CN109222859A - A kind of intelligent endoscope image system with AI auxiliary diagnosis function - Google Patents
A kind of intelligent endoscope image system with AI auxiliary diagnosis function Download PDFInfo
- Publication number
- CN109222859A CN109222859A CN201810877835.3A CN201810877835A CN109222859A CN 109222859 A CN109222859 A CN 109222859A CN 201810877835 A CN201810877835 A CN 201810877835A CN 109222859 A CN109222859 A CN 109222859A
- Authority
- CN
- China
- Prior art keywords
- image data
- unit
- endoscope
- server
- image
- 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
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
- A61B1/04—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor combined with photographic or television appliances
- A61B1/05—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor combined with photographic or television appliances characterised by the image sensor, e.g. camera, being in the distal end portion
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Surgery (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biomedical Technology (AREA)
- Optics & Photonics (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Biophysics (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of intelligent endoscope image system with AI auxiliary diagnosis function, including endoscope, single-chip microcontroller and AI server, the endoscope output end is connect with AI server connecting pin.The present invention passes through the setting of AI server, be conducive to carry out intelligent analysis to the image data that endoscope obtains, the image data of network storage is compared with the image data that endoscope obtains by comparing unit and mark unit for AI server, and the difference of comparison is identified, reduce doctor in the workload of diagnosis process study image, the error diagnosis that may largely occur is avoided, provides strong help to the medical diagnosis on disease work of doctor.
Description
Technical field
The present invention relates to medical instruments field, in particular to a kind of intelligent endoscope image with AI auxiliary diagnosis function
System.
Background technique
Doctor is that viewing endoscope display screen is operated, traditional is interior when being checked or being performed the operation using endoscope
Sight glass is only capable of the organization of human body to be observed by image or video display, and function is relatively single, cannot provide doctor more
Back work.
Summary of the invention
The purpose of the present invention is to provide one kind to assist with artificial intelligence (Artificial Intelligence, AI)
The intelligent endoscope image system of diagnostic function is mentioned by the situation of the AI server intelligent analysis state of an illness for the work of doctor
For more more effectively auxiliary.
Technical solution provided by the invention is as follows:
The present invention provides a kind of intelligent endoscope image system with AI auxiliary diagnosis function, including endoscope and AI service
Device, the endoscope output end are connect with AI server connecting pin, and acquisition unit, signal transmitting list are provided in the endoscope
Member and display unit；
The acquisition unit is made of multiple groups miniature webcam, is seen for acquiring endoscope by the multiple groups miniature webcam
The image data in the region examined；
The signal transfer unit is used to pass to described image data the AI server, and receives the AI server
Image data after the mark of passback；
Display unit, for show it is described mark unit marks after image data；
Image analysis unit, comparing unit, mark unit and image receiving unit, image is provided in the AI server to transfer
Unit；
Described image receiving unit, for receiving the image data of endoscope transmitting；
Described image resolution unit, for being parsed to the received image data of described image receiving unit；
Described image transfers unit for transferring image data corresponding with the image data after parsing out of network server；
Comparing unit determines distinct for compareing the received image data with the image data transferred
Pixel；
Unit is identified, the pixel for determining in the received image data to comparing unit is identified, and will mark
Image data after knowledge returns to the endoscope.
In some embodiments, memory, processor are additionally provided in the endoscope, the display unit includes display
Screen.
In some embodiments, the display screen is set as the full touching display screen of LED, and setting is useful in the processor
In be provided in the screenshot unit intercepted to image, the display screen for incude touch photosensitive sensors, described section
Figure unit is electrically connected with display screen.
In some embodiments, the photosensitive sensors are attached with RS-232 serial-port interface with single-chip microcontroller.
In some embodiments, AI server connecting pin is provided with network server, the AI server and network
Server is attached by wired or wireless network, and medical information memory is provided in the network server.
Another aspect of the present invention also provides a kind of AI aided diagnosis method for intelligent endoscope image system, comprising:
Endoscope obtains the image data in region observed by multiple groups miniature webcam acquisition endoscope；
Described image data are passed to AI server by endoscope；
AI server parses received image data；
AI server transfers image data corresponding with the image data after parsing out of network server；
AI server compares the received image data with the image data transferred, and determines distinct pixel
Point；
The pixel that AI server determines comparing unit in the received image data is identified, and returning will be after mark
Data back give the endoscope；
Endoscope receives the image data after the mark of the AI server passback, and shows the figure after the mark unit marks
As data.
In some embodiments, this method further include:
The touch signal for receiving touch display screen feedback, intercepts the image currently shown based on the touch signal, and
Image after display interception.
