CN110298836A - The methods, devices and systems of INTESTINAL CLEANSING quality are judged by artificial intelligence - Google Patents
The methods, devices and systems of INTESTINAL CLEANSING quality are judged by artificial intelligence Download PDFInfo
- Publication number
- CN110298836A CN110298836A CN201910604500.9A CN201910604500A CN110298836A CN 110298836 A CN110298836 A CN 110298836A CN 201910604500 A CN201910604500 A CN 201910604500A CN 110298836 A CN110298836 A CN 110298836A
- Authority
- CN
- China
- Prior art keywords
- intestinal cleansing
- quality
- picture
- intestinal
- excreta
- 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
- 230000000968 intestinal effect Effects 0.000 title claims abstract description 168
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 29
- 210000003608 fece Anatomy 0.000 claims abstract description 61
- 238000012372 quality testing Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 32
- 238000001356 surgical procedure Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000002052 colonoscopy Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 230000005055 memory storage Effects 0.000 claims description 4
- 238000013136 deep learning model Methods 0.000 claims description 3
- 239000012141 concentrate Substances 0.000 claims 1
- 238000001514 detection method Methods 0.000 claims 1
- 230000029142 excretion Effects 0.000 claims 1
- 238000003062 neural network model Methods 0.000 abstract description 6
- 239000003814 drug Substances 0.000 description 16
- 229940079593 drug Drugs 0.000 description 15
- 230000006870 function Effects 0.000 description 10
- 230000016776 visual perception Effects 0.000 description 5
- 230000013872 defecation Effects 0.000 description 4
- 239000007788 liquid Substances 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 210000001035 gastrointestinal tract Anatomy 0.000 description 3
- 210000000936 intestine Anatomy 0.000 description 3
- 239000004698 Polyethylene Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 210000001072 colon Anatomy 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000003792 electrolyte Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- -1 polyethylene Polymers 0.000 description 2
- 229920000573 polyethylene Polymers 0.000 description 2
- 239000000843 powder Substances 0.000 description 2
- 239000002893 slag Substances 0.000 description 2
- 206010010774 Constipation Diseases 0.000 description 1
- 206010012735 Diarrhoea Diseases 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000002483 medication Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 210000000664 rectum Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- 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
- G06T2207/30028—Colon; Small intestine
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radiology & Medical Imaging (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
This application involves a kind of methods, devices and systems that INTESTINAL CLEANSING quality is judged by artificial intelligence.The described method includes: obtaining the excreta picture that patient terminal is sent；Excreta picture is input to INTESTINAL CLEANSING quality comparison model trained in advance, obtains the comparison result of INTESTINAL CLEANSING quality testing model output；The corresponding INTESTINAL CLEANSING quality of excreta picture is determined according to comparison result.Using technical solution provided by the embodiments of the present application, the quality of INTESTINAL CLEANSING is judged relative to excreta is directly visually observed, and there are three advantages, first is that it is objective to evaluate since the process of judgement is realized by neural network model, the experience and level of patient and medical staff are not depended on；Second is that artificial intelligence judges quickly and can realize to timely feedback, then patient can quickly obtain as a result, without falling into a long wait；Suitably suggest third is that medical worker can give patient according to the result that artificial intelligence judges, improves the cleannes of INTESTINAL CLEANSING.
Description
Technical field
This application involves artificial intelligence field more particularly to a kind of sides that INTESTINAL CLEANSING quality is judged by artificial intelligence
Method, device and system.
Background technique
Necessity before INTESTINAL CLEANSING is colonoscopy or intestinal surgery works.The INTESTINAL CLEANSING of high quality can be knot
Enteroscopy and intestinal surgery provide the clearly visual field, are to guarantee that inspection and operation go on smoothly, reduce the important of wrong diagnosis and escape
Link.Generally promote patient's defecation by the way of taking drugs (such as polyethylene glycol-electrolyte powder) at present, thus
Cleaning intestinal tract is carried out to patient.
After patient's defecation, direct observation generally by medical staff or patient to excreta judges intestines from side
The quality of road preparation, to determine whether patient needs to continue medication, continuation dosage etc..This medical staff or patient
The directly mode of observation judgement, first is that judging result may be caused to have difference due to the experience and horizontal difference of medical staff or patient
It is different；Second is that if patient can not oneself judgement and medical staff it is relatively busy when can not handle in time, will lead to patient and need additional wait
Regular hour.
That is, by way of judging INTESTINAL CLEANSING quality, there is judgement direct visual perception not in time or sentence
The problem of disconnected result inaccuracy.
Summary of the invention
The application provides a kind of methods, devices and systems that INTESTINAL CLEANSING quality is judged by artificial intelligence, at least to exist
It solves to judge existing for by way of judging INTESTINAL CLEANSING quality not in time or judgement direct visual perception to a certain extent
As a result inaccurate problem.
