CN112530580A - Medical image picture processing method and computer readable storage medium - Google Patents
Medical image picture processing method and computer readable storage medium Download PDFInfo
- Publication number
- CN112530580A CN112530580A CN202011412788.9A CN202011412788A CN112530580A CN 112530580 A CN112530580 A CN 112530580A CN 202011412788 A CN202011412788 A CN 202011412788A CN 112530580 A CN112530580 A CN 112530580A
- Authority
- CN
- China
- Prior art keywords
- medical image
- image picture
- analysis result
- neural network
- cloud
- 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
Images
Classifications
-
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
- G06K17/0025—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device the arrangement consisting of a wireless interrogation device in combination with a device for optically marking the record carrier
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- 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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Computational Linguistics (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Computer Networks & Wireless Communication (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a processing method of a medical image picture and a computer readable storage medium, wherein the processing method comprises the following steps: acquiring an identification code bound with the medical image picture; scanning the identification code to obtain identification information corresponding to the medical image picture and sending the identification information to a server; receiving a medical image picture acquired by a server after being inquired based on the identification information; sending the medical image picture or the identification information to the cloud end to request image analysis; receiving a first analysis result fed back by the cloud end; the first analysis result is obtained after the cloud analyzes the medical image picture based on the trained neural network model; and the trained neural network model is obtained based on the sample image and the gold standard training. The method and the device can acquire the shot medical image picture in time, and can identify the analysis result based on the trained neural network model, so that a user can conveniently acquire the reading information of the medical image picture in time.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to a medical image processing method and a computer-readable storage medium.
Background
The medical image picture diagnosis usually needs the patient to wait for the report after taking a picture, and then go to the relevant department, and the doctor can diagnose whether the medical image picture has diseases or hidden troubles or not by the personal experience and knowledge and naked eyes. Usually, a reservation is needed before shooting, and a report is needed to be taken after shooting. Medical image picture recognition in hospitals is generally performed by professional imaging physicians to make image diagnosis reports. Doctors in the same hospital clinical departments and doctors in the primary hospitals carry out the next diagnosis and treatment according to the image diagnosis reports.
After the medical image picture is taken out, the patient cannot timely know the reading information about the medical image picture, and must return to the hospital again to ask the doctor to manually read the medical image picture, so that time and labor are wasted in order to know the reading information, and the user experience is poor. In addition, the accuracy of manual diagnosis greatly depends on the personal experience of doctors and the state of doctors during diagnosis, and in addition, the number of patients to be received by doctors is large, the number of examination and shooting pictures is large, the waiting time of the patients is long, and the doctors are easy to have missed diagnosis or inaccurate diagnosis. Meanwhile, due to the fact that image professional knowledge and experience of doctors in clinical departments of the same-level hospitals and doctors in primary hospitals are insufficient, the doctors cannot make image accurate diagnosis reports on medical image pictures in time, and diagnosis and treatment of patients are delayed.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defect that in the prior art, the user needs to know the reading information time and labor after the medical image picture is taken out, so that the user experience is poor, and provide a medical image picture processing method and a computer-readable storage medium, which can facilitate the user to know the reading information of the taken medical image picture in time.
The invention solves the technical problems through the following technical scheme:
the invention provides a medical image picture processing method, which is applied to an intelligent terminal and comprises the following steps:
acquiring an identification code bound with the medical image picture;
scanning the identification code to obtain identification information corresponding to the medical image picture and sending the identification information to a server;
receiving the medical image picture acquired by the server based on the identification information;
sending the medical image picture or the identification information to a cloud end to request image analysis;
receiving a first analysis result fed back by the cloud end;
the first analysis result is obtained after the cloud analyzes the medical image picture based on the trained neural network model;
the trained neural network model is obtained based on sample images and gold standard training.
Preferably, the processing method further comprises the following steps:
sending the medical image picture or the first analysis result to a case database;
receiving reference information of similar cases fed back by the case database;
the similar case is a similar historical case found by the case database based on the medical image picture or the first analysis result.
Preferably, the processing method further comprises the following steps:
responding to an instruction of selecting a target area of the medical image picture by a user;
sending a target area of the medical image picture to the cloud to request image analysis aiming at the target area;
receiving a second analysis result fed back by the cloud end;
and the second analysis result is obtained after the cloud identifies the target area and calls a trained neural network model for analysis.
