CN109907720A - Video image dendoscope auxiliary examination method and video image dendoscope control system - Google Patents
Video image dendoscope auxiliary examination method and video image dendoscope control system Download PDFInfo
- Publication number
- CN109907720A CN109907720A CN201910295616.9A CN201910295616A CN109907720A CN 109907720 A CN109907720 A CN 109907720A CN 201910295616 A CN201910295616 A CN 201910295616A CN 109907720 A CN109907720 A CN 109907720A
- Authority
- CN
- China
- Prior art keywords
- reference picture
- video image
- model
- dendoscope
- digestive tract
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Processing (AREA)
- Endoscopes (AREA)
- Image Analysis (AREA)
Abstract
The invention proposes a kind of video image dendoscope auxiliary examination method and video image dendoscope control system, the reference picture model of upper digestive tract the method comprising the steps of S1-S3 or S2-S3:S1, is obtained, and the model show on inspection interface;S2, when inspection, analyze video image dendoscope currently upper digestive tract image collected location on reference picture model, and the position mark is come out, if can not find position corresponding with video image dendoscope upper digestive tract image collected on reference picture model, reference picture model is not dealt with;S3 checks in reference picture model whether be all marked, if be all marked, terminates to check;If it is not, continuing checking the region not being marked in reference picture model.This method can effectively prevent doctor to miss some regions of upper digestive tract during the inspection process, guarantee the comprehensive of inspection, can effectively avoid the case where failing to pinpoint a disease in diagnosis appearance.
Description
Technical field
The present invention relates to medical instruments fields, and in particular to a kind of video image dendoscope auxiliary examination method and video image dendoscope control
System.
Background technique
Currently, the inspection to disease of upper digestive tract is mainly checked by capsule endoscope and video image dendoscope, although capsule
Endoscope has many advantages, such as flexible operation, and comfort level is high, but since the visual field of video image dendoscope is better than capsule endoscope, electronics
Scope is in the diagnosis of disease of upper digestive tract still using extremely extensively.But due to doctor's level and clinical experience it is irregular not
Together, some regions that may miss stomach during the inspection process in certain hospitals or certain doctors, cause to fail to pinpoint a disease in diagnosis, lead to disease
People undertakes biggish risk.
Application No. is a kind of 201711268869.4 entitled control methods of capsule endoscope, device and readable storage mediums
A kind of control method of capsule endoscope is disclosed in the patent document of matter, this method first will need before checking stomach
Capsule endoscope is moved to target position, after determining good position, then carries out inspection of taking pictures to stomach by the motion profile of setting again.
Although this can avoid capsule endoscope to a certain extent, stomach region is clapped in leakage, and the review time is long, is easy to increase patient's
Burden, meanwhile, height is required to the motion profile of capsule endoscope, capsule endoscope movement such as cannot be preferably controlled, then still be easy
There is the possibility that leakage is clapped.
Summary of the invention
In order to overcome above-mentioned defect existing in the prior art, the object of the present invention is to provide a kind of video image dendoscope auxiliary to examine
Checking method and video image dendoscope control system.
In order to realize above-mentioned purpose of the invention, the present invention provides a kind of video image dendoscope auxiliary examination methods, including step
Rapid S1-S3 or S2-S3:
S1, the reference picture model for obtaining upper digestive tract, and the model is shown on checking interface;
S2, when inspection, controller receives video image dendoscope upper digestive tract image collected and simultaneously analyzes the current institute of video image dendoscope
The upper digestive tract image of acquisition comes out the position mark the location of on reference picture model, if with reference to figure
As can not find position corresponding with video image dendoscope upper digestive tract image collected on model, then reference picture model is not made
Processing;
S3 checks in reference picture model whether be all marked, if be all marked, terminates
It checks;If it is not, continuing checking the region not being marked in reference picture model.
This method can effectively prevent doctor to miss some regions of upper digestive tract during the inspection process, guarantee to check complete
Face property can effectively avoid the case where failing to pinpoint a disease in diagnosis appearance.And this method does not need to search and checks initial position, does not need according to the rules yet
Path mobile electron scope, but video image dendoscope be located at where can clap where, where photographed can be by the position
Image is compared with reference picture model, is found position of the image in reference picture model, is saved the review time.
Further, the reference picture model of upper digestive tract is obtained in step S1 method particularly includes:
The picture of N different parts in the upper digestive tract shot under specified light is collected, this N picture, which includes at least, above to disappear
The picture for changing M privileged site on road, is trained this N picture and position identifies, obtains the classification mould of M privileged site
Type;
The disaggregated model of M privileged site of acquisition is spliced into a complete upper digestive tract model to get at this
Then the reference picture model show on inspection interface by the reference picture model under specified light, the N and M are positive whole
Number, and N is not less than M.