The above-mentioned purpose of the application is achieved through the following technical solutions:
In a first aspect, the embodiment of the present application provides a kind of method that INTESTINAL CLEANSING quality is judged by artificial intelligence, it is described
INTESTINAL CLEANSING is the preparation before enteroscopy or intestinal surgery, which comprises
Obtain the excreta picture that patient terminal is sent；
The excreta picture is input to INTESTINAL CLEANSING quality comparison model trained in advance, obtains the INTESTINAL CLEANSING
The comparison result of quality testing model output；Wherein, the INTESTINAL CLEANSING quality comparison model with faecal samples pictures and
Corresponding INTESTINAL CLEANSING quality identification is obtained as training sample training；The faecal samples pictures include that enteron aisle is quasi-
The picture of standby corresponding INTESTINAL CLEANSING quality of each stage；The comparison result include in the faecal samples pictures with it is described
The immediate picture of excreta picture；
The corresponding INTESTINAL CLEANSING quality of the excreta picture is determined according to the comparison result.
Optionally, the training process of the INTESTINAL CLEANSING quality comparison model, comprising:
Obtain faecal samples pictures gathered in advance；
For picture each in the faecal samples pictures, corresponding INTESTINAL CLEANSING quality identification is set；
Using faecal samples pictures and corresponding INTESTINAL CLEANSING quality identification as training sample, the preparatory structure of training
The deep learning model built obtains the INTESTINAL CLEANSING quality comparison model.
Optionally, it is described the corresponding INTESTINAL CLEANSING quality of the excreta picture is determined according to the comparison result after,
Further include:
The INTESTINAL CLEANSING quality is sent to the patient terminal, with assist patient according to the INTESTINAL CLEANSING quality
Corresponding preset processing mode adjusts itself subsequent INTESTINAL CLEANSING work.
Optionally, it is described the corresponding INTESTINAL CLEANSING quality of the excreta picture is determined according to the comparison result after,
Further include:
The INTESTINAL CLEANSING quality is sent to doctor terminal, with assist doctor according to the INTESTINAL CLEANSING quality and from
The subsequent INTESTINAL CLEANSING work of the experience adjustments patient of body.
Optionally, the method also includes:
The excreta picture is sent to the doctor terminal；
Obtain the correction result to the INTESTINAL CLEANSING quality that doctor terminal is sent；The correction result be doctor according to
The amendment that experience makes the INTESTINAL CLEANSING quality；
The faecal samples pictures are added in the corresponding excreta picture of the correction result.
Optionally, the method also includes:
Obtain patient terminal send patient observe itself shooting excreta picture after to current INTESTINAL CLEANSING quality
Self-assessment information；
The self-assessment information is sent to doctor terminal；
Obtain the doctor to current INTESTINAL CLEANSING quality corresponding with the self-assessment information that the doctor terminal is sent
Raw evaluation information.
Optionally, the method also includes:
Receive and the retraining of the INTESTINAL CLEANSING quality comparison model instructed, with to the INTESTINAL CLEANSING mass ratio to mould
Type carries out incremental training or re -training.
Second aspect, the embodiment of the present application also provide a kind of device that INTESTINAL CLEANSING quality is judged by artificial intelligence, institute
Stating INTESTINAL CLEANSING is the preparation before enteroscopy or intestinal surgery, and described device includes:
Module is obtained, for obtaining the excreta picture of patient terminal transmission；
Comparison module is obtained for the excreta picture to be input to INTESTINAL CLEANSING quality comparison model trained in advance
The comparison result exported to the INTESTINAL CLEANSING quality testing model；Wherein, the INTESTINAL CLEANSING quality comparison model is to drain
Object sample pictures collection and corresponding INTESTINAL CLEANSING quality identification are obtained as training sample training；The faecal samples figure
Piece collection includes the picture of INTESTINAL CLEANSING each stage corresponding INTESTINAL CLEANSING quality；The comparison result includes the faecal samples
In pictures with the immediate picture of excreta picture；
Determining module, for determining the corresponding INTESTINAL CLEANSING quality of the excreta picture according to the comparison result.
The third aspect, the embodiment of the present application also provide a kind of system that INTESTINAL CLEANSING quality is judged by artificial intelligence, institute
Stating INTESTINAL CLEANSING is the preparation before enteroscopy or intestinal surgery, the system comprises:
Cloud Server, and the patient terminal with Cloud Server communication connection；
The Cloud Server includes:
Memory and the processor being connected with the memory；
The memory, for storing program, described program, which is at least used to execute, above-mentioned only relates to patient terminal and cloud
The method that INTESTINAL CLEANSING quality is judged by artificial intelligence of server；
The processor, for calling and executing the described program of the memory storage.
Optionally, the system also includes: with the Cloud Server communication connection doctor terminal；
The described program stored in the memory, be also used to execute it is above-mentioned be related to doctor terminal pass through artificial intelligence
Judge the method for INTESTINAL CLEANSING quality；
The processor, for calling and executing the described program of the memory storage.
