CN109509541B - Report issuing method and device based on medical image - Google Patents
Report issuing method and device based on medical image Download PDFInfo
- Publication number
- CN109509541B CN109509541B CN201811261521.7A CN201811261521A CN109509541B CN 109509541 B CN109509541 B CN 109509541B CN 201811261521 A CN201811261521 A CN 201811261521A CN 109509541 B CN109509541 B CN 109509541B
- Authority
- CN
- China
- Prior art keywords
- medical image
- result
- report
- interpretation
- interpretation result
- 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.)
- Active
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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
According to the report issuing method based on the medical image, disclosed by the embodiment of the invention, when a report issuing instruction about the medical image is received, an AI interpretation result of the medical image is obtained; when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation result of any doctor user on the medical image is consistent with the AI interpretation result, a report sheet about the medical image is issued, and the negative result is marked in the report sheet; when the AI interpretation result of the medical image is judged to be a positive result, the artificial interpretation result of the medical image is requested to any two doctor users, and when the artificial interpretation result of the medical image by the two doctor users is consistent with the AI interpretation result, a report sheet about the medical image is issued, and the positive result is identified in the report sheet, so that artificial intelligence can be applied to report issuance of clinical practice, the development of medical intelligence is facilitated, and the report issuance efficiency is improved.
Description
Technical Field
The invention relates to the field of intelligent medical treatment, in particular to a report issuing method and device based on medical images.
Background
Machine learning requires large amounts of high quality annotation data before it can be used for medical image analysis. How to ensure the reliability of the labeling quality result and how to issue a medical report under the assistance of artificial intelligence are the problems to be faced and solved in the future artificial intelligence application in clinical practice. There is also a lack of systematic methods in the accuracy of constantly validating and debugging artificial intelligence. An artificial intelligence auxiliary diagnosis system in scientific research is grounded in clinical medical practice, so that the reliability and accuracy of a diagnosis result are ensured, and a good working flow is required between a doctor and artificial intelligence. There are mechanisms associated with finding problems that artificial intelligence now exists or may encounter in the future that are constantly learned and adjusted.
At present, artificial intelligence is applied to medical image labeling in a certain range, but the artificial intelligence is not applied to clinical practice of report issuing, and the deep development of the artificial intelligence in intelligent medicine is influenced.
Disclosure of Invention
The embodiment of the invention provides a report issuing method and device based on a medical image, which can effectively solve the problems of high energy consumption and long time consumption of the existing automatic auditing method, reduce the calculation amount of a computer, improve the efficiency and facilitate the quick and accurate operation of medical inspection work.
An embodiment of the invention provides a report issuing method based on a medical image, which comprises the following steps:
when a report issuing instruction about a medical image is received, acquiring A I interpretation results of the medical image; wherein the AI interpretation results of the medical image comprise negative results and positive results;
when the AI interpretation result of the medical image is judged to be a negative result, requesting the manual interpretation result of the medical image from any doctor user;
when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation result of the doctor user on the medical image is consistent with the AI interpretation result, issuing a report sheet about the medical image and marking the negative result in the report sheet;
when the AI interpretation result of the medical image is judged to be a positive result, requesting the manual interpretation result of the medical image from any two doctor users;
and when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation results of the two doctor users on the medical image are consistent with the AI interpretation result, issuing a report sheet about the medical image and marking a positive result in the report sheet.
Compared with the prior art, the report issuing method based on the medical image, disclosed by the embodiment of the invention, has the advantages that when a report issuing instruction about the medical image is received, the AI interpretation result of the medical image is obtained; when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation result of any doctor user on the medical image is consistent with the AI interpretation result, a report sheet about the medical image is issued, and the negative result is marked in the report sheet; when the AI interpretation result of the medical image is judged to be a positive result, requesting the manual interpretation result of the medical image from any two doctor users, and when the manual interpretation results of the medical image by the two doctor users are consistent with the AI interpretation result, issuing a report sheet about the medical image, and marking the positive result in the report sheet, so that artificial intelligence can be applied to report issuance of clinical practice, development of medical intelligence is facilitated, and report issuance efficiency is improved.
As an improvement of the above, the method further comprises the steps of:
and when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation result of at least one doctor user on the medical image is inconsistent with the AI interpretation result in the two doctor users, sending an interpretation request or an organization discussion request of the medical image to other doctor users or expert doctor users.
As an improvement of the above, the method further comprises the steps of:
when the results of the manual interpretation of the medical image by the other doctor users or the expert doctor users are received, a report sheet about the medical image is issued, and the results of the manual interpretation of the medical image by the other users or the expert users are indicated in the report sheet.
