CN109740488A - A kind of endoscope cleaning sterilisation quality control system and method based on deep learning - Google Patents
A kind of endoscope cleaning sterilisation quality control system and method based on deep learning Download PDFInfo
- Publication number
- CN109740488A CN109740488A CN201811609481.0A CN201811609481A CN109740488A CN 109740488 A CN109740488 A CN 109740488A CN 201811609481 A CN201811609481 A CN 201811609481A CN 109740488 A CN109740488 A CN 109740488A
- Authority
- CN
- China
- Prior art keywords
- image
- user terminal
- endoscope cleaning
- server
- deep learning
- 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
- 238000004140 cleaning Methods 0.000 title claims abstract description 60
- 238000004659 sterilization and disinfection Methods 0.000 title claims abstract description 36
- 238000013135 deep learning Methods 0.000 title claims abstract description 21
- 238000003908 quality control method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 title abstract description 15
- 230000005540 biological transmission Effects 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 20
- 238000013527 convolutional neural network Methods 0.000 claims description 19
- 230000001954 sterilising effect Effects 0.000 claims description 15
- 238000011017 operating method Methods 0.000 claims description 12
- 230000033001 locomotion Effects 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 6
- 102000004190 Enzymes Human genes 0.000 claims description 5
- 108090000790 Enzymes Proteins 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims 1
- 206010011409 Cross infection Diseases 0.000 abstract description 4
- 206010029803 Nosocomial infection Diseases 0.000 abstract description 4
- 238000001839 endoscopy Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000249 desinfective effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 210000002189 macula lutea Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Abstract
The invention discloses a kind of endoscope cleaning sterilisation quality control system and method based on deep learning, system includes image collecting device, user terminal, server-side;Image collecting device is arranged near scope cleaning sink, and acquisition endoscope cleaning disinfection personnel operate image, and the image of acquisition is passed through network transmission to user terminal;The image of acquisition is passed through network transmission to server-side by user terminal, and receives and show the analysis result of server-side feedback;Server-side according to the image transmitted from user terminal, is judged that endoscope cleaning disinfection personnel operate the corresponding operation of image and operating characteristics immediately, analysis result is fed back to user terminal using REST framework.The present invention is monitored scope cleaning quality, the purpose for finally realizing and reducing nosocomial infection, improve endoscopy quality.
Description
Technical field
The invention belongs to image identification technical fields, are related to a kind of endoscope cleaning sterilisation quality control system and method, tool
Body is related to a kind of endoscope cleaning sterilisation quality control system and method based on deep learning.
Background technique
In recent years, scope using increasingly extensive, it has also become the essential inspection of medical institutions and therapeutic equipment.As
A kind of to go deep into the endoceliac instrument of people, cleaning, which is not thorough, will lead to nosocomial infection;Lumen can also be blocked by improperly sterilizing,
Endoscope surface forms macula lutea, influences doctor and observes operation;Scope fine structure, cleaning and sterilizing is lack of standardization also to accelerate scope old
Change.Therefore, the cleaning and sterilizing quality for improving scope is worth the medical institutions for causing each development endoscope diagnosis and treatment to work to pay attention to.It is existing
Some endoscope washing disinfecting quality traceability systems solve cleaning and sterilizing process sequence error, and cleaning and sterilizing time deficiency etc. is asked
Topic has real time monitoring, mistake warning function.The system stores corresponding endoscope cleaning sterilizing operation process and information simultaneously
In the database of PC server, is inquired convenient for doctor and patient, realize data traceability function.Although system specifications operation
Process ensures each step deadline, but there is likely to be the nonstandard problems of operational motion in each cleaning and sterilizing step.
Summary of the invention
The endoscope cleaning sterilisation quality control based on deep learning that in order to solve the above-mentioned technical problems, the present invention provides a kind of
System and method processed, specification cleaning and sterilizing personnel's operational motion, real time monitoring are reminded, it is ensured that endoscope cleaning sterilisation quality in time.