The technical solution that embodiments herein provides can include the following benefits:
Using technical solution provided by the embodiments of the present application, patient is when carrying out INTESTINAL CLEANSING, after can taking drugs
Excreta taken pictures by intelligent terminal after be uploaded to Cloud Server, trained neural network mould is provided in Cloud Server
Type can find out the excreta figure uploaded with patient by neural network model from pre-set faecal samples pictures
The immediate picture of piece, to can quickly judge the INTESTINAL CLEANSING of patient according to the INTESTINAL CLEANSING quality identification for including in picture
Whether quality, i.e. patient also need to continue medication etc..So set, for directly visually observing and judging, first is that people
Work intelligent decision very quickly (can regard real-time as) and can be realized and be timely feedbacked, then can be fast after patient's shooting photo
Speed obtain as a result, medical staff without waiting compared with busy；Second is that since the process of judgement is real by model trained in advance
It is existing, as long as judging result is accurate and objective enough then sample size is enough, and do not depend on medical staff or patient
Experience and level, therefore be able to solve too late to judge existing for by way of judging INTESTINAL CLEANSING quality direct visual perception
When or judging result inaccuracy problem.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The application can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the application
Example, and together with specification it is used to explain the principle of the application.
Fig. 1 is a kind of process for the method that INTESTINAL CLEANSING quality is judged by artificial intelligence provided by the embodiments of the present application
Figure；
Fig. 2 is that a kind of structure for the device that INTESTINAL CLEANSING quality is judged by artificial intelligence provided by the embodiments of the present application is shown
It is intended to；
Fig. 3 is that a kind of structure for the system that INTESTINAL CLEANSING quality is judged by artificial intelligence provided by the embodiments of the present application is shown
It is intended to.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the application.
The technical solution of the application is more directed in addition to applying in medical staff's relatively busy the case where can not handling in time
The case where patient is not hospitalized, i.e., patient voluntarily carries out INTESTINAL CLEANSING according to doctor's advice at home, this is passed if used in this case
The method (direct visual perception) of system, patient oneself can only judge or issue medical staff by communication software after taking pictures to sentence
It is disconnected, if patient oneself judges, since patient's experience deficiency is difficult to ensure the accuracy of judging result；If passing through communication after taking pictures
Software issues medical staff's judgement, then medical staff possibly can not reply in time, so that being returned to patient oneself must judge, because
This, to solve the above-mentioned problems, it is necessary to which INTESTINAL CLEANSING quality and judging result foot can quickly be judged by providing one kind
Enough accurate methods.
In consideration of it, the embodiment of the present application the following technical schemes are provided:
Embodiment
Referring to Fig. 1, Fig. 1 is a kind of side for judging INTESTINAL CLEANSING quality by artificial intelligence provided by the embodiments of the present application
The flow chart of method.As shown in Figure 1, this method comprises:
S101: the excreta picture that patient terminal is sent is obtained；
Specifically, described excreta picture is that patient is taking drugs (such as polyethylene glycol-electrolyte powder) defecation
Oneself (being obviously also possible to families of patients) shoots afterwards.
In addition, patient terminal can be the intelligent movable equipment of patient's carrying, the photo of such as smart phone etc., shooting is logical
It crosses network and is sent to the processing to be analyzed such as Cloud Server.
S102: the excreta picture is input to INTESTINAL CLEANSING quality comparison model trained in advance, obtains the intestines
Road prepares the comparison result of quality testing model output；Wherein, the INTESTINAL CLEANSING quality comparison model is with faecal samples figure
Piece collection and corresponding INTESTINAL CLEANSING quality identification are obtained as training sample training；The faecal samples pictures include
The picture of INTESTINAL CLEANSING each stage corresponding INTESTINAL CLEANSING quality；The comparison result includes in the faecal samples pictures
With the immediate picture of excreta picture；
Specifically, the INTESTINAL CLEANSING quality comparison model be Cloud Server management service personnel it is trained in advance,
Such as it can be based on CNN (Convolutional Neural Networks, convolutional neural networks) model or other nerve nets
Network model training.Further, the specific programming of neural network model is realized, can be developed using relevant teams, Google
TensorFlow system framework, which open source code and is widely used from November 9th, 2015.
In addition, Cloud Server can choose Ali's cloud ECS or other similar product, this is not restricted.
Optionally, the training process of INTESTINAL CLEANSING quality comparison model includes:
Obtain faecal samples pictures gathered in advance；
For picture each in the faecal samples pictures, corresponding INTESTINAL CLEANSING quality identification is set；
Using faecal samples pictures and corresponding INTESTINAL CLEANSING quality identification as training sample, the preparatory structure of training
The deep learning model built obtains the INTESTINAL CLEANSING quality comparison model.
That is, needing to be ready to a large amount of fecal matter sample picture first before training INTESTINAL CLEANSING quality comparison model
It is accurate enough with the model for guaranteeing that training obtains, and corresponding INTESTINAL CLEANSING quality mark is set for every picture in the training process
Know, after the completion of training, every samples pictures only include a corresponding INTESTINAL CLEANSING quality identification, but multiple samples pictures can be with
Comprising identical INTESTINAL CLEANSING quality identification, in order in the excreta for being uploaded patient using INTESTINAL CLEANSING quality comparison model
After the completion of picture compares, it can and be only capable of obtaining unique immediate samples pictures.