Further, when inspection, using disaggregated model by video image dendoscope the upper digestive tract collected under the specified light
Image is compared with the reference picture model under identical specified light, obtain video image dendoscope it is collected in the case where this specifies light on
Alimentary canal image marks in the reference picture model the location of on the reference picture model under identical specified light
Come.It checks in reference picture model whether be all marked, if be all marked, terminates to check;Such as
Fruit does not have, then continues checking the region not being marked in reference picture model.
Alternatively, video image dendoscope shoots picture to the privileged site of upper digestive tract under the specified light, by electronics when checking
Position picture captured by scope carries out image procossing and in real time splicing, and the picture spliced is shown under the specified light
Reference picture model on corresponding region;The privileged site includes at least position as defined in electronic endoscopy standard;
It checks whether the region of the reference picture model all splices to complete, if splicing is completed, inspection terminates;If
There are still the regions that do not splice for the reference picture model, then continuing checking in the reference picture model does not have the region that do not splice.
Identification video image dendoscope acquired image position locating on reference picture model can be effectively improved using this method
The accuracy rate set.
Preferably, the N is not less than 32, can preferably ensure all areas of entire upper digestive tract all on inspection.
Preferably, the specified light is one of white light, purple light, blue and green light, guarantees that the inspection to a variety of lesions is quasi-
True rate.
Further, when establishing reference picture model and checking, privileged site in upper digestive tract is placed in video image dendoscope
Field of view center acquire image.
Further, there is overlapping or coincident between the shooting image of adjacent privileged site.
This can preferably ensure that all areas of entire upper digestive tract all on inspection, improve identification video image dendoscope and adopted
Accuracy rate of the image of collection the location of on reference picture model, effectively avoids the case where failing to pinpoint a disease in diagnosis appearance.
The invention also provides a kind of video image dendoscope control systems, including reference picture model acquiring unit, image to compare
Unit, position judging unit and control unit;
The reference picture model acquiring unit, image comparing unit, position judging unit are connect with control unit, ginseng
Iconic model acquiring unit, image comparing unit, position judging unit are examined by the described in any item electronics of claim 1 to 8
Mirror auxiliary examination method obtain reference picture model, by video image dendoscope upper digestive tract image collected and reference picture model into
Row compares, analysis video image dendoscope upper digestive tract image collected is the location of on reference picture model, and the control is single
Member control video image dendoscope shoots image.
The beneficial effects of the present invention are: this method can effectively prevent doctor miss during the inspection process upper digestive tract certain
A little regions guarantee the comprehensive of inspection, can effectively avoid the case where failing to pinpoint a disease in diagnosis appearance.
Additional aspect and advantage of the invention will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
When Fig. 1 is using AI method, flow chart of the invention;
When Fig. 2 is using image procossing and joining method, flow chart of the invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not considered as limiting the invention.
In the description of the present invention, unless otherwise specified and limited, it should be noted that term " installation ", " connected ",
" connection " shall be understood in a broad sense, for example, it may be mechanical connection or electrical connection, the connection being also possible to inside two elements can
, can also indirectly connected through an intermediary, for the ordinary skill in the art to be to be connected directly, it can basis
Concrete condition understands the concrete meaning of above-mentioned term.
As shown in Figure 1, the present invention provides a kind of video image dendoscope auxiliary examination method, including the following steps:
S1, the reference picture model for obtaining upper digestive tract, and the model is shown on checking interface.
In real work, existing upper digestive tract iconic model is can be used in reference picture model, can also be used with lower section
Method obtains: collecting the picture of N different parts in the upper digestive tract shot under specified light, this N picture, which includes at least, above to disappear
The picture for changing M privileged site on road, is trained this N picture and position identifies, obtains the classification mould of M privileged site
Type.
The disaggregated model of M privileged site of acquisition is spliced into a complete upper digestive tract model to get at this
Then the reference picture model show on inspection interface by the reference picture model under specified light, the N and M are positive whole
Number, and N is not less than M.
Know from clinical examination, it is to be ensured that the integrality of inspection, doctor can need to clap to each position of upper digestive tract
At least 32 pictures are taken the photograph, just can ensure that all areas of entire upper digestive tract so all on inspection, therefore N and M are not less than
32.Specified light is preferably but not limited to as one of white light, purple light, blue and green light.
Here picture is trained and position identifies and splicing is using existing method, it is preferred to use convolutional Neural
Network algorithm is trained picture.