Technical effect and advantage of the invention:
1, by the setting of AI server, be conducive to carry out intelligent analysis, AI server to the image data that endoscope obtains
The image data of network storage is compared with the image data that endoscope obtains by comparing unit and mark unit, and
The difference of comparison is identified, reduces doctor in the workload of diagnosis process study image, avoids a large amount of possibility
The error diagnosis of generation provides strong help to the medical diagnosis on disease work of doctor；
2, by screenshot unit and photosensitive sensors, be conducive to carry out screenshot to endoscope acquired image, make extra figure
As being partially removed, main part is left, it is possible to reduce the workload of image analysis, while can also be improved AI server
To the accuracy of illness analysis.
Detailed description of the invention
Fig. 1 is the intelligent endoscope image system structural schematic diagram provided by the invention with AI auxiliary diagnosis function.
Fig. 2 is the AI aided diagnosis method flow chart provided by the present invention for intelligent endoscope image system.
Specific embodiment
Embodiment 1
The present invention provides a kind of intelligent endoscope image system with AI auxiliary diagnosis function as shown in Figure 1, including it is interior
Sight glass 101 and AI server 102,101 output end of endoscope are connect with 102 connecting pin of AI server, the endoscope 101
It is inside provided with acquisition unit 1011 and signal transfer unit 1012, the acquisition unit 1011 is made of multiple groups miniature webcam,
It is provided with image analysis unit 1021, comparing unit 1022, mark unit 1023 and image in the AI server 102 and receives list
Member 1024, image transfer unit 1025；
The acquisition unit is made of multiple groups miniature webcam, is seen for acquiring endoscope by the multiple groups miniature webcam
The image data in the region examined；
The signal transfer unit is used to pass to described image data the AI server, and receives the AI server
Image data after the mark of passback；
Display unit, for show it is described mark unit marks after image data；
Image analysis unit, comparing unit, mark unit and image receiving unit, image is provided in the AI server to transfer
Unit；
Described image receiving unit, for receiving the image data of endoscope transmitting；
Described image resolution unit, for being parsed to the received image data of described image receiving unit；
Described image transfers unit for transferring image data corresponding with the image data after parsing out of network server；
Comparing unit determines distinct for compareing the received image data with the image data transferred
Pixel；
Unit is identified, the pixel for determining in the received image data to comparing unit is identified, and will mark
Image data after knowledge returns to the endoscope.
The present embodiment the utility model has the advantages that
By the setting of AI server, be conducive to carry out intelligent analysis to the image data that endoscope obtains, AI server is logical
It crosses comparing unit and the image data of network storage is compared with the image data that endoscope obtains for mark unit, and handle
The difference of comparison is identified, and reduces doctor in the workload of diagnosis process study image, and avoiding largely may hair
Raw error diagnosis provides strong help to the medical diagnosis on disease work of doctor.
Preferably, being additionally provided with memory, processor in the endoscope, the display unit includes display screen.
In some embodiments, the display screen is set as the full touching display screen of LED, and setting is useful in the processor
In be provided in the screenshot unit intercepted to image, the display screen for incude touch photosensitive sensors, described section
Figure unit is electrically connected with display screen.
In some embodiments, the photosensitive sensors are attached with RS-232 serial-port interface with single-chip microcontroller.
Optionally, full touching display screen can be resistance-type, condenser type, infrared-type, surface acoustic wave type or optics
Formula.
In some embodiments, AI server connecting pin is provided with network server, the AI server and network
Server is attached by wired or wireless network, and medical information memory is provided in the network server.
The network server includes hospital's director server, medical research server and diseases monitoring department server；
The endoscope is set as soft fiber glass sebific duct, and by polishing disinfection treatment.
As shown in Fig. 2, another aspect of the present invention also provides a kind of AI auxiliary diagnosis for intelligent endoscope image system
Method, comprising:
S201, endoscope obtain the image data in region observed by multiple groups miniature webcam acquisition endoscope；
Described image data are passed to AI server by S202, endoscope；
S203, AI server parse received image data；
S204, AI server transfer image data corresponding with the image data after parsing out of network server；
S205, AI server compare the received image data with the image data transferred, and determine distinct
Pixel；
The pixel that S206, AI server determine comparing unit in the received image data is identified, and returning will
Data back after mark gives the endoscope；
S207, endoscope receive the image data after the mark of the AI server passback, and show the mark unit marks
Image data afterwards.
In some embodiments, this method further include:
The touch signal for receiving touch display screen feedback, intercepts the image currently shown based on the touch signal, and
Image after display interception.
Preferably, S202 can be, image data is shown by touch display screen, receives touch display screen feedback
Touch signal, the image currently shown is intercepted based on the touch signal, and show interception after image, and will cut
Image data after taking passes to AI server, to reduce the image processing work amount of AI server.
The signal transfer unit of endoscope, is also used to, and image data is passed to processor, by processor by image data
Shown by touching display screen, and obtain touching display screen feedback touch signal, based on the touch signal into
Row image interception, and the image data after interception is shown, and the image data after interception is transmitted into list by signal
Member passes to AI server.Then display unit is also used to video-stream processor and indicates its image data shown.