S103: the corresponding INTESTINAL CLEANSING quality of the excreta picture is determined according to the comparison result.
Specifically, after obtaining immediate samples pictures, it can be according to the INTESTINAL CLEANSING quality that the samples pictures include
Identify the INTESTINAL CLEANSING quality for determining that patient is current.
Wherein, the evaluation criterion of the INTESTINAL CLEANSING quality can be set according to actual needs, it is only necessary to be met
The defecation the clean, and INTESTINAL CLEANSING is closer to be ready to complete.
For example, the clean-up performance of INTESTINAL CLEANSING is generally divided into first class, second class, third class, fourth grade.First class refers to nothing in Colon and rectum
Excrement slag, or product have a small amount of clear liquid.Second class, which refers to, a small amount of excrement slag, or product has a small amount of more clear liquid, but not shadow
It rings into mirror and observation.Third class refers in each section of enteron aisle that interruption has the liquid dung of middle amount, by attracting, changing position still can be smooth
It observes each section of colon, does not influence to observe result.Fourth grade refers to that enteron aisle is unclean, has a large amount of muddy liquid dungs or loose stools, passes through suction
Draw or changing position still cannot be observed smoothly.Therefore, INTESTINAL CLEANSING quality can be set according to every kind of clean-up performance grade, when
So, it can also voluntarily be set according to the experience of doctor, this is not restricted.
In addition, the excreta picture that patient terminal is sent to be input to enteron aisle standard trained in advance for the ease of Cloud Server
Standby quality comparison model is compared, and the picture that patient terminal is sent can be normalized, normalized is figure
A kind of common processing mode when piece compares, compare two pictures it is whether identical when, usually using Euclidean distance, (i.e. Europe is several
In must measure) as discriminant function, but the value range of the function result is theoretically located at 0 between just infinite, may
The computer capacity of computer can be exceeded, it is therefore necessary to use normalized, treatment process is the prior art, therefore herein not
It is described in detail again.Further, picture pixels can also be all adjusted to unanimously for the ease of comparing, such as is adjusted to 299*
299.In addition, checking and managing for convenience, when saving the excreta picture that patient terminal is sent, every figure can also be recorded
The shooting time information of piece.
The technical solution that embodiments herein provides can include the following benefits:
Using technical solution provided by the embodiments of the present application, patient is when carrying out INTESTINAL CLEANSING, after can taking drugs
Excreta taken pictures by intelligent terminal after be uploaded to Cloud Server, trained neural network mould is provided in Cloud Server
Type can find out the excreta figure uploaded with patient by neural network model from pre-set faecal samples pictures
The immediate picture of piece, to can quickly judge the INTESTINAL CLEANSING of patient according to the INTESTINAL CLEANSING quality identification for including in picture
Whether quality, i.e. patient also need to continue medication etc..So set, for directly visually observing and judging, first is that people
Work intelligent decision very quickly (can regard real-time as) and can be realized and be timely feedbacked, then can be fast after patient's shooting photo
Speed obtain as a result, medical staff without waiting compared with busy；Second is that since the process of judgement is real by model trained in advance
It is existing, as long as judging result is accurate and objective enough then sample size is enough, and do not depend on medical staff or patient
Experience and level, therefore be able to solve too late to judge existing for by way of judging INTESTINAL CLEANSING quality direct visual perception
When or judging result inaccuracy problem.
In order to which the practical situations to technical scheme better illustrate, the embodiment of the present application also provide with
Lower expansion scheme.All expansion schemes are all made on the basis of the above embodiments.
Optionally, after Cloud Server determines the INTESTINAL CLEANSING quality of patient, determining result can be fed back into disease again
People's terminal, to assist patient to adjust itself subsequent INTESTINAL CLEANSING according to preset processing mode corresponding with INTESTINAL CLEANSING quality
Work.In practical application, arriving since since Cloud Server receiving the excreta picture that patient sends and utilizing neural network
Model is compared, then to final definitive result process be it is very short, it is general only to need can be completed within most more than ten seconds several seconds, because
This, in order to improve the usage experience of patient, result, which is fed back to patient's this operation, be can be set into existing for default, sick in this way
People is after receiving feedback it may determine that subsequent situations such as whether needing to continue medication.
As a kind of mode of specific implementation, patient terminal can be by installing wechat small routine by taking smart phone as an example
To realize the operation for taking pictures and being uploaded to server.Further, in order to facilitate patient's use, in wechat small routine can in
The points for attention of some medications, including the director informations such as eating attention and dosage, medication speed are set, to help patient more preferable
Complete INTESTINAL CLEANSING work in ground.In addition, in wechat small routine can with the explanatory note of built-in some cleaning intestinal tract scale standards with
And samples pictures, auxiliary patient judge the case where itself INTESTINAL CLEANSING.
In addition, patient can complete the registering and logging of user first before stating wechat small routine in use, in order into
The information of the typing of row personal information, typing includes but is not limited to: name, the ID number put on record in hospital and to the subsequent clothes of patient
Medicine situation is influential that non-diabetic, whether there is or not the medical histories such as constipation.It, can be by these information after patient completes data input
The management system of hospital is shared to, so that doctor checks.