Preferably, the identification code is a two-dimensional code automatically generated by the medical imaging device after the medical image picture is taken.
Preferably, the first analysis result comprises a pulmonary report including the size, number and location of lung nodules.
Preferably, the reference information includes at least one of treatment modality, attention, age of onset, sex, recovery period, forewarning, and quantitative analysis.
Preferably, the target region is a region corresponding to a preset disease type, and the disease type includes one of a lung nodule, a bone fracture, and a tumor.
Preferably, the processing method further comprises the following steps:
receiving a follow-up result fed back by the cloud end;
the follow-up result is a result obtained by comparing the first analysis result with the historical first analysis result of the user corresponding to the medical image picture by the cloud.
Preferably, the neural network model is a convolutional neural network model, and/or the medical image picture is a CT (Computed Tomography) picture or a magnetic resonance picture.
A second aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the method for processing a medical image picture according to the first aspect.
The invention provides a processing system for medical image pictures, which comprises:
the first acquisition module is used for acquiring the identification code bound with the medical image picture;
the second acquisition module is used for scanning the identification code to acquire identification information corresponding to the medical image picture and sending the identification information to the server;
the first receiving module is used for receiving the medical image picture acquired by the server after being inquired based on the identification information;
the first sending module is used for sending the medical image picture or the identification information to a cloud end to request for image analysis;
the second receiving module is used for receiving a first analysis result fed back by the cloud end;
the first analysis result is obtained after the cloud analyzes the medical image picture based on the trained neural network model;
the trained neural network model is obtained based on sample images and gold standard training.
Preferably, the processing system further comprises:
the second sending module is used for sending the medical image picture or the first analysis result to a case database;
the third receiving module is used for receiving the reference information of the similar cases fed back by the case database;
the similar case is a similar historical case found by the case database based on the medical image picture or the first analysis result.
Preferably, the processing system further comprises:
the response module is used for responding to an instruction of selecting a target area of the medical image picture by a user;
the third sending module is used for sending a target area of the medical image picture to the cloud to request image analysis aiming at the target area;
the fourth receiving module is used for receiving a second analysis result fed back by the cloud end;
and the second analysis result is obtained after the cloud identifies the target area and calls a trained neural network model for analysis.
Preferably, the identification code is a two-dimensional code automatically generated by the medical imaging device after the medical image picture is taken.
Preferably, the first analysis result comprises a pulmonary report including the size, number and location of lung nodules.
Preferably, the reference information includes at least one of treatment modality, attention, age of onset, sex, recovery period, forewarning, and quantitative analysis.
Preferably, the target region is a region corresponding to a preset disease type, and the disease type includes one of a lung nodule, a bone fracture, and a tumor.
Preferably, the processing system further comprises:
the fifth receiving module is used for receiving the follow-up result fed back by the cloud end;
the follow-up result is a result obtained by comparing the first analysis result with the historical first analysis result of the user corresponding to the medical image picture by the cloud.
Preferably, the neural network model is a convolutional neural network model, and/or the medical image picture is a CT picture or a nuclear magnetic resonance picture.
The invention provides an intelligent terminal, which comprises the medical image picture processing system according to the third aspect.
Preferably, the intelligent terminal is a smart phone or a smart tablet.
The positive progress effects of the invention are as follows: compared with the prior art, the method and the system have the advantages that the user can timely acquire the shot medical image picture from the server after scanning the identification code through equipment such as the intelligent terminal and the like, and can recognize the analysis result corresponding to the medical image picture based on the trained neural network model, so that the user can conveniently acquire the reading information of the shot medical image picture in time and know the self health condition in advance.
Furthermore, the invention can acquire similar cases through equipment such as an intelligent terminal according to the acquired medical image picture, understand prognosis, clearly realize self diseases and improve precaution consciousness.
Furthermore, the invention also realizes that the user can independently click the region to be diagnosed or the disease type to be diagnosed in the medical image picture extracted from the intelligent terminal and other equipment, and the selected region or the disease type is diagnosed again through the trained neural network model, so that the user can know the health conditions of other similar body organs or parts except the specific examination region through one-time shooting, and early warning is carried out to prevent the omission of diagnosis.