S2, when inspection, controller receives video image dendoscope upper digestive tract image collected and simultaneously analyzes the current institute of video image dendoscope
The upper digestive tract image of acquisition comes out the position mark the location of on reference picture model, if with reference to figure
As can not find position corresponding with video image dendoscope upper digestive tract image collected on model, then reference picture model is not made
Processing;
S3 checks in reference picture model whether be all marked, if be all marked, terminates
It checks;If it is not, continuing checking the region not being marked in reference picture model.
Analyzing video image dendoscope, currently upper digestive tract image collected, can when the location of on reference picture model
It is realized, can also be realized using image procossing and joining method using AI method.
As shown in Figure 1, when being realized with AI method, when inspection, using disaggregated model by video image dendoscope under the specified light
Upper digestive tract image collected is compared with the reference picture model under identical specified light, and acquisition video image dendoscope refers at this
Determine upper digestive tract image location on the reference picture model under identical specified light collected under light, and in the reference
It is marked in iconic model, such as lights the position, check whether reference picture model has all been lit, if entirely
Portion lights, then terminates to check;If it is not, continuing checking the region not being lit in reference picture model.
Preferably, by video image dendoscope under the specified light upper digestive tract image collected under identical specified light
Reference picture model when comparing, carried out again with reference picture model after can first being spliced the image of adjacent position pair
Than identification, the inspection accuracy in video image dendoscope field of view edge region can be effectively improved in this way.
As shown in Fig. 2, during the inspection process, video image dendoscope is in specified light when being realized using image procossing and joining method
Under picture is shot to the privileged site of upper digestive tract, such as the cardia of stomach, stomach bottom, lesser curvature, greater curvature, stomach angle, antrum, pylorus
Position picture captured by video image dendoscope is carried out image procossing and splicing, and the figure that will splice in real time by equal privileged sites
Piece is shown to the corresponding region on the reference picture model under the specified light, and privileged site includes at least electronic endoscopy here
Position as defined in standard.
It checks whether the region of the reference picture model all splices to complete, if splicing is completed, inspection terminates;If
There are still the regions that do not splice for the reference picture model, then continuing checking in the reference picture model does not have the region that do not splice.
Preferably to realize the comparison of image and avoiding failing to pinpoint a disease in diagnosis, when establishing reference picture model and/or checking, disappear by
Change the field of view center acquisition image that privileged site in road is placed in video image dendoscope, has between the shooting image of adjacent privileged site overlapping
Or coincident.
Judgement and prompting in by the above process, can prevent doctor from missing the certain of upper digestive tract during the inspection process
Region guarantees the comprehensive of inspection, is further ensured that and fails to pinpoint a disease in diagnosis.
The invention also provides a kind of video image dendoscope control systems, including reference picture model acquiring unit, image to compare
Unit, position judging unit and control unit.
The reference picture model acquiring unit, image comparing unit, position judging unit are connect with control unit, ginseng
Iconic model acquiring unit, image comparing unit, position judging unit is examined to obtain by above-mentioned video image dendoscope auxiliary examination method
Video image dendoscope upper digestive tract image collected is compared with reference picture model, analyzes in electronics by reference picture model
Mirror upper digestive tract image collected is marked the position, the control the location of on reference picture model
Unit controls video image dendoscope and shoots image.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: not
A variety of change, modification, replacement and modification can be carried out to these embodiments in the case where being detached from the principle of the present invention and objective, this
The range of invention is defined by the claims and their equivalents.
Claims (9)
1. a kind of video image dendoscope auxiliary examination method, which is characterized in that including step S1-S3 or S2-S3:
S1, the reference picture model for obtaining upper digestive tract, and the model is shown on checking interface;
S2, when inspection, controller receive video image dendoscope upper digestive tract image collected and analyze video image dendoscope it is collected on
Alimentary canal image comes out the position mark the location of on reference picture model, if on reference picture model
It can not find position corresponding with video image dendoscope upper digestive tract image collected, then reference picture model do not dealt with;
S3 checks in reference picture model whether be all marked, if be all marked, terminates to examine
It looks into;If it is not, continuing checking the region not being marked in reference picture model.
2. video image dendoscope auxiliary examination method according to claim 1, which is characterized in that obtain upper digestive tract in step S1
Reference picture model method particularly includes:
The picture of N different parts in the upper digestive tract shot under specified light is collected, this N picture includes at least upper digestive tract
The picture of upper M privileged site, is trained this N picture and position identifies, obtains the disaggregated model of M privileged site;
The disaggregated model of M privileged site of acquisition is spliced into a complete upper digestive tract model to get to specifying at this
Then the reference picture model is shown that on checking interface, the N and M are positive integer by the reference picture model under light, and
N is not less than M.