As an improvement of the above, the method further comprises the steps of:
and when final manual interpretation results sent by the two doctor users and the other doctor users or specialist users after discussion are received, issuing a report sheet about the medical image, and indicating the final interpretation results in the report sheet.
As an improvement of the above solution, the AI interpretation result of the medical image is obtained by interpreting through a preset classifier, and the classifier is trained through a plurality of medical images marked with reference marking results; the reference labeling result is determined by the manual labeling results of a labeling users; wherein a is more than or equal to 1.
As an improvement of the above solution, the medical image is generated by:
dividing an original scanning image of a pathological section into n small pictures, and calculating a pathological index of each small picture in the n small pictures; wherein, n is more than or equal to 10^10 and more than or equal to 10;
acquiring the pathological index of each small picture in the n small pictures, and taking the front m small pictures with the highest pathological index in the n small pictures as the medical image; wherein, m is more than or equal to 50 and more than or equal to 5.
The invention correspondingly provides a report issuing device based on medical images, which comprises:
a I interpretation result acquisition module, for acquiring AI interpretation result of a medical image when receiving report issuance instruction about the medical image; wherein the AI interpretation results of the medical image comprise negative results and positive results;
the first manual interpretation result acquisition module is used for requesting the manual interpretation result of the medical image to any doctor user when the AI interpretation result of the medical image is judged to be a negative result;
the first report issuing module is used for issuing a report sheet about the medical image and marking a negative result in the report sheet when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation result of the medical image by the doctor user is consistent with the AI interpretation result;
the second manual interpretation result acquisition module is used for requesting the manual interpretation result of the medical image from any two doctor users when the AI interpretation result of the medical image is judged to be a positive result;
and the second report issuing module is used for issuing a report sheet about the medical image and identifying a positive result in the report sheet when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation results of the two doctor users on the medical image are consistent with the AI interpretation result.
Another embodiment of the present invention provides a medical image-based report issuing apparatus, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the medical image-based report issuing method according to any of the above embodiments of the present invention when executing the computer program.
Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, the apparatus on which the computer-readable storage medium is located is controlled to execute the medical image-based report issuing method according to any one of the above-mentioned embodiments.
Drawings
Fig. 1 is a flowchart illustrating a method for issuing a report based on a medical image according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of segmentation of an original scan image of a pathological section according to an embodiment of the present invention.
Fig. 3(a) is a small picture of single cell cutting in cervical cytology.
Fig. 3(b) is a small picture of the cutting of cervical cytology cell masses.
Fig. 4 is a schematic structural diagram of a medical image-based report issuing apparatus according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a medical image-based report issuing apparatus according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without any inventive step, are within the scope of the present invention.
Referring to fig. 1, it is a flow chart of a report issuing method based on medical images according to an embodiment of the present invention, including:
s1, when a report issuing instruction about a medical image is received, obtaining an AI interpretation result of the medical image; wherein the AI interpretation results of the medical image comprise negative results and positive results;
in step S1, preferably, the medical image is generated by:
firstly, as shown in fig. 2, after an original scanning image of a pathological section is divided into n small pictures, calculating a pathological index of each of the n small pictures; wherein, n is more than or equal to 10^10 and more than or equal to 10;
then, acquiring the pathological index of each small picture in the n small pictures, and taking the first m small pictures with the highest pathological index in the n small pictures as the medical image; wherein, m is more than or equal to 50 and more than or equal to 5.
The above calculation of the pathological index of each of the n small pictures is completed by artificial intelligence, for example, 20 images can be preferentially selected and sorted from a large number of images through artificial intelligence, so that the workload of doctors can be greatly reduced.
In general, the original scan image is obtained by converting a cytopathology slide into a digital image of X400 times, which can reach several G to several tens of G, by a digital slice scanner. If artificial intelligence judgment needs to be completed, the calculation amount is very large, the judgment can be completed only by a specific machine, and the site is limited. Therefore, after the original digital image is cut, AI interpretation can be completed through a common mobile terminal, and the cut image can be loaded without a large-capacity computer, so that the calculation amount and the energy consumption are reduced. Fig. 3(a) shows a small picture of the cutting of single cells in cervical cytology, and fig. 3(b) shows a small picture of the cutting of clusters of cervical cytology cells.
In addition, the small pictures can be conveniently downloaded to different receiving platforms on the internet, and can be conveniently and quickly responded to the mobile terminal device at the cloud end, so that quick operation is realized, and the AI interpretation process is completed.