Furthermore, the invention also realizes the follow-up function on equipment such as an intelligent terminal, and the like, and can compare the medical image picture with the previous image record of the user and analyze whether the symptom of the user is worsened or improved.
Drawings
Fig. 1 is a flowchart of a medical image processing method according to embodiment 1 of the present invention.
Fig. 2 is a block diagram of a medical image processing system according to embodiment 3 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
The following embodiment is implemented based on interaction among the intelligent terminal, the cloud terminal and the server side of the hospital where the medical imaging device is located, and the communication mode among the intelligent terminal, the cloud terminal and the server side is implemented by using the existing network, such as a mobile internet. During concrete implementation, the server also can not set up in the hospital, and the high in the clouds also can unite two into one with the server end, and the concrete implementation of the two is prior art, can not constitute any restriction to this application embodiment.
Example 1
As shown in fig. 1, the present embodiment provides a method for processing a medical image picture, which is applied to an intelligent terminal, such as a mobile phone, where the medical image picture may be an X-ray film, a CT picture, or a nuclear magnetic resonance picture, and the method includes the following steps:
And 102, scanning the two-dimensional code to obtain identification information corresponding to the medical image picture and sending the identification information to a server.
And 103, receiving the medical image picture acquired by the server based on the identification information.
And step 104, sending the medical image picture or the identification information to the cloud to request for image analysis.
In this step, when the identification information is sent to the cloud, the cloud may acquire the medical image picture acquired by the server after being queried based on the identification information through interaction with the server.
105, receiving a first analysis result fed back by the cloud; the first analysis result is obtained after the cloud analyzes the medical image picture based on the trained neural network model; and the trained neural network model is obtained based on the sample image and the gold standard training. The sample image may be a historical medical image picture, and the gold standard may be a diagnosis or follow-up visit corresponding to the historical medical image picture. In this embodiment, the first analysis result is a lung report, specifically including the size, number, and location of lung nodules.
In this embodiment, the neural network model is a convolutional neural network model. It should be noted that, in other optional embodiments, other existing neural network models, such as a deep learning algorithm model, may also be used as long as the medical image picture can be identified to obtain a preliminary diagnosis result.
The way in which the neural network model is trained using the sample images and gold standards is prior art. And when the golden standard is diagnosis, inputting the sample image into a neural network model to be trained, carrying out model training based on corresponding diagnosis to obtain the trained neural network model, and analyzing the new medical image picture to obtain the corresponding diagnosis. And when the gold standard is follow-up visit, inputting the sample image into the neural network model to be trained, carrying out model training based on the corresponding follow-up visit to obtain the trained neural network model, and analyzing the new medical image picture to obtain the corresponding follow-up visit by using the trained neural network model.
And step 106, sending the medical image picture or the first analysis result to a case database.
And step 107, receiving reference information of the similar cases fed back by the case database, wherein the reference information comprises at least one of treatment modes, cautions, age groups of onset, sex, recovery period, early warning and quantitative analysis. The similar cases are similar historical cases found by the case database based on the medical image picture or the first analysis result.
In a specific implementation process, the case database can compare the first analysis result with a diagnosis report stored in the case database, or can compare the medical image picture with an image picture stored in the case database, wherein the comparison of the pictures can be performed on the segmented image focus, or on the whole image picture. The implementation manner of the case database side search is not specifically limited in this embodiment, as long as the case database can implement feedback of the reference information of the similar cases.
In other alternative embodiments, the following steps may also be included: receiving a follow-up result fed back by the cloud; the follow-up result is a result obtained by comparing the first analysis result with the historical first analysis result of the user corresponding to the medical image picture by the cloud. The embodiment realizes the follow-up function, can compare the medical image picture with the previous image record of the user, and analyzes whether the symptom of the user is worsened or improved.
The medical image picture processing method provided by the embodiment realizes that a user can timely acquire a shot medical image picture from a server after scanning the identification code through the intelligent terminal, and can recognize the analysis result corresponding to the medical image picture based on the trained neural network model, so that the user can timely know the reading information of the shot medical image picture, and can know the health condition of the user in advance.