Certainly, it will be apparent to a skilled person that the program of patient terminal installation is not limited to wechat small routine,
Such as the feasible mode such as cell phone application specially designed also can, this is not limited.
In addition, it is optional, after Cloud Server determines the INTESTINAL CLEANSING quality of patient, determining result can be sent to
Doctor terminal, to assist doctor to be worked according to INTESTINAL CLEANSING quality and the subsequent INTESTINAL CLEANSING of the experience adjustments patient of itself.
In practical application, even if Cloud Server as stated above has sent judging result to patient, and it is built-in in patient terminal
The points for attention and cleaning intestinal tract scale of medication are quasi-, but the observing situation of patient is uncertain, first is that because enteron aisle
The process of preparation be for patient it is very painful, patient firstly the need of drink in a short time largely be watered after drug (2
Rise even more), the process that secondly drug comes into force in enteron aisle is also to be difficult to receive for patient, therefore, according to patient body
The quality of the difference of matter and willpower, final INTESTINAL CLEANSING would also vary from, and if in the case where there is doctor's advice
Patient generally can preferably adhere to, so that completes is more preferable；Although patient is second is that Cloud Server can provide judging result
It is the subjective judgement for having oneself, patient may think that the inaccuracy of machine judgement after the excreta for observing oneself, from
And occur it is that Cloud Server provides the result is that it is offhand completion but patient think to have been prepared for completing according to the judgement of oneself
And situations such as not continuing to medication, therefore in order to avoid it is necessary to notify doctor to instruct patient for such case.
Specifically, the guidance can be doctor patient is instructed face-to-face or patient be in can not be face-to-face
When instructing, it can be realized by modes such as phone, voice communication or video callings.
It should be noted that above-mentioned described doctor might not to the guidance of patient according to the judging result of Cloud Server
It is real-time, such as is also possible to carry out enteroscopy or enteron aisle hand to hospital after the completion of patient carries out INTESTINAL CLEANSING at home
Art, checks or operation consent doctor instructs it according to the actual conditions of patient, is thinking the quality of patient's INTESTINAL CLEANSING not
Patient is set to continue to take medicine when reaching a standard.
As a kind of method of specific implementation, doctor terminal is mobile in addition to using smart phone etc. as patient terminal
It, can also be using electronic equipments such as desktop computers because of situations such as not being related to taking pictures except smart machine.Further,
Doctor terminal can also carry out relevant operation by modes such as wechat small routine, cell phone application and computer programs.
It should be noted that in order to guarantee that Cloud Server can be by judging result and the excreta figure of patient terminal transmission
The information such as piece are sent to the doctor being responsible for the patient, can be set to doctor terminal also need complete user log in and fill in
Corresponding information.In addition, other than the excreta picture that patient terminal is sent is transmitted to doctor terminal by Cloud Server,
It can be set to that Cloud Server backstage is actively gone to check and download corresponding picture after doctor terminal logs in.
Further, Cloud Server can also incite somebody to action other than the INTESTINAL CLEANSING quality that will be determined is sent to doctor terminal
The excreta picture that patient terminal is sent also is transmitted to doctor terminal, so that doctor can be according to oneself previous experience to patient
The excreta picture that terminal is sent judge and be modified if necessary to the judging result that Cloud Server provides, and will
Modified result is retransmited to Cloud Server, the excreta figure that Cloud Server sends the corresponding patient terminal of correction result later
Faecal samples pictures are added in piece, so that faecal samples pictures are modified and be supplemented.
In addition, it is optional, faecal samples are added in the corresponding excreta picture of correction result for automatically sending doctor
After pictures, the incremental training or again of doctor's (or maintenance management personnel of Cloud Server) not timing starting can also be received
Training, thus the picture sample data before can either re-using, additionally it is possible in time using the image data newly received, such as
This setting, the judging result that neural network model can be made to obtain are more and more accurate.
In addition, optional, the above method can also include: patient when uploading the excreta picture of shooting to server,
Oneself self-assessment (namely to the subjective judgement in current INTESTINAL CLEANSING stage) to INTESTINAL CLEANSING quality is provided simultaneously, so as to
Yu doctor check after understand patient view, later doctor can also the excreta picture to patient assessment evaluate, this two
A evaluation information can be corresponded to and is stored in Cloud Server, in this way after getting a large amount of evaluation informations of both sides, according to statistics
Data can help doctor to be better understood by the universal idea of patient, in order to face identical situation in other patients later
When, provide preferably instrucion and explanation.
In order to more fully be introduced technical solution of the present invention, provided corresponding to the above embodiment of the present invention logical
The method for crossing artificial intelligent decision INTESTINAL CLEANSING quality, the embodiment of the present invention also provide one kind and judge enteron aisle standard by artificial intelligence
The device of standby quality.