Technical solution used by system of the invention is: a kind of endoscope cleaning sterilisation quality control based on deep learning
System, it is characterised in that: including image collecting device, user terminal, server-side;
Described image acquisition device is arranged near scope cleaning sink, acquires endoscope cleaning disinfection personnel's operation diagram
Picture, and the image of acquisition is given to the user terminal by network transmission;The image of acquisition is passed through network by the user terminal
It is transferred to the server-side, and receives and show the analysis result of the server-side feedback;The server-side is according to whole from user
The image of transmission is held, judges that endoscope cleaning disinfection personnel operate the corresponding operation of image and operating characteristics immediately, will analyze
As a result user terminal is fed back to.
Technical solution used by method of the invention is: a kind of endoscope cleaning sterilisation quality control based on deep learning
Method, which comprises the following steps:
Step 1: obtaining training image collection, including side leakage, scrub, previous cleaning, enzyme are washed, rinsed, sterilizing, terminal rinsing, dry
The all operationss characteristic image for including in eight each operating procedures of step;
Step 2: using the training image collection, the convolutional neural networks after training convolutional neural networks model training
Model;
Step 3: image acquisition device endoscope cleaning disinfection personnel operate image, and are transmitted by user terminal
To server-side;
Step 4: server-side calls the judgement of convolutional neural networks model progress feature using the image received as parameter,
It obtains analysis result and feeds back to user terminal;
Step 5: user terminal receives and the analysis result of display server-side feedback.
Compared with existing scope quality tracing technology, the present invention adds in scope cleaning and sterilizing quality traceability system
Deep learning element carries out operating characteristics identification to the operational motion of cleaning and sterilizing scope staff, it is ensured that cleaning and sterilizing is dynamic
The normalization of work.When staff's movement is lack of standardization, the present invention carries out early warning prompting in time, ensure that endoscope cleaning disinfection
Quality, it is final to realize the purpose for reducing nosocomial infection, improving endoscopy quality.
Detailed description of the invention
Fig. 1 is the system structure diagram of the embodiment of the present invention;
Fig. 2 is the method flow diagram of the embodiment of the present invention;
Fig. 3 is convolutional neural networks model training flow chart in the embodiment of the present invention.
Specific embodiment
Understand for the ease of those of ordinary skill in the art and implement the present invention, with reference to the accompanying drawings and embodiments to this hair
It is bright to be described in further detail, it should be understood that implementation example described herein is merely to illustrate and explain the present invention, not
For limiting the present invention.
Referring to Fig.1, a kind of endoscope cleaning sterilisation quality control system based on deep learning provided by the invention, including figure
As acquisition device, user terminal, server-side;
Image collecting device is arranged near scope cleaning sink, and acquisition endoscope cleaning disinfection personnel operate image,
And the image of acquisition is passed through into network transmission to user terminal;User terminal is by the image of acquisition by network transmission to service
End, and receive and the analysis of display server-side feedback is as a result, if operator's cleaning action specification, each operation of the completion that do not omit
The all operationss feature that step requires, then user terminal prompt enter next step;Otherwise, user terminal gives early warning prompting,
It informs operation exception, issues warning note;Server-side is sentenced using REST framework according to the image transmitted from user terminal immediately
Disconnected endoscope cleaning disinfection personnel operate the corresponding operation of image and operating characteristics, and analysis result is fed back to user terminal.
The server-side of the present embodiment includes sample database, convolutional neural networks model and web service module;Sample data
Library is used to store endoscope cleaning disinfection personnel and operates the sample of image as training image collection, including side leakage, scrub, first
It washes, enzyme is washed, rinses, sterilize, terminal rinsing, dries all operationss characteristic image for including in eight each operating procedures of step;
Convolutional neural networks model is to operate image for endoscope cleaning disinfection personnel using the trained model of training image collection
The judgement of respective operations feature;Web service module be used for receive user terminal transmission come image, using the image received as
Parameter calls convolutional neural networks model to carry out the judgement of operating procedure motion characteristic, obtains analysis result and feeds back to user's end
End.
The Web service module of the present embodiment, when progress operating procedure motion characteristic judges, it is necessary to each comprising all steps
The identification of self-contained all operationss characteristic image, if lacking any action in wherein step, sending is prompted to user terminal.