The embodiment can also acquire similar cases through the intelligent terminal according to the acquired medical image pictures, understand prognosis, clearly realize diseases per se and improve precaution consciousness.
The embodiment also realizes that the user can independently click the region to be diagnosed or the disease type to be diagnosed in the medical image picture extracted from the intelligent terminal, and the selected region or the disease type is diagnosed again through the trained neural network model, so that the user can know the health conditions of other similar body organs or parts except the specific examination region through one-time shooting, and early warning is carried out to prevent omission of diagnosis.
Example 2
The present embodiment provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements the steps of the method for processing a medical image picture of embodiment 1.
More specific examples, among others, that the readable storage medium may employ may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation manner, the present invention can also be implemented in the form of a program product including program code for causing a terminal device to execute the steps of implementing the processing method of medical image pictures in example 1 when the program product is run on the terminal device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may be executed entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on a remote device or entirely on the remote device.
Example 3
As shown in fig. 2, the present embodiment provides a processing system for medical image pictures, which is used in an intelligent terminal, such as a mobile phone, and the processing system includes:
the first acquisition module 1 is used for acquiring the identification code bound with the medical image picture. The identification code is a two-dimensional code automatically generated by the medical imaging equipment after the medical image picture is shot.
And the second acquisition module 2 is used for scanning the identification code to acquire identification information corresponding to the medical image picture and sending the identification information to the server.
And the first receiving module 3 is used for receiving the medical image picture acquired by the server based on the identification information inquiry.
The first sending module 4 is configured to send the medical image picture or the identification information to the cloud for requesting image analysis.
And the second receiving module 5 is configured to receive the first analysis result fed back by the cloud. The first analysis result is obtained after the cloud analyzes the medical image picture based on the trained neural network model. And the trained neural network model is obtained based on the sample image and the gold standard training. The sample image may be a historical medical image picture, and the gold standard may be a diagnosis or follow-up visit corresponding to the historical medical image picture. In this embodiment, the first analysis result is a lung report, specifically including the size, number, and location of lung nodules.
In this embodiment, the neural network model is a convolutional neural network model. It should be noted that, in other optional embodiments, other existing neural network models, such as a deep learning algorithm model, may also be used as long as the medical image picture can be identified to obtain a preliminary diagnosis result.
And the second sending module 6 is used for sending the medical image picture or the first analysis result to the case database.
And the third receiving module 7 is configured to receive reference information of similar cases fed back by the case database, where the reference information includes at least one of a treatment mode, a notice, an age group of onset, a sex, a recovery period, an early warning, and a quantitative analysis. The similar cases are similar historical cases found by the case database based on the medical image picture or the first analysis result.
And the response module 8 is used for responding to an instruction of selecting the target area of the medical image picture by the user. The target region may be a specific part, such as a vertebral region, or may be a region corresponding to a predetermined disease type, where the disease type includes a lung nodule, a bone fracture, a tumor, and the like.
The third sending module 9 is configured to send the target area of the medical image picture to the cloud to request image analysis on the target area.
The fourth receiving module 10 is configured to receive a second analysis result fed back by the cloud. And the second analysis result is obtained after the cloud terminal identifies the target area and calls the trained neural network model for analysis.
The fifth receiving module 11 is configured to receive a follow-up result fed back by the cloud; the follow-up result is a result obtained by comparing the first analysis result with the historical first analysis result of the user corresponding to the medical image picture by the cloud. The embodiment realizes the follow-up function, can compare the medical image picture with the previous image record of the user, and analyzes whether the symptom of the user is worsened or improved.
The processing system for the medical image picture provided by the embodiment realizes that the user can timely acquire the shot medical image picture from the server after scanning the identification code through the intelligent terminal, and can identify the analysis result corresponding to the medical image picture based on the trained neural network model, so that the user can conveniently and timely know the reading information of the shot medical image picture, and can know the health condition of the user in advance.
The embodiment can also acquire similar cases through the intelligent terminal according to the acquired medical image pictures, understand prognosis, clearly realize diseases per se and improve precaution consciousness.
The embodiment also realizes that the user can independently click the region to be diagnosed or the disease type to be diagnosed in the medical image picture extracted from the intelligent terminal, and the selected region or the disease type is diagnosed again through the trained neural network model, so that the user can know the health conditions of other similar body organs or parts except the specific examination region through one-time shooting, and early warning is carried out to prevent omission of diagnosis.