Referring to Fig. 2, Fig. 2 is a kind of dress for judging INTESTINAL CLEANSING quality by artificial intelligence provided by the embodiments of the present application
The structural schematic diagram set.Wherein, INTESTINAL CLEANSING is the preparation before enteroscopy or intestinal surgery.As shown in Fig. 2, the device
Include:
Module 21 is obtained, for obtaining the excreta picture of patient terminal transmission；
Comparison module 22, for the excreta picture to be input to INTESTINAL CLEANSING quality comparison model trained in advance,
Obtain the comparison result of the INTESTINAL CLEANSING quality testing model output；Wherein, the INTESTINAL CLEANSING quality comparison model is to arrange
Object sample pictures collection and corresponding INTESTINAL CLEANSING quality identification is let out to obtain as training sample training；The faecal samples
Pictures include the picture of INTESTINAL CLEANSING each stage corresponding INTESTINAL CLEANSING quality；The comparison result includes the excreta sample
In product pictures with the immediate picture of excreta picture；
Determining module 23, for determining the corresponding INTESTINAL CLEANSING quality of the excreta picture according to the comparison result.
Specifically, the specific implementation of the function of above-mentioned each module is referred to judge intestines above by artificial intelligence
Road prepares the content in the method for quality to realize, this will not be detailed here.
In order to more fully be introduced technical solution of the present invention, provided corresponding to the above embodiment of the present invention logical
The method for crossing artificial intelligent decision INTESTINAL CLEANSING quality, the embodiment of the present invention also provide one kind and judge enteron aisle standard by artificial intelligence
The system of standby quality.
Referring to Fig. 3, Fig. 3 is provided by the embodiments of the present application a kind of is by what artificial intelligence judged INTESTINAL CLEANSING quality
The structural schematic diagram of system.Wherein, INTESTINAL CLEANSING is the preparation before enteroscopy or intestinal surgery.As shown in figure 3, the system
It includes at least:
Cloud Server 3, and the patient terminal 4 with the Cloud Server 3 communication connection；
The Cloud Server 3 includes:
Memory 31 and the processor 32 being connected with the memory 31；
The memory 31, for storing program, described program is at least used to execute and only relate to described in above-described embodiment
The method that INTESTINAL CLEANSING quality is judged by artificial intelligence of patient terminal 4 and Cloud Server 3；
The processor 32, the described program stored for calling and executing the memory 31.
Optionally, system further include: the doctor terminal 5 with the Cloud Server 3 communication connection；
The described program stored in the memory 31, is also used to execute and is related to doctor terminal 5 described in above-described embodiment
The method that INTESTINAL CLEANSING quality is judged by artificial intelligence；
The processor 32, the described program stored for calling and executing the memory 31.
Specifically, the specific implementation of the function of above procedure is referred to judge enteron aisle standard above by artificial intelligence
Content in the method for standby quality realizes that this will not be detailed here.
It is understood that same or similar part can mutually refer in the various embodiments described above, in some embodiments
Unspecified content may refer to the same or similar content in other embodiments.
It should be noted that term " first ", " second " etc. are used for description purposes only in the description of the present application, without
It can be interpreted as indication or suggestion relative importance.In addition, in the description of the present application, unless otherwise indicated, the meaning of " multiple "
Refer at least two.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be by the application
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, can integrate in a processing module in each functional unit in each embodiment of the application
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..
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 contained at least one embodiment or example of the application.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 embodiments herein has been shown and described above, it is to be understood that above-described embodiment is example
Property, it should not be understood as the limitation to the application, those skilled in the art within the scope of application can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of method for judging INTESTINAL CLEANSING quality by artificial intelligence, which is characterized in that the INTESTINAL CLEANSING is colonoscopy inspection
Look into or intestinal surgery before preparation, which comprises
Obtain the excreta picture that patient terminal is sent；
The excreta picture is input to INTESTINAL CLEANSING quality comparison model trained in advance, obtains the INTESTINAL CLEANSING quality
The comparison result of detection model output；Wherein, the INTESTINAL CLEANSING quality comparison model with faecal samples pictures and respectively
Corresponding INTESTINAL CLEANSING quality identification is obtained as training sample training；The faecal samples pictures include that INTESTINAL CLEANSING is each
The picture of stage corresponding INTESTINAL CLEANSING quality；The comparison result include in the faecal samples pictures with the excretion
The immediate picture of object picture；
The corresponding INTESTINAL CLEANSING quality of the excreta picture is determined according to the comparison result.
2. the method according to claim 1, wherein the training process of the INTESTINAL CLEANSING quality comparison model,
Include:
Obtain faecal samples pictures gathered in advance；
For picture each in the faecal samples pictures, corresponding INTESTINAL CLEANSING quality identification is set；
Faecal samples pictures and corresponding INTESTINAL CLEANSING quality identification are constructed in advance as training sample, training
Deep learning model obtains the INTESTINAL CLEANSING quality comparison model.
3. the method according to claim 1, wherein described determine the excreta figure according to the comparison result
After the corresponding INTESTINAL CLEANSING quality of piece, further includes:
The INTESTINAL CLEANSING quality is sent to the patient terminal, to assist patient according to corresponding with the INTESTINAL CLEANSING quality
Preset processing mode adjust the work of itself subsequent INTESTINAL CLEANSING.
4. the method according to claim 1, wherein described determine the excreta figure according to the comparison result
After the corresponding INTESTINAL CLEANSING quality of piece, further includes:
The INTESTINAL CLEANSING quality is sent to doctor terminal, with assist doctor according to the INTESTINAL CLEANSING quality and itself
The subsequent INTESTINAL CLEANSING work of experience adjustments patient.
5. according to the method described in claim 4, it is characterized by further comprising:
The excreta picture is sent to the doctor terminal；
Obtain the correction result to the INTESTINAL CLEANSING quality that doctor terminal is sent；The correction result is doctor according to itself
The amendment that experience makes the INTESTINAL CLEANSING quality；
The faecal samples pictures are added in the corresponding excreta picture of the correction result.
6. the method according to claim 1, wherein further include:
Obtain patient terminal send patient observe itself shooting excreta picture after to current INTESTINAL CLEANSING quality self
Evaluation information；
The self-assessment information is sent to doctor terminal；
Obtain commenting the doctor of current INTESTINAL CLEANSING quality corresponding with the self-assessment information for the doctor terminal transmission
Valence information.
7. the method according to claim 1, wherein further include:
Receive and the retraining of the INTESTINAL CLEANSING quality comparison model instructed, with to the INTESTINAL CLEANSING quality comparison model into
Row incremental training or re -training.
8. a kind of device for judging INTESTINAL CLEANSING quality by artificial intelligence, which is characterized in that the INTESTINAL CLEANSING is colonoscopy inspection
Look into or intestinal surgery before preparation, described device includes:
Module is obtained, for obtaining the excreta picture of patient terminal transmission；
Comparison module obtains institute for the excreta picture to be input to INTESTINAL CLEANSING quality comparison model trained in advance
State the comparison result of INTESTINAL CLEANSING quality testing model output；Wherein, the INTESTINAL CLEANSING quality comparison model is with excreta sample
Product pictures and corresponding INTESTINAL CLEANSING quality identification are obtained as training sample training；The faecal samples pictures
Picture comprising INTESTINAL CLEANSING each stage corresponding INTESTINAL CLEANSING quality；The comparison result includes the faecal samples picture
It concentrates and the immediate picture of excreta picture；
Determining module, for determining the corresponding INTESTINAL CLEANSING quality of the excreta picture according to the comparison result.
9. a kind of system for judging INTESTINAL CLEANSING quality by artificial intelligence, which is characterized in that the INTESTINAL CLEANSING is colonoscopy inspection
Look into or intestinal surgery before preparation, the system comprises:
Cloud Server, and the patient terminal with Cloud Server communication connection；
The Cloud Server includes:
Memory and the processor being connected with the memory；
The memory, for storing program, described program, which is at least used to execute, passes through people as described in claim 1,2 or 7
The method of work intelligent decision INTESTINAL CLEANSING quality；
The processor, for calling and executing the described program of the memory storage.
10. system according to claim 9, which is characterized in that further include: the doctor with Cloud Server communication connection
Terminal；
The described program stored in the memory is also used to execute as claim 3-6 is described in any item by artificial intelligence
It can judge the method for INTESTINAL CLEANSING quality；
The processor, for calling and executing the described program of the memory storage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910604500.9A CN110298836A (en) | 2019-07-05 | 2019-07-05 | The methods, devices and systems of INTESTINAL CLEANSING quality are judged by artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910604500.9A CN110298836A (en) | 2019-07-05 | 2019-07-05 | The methods, devices and systems of INTESTINAL CLEANSING quality are judged by artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110298836A true CN110298836A (en) | 2019-10-01 |
Family
ID=68030457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910604500.9A Pending CN110298836A (en) | 2019-07-05 | 2019-07-05 | The methods, devices and systems of INTESTINAL CLEANSING quality are judged by artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298836A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111798943A (en) * | 2020-06-30 | 2020-10-20 | 南方医科大学南方医院 | Method, system, device and storage medium for recording output and input quantities |
| CN112786153A (en) * | 2021-01-06 | 2021-05-11 | 南通大学附属医院 | Diet control method and system for old people |
| CN113075208A (en) * | 2021-03-24 | 2021-07-06 | 贵州省草业研究所 | Intelligent cattle and sheep fermented feed quality evaluation method and device based on picture collection |
| CN117198473A (en) * | 2023-11-03 | 2023-12-08 | 首都医科大学宣武医院 | Intestinal tract preparation quality judging system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022380A (en) * | 2016-05-25 | 2016-10-12 | 中国科学院自动化研究所 | Individual identity identification method based on deep learning |