See Fig. 2, a kind of endoscope cleaning sterilisation quality control method based on deep learning provided by the invention, including with
Lower step:
Step 1: obtaining training image collection, including side leakage, scrub, previous cleaning, enzyme are washed, rinsed, sterilizing, terminal rinsing, dry
The all operationss characteristic image for including in eight each operating procedures of step;
Step 2: training image collection is used, after deep learning algorithm training convolutional neural networks model training
Convolutional neural networks model;
Model is Resnet50, is developed using Python, and being packaged into RESTful API, (network of REST style connects
Mouthful) after called by other modules.The training process of convolutional neural networks model is as shown in figure 3, convolutional neural networks model is used for
Field of image recognition is conventional technical means, is no longer repeated herein.
Step 3: image acquisition device endoscope cleaning disinfection personnel operate image, and are transmitted by user terminal
To server-side;
Step 4: server-side calls the judgement of convolutional neural networks model progress feature using the image received as parameter,
It obtains analysis result and feeds back to user terminal;
Step 5: if operator's cleaning action specification, all operationss that each operating procedure of completion that do not omit requires are special
Sign, then user terminal prompt enter next step;Otherwise, user terminal gives early warning prompting, informs operation exception, issues alarm
Prompt.
A kind of endoscope cleaning sterilisation quality control system and method based on deep learning proposed by the present invention, it is clear to scope
It washes quality to be monitored, the purpose for finally realizing and reducing nosocomial infection, improve endoscopy quality.
It should be understood that the part that this specification does not elaborate belongs to the prior art.
It should be understood that the above-mentioned description for preferred embodiment is more detailed, can not therefore be considered to this
The limitation of invention patent protection range, those skilled in the art under the inspiration of the present invention, are not departing from power of the present invention
Benefit requires to make replacement or deformation under protected ambit, fall within the scope of protection of the present invention, this hair
It is bright range is claimed to be determined by the appended claims.
Claims (8)
1. a kind of endoscope cleaning sterilisation quality control system based on deep learning, it is characterised in that: including image collecting device,
User terminal, server-side;
Described image acquisition device is arranged near scope cleaning sink, and acquisition endoscope cleaning disinfection personnel operate image,
And the image of acquisition is given to the user terminal by network transmission;The image of acquisition is passed through network transmission by the user terminal
To the server-side, and receive and show the analysis result of the server-side feedback;The server-side is passed according to from user terminal
Defeated image judges that endoscope cleaning disinfection personnel operate the corresponding operation of image and operating characteristics immediately, will analyze result
Feed back to user terminal.
2. the endoscope cleaning sterilisation quality control system according to claim 1 based on deep learning, it is characterised in that: institute
Stating server-side includes sample database, convolutional neural networks model and web service module;
The sample database is used to store endoscope cleaning disinfection personnel and operates the sample of image as training image collection, packet
Include the whole that side leakage, scrub, previous cleaning, enzyme is washed, rinsed, sterilizing, terminal rinses, includes in dry eight each operating procedures of step
Operating characteristics image;
The convolutional neural networks model is to be used for endoscope cleaning disinfection personnel using the trained model of training image collection
Operate the judgement of image respective operations feature;
The Web service module is used to receive the image that user terminal transmission comes, and the image received is called as parameter and is rolled up
Product neural network model carries out the judgement of operating procedure motion characteristic, obtains analysis result and feeds back to the user terminal.
3. the endoscope cleaning sterilisation quality control system according to claim 2 based on deep learning, it is characterised in that: institute
Web service module is stated, when progress operating procedure motion characteristic judges, it is necessary to all operationss respectively contained comprising all steps
The identification of characteristic image, if lacking any action in wherein step, sending is prompted to user terminal.
4. the endoscope cleaning sterilisation quality control system according to claim 1 based on deep learning, it is characterised in that: if
Operator's cleaning action specification, that does not omit completes all operationss feature of each operating procedure requirement, then the user terminal
Prompt enters next step;Otherwise, the user terminal gives early warning prompting, informs operation exception, issues warning note.
5. the endoscope cleaning sterilisation quality control system according to any one of claims 1-4 based on deep learning,
It is characterized in that: the server-side, using REST framework.
6. a kind of endoscope cleaning sterilisation quality control method based on deep learning, which comprises the following steps:
Step 1: obtaining training image collection, including side leakage, scrub, previous cleaning, enzyme are washed, rinsed, sterilizing, terminal rinsing, eight dry
The all operationss characteristic image for including in each operating procedure of step;
Step 2: using the training image collection, the convolutional neural networks mould after training convolutional neural networks model training
Type;
Step 3: image acquisition device endoscope cleaning disinfection personnel operate image, and are transferred to clothes by user terminal
Business end;
Step 4: server-side calls convolutional neural networks model to carry out the judgement of feature for the image received as parameter, obtains
Analysis result feeds back to user terminal;
Step 5: user terminal receives and the analysis result of display server-side feedback.
7. the endoscope cleaning sterilisation quality control method according to claim 6 based on deep learning, it is characterised in that: step
In rapid 2, using the convolutional neural networks model after deep learning algorithm training convolutional neural networks model training.
8. the endoscope cleaning sterilisation quality control method according to claim 6 based on deep learning, it is characterised in that: step
In rapid 5, if operator's cleaning action specification, that does not omit completes all operationss feature of each operating procedure requirement, then user
Terminal notifying enters next step;Otherwise, user terminal gives early warning prompting, informs operation exception, issues warning note.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811609481.0A CN109740488A (en) | 2018-12-27 | 2018-12-27 | A kind of endoscope cleaning sterilisation quality control system and method based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811609481.0A CN109740488A (en) | 2018-12-27 | 2018-12-27 | A kind of endoscope cleaning sterilisation quality control system and method based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109740488A true CN109740488A (en) | 2019-05-10 |
Family
ID=66361432
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811609481.0A Pending CN109740488A (en) | 2018-12-27 | 2018-12-27 | A kind of endoscope cleaning sterilisation quality control system and method based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109740488A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111738681A (en) * | 2020-06-17 | 2020-10-02 | 浙江大学 | Intelligent disinfection behavior judgment system and method based on deep learning and intelligent socket |
CN111931737A (en) * | 2020-09-28 | 2020-11-13 | 汉桑(南京)科技有限公司 | Corneal mirror abnormity judgment method and system |
CN112422897A (en) * | 2020-10-26 | 2021-02-26 | 北京嘀嘀无限科技发展有限公司 | Treatment method, device, equipment and storage medium for determining disinfection |
CN113017863A (en) * | 2021-03-25 | 2021-06-25 | 江苏省人民医院(南京医科大学第一附属医院) | Instrument cleaning quality self-checking system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202142061U (en) * | 2011-06-09 | 2012-02-08 | 杭州维科软件工程有限责任公司 | Endoscope washing disinfecting quality traceability system |
US20140305507A1 (en) * | 2013-04-15 | 2014-10-16 | General Cybernation Group, Inc. | Self-organizing multi-stream flow delivery process and enabling actuation and control |
CN106971206A (en) * | 2017-04-13 | 2017-07-21 | 广东工业大学 | A kind of care actions wire examination method and system |
CN107563439A (en) * | 2017-08-31 | 2018-01-09 | 湖南麓川信息科技有限公司 | A kind of model for identifying cleaning food materials picture and identification food materials class method for distinguishing |
CN108292366A (en) * | 2015-09-10 | 2018-07-17 | 美基蒂克艾尔有限公司 | The system and method that suspect tissue region is detected in endoscopic surgery |
CN108647848A (en) * | 2018-03-28 | 2018-10-12 | 老肯医疗科技股份有限公司 | The method that formula endoscope cleaning decontamination system can be traced and carry out cleaning and sterilizing using it |
CN108734090A (en) * | 2018-04-03 | 2018-11-02 | 上海感信信息科技股份有限公司 | Endoscope cleaning disinfection retroactive method and traceability system based on computer vision |
-
2018
- 2018-12-27 CN CN201811609481.0A patent/CN109740488A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202142061U (en) * | 2011-06-09 | 2012-02-08 | 杭州维科软件工程有限责任公司 | Endoscope washing disinfecting quality traceability system |
US20140305507A1 (en) * | 2013-04-15 | 2014-10-16 | General Cybernation Group, Inc. | Self-organizing multi-stream flow delivery process and enabling actuation and control |
CN108292366A (en) * | 2015-09-10 | 2018-07-17 | 美基蒂克艾尔有限公司 | The system and method that suspect tissue region is detected in endoscopic surgery |
CN106971206A (en) * | 2017-04-13 | 2017-07-21 | 广东工业大学 | A kind of care actions wire examination method and system |
CN107563439A (en) * | 2017-08-31 | 2018-01-09 | 湖南麓川信息科技有限公司 | A kind of model for identifying cleaning food materials picture and identification food materials class method for distinguishing |
CN108647848A (en) * | 2018-03-28 | 2018-10-12 | 老肯医疗科技股份有限公司 | The method that formula endoscope cleaning decontamination system can be traced and carry out cleaning and sterilizing using it |
CN108734090A (en) * | 2018-04-03 | 2018-11-02 | 上海感信信息科技股份有限公司 | Endoscope cleaning disinfection retroactive method and traceability system based on computer vision |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111738681A (en) * | 2020-06-17 | 2020-10-02 | 浙江大学 | Intelligent disinfection behavior judgment system and method based on deep learning and intelligent socket |
CN111738681B (en) * | 2020-06-17 | 2021-09-03 | 浙江大学 | Intelligent disinfection behavior judgment system and method based on deep learning and intelligent socket |
CN111931737A (en) * | 2020-09-28 | 2020-11-13 | 汉桑(南京)科技有限公司 | Corneal mirror abnormity judgment method and system |
CN112422897A (en) * | 2020-10-26 | 2021-02-26 | 北京嘀嘀无限科技发展有限公司 | Treatment method, device, equipment and storage medium for determining disinfection |
CN112422897B (en) * | 2020-10-26 | 2023-06-23 | 北京嘀嘀无限科技发展有限公司 | Processing method, device, equipment and storage medium for determining disinfection |
CN113017863A (en) * | 2021-03-25 | 2021-06-25 | 江苏省人民医院(南京医科大学第一附属医院) | Instrument cleaning quality self-checking system |
CN113017863B (en) * | 2021-03-25 | 2021-09-17 | 江苏省人民医院(南京医科大学第一附属医院) | Instrument cleaning quality self-checking system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109740488A (en) | A kind of endoscope cleaning sterilisation quality control system and method based on deep learning | |
CN101738969B (en) | Infection control traceability system for central sterile supply department of hospital | |
JP2017524438A (en) | Endoscope scope management system and method | |
DE69814172D1 (en) | SYSTEMS, METHODS AND COMPUTER PROGRAM PRODUCTS FOR MONITORING, DIAGNOSIS AND TREATING MEDICAL CONDITIONS OF REMOTE DISEASES | |
US20120073614A1 (en) | Endoscope cleaning system and endoscope cleaning method | |
CN113130058A (en) | Hand hygiene management system, method, computer device, and readable storage medium | |
CN105574559B (en) | A kind of mobile high-voltage oxygen workstation system based on Internet of Things | |
EP3852603A1 (en) | Endoscope cleaning and inspection system and method | |
CN103606026A (en) | Internet of things-based endoscope disinfection tracing management system | |
CN110223491A (en) | Alarm method, warning device, alarm system and computer readable storage medium | |
CN108647848A (en) | The method that formula endoscope cleaning decontamination system can be traced and carry out cleaning and sterilizing using it | |
US20210151174A1 (en) | System and method of managing, maintaining and reporting endoscope medical devices and using device-related status data | |
CN102894946A (en) | Whole-process intelligentized quality control system for cleanness and disinfection for gastrointestinal endoscopy | |
CN105682692B (en) | System and method for washing, disinfecting and/or sterilizing | |
Pynnonen et al. | Reprocessing flexible endoscopes in the otolaryngology clinic | |
DE102013100142B4 (en) | Method for equipping and for cleaning a dishwasher | |
Lehne et al. | Error-related EEG patterns during tactile human-machine interaction | |
KR101955795B1 (en) | Endoscope reprocessing and service offering system based on IoT | |
CN110063268A (en) | Monitoring method, monitoring device, monitoring system and computer readable storage medium | |
Backhouse | Establishing a protocol for the cleaning and sterilisation/disinfection of ultrasound transducers | |
CN213024593U (en) | Medical supplies sells cabinet | |
Hildebrand et al. | An expert perspective of errors in endoscope reprocessing | |
US20230343448A1 (en) | System and method for traceability and hygiene compliance management reprocessing of reusable medical devices and environments | |
JP2023534506A (en) | Confirmation of mixed treatment in the decontamination process | |
Sardinha et al. | Efficiency and productivity of a sheathed fiberoptic sigmoidoscope compared with a conventional sigmoidoscope |
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: 20190510 |
|
RJ01 | Rejection of invention patent application after publication |