The processing system for medical image pictures provided by the embodiment enables a user to directly scan the two-dimensional code after shooting, and check or extract the medical image pictures shot by the user and the results of artificial intelligence diagnosis. And the user can click a certain area of the medical image picture or the type of the relevant disease to be diagnosed by the mobile phone, and the diagnosis result obtained by the trained neural network model analysis can be directly obtained from the analysis platform at the cloud. Furthermore, the method can be compared with the prior shot image of the user, and meanwhile, the data, the treatment mode, the attention points and the like of other similar cases with similar disease conditions in the case base are called out, so that the user can know the health condition of the user at the first time. In specific implementation, the first analysis result, the second analysis result and the like can be fed back to the doctor, so that the diagnosis process of the doctor can be accelerated, the diagnosis quality of the doctor can be improved, and the burden of the doctor can be reduced.
Example 4
The embodiment provides an intelligent terminal, which comprises the medical image picture processing system described in embodiment 3. The intelligent terminal can be a smart phone and also can be a smart tablet, the intelligent terminal is a smart phone in the embodiment, the specific implementation form of the processing system of the medical image picture is an APP (Application) installed in the smart phone, and the APP can store personal information, health condition reports, the medical image picture and the like of a user.
The user uses the smart phone provided by the embodiment, the APP installed in the smart phone can be used for acquiring the two-dimensional code which is generated by the CT equipment or the nuclear magnetic resonance equipment and is bound with the medical image picture taken by the user, and the two-dimensional code is scanned to acquire the identification information corresponding to the medical image picture. APP sends the identification information to the corresponding server, and therefore the medical image picture which is shot through the smart phone at the first time is not required to be obtained when a user goes to a hospital. Specifically, after a user takes a picture, a two-dimensional code is automatically generated on the medical imaging equipment. A user logs in a personal account on the mobile phone APP, and medical image pictures shot by the person can be read in real time through mobile phone code scanning. Furthermore, the trained neural network model can be used for image analysis through the APP, and the database is used for obtaining similar cases, knowing the prognosis, quantitatively analyzing, early warning and other conditions. For example, medical image pictures, personal information and the like on the APP are uploaded to the cloud, and analysis results are fed back to the APP end through the large-scale computer in the cloud background after being processed through an artificial intelligence algorithm and cloud computing, so that a user such as a patient or a doctor can check the analysis results. The accuracy of the result obtained after the trained neural network model is analyzed is not lower than that of the image diagnosis report of a professional image subject doctor, and rapid and accurate diagnosis and treatment can be realized. If the medical image is taken for the lung, the patient can obtain a preliminary lung diagnosis report, and the specific size, number, location, etc. of the lung nodules can be quantitatively given in the specific implementation process.
The invention provides a method for identifying a shot medical image picture through a trained neural network model by utilizing an artificial intelligence technology, and also can select a certain partition of the shot medical image picture such as an X-ray according to the requirement of a user to diagnose and directly transmit the partition to the user through an APP.
The invention also realizes follow-up analysis aiming at multiple medical image pictures shot by the user and feeds back follow-up results to the user. Through the follow-up function of this APP, can carry out the analysis and comparison with picture and the diagnostic result that this medical image picture and patient taken before, for example to the patient of lung nodule, can confirm through this follow-up function whether the quantity of lung nodule reduces, whether the size changes, whether the diseased region spreads or reduces, in time follows up patient's state of an illness.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (10)
1. A medical image picture processing method is applied to an intelligent terminal and comprises the following steps:
acquiring an identification code bound with the medical image picture;
scanning the identification code to obtain identification information corresponding to the medical image picture and sending the identification information to a server;
receiving the medical image picture acquired by the server based on the identification information;
sending the medical image picture or the identification information to a cloud end to request image analysis;
receiving a first analysis result fed back by the cloud end;
the first analysis result is obtained after the cloud analyzes the medical image picture based on the trained neural network model;
the trained neural network model is obtained based on sample images and gold standard training.
2. The method for processing medical image pictures as claimed in claim 1, wherein the method further comprises the steps of:
sending the medical image picture or the first analysis result to a case database;
receiving reference information of similar cases fed back by the case database;
the similar case is a similar historical case found by the case database based on the medical image picture or the first analysis result.
3. The method for processing medical image pictures as claimed in claim 1, wherein the method further comprises the steps of:
responding to an instruction of selecting a target area of the medical image picture by a user;
sending a target area of the medical image picture to the cloud to request image analysis aiming at the target area;
receiving a second analysis result fed back by the cloud end;
and the second analysis result is obtained after the cloud identifies the target area and calls a trained neural network model for analysis.
4. The method as claimed in claim 1, wherein the identification code is a two-dimensional code automatically generated by the medical imaging device after the medical image is taken.
5. The method of claim 1, wherein the first analysis result comprises a lung report, and the lung report comprises a size, a number, and a location of lung nodules.
6. The method as claimed in claim 2, wherein the reference information includes at least one of treatment mode, attention points, age of onset, sex, recovery period, pre-warning and quantitative analysis.
7. The method as claimed in claim 3, wherein the target region is a region corresponding to a predetermined disease type, and the disease type includes one of a lung nodule, a bone fracture, and a tumor.
8. The method for processing medical image pictures as claimed in claim 1, wherein the method further comprises the steps of:
receiving a follow-up result fed back by the cloud end;
the follow-up result is a result obtained by comparing the first analysis result with the historical first analysis result of the user corresponding to the medical image picture by the cloud.
9. The method for processing a medical image according to claim 1, wherein the neural network model is a convolutional neural network model, and/or the medical image is a CT image or a nuclear magnetic resonance image.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for processing a medical image picture according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011412788.9A CN112530580A (en) | 2020-12-03 | 2020-12-03 | Medical image picture processing method and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011412788.9A CN112530580A (en) | 2020-12-03 | 2020-12-03 | Medical image picture processing method and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112530580A true CN112530580A (en) | 2021-03-19 |
Family
ID=74997757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011412788.9A Pending CN112530580A (en) | 2020-12-03 | 2020-12-03 | Medical image picture processing method and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112530580A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114400075A (en) * | 2022-01-18 | 2022-04-26 | 平安好医投资管理有限公司 | Image file processing method, device and equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372390A (en) * | 2016-08-25 | 2017-02-01 | 姹ゅ钩 | Deep convolutional neural network-based lung cancer preventing self-service health cloud service system |
| CN107292120A (en) * | 2017-08-16 | 2017-10-24 | 安徽影联乐金信息科技有限公司 | A kind of self-service system and method for obtaining electronic image memory device |
| CN108229979A (en) * | 2018-01-24 | 2018-06-29 | 亳州职业技术学院 | Based on wechat small routine and the American Ginseng of depth learning technology tasting assistant |
| CN108231145A (en) * | 2016-12-22 | 2018-06-29 | 上海哲康医学科技有限公司 | The method for obtaining the Medical imaging diagnostic reports of subsidiary Quick Response Code and bar code |
| CN108510495A (en) * | 2018-04-09 | 2018-09-07 | 沈阳东软医疗***有限公司 | A kind of lung image data processing method based on artificial intelligence, apparatus and system |
| CN109769079A (en) * | 2018-12-28 | 2019-05-17 | 苏州承泽医疗科技有限公司 | A kind of medical image transmission method |
| CN109830284A (en) * | 2017-11-23 | 2019-05-31 | 天启慧眼(北京)信息技术有限公司 | The analysis method and device of medical image |
| CN110427954A (en) * | 2019-07-26 | 2019-11-08 | 中国科学院自动化研究所 | The image group feature extracting method of multizone based on tumor imaging |
| WO2020037454A1 (en) * | 2018-08-20 | 2020-02-27 | 深圳市全息医疗科技有限公司 | Smart auxiliary diagnosis and treatment system and method |
| CN111899865A (en) * | 2020-07-15 | 2020-11-06 | 医渡云（北京）技术有限公司 | Medical information recommendation method, device, medium and electronic equipment |