| CN106096254A (en) * | 2016-06-03 | 2016-11-09 | 宁波大红鹰学院 | A kind of medical service system and method |
| CN106651883A (en) * | 2016-12-30 | 2017-05-10 | 四川沃文特生物技术有限公司 | Machine vision-based excrement shape identification method |
| CN106778604A (en) * | 2015-12-15 | 2017-05-31 | 西安电子科技大学 | Pedestrian's recognition methods again based on matching convolutional neural networks |
| CN107545241A (en) * | 2017-07-19 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Neural network model is trained and biopsy method, device and storage medium |
| CN109033472A (en) * | 2018-09-05 | 2018-12-18 | 深圳灵图慧视科技有限公司 | Picture retrieval method and device, computer equipment and computer-readable medium |
-
2019
- 2019-07-05 CN CN201910604500.9A patent/CN110298836A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778604A (en) * | 2015-12-15 | 2017-05-31 | 西安电子科技大学 | Pedestrian's recognition methods again based on matching convolutional neural networks |
| CN106022380A (en) * | 2016-05-25 | 2016-10-12 | 中国科学院自动化研究所 | Individual identity identification method based on deep learning |
| CN106096254A (en) * | 2016-06-03 | 2016-11-09 | 宁波大红鹰学院 | A kind of medical service system and method |
| CN106651883A (en) * | 2016-12-30 | 2017-05-10 | 四川沃文特生物技术有限公司 | Machine vision-based excrement shape identification method |
| CN107545241A (en) * | 2017-07-19 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Neural network model is trained and biopsy method, device and storage medium |
| CN109033472A (en) * | 2018-09-05 | 2018-12-18 | 深圳灵图慧视科技有限公司 | Picture retrieval method and device, computer equipment and computer-readable medium |
Non-Patent Citations (2)
| Title |
|---|
| 李秋霞: "肠道准备对比图在肠镜前健康宣教中的应用体会", 《按摩与康复医学》 * |
| 李秋霞: "肠道准备对比图在肠镜前健康宣教中的应用体会", 《按摩与康复医学》, vol. 9, no. 12, 31 May 2018 (2018-05-31), pages 88 - 89 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111798943A (en) * | 2020-06-30 | 2020-10-20 | 南方医科大学南方医院 | Method, system, device and storage medium for recording output and input quantities |
| CN112786153A (en) * | 2021-01-06 | 2021-05-11 | 南通大学附属医院 | Diet control method and system for old people |
| CN112786153B (en) * | 2021-01-06 | 2022-11-25 | 南通大学附属医院 | Diet control method and system for old people |
| CN113075208A (en) * | 2021-03-24 | 2021-07-06 | 贵州省草业研究所 | Intelligent cattle and sheep fermented feed quality evaluation method and device based on picture collection |
| CN117198473A (en) * | 2023-11-03 | 2023-12-08 | 首都医科大学宣武医院 | Intestinal tract preparation quality judging system |
| CN117198473B (en) * | 2023-11-03 | 2024-02-23 | 首都医科大学宣武医院 | Intestinal tract preparation quality judging system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298836A (en) | The methods, devices and systems of INTESTINAL CLEANSING quality are judged by artificial intelligence | |
| US11806267B2 (en) | Ostomy patient care system and method | |
| Chang et al. | A context-aware, interactive M-health system for diabetics | |
| KR101944859B1 (en) | System for analyzing and predecting disease | |
| Miglioretti et al. | Effect of breast augmentation on the accuracy of mammography and cancer characteristics | |
| Bourne et al. | An AOA critical issue the outcome of the outcomes movement | |
| CN109616164A (en) | A kind of medical follow up system and its follow-up method | |
| Clegg et al. | Telemedicine in a rural community hospital for remote wound care consultations | |
| CN110428410A (en) | Eyeground medical image processing method, device, equipment and storage medium | |
| CN107799184A (en) | A kind of self-service detection technique scheme of excreta and its implementation | |
| KR101673682B1 (en) | System and method for integrated management of animal | |
| US20220108447A1 (en) | Wound healing analysis and tracking | |
| Vaziri et al. | Feasibility of telemedicine in detecting diabetic retinopathy and age-related macular degeneration | |
| Ogunyemi et al. | Teleretinal screening for diabetic retinopathy in six Los Angeles urban safety-net clinics: final study results | |
| CN111863252A (en) | Health monitoring method, system, computer equipment and storage medium | |
| CN104992395A (en) | Method for creating personalized health service archive | |
| CN112820369A (en) | Anorectal surgery information management system based on big data | |
| Wood et al. | Transition Readiness Assessment Questionnaire Spina Bifida (TRAQ-SB) specific module and its association with clinical outcomes among youth and young adults with spina bifida | |
| Kumar et al. | Diabetic retinopathy screening and management in India: Challenges and possible solutions | |
| US20190374152A1 (en) | Patient monitoring system | |
| US11894144B2 (en) | Animal health decision support system and methods | |
| Dash et al. | A comprehensive study of mobile computing in telemedicine | |
| CN109979570A (en) | First aid hand-held diagnostic device and diagnostic method with X-ray check function | |
| Jayaraman et al. | An ontology-based framework for real-time collection and visualization of mobile field triage data in mass gatherings | |
| CN107622794A (en) | Medical treatment ＆ health system and medical treatment ＆ health car |
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 |