S2, when the AI interpretation result of the medical image is judged to be a negative result, requesting the manual interpretation result of the medical image from any doctor user;
specifically, the doctor user is a user with issuance qualification, and generally has a medical practitioner certificate.
Because the medical image is a cut small picture, the medical image can be loaded to a mobile terminal held by a doctor user for displaying. Therefore, the doctor user can use the mobile terminal (such as a mobile phone and the like) to perform test labeling in spare time of leisure (such as in the process of sitting on a car, waiting on a car and the like), can also use a common PC (personal computer) to interpret at home or in an office, can synchronously operate on different equipment, greatly increases convenience, and utilizes the fragmentary time operation of the doctor user to the maximum. Moreover, the small pictures after being screened through artificial intelligence can greatly reduce the workload of the doctor user and reduce the risk of error easily caused by fatigue of the doctor user.
S3, when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation result of the medical image by the doctor user is consistent with the AI interpretation result, issuing a report sheet about the medical image and marking the negative result in the report sheet;
in step S3, since the probability of a negative result is much higher than that of a positive result, the error rate is low and the order can be made without the need for review by a plurality of doctor users.
S4, when the AI interpretation result of the medical image is judged to be a positive result, requesting the manual interpretation result of the medical image from any two doctor users;
in step S3, by randomly conforming the AI interpretation results to any two doctor users, the objectivity of the positive result is ensured, and a result error caused by a bias of one doctor user or the like is avoided. In the medical field, the probability of positive results is low, and careful treatment is needed, so that two doctors are required to check the results to obtain a list.
And S5, when the AI interpretation result of the medical image is judged to be a positive result and the manual interpretation results of the two doctor users on the medical image are consistent with the AI interpretation result, issuing a report sheet about the medical image and marking the positive result in the report sheet.
It can be understood that when the users of both doctors agree with the AI interpretation result, the AI interpretation result is proved to have higher objectivity and accuracy, and a report sheet about the medical image can be issued.
For a mobile terminal held by a doctor user, when a request for requesting manual interpretation is received, when the medical image is displayed, an AI interpretation result of the medical image is displayed on the display interface, and a second option button for displaying whether the AI interpretation result of the medical image is agreed or not is displayed; wherein the second option buttons include an agree button and an objection button;
when the click operation of the doctor user on the consent button is received, determining that the manual interpretation result of the doctor user is consistent with the AI interpretation result of the medical image;
and when the clicking operation of the doctor user on the objection button is received, determining that the manual interpretation result of the doctor user is inconsistent with the AI interpretation result of the medical image.
In the implementation process, the embodiment of the invention can apply artificial intelligence to report issuance in clinical practice, is beneficial to the development of medical intelligence, improves the report issuance efficiency, ensures medical safety under artificial intelligence auxiliary diagnosis, and improves the medical quality without reducing the quality when the number of patients increases.
Further, on the basis of the above embodiment, another embodiment further comprises the steps of:
when the AI interpretation result of the medical image is judged to be a positive result and the manual interpretation result of at least one doctor user on the medical image is inconsistent with the AI interpretation result, sending an interpretation request or an organization discussion request of the medical image to other doctor users or expert doctor users;
when the manual interpretation result of the medical image by the other doctor user or the expert doctor user is received, issuing a report sheet about the medical image, and indicating the manual interpretation result of the medical image by the other user or the expert user in the report sheet;
and when final manual interpretation results sent by the two doctor users and the other doctor users or specialist users after discussion are received, issuing a report sheet about the medical image, and indicating the final interpretation results in the report sheet.
Preferably, the AI interpretation result of the medical image is obtained after being interpreted by a preset classifier, and the classifier is trained by a plurality of medical images marked with reference marking results; the reference annotation result is determined by the manual annotation result of a annotation users; wherein a is more than or equal to 1.
The labeling user is different from the doctor user, the labeling user only has the pathology labeling qualification, and the doctor user also has the report issuing qualification which is responsible for the content of the report. The user needs to be specially tested to grant the pathological labeling qualification, for example, s medical images (s is more than or equal to 10) are randomly called to test the medical images of the user, the labeling result of the user on each medical image is obtained, the labeling result of the user on each medical image is compared with the correct labeling result, the labeling accuracy of the user on the s medical images with the correct labeling result is obtained, and when the labeling accuracy is judged to be larger than a preset first threshold value, the user is determined to have the pathological labeling qualification. The marking workers are screened through unified testing, so that higher medical level can be guaranteed, consