
It should be noted that all the automatically interpreted report results can be modified, saved and confirmed, and the detection personnel can compare the image of the detection box to be identified corresponding to the sample and save the edited report results. Before saving, the inspector can view the edited report results to determine whether there is an error. After the report result is determined to be accurate, the report result is associated with the corresponding sample number and color identification, and is stored together with the auxiliary information and uploaded to a designated electronic system, so that the whole process is completed.
In a further embodiment, further comprising: performing abnormal judgment on the report result according to a preset abnormal result judgment rule, and marking the sample with a completion label if the judgment result is normal; and if the judgment result is abnormal, marking the sample with an abnormal label, and auditing and editing the report result through manual intervention.
Illustratively, the abnormal result judgment rule may be: 1. the negative control analysis item judges that the result is drug-resistant, or the positive control analysis item judges that the result is sensitive, the result is not input at the moment, and the whole label is abnormal; 2. judging that the number of returned results has a problem, and at the moment, not inputting the results, and marking the whole abnormal; 3. the corresponding analysis item of the brown original result appears, the result is not input, and the result is marked as abnormal; 4. color combinations of the original results of the analysis items, which are not in the range of possible results, are not recorded, and the corresponding analysis items are abnormal.
In addition, by setting a button for "viewing interpretation record", the button defaults to a white background button; and when the sample has an abnormal result, displaying a yellow bottom button to prompt a user to conduct manual auditing.
In an alternative embodiment, further comprising: providing an interface for checking the to-be-identified detection box image, the image identification result and the report result for the human, and checking the to-be-identified detection box image, the image identification result and the report result through the human;
in response to the passing of the audit, uploading the report result to a specified electronic system;
and if the verification is not passed, modifying the image recognition result and the report result according to the manual detection result, saving the modified image recognition result and the modified report result again, and uploading the modified report result to the appointed electronic system.
Specifically, after a user selects a record with a mycoplasma item, a corresponding report result can be displayed, and an image of a detection box to be identified and an image identification result can be checked, so that manual verification, namely rechecking, can be performed, and the accuracy of the report result can be greatly improved.
Wherein the audit includes at least one of: whether the detection box image to be identified is blocked, whether the detection box image to be identified is clear, whether the image identification result is correct and whether the report item result is correct.
Example 2
As shown in fig. 5, a mycoplasma identification and recording system based on image processing technology according to embodiment 2 of the present application includes:
the image acquisition module 100 is configured to acquire an image of a detection box to be identified, where the image includes sample hole site images and sample tag two-dimensional codes;
the model construction module 200 is used for constructing and training a target detection and identification model, wherein the target detection and identification model is used for identifying sample tag two-dimensional codes, sample hole site colors and hole site coordinate information;
the database construction module 300 is used for constructing a first database of the corresponding relation between the hole position coordinate information and the report item and a second database of the corresponding relation between the color and the report item result;
the identifying module 400 is configured to identify the to-be-identified detection box image through the target detection identifying model, so as to obtain a sample number, a sample hole site color and hole site coordinate information;
the result matching module 500 is configured to match the image recognition result with the first database and the second database to obtain a report result, where the report result includes a sample tag two-dimensional code, a report item, and a corresponding report item result;
and the output module 600 is used for storing the to-be-identified detection box image, the image identification result and the report result and uploading the report result to a specified electronic system.
In a further embodiment, further comprising: the abnormal marking module is used for carrying out abnormal judgment on the report result according to a preset abnormal result judgment rule, and marking the sample with a completion label if the judgment result is normal; and if the judgment result is abnormal, marking the sample with an abnormal label, and auditing and editing the report result through manual intervention.
In an alternative embodiment, further comprising: the manual auditing and recording module is used for providing an interface for checking the to-be-identified detection box image, the image identification result and the report result for the manual, and auditing the to-be-identified detection box image, the image identification result and the report result through the manual;
in response to the passing of the audit, uploading the report result to a specified electronic system;
and if the verification is not passed, modifying the image recognition result and the report result according to the manual detection result, saving the modified image recognition result and the modified report result again, and uploading the modified report result to the appointed electronic system.
It should be noted that, in the embodiment of the present application, other specific implementations of the mycoplasma identification and recording system based on the image processing technology may be referred to the specific implementations of the mycoplasma identification and recording method based on the image processing technology, so that redundancy is avoided, and no further description is made here, the system uses the target detection identification model to automatically identify the sample label two-dimensional code of the mycoplasma sample box and the color results of all the holes of the sample detection box, and automatically save and record the report results into a specified electronic system, thereby achieving the purposes of reducing the manual workload and accelerating the detection speed.