Preferably, S203 carries out image analysis, image analysis can be carried out by deep learning, transfers and parses in S204
The corresponding image data of image data afterwards can be the image data after transferring and parsing, what similarity was greater than the set value
Image data.The setting value can be 75%.
In S205, AI server compares the received image data with the image data transferred, and determines and exists
The pixel of difference can determine distinct pixel by the method for deep learning.Working principle of the present invention: it uses
When, endoscope is put into position to be detected, acquisition unit carries out image data acquiring to the portion structure of detection, and passes in real time
Pass processor, processor shows image data, and is stored by memory, then doctor's finger or
Felt pen carries out screenshotss to the image of display screen display, and after photosensitive sensors receive signal, according to finger or felt pen
The part contacted carries out screenshot by screenshot unit, and cut figure is passed to AI server, and AI server is to reception
Image parsed, and transfer corresponding image from the medical information memory in network server, then comparing unit
The received image of AI server is compared with the image transferred, compares out difference, and identify unit to difference
Place is identified, and then by returning to endoscope, on a display screen, it is healthy for storing in medical information memory for display
Image data, and the difference of the image data of received image and health is identified, doctor can be helped to diagnose.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The shape for the computer program product implemented in usable storage medium (including but not limited to magnetic disk storage and optical memory etc.)
Formula.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (7)
1. a kind of intelligent endoscope image system with AI auxiliary diagnosis function, which is characterized in that taken including endoscope and AI
Business device, the endoscope output end are connect with AI server connecting pin, and acquisition unit, signal transmitting are provided in the endoscope
Unit and display unit；
The acquisition unit is made of multiple groups miniature webcam, is seen for acquiring endoscope by the multiple groups miniature webcam
The image data in the region examined；
The signal transfer unit is used to pass to described image data the AI server, and receives the AI server
Image data after the mark of passback；
Display unit, for show it is described mark unit marks after image data；
Image analysis unit, comparing unit, mark unit and image receiving unit, image is provided in the AI server to transfer
Unit；
Described image receiving unit, for receiving the image data of endoscope transmitting；
Described image resolution unit, for being parsed to the received image data of described image receiving unit；
Described image transfers unit for transferring image data corresponding with the image data after parsing out of network server；
Comparing unit determines distinct for compareing the received image data with the image data transferred
Pixel；
Unit is identified, the pixel for determining in the received image data to comparing unit is identified, and will mark
Image data after knowledge returns to the endoscope.
2. the system as claimed in claim 1, which is characterized in that memory, processor are additionally provided in the endoscope, it is described
Display unit includes display screen.
3. system as claimed in claim 2, which is characterized in that the display screen is set as the full touching display screen of LED, described
It is provided with the screenshot unit for being intercepted to image in processor, is provided in the display screen for incuding the light touched
Propagated sensation sensor, the screenshot unit are electrically connected with display screen.
4. system as claimed in claim 3, which is characterized in that the photosensitive sensors are with RS-232 serial-port interface and monolithic
Machine is attached.
5. the system as claimed in claim 1, which is characterized in that the AI server and network server pass through wired or nothing
Gauze network is attached, and medical information memory is provided in the network server.
6. a kind of AI aided diagnosis method for intelligent endoscope image system characterized by comprising
Endoscope obtains the image data in region observed by multiple groups miniature webcam acquisition endoscope；
Described image data are passed to AI server by endoscope；
AI server parses received image data；
AI server transfers image data corresponding with the image data after parsing out of network server；
AI server compares the received image data with the image data transferred, and determines distinct pixel
Point；
The pixel that AI server determines comparing unit in the received image data is identified, and returning will be after mark
Data back give the endoscope；
Endoscope receives the image data after the mark of the AI server passback, and shows the figure after the mark unit marks
As data.
7. method as claimed in claim 6, which is characterized in that further include:
The touch signal for receiving touch display screen feedback, intercepts the image currently shown based on the touch signal, and
Image after display interception.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810877835.3A CN109222859A (en) | 2018-08-03 | 2018-08-03 | A kind of intelligent endoscope image system with AI auxiliary diagnosis function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810877835.3A CN109222859A (en) | 2018-08-03 | 2018-08-03 | A kind of intelligent endoscope image system with AI auxiliary diagnosis function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109222859A true CN109222859A (en) | 2019-01-18 |
Family
ID=65070447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810877835.3A Pending CN109222859A (en) | 2018-08-03 | 2018-08-03 | A kind of intelligent endoscope image system with AI auxiliary diagnosis function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109222859A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112788300A (en) * | 2021-01-20 | 2021-05-11 | 肖志宏 | Novel arthroscope and control method thereof |
| CN114049934A (en) * | 2021-11-10 | 2022-02-15 | 富士胶片（中国）投资有限公司 | Auxiliary diagnosis method, device, system, equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002085330A (en) * | 2000-09-12 | 2002-03-26 | Olympus Optical Co Ltd | Stereoscopic endoscope device |
| CN106068092A (en) * | 2015-02-23 | 2016-11-02 | Hoya株式会社 | Image processing apparatus |
| CN107203995A (en) * | 2017-06-09 | 2017-09-26 | 合肥工业大学 | Endoscopic images intelligent analysis method and system |
| CN107220975A (en) * | 2017-07-31 | 2017-09-29 | 合肥工业大学 | Uterine neck image intelligent auxiliary judgment system and its processing method |
| CN108055454A (en) * | 2017-12-08 | 2018-05-18 | 合肥工业大学 | The architectural framework and image processing method of medical endoscope artificial intelligence chip |
| CN108042090A (en) * | 2017-12-08 | 2018-05-18 | 合肥工业大学 | Configure the medical endoscope system and image processing method of artificial intelligence chip |
-
2018
- 2018-08-03 CN CN201810877835.3A patent/CN109222859A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002085330A (en) * | 2000-09-12 | 2002-03-26 | Olympus Optical Co Ltd | Stereoscopic endoscope device |
| CN106068092A (en) * | 2015-02-23 | 2016-11-02 | Hoya株式会社 | Image processing apparatus |
| CN107203995A (en) * | 2017-06-09 | 2017-09-26 | 合肥工业大学 | Endoscopic images intelligent analysis method and system |
| CN107220975A (en) * | 2017-07-31 | 2017-09-29 | 合肥工业大学 | Uterine neck image intelligent auxiliary judgment system and its processing method |
| CN108055454A (en) * | 2017-12-08 | 2018-05-18 | 合肥工业大学 | The architectural framework and image processing method of medical endoscope artificial intelligence chip |
| CN108042090A (en) * | 2017-12-08 | 2018-05-18 | 合肥工业大学 | Configure the medical endoscope system and image processing method of artificial intelligence chip |
Non-Patent Citations (1)
| Title |
|---|
| 楼晓敏: "《集成式内窥镜数字影像工作站的研制与开发》", 《集成式内窥镜数字影像工作站的研制与开发》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112788300A (en) * | 2021-01-20 | 2021-05-11 | 肖志宏 | Novel arthroscope and control method thereof |
| CN114049934A (en) * | 2021-11-10 | 2022-02-15 | 富士胶片（中国）投资有限公司 | Auxiliary diagnosis method, device, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106251751B (en) | A kind of simulated medical surgery analogue system based on VR technology | |
| US11723582B2 (en) | Non-invasive and non-contact measurement in early therapeutic intervention | |
| CN109313817A (en) | System and method for generating medical diagnosis | |
| CN109215774B (en) | Real-time remote pulse-taking system and working method thereof | |
| CN105975780A (en) | Machine inquiry system based on virtual reality interaction technology | |
| CN104146684A (en) | Blinder type dizziness detector | |
| Penhaker et al. | Cloud computing environments for biomedical data services | |
| CN109222859A (en) | A kind of intelligent endoscope image system with AI auxiliary diagnosis function | |
| CN104462765A (en) | Three-dimensional visualization doctor-patient communication platform construction method and system | |
| CN104462761A (en) | Three-dimensional visualization digital monitoring method and system | |
| CN109310330A (en) | System and method for medical device patient measurement | |
| CN103384886A (en) | Learning and optimizing care protocols. | |
| CN111916203B (en) | Health detection method, apparatus, electronic device and storage medium | |
| CN105769174A (en) | Cardiovascular department detector | |
| CN106652624B (en) | A kind of medical operating analogue system based on VR technology and transient noise noise-removed technology | |
| CN104382584B (en) | A kind of wearable electrocardiosignal monitoring and evaluating system and implementation method | |
| JP7203000B2 (en) | Program, information processing method and information processing apparatus | |
| WO2024093099A1 (en) | Thyroid ultrasound image processing method and apparatus, medium and electronic device | |
| Ahmed et al. | Architecture and design of real-time system for elderly health monitoring | |
| JP5458428B2 (en) | Motor function evaluation apparatus and program | |
| US20220257171A1 (en) | User device based parkinson's disease detection | |
| CN110200599A (en) | A kind of pulse wave detecting method, terminal device and system | |
| CN115568834A (en) | Data processing method and device | |
| CN113628758B (en) | Information processing method and device based on AI and RPA | |
| Jackson et al. | Computer-assisted approaches for measuring, segmenting, and analyzing functional upper extremity movement: a narrative review of the current state, limitations, and future directions |
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: 20190118 |
|
| RJ01 | Rejection of invention patent application after publication |