-
2020
- 2020-12-03 CN CN202011412788.9A patent/CN112530580A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372390A (en) * | 2016-08-25 | 2017-02-01 | 姹ゅ钩 | Deep convolutional neural network-based lung cancer preventing self-service health cloud service system |
| CN108231145A (en) * | 2016-12-22 | 2018-06-29 | 上海哲康医学科技有限公司 | The method for obtaining the Medical imaging diagnostic reports of subsidiary Quick Response Code and bar code |
| CN107292120A (en) * | 2017-08-16 | 2017-10-24 | 安徽影联乐金信息科技有限公司 | A kind of self-service system and method for obtaining electronic image memory device |
| CN109830284A (en) * | 2017-11-23 | 2019-05-31 | 天启慧眼(北京)信息技术有限公司 | The analysis method and device of medical image |
| CN108229979A (en) * | 2018-01-24 | 2018-06-29 | 亳州职业技术学院 | Based on wechat small routine and the American Ginseng of depth learning technology tasting assistant |
| CN108510495A (en) * | 2018-04-09 | 2018-09-07 | 沈阳东软医疗***有限公司 | A kind of lung image data processing method based on artificial intelligence, apparatus and system |
| WO2020037454A1 (en) * | 2018-08-20 | 2020-02-27 | 深圳市全息医疗科技有限公司 | Smart auxiliary diagnosis and treatment system and method |
| CN109769079A (en) * | 2018-12-28 | 2019-05-17 | 苏州承泽医疗科技有限公司 | A kind of medical image transmission method |
| CN110427954A (en) * | 2019-07-26 | 2019-11-08 | 中国科学院自动化研究所 | The image group feature extracting method of multizone based on tumor imaging |
| CN111899865A (en) * | 2020-07-15 | 2020-11-06 | 医渡云（北京）技术有限公司 | Medical information recommendation method, device, medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 刘继兰 主编: "《国际标准 中国实践：JCI+HIMSS标准的中国故事》", 光明日报出版社, pages: 307 - 311 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114400075A (en) * | 2022-01-18 | 2022-04-26 | 平安好医投资管理有限公司 | Image file processing method, device and equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210158531A1 (en) | Patient Management Based On Anatomic Measurements | |
| KR101818074B1 (en) | Artificial intelligence based medical auto diagnosis auxiliary method and system therefor | |
| KR102289277B1 (en) | Medical image diagnosis assistance apparatus and method generating evaluation score about a plurality of medical image diagnosis algorithm | |
| JP2019153250A (en) | Device, method, and program for supporting preparation of medical document | |
| JP2009157527A (en) | Medical image processor, medical image processing method and program | |
| CN107978362B (en) | Query with data distribution in hospital networks | |
| CN112599225A (en) | Protocol planning client for determining a protocol for use in a medical procedure | |
| US10783637B2 (en) | Learning data generation support apparatus, learning data generation support method, and learning data generation support program | |
| CN111583249B (en) | Medical image quality monitoring system and method | |
| US20200311938A1 (en) | Platform for evaluating medical information and method for using the same | |
| CN111986182A (en) | Auxiliary diagnosis method, system, electronic device and storage medium | |
| CN113841171A (en) | System and method for automating clinical workflow decisions and generating priority read indicators | |
| US10860894B2 (en) | Learning data generation support apparatus, operation method of learning data generation support apparatus, and learning data generation support program | |
| US11837346B2 (en) | Document creation support apparatus, method, and program | |
| JP2024009342A (en) | Document preparation supporting device, method, and program | |
| CN115719334A (en) | Medical image evaluation method, device, equipment and medium based on artificial intelligence | |
| CN111226287B (en) | Method, system, program product and medium for analyzing medical imaging data sets | |
| JP7102999B2 (en) | Information collection processing equipment, information collection processing method and program | |
| EP3544020A1 (en) | Automatic analysis of a large patient population using medical imaging data | |
| CN112530580A (en) | Medical image picture processing method and computer readable storage medium | |
| JP2023504026A (en) | Automatic protocol specification in medical imaging systems | |
| US11574726B2 (en) | Image analysis method for multicenter study and system thereof | |
| KR102337031B1 (en) | Medical image reconstruction apparatus and method for screening a plurality of types lung diseases | |
| WO2021193548A1 (en) | Document creation assistance device, method, and program | |
| CN110622255B (en) | Apparatus, system, and method for determining a reading environment by integrating downstream requirements |
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 |