Example 3
A computer-readable storage medium according to embodiment 3 of the present application stores program code for execution by a device, the program code including steps for performing the method as in any one of the implementations of embodiment 1 of the present application;
wherein the computer readable storage medium may be a Read Only Memory (ROM), a static storage device, a dynamic storage device, or a random access memory (random access memory, RAM); the computer readable storage medium may store a program code which, when executed by a processor, is adapted to perform the steps of the method as in any one of the implementations of embodiment 1 of the application.
Example 4
As shown in fig. 6, embodiment 4 of the present application relates to an electronic device, where the electronic device includes a processor, a memory, and a program or an instruction stored on the memory and executable on the processor, where the program or the instruction implements the method according to any one of the implementation manners of embodiment 1 of the present application when executed by the processor;
the processor may be a general-purpose central processing unit (central processing unit, CPU), microprocessor, application specific integrated circuit (application specific integrated circuit, ASIC), graphics processor (graphics processing unit, GPU) or one or more integrated circuits for executing associated programs to implement the methods of any of the implementations of embodiment 1 of the present application.
The processor may also be an integrated circuit electronic device with signal processing capabilities. In implementation, each step of the method in any implementation of embodiment 1 of the present application may be implemented by an integrated logic circuit of hardware in a processor or an instruction in a software form.
The processor may also be a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (field programmable gatearray, FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads information in the memory, and in combination with its hardware, performs functions necessary for execution by units included in the data processing system according to the embodiment of the present application, or performs a method in any implementation manner of the embodiment 1 of the present application.
The above is only a preferred embodiment of the present application; the scope of the application is not limited in this respect. Any person skilled in the art, within the technical scope of the present disclosure, may apply to the present application, and the technical solution and the improvement thereof are all covered by the protection scope of the present application.
Claims (10)
1. The mycoplasma identification and input method based on the image processing technology is characterized by comprising the following steps:
acquiring a to-be-identified detection box image containing sample information, wherein the sample information comprises a sample hole site image and a sample label two-dimensional code;
constructing and training a target detection and identification model, wherein the target detection and identification model is used for identifying sample tag two-dimensional codes, sample hole site colors and hole site coordinate information;
constructing a first database of the corresponding relation between the hole position coordinate information and the report item and a second database of the corresponding relation between the color and the report item result;
identifying the to-be-identified detection box image through the target detection identification model to obtain sample numbers, sample hole site colors and hole site coordinate information;
matching the image recognition result with a first database and a second database to obtain a report result, wherein the report result comprises a sample tag two-dimensional code, a report item and a corresponding report item result;
and storing the detection box image to be identified, the image identification result and the report result, and uploading the report result to a specified electronic system.
2. The image processing technology-based mycoplasma identification and typing method of claim 1, further comprising: performing abnormal judgment on the report result according to a preset abnormal result judgment rule, and marking the sample with a completion label if the judgment result is normal; and if the judgment result is abnormal, marking the sample with an abnormal label, and prompting related personnel to audit and edit the report result through manual intervention.
3. The image processing technology-based mycoplasma identification and typing method of claim 1, further comprising: providing an interface for checking the to-be-identified detection box image, the image identification result and the report result for the human, and checking the to-be-identified detection box image, the image identification result and the report result through the human;
in response to the passing of the audit, uploading the report result to a specified electronic system;
and if the verification is not passed, modifying the image recognition result and the report result according to the manual detection result, saving the modified image recognition result and the modified report result again, and uploading the modified report result to the appointed electronic system.
4. A mycoplasma identification and typing method based on image processing technology according to claim 3, wherein the auditing includes at least one of: whether the detection box image to be identified is blocked, whether the detection box image to be identified is clear, whether the image identification result is correct and whether the report item result is correct.
5. The mycoplasma recognition and typing method based on image processing technology of claim 1, wherein constructing and training a target detection recognition model includes:
acquiring a sample detection box image containing sample information and constructing an image set;
taking the deep-learning convolutional neural network model as a target detection and identification model;
dividing the image set into a training set and a testing set, and training and testing the target detection recognition model by using the training set and the testing set to obtain the target detection recognition model with the target recognition precision reaching a preset threshold.