3. video image dendoscope auxiliary examination method according to claim 2, which is characterized in that when inspection, utilize disaggregated model
By video image dendoscope under the specified light upper digestive tract image collected and the reference picture model under identical specified light into
Row comparison obtains the video image dendoscope reference picture mould of upper digestive tract image collected under identical specified light in the case where this specifies light
The location of in type, and it is marked in the reference picture model.
4. video image dendoscope auxiliary examination method according to claim 2, which is characterized in that when inspection, video image dendoscope is in institute
It states and picture is shot to the privileged site of upper digestive tract under specified light, position picture captured by video image dendoscope is subjected to image procossing
And splice in real time, and the picture spliced is shown to the corresponding region on the reference picture model under the specified light;It is described
Privileged site includes at least position as defined in electronic endoscopy standard;
It checks whether the region of the reference picture model all splices to complete, if splicing is completed, inspection terminates;If the ginseng
Examining iconic model, there are still the regions that do not splice, then continuing checking in the reference picture model does not have the region that do not splice.
5. video image dendoscope auxiliary examination method according to claim 2, which is characterized in that the N is not less than 32.
6. video image dendoscope auxiliary examination method according to claim 2, which is characterized in that the specified light is white light, purple
One of light, blue and green light.
7. video image dendoscope auxiliary examination method according to claim 2, which is characterized in that establish reference picture model and
When inspection, the field of view center that privileged site in upper digestive tract is placed in video image dendoscope is acquired into image.
8. the video image dendoscope auxiliary examination method according to claim 4 or 7, which is characterized in that the bat of adjacent privileged site
Taking the photograph between image has overlapping or coincident.
9. a kind of video image dendoscope control system, which is characterized in that including reference picture model acquiring unit, image comparing unit,
Position judging unit and control unit;
The reference picture model acquiring unit, image comparing unit, position judging unit are connect with control unit, with reference to figure
As model acquiring unit, image comparing unit, position judging unit are auxiliary by the described in any item video image dendoscopes of claim 1 to 8
It helps inspection method to obtain reference picture model, compare video image dendoscope upper digestive tract image collected and reference picture model
To, analysis video image dendoscope upper digestive tract image collected the location of on reference picture model, described control unit control
Video image dendoscope processed shoots image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910295616.9A CN109907720A (en) | 2019-04-12 | 2019-04-12 | Video image dendoscope auxiliary examination method and video image dendoscope control system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910295616.9A CN109907720A (en) | 2019-04-12 | 2019-04-12 | Video image dendoscope auxiliary examination method and video image dendoscope control system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109907720A true CN109907720A (en) | 2019-06-21 |
Family
ID=66969748
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910295616.9A Pending CN109907720A (en) | 2019-04-12 | 2019-04-12 | Video image dendoscope auxiliary examination method and video image dendoscope control system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109907720A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110613417A (en) * | 2019-09-24 | 2019-12-27 | 浙江同花顺智能科技有限公司 | Method, equipment and storage medium for outputting upper digestion endoscope operation information |
CN111128396A (en) * | 2019-12-20 | 2020-05-08 | 山东大学齐鲁医院 | Digestive tract disease auxiliary diagnosis system based on deep learning |
WO2022194015A1 (en) * | 2021-03-17 | 2022-09-22 | 安翰科技(武汉)股份有限公司 | Area-by-area completeness self-checking method of capsule endoscope, electronic device, and readable storage medium |
WO2022194014A1 (en) * | 2021-03-17 | 2022-09-22 | 安翰科技(武汉)股份有限公司 | Completeness self-checking method of capsule endoscope, electronic device, and readable storage medium |
CN115861299A (en) * | 2023-02-15 | 2023-03-28 | 浙江华诺康科技有限公司 | Electronic endoscope quality control method and device based on two-dimensional reconstruction |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101584571A (en) * | 2009-06-15 | 2009-11-25 | 无锡骏聿科技有限公司 | Capsule endoscopy auxiliary film reading method |