6. A mycoplasma identification and entry system based on image processing technology, comprising:
the image acquisition module is used for acquiring a to-be-identified detection box image containing sample information, wherein the sample information comprises a sample hole site image and a sample label two-dimensional code;
the model construction module is used for constructing and training a target detection and identification model, wherein the target detection and identification model is used for identifying sample tag two-dimensional codes, sample hole site colors and hole site coordinate information;
the database construction module is used for constructing a first database of the corresponding relation between the hole position coordinate information and the report item and a second database of the corresponding relation between the color and the report item result;
the identification module is used for identifying the to-be-identified detection box image through the target detection identification model so as to obtain sample numbers, sample hole site colors and hole site coordinate information;
the result matching module is used for matching the image recognition result with the first database and the second database to obtain a report result, and the report result comprises a sample tag two-dimensional code, a report item and a corresponding report item result;
and the output module is used for storing the detection box image to be identified, the image identification result and the report result and uploading the report result to a specified electronic system.
7. The image processing technology based mycoplasma identification and typing system of claim 6, further comprising: the abnormal marking module is used for carrying out abnormal judgment on the report result according to a preset abnormal result judgment rule, and marking the sample with a completion label if the judgment result is normal; and if the judgment result is abnormal, marking the sample with an abnormal label, and auditing and editing the report result through manual intervention.
8. The image processing technology based mycoplasma identification and typing system of claim 6, further comprising: the manual auditing and recording module is used for providing an interface for checking the to-be-identified detection box image, the image identification result and the report result for the manual, and auditing the to-be-identified detection box image, the image identification result and the report result through the manual;
in response to the passing of the audit, uploading the report result to a specified electronic system;
and if the verification is not passed, modifying the image recognition result and the report result according to the manual detection result, saving the modified image recognition result and the modified report result again, and uploading the modified report result to the appointed electronic system.
9. A computer readable storage medium storing program code for execution by a device, the program code comprising steps for performing the method of any one of claims 1-5.
10. An electronic device comprising a processor, a memory, and a program or instruction stored on the memory and executable on the processor, which when executed by the processor, implements the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311372618.6A CN117152745A (en) | 2023-10-23 | 2023-10-23 | Mycoplasma recognition and input method and system based on image processing technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311372618.6A CN117152745A (en) | 2023-10-23 | 2023-10-23 | Mycoplasma recognition and input method and system based on image processing technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117152745A true CN117152745A (en) | 2023-12-01 |
Family
ID=88910325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311372618.6A Pending CN117152745A (en) | 2023-10-23 | 2023-10-23 | Mycoplasma recognition and input method and system based on image processing technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117152745A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034287A (en) * | 2018-05-23 | 2018-12-18 | 佛山市德淙科学仪器有限公司 | A kind of sample cell puts information input method and device, spiral cover equipment |
| CN209287383U (en) * | 2018-11-30 | 2019-08-23 | 武汉大学人民医院（湖北省人民医院） | A kind of rack for test tube |
| CN110348360A (en) * | 2019-07-04 | 2019-10-18 | 上海眼控科技股份有限公司 | A kind of examining report recognition methods and equipment |
| CN110459289A (en) * | 2019-07-25 | 2019-11-15 | 珠海九松科技有限公司 | Solution release system is reported based on the medical consultations of artificial intelligence and image recognition |
| CN111403004A (en) * | 2020-02-26 | 2020-07-10 | 广州和硕信息技术有限公司 | Artificial intelligence ANA detection picture and text report system |
| CN112001282A (en) * | 2020-08-12 | 2020-11-27 | 腾讯音乐娱乐科技（深圳）有限公司 | Image recognition method |
| CN112966537A (en) * | 2021-02-10 | 2021-06-15 | 北京邮电大学 | Form identification method and system based on two-dimensional code positioning |
| CN113610649A (en) * | 2021-08-10 | 2021-11-05 | 平安国际智慧城市科技股份有限公司 | Image recognition-based auditing method, device, equipment and storage medium |
| CN114742993A (en) * | 2022-04-08 | 2022-07-12 | 上海瞳熵科技有限公司 | Method, device, processor and storage medium for realizing COVID-19Ag antigen detection result identification based on vision |
| CN114913376A (en) * | 2022-05-18 | 2022-08-16 | 广东电网有限责任公司广州供电局 | Image-based defect automatic identification method, device and system and storage medium |
| CN115564750A (en) * | 2022-10-21 | 2023-01-03 | 北京知见生命科技有限公司 | Intraoperative frozen slice image identification method, intraoperative frozen slice image identification device, intraoperative frozen slice image identification equipment and intraoperative frozen slice image storage medium |
| CN116524477A (en) * | 2023-04-10 | 2023-08-01 | 北京谊安医疗系统股份有限公司 | Method and system for identifying detection result of detection box |
-
2023
- 2023-10-23 CN CN202311372618.6A patent/CN117152745A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034287A (en) * | 2018-05-23 | 2018-12-18 | 佛山市德淙科学仪器有限公司 | A kind of sample cell puts information input method and device, spiral cover equipment |
| CN209287383U (en) * | 2018-11-30 | 2019-08-23 | 武汉大学人民医院（湖北省人民医院） | A kind of rack for test tube |
| CN110348360A (en) * | 2019-07-04 | 2019-10-18 | 上海眼控科技股份有限公司 | A kind of examining report recognition methods and equipment |
| CN110459289A (en) * | 2019-07-25 | 2019-11-15 | 珠海九松科技有限公司 | Solution release system is reported based on the medical consultations of artificial intelligence and image recognition |
| CN111403004A (en) * | 2020-02-26 | 2020-07-10 | 广州和硕信息技术有限公司 | Artificial intelligence ANA detection picture and text report system |
| CN112001282A (en) * | 2020-08-12 | 2020-11-27 | 腾讯音乐娱乐科技（深圳）有限公司 | Image recognition method |
| CN112966537A (en) * | 2021-02-10 | 2021-06-15 | 北京邮电大学 | Form identification method and system based on two-dimensional code positioning |
| CN113610649A (en) * | 2021-08-10 | 2021-11-05 | 平安国际智慧城市科技股份有限公司 | Image recognition-based auditing method, device, equipment and storage medium |
| CN114742993A (en) * | 2022-04-08 | 2022-07-12 | 上海瞳熵科技有限公司 | Method, device, processor and storage medium for realizing COVID-19Ag antigen detection result identification based on vision |
| CN114913376A (en) * | 2022-05-18 | 2022-08-16 | 广东电网有限责任公司广州供电局 | Image-based defect automatic identification method, device and system and storage medium |
| CN115564750A (en) * | 2022-10-21 | 2023-01-03 | 北京知见生命科技有限公司 | Intraoperative frozen slice image identification method, intraoperative frozen slice image identification device, intraoperative frozen slice image identification equipment and intraoperative frozen slice image storage medium |
| CN116524477A (en) * | 2023-04-10 | 2023-08-01 | 北京谊安医疗系统股份有限公司 | Method and system for identifying detection result of detection box |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008933B (en) | Universal intelligent marking system and method | |
| CN108171297A (en) | A kind of answer card identification method and device | |
| CN110659636A (en) | Pointer instrument reading identification method based on deep learning | |
| CN110232445B (en) | Cultural relic authenticity identification method based on knowledge distillation | |
| CN108764134A (en) | A kind of automatic positioning of polymorphic type instrument and recognition methods suitable for crusing robot | |
| WO2021254074A1 (en) | Intelligent examination paper marking method and apparatus | |
| WO2022247823A1 (en) | Image detection method, and device and storage medium | |
| CN109389109A (en) | The automated testing method and equipment of a kind of this recognition correct rate of OCR full text | |
| CN111259184B (en) | Image automatic labeling system and method for new retail | |
| CN109147883A (en) | Original document mapping, management method and its system applied to clinical testing data | |
| CN115294317A (en) | Pointer type instrument reading intelligent detection method for industrial production factory | |
| CN115599844A (en) | Visual detection method for misloading and neglected loading of airplane airfoil connecting piece | |
| CN109191386A (en) | A kind of quick Gamma bearing calibration and device based on BPNN | |
| CN110188662A (en) | A kind of AI intelligent identification Method of water meter number | |
| CN116721104B (en) | Live three-dimensional model defect detection method and device, electronic equipment and storage medium | |
| CN117152745A (en) | Mycoplasma recognition and input method and system based on image processing technology | |
| CN113076730A (en) | Test report intelligent management method, device, system and storage medium | |
| CN112434582A (en) | Lane line color identification method and system, electronic device and storage medium | |
| CN113076795A (en) | Automatic auditing method for form protocol image with seal | |
| CN115937555A (en) | Industrial defect detection algorithm based on standardized flow model | |
| CN115115609A (en) | Image analysis method and system for plant leaf positive phenotypic characters | |
| CN114694128A (en) | Pointer instrument detection method and system based on abstract metric learning | |
| CN110909653B (en) | Method for automatically calibrating screen cabinet of distribution room by indoor robot | |
| CN105046608A (en) | O2O exercise and/or knowledge point number recording method and system | |
| CN114663891A (en) | Daily work wrong question book generation method and system based on configured answer sheet |
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 |