JP5028191B2 (en) * | 2007-09-03 | 2012-09-19 | オリンパスメディカルシステムズ株式会社 | Endoscope device |
CN107967946A (en) * | 2017-12-21 | 2018-04-27 | 武汉大学 | Operating gastroscope real-time auxiliary system and method based on deep learning |
CN109035339A (en) * | 2017-10-27 | 2018-12-18 | 重庆金山医疗器械有限公司 | The location recognition method of capsule endoscope system and its operation area detection picture |
CN109146884A (en) * | 2018-11-16 | 2019-01-04 | 青岛美迪康数字工程有限公司 | Endoscopy monitoring method and device |
-
2019
- 2019-04-12 CN CN201910295616.9A patent/CN109907720A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5028191B2 (en) * | 2007-09-03 | 2012-09-19 | オリンパスメディカルシステムズ株式会社 | Endoscope device |
CN101584571A (en) * | 2009-06-15 | 2009-11-25 | 无锡骏聿科技有限公司 | Capsule endoscopy auxiliary film reading method |
CN109035339A (en) * | 2017-10-27 | 2018-12-18 | 重庆金山医疗器械有限公司 | The location recognition method of capsule endoscope system and its operation area detection picture |
CN107967946A (en) * | 2017-12-21 | 2018-04-27 | 武汉大学 | Operating gastroscope real-time auxiliary system and method based on deep learning |
CN109146884A (en) * | 2018-11-16 | 2019-01-04 | 青岛美迪康数字工程有限公司 | Endoscopy monitoring method and device |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110613417A (en) * | 2019-09-24 | 2019-12-27 | 浙江同花顺智能科技有限公司 | Method, equipment and storage medium for outputting upper digestion endoscope operation information |
CN111128396A (en) * | 2019-12-20 | 2020-05-08 | 山东大学齐鲁医院 | Digestive tract disease auxiliary diagnosis system based on deep learning |
WO2022194015A1 (en) * | 2021-03-17 | 2022-09-22 | 安翰科技(武汉)股份有限公司 | Area-by-area completeness self-checking method of capsule endoscope, electronic device, and readable storage medium |
WO2022194014A1 (en) * | 2021-03-17 | 2022-09-22 | 安翰科技(武汉)股份有限公司 | Completeness self-checking method of capsule endoscope, electronic device, and readable storage medium |
CN115861299A (en) * | 2023-02-15 | 2023-03-28 | 浙江华诺康科技有限公司 | Electronic endoscope quality control method and device based on two-dimensional reconstruction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109907720A (en) | Video image dendoscope auxiliary examination method and video image dendoscope control system | |
US9149179B2 (en) | System and method for identifying eye conditions | |
CN104114077B (en) | Image processing apparatus and image processing method | |
EP1849402B1 (en) | Medical image processing device, lumen image processing device, lumen image processing method, and programs for them | |
US7319781B2 (en) | Method and system for multiple passes diagnostic alignment for in vivo images | |
EP1994878B9 (en) | Medical image processing device and medical image processing method | |
US8353816B2 (en) | Endoscopy system and method therefor | |
WO2021147429A1 (en) | Endoscopic image display method, apparatus, computer device, and storage medium | |
CN112770662B (en) | Medical image processing device, medical image processing method, program, diagnosis support device, and endoscope system | |
CN113543694B (en) | Medical image processing device, processor device, endoscope system, medical image processing method, and recording medium | |
CN106793939A (en) | For the method and system of the diagnostic mapping of bladder | |
CN102596001B (en) | Image processing device and image processing method | |
US20130064436A1 (en) | Medical image processing apparatus and method of operating medical image processing apparatus | |
CN114259197B (en) | Capsule endoscope quality control method and system | |
JP2006223376A (en) | Medical image processing apparatus | |
KR102625668B1 (en) | A capsule endoscope apparatus and supporting methods for diagnosing the lesions | |
KR20110019992A (en) | Diagnosing system and method using iridology | |
WO2022080141A1 (en) | Endoscopic imaging device, method, and program | |
CN112190222B (en) | Peptic ulcer detection device | |
CN111260635A (en) | Full-automatic fundus photo acquisition, eye disease identification and personalized management system with embedded lightweight artificial neural network | |
CN117974440B (en) | Method and system for stitching endoscope images | |
JP2015226599A (en) | Apparatus for measuring chromaticity of living body | |
WO2021241735A1 (en) | Endoscope processor device | |
JP7432328B2 (en) | medical system | |
WO2015068495A1 (en) | Organ image capturing device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201130 Address after: No.18, nishang Avenue, Huixing street, Yubei District, Chongqing Applicant after: CHONGQING JINSHAN SCIENCE & TECHNOLOGY (GROUP) Co.,Ltd. Address before: 401120 Chongqing city Yubei District Huixing Street neon Road No. 18, Jinshan International Industrial City 1 office buildings Applicant before: CHONGQING JINSHAN MEDICAL APPLIANCE Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190621 |
|
RJ01 | Rejection of invention patent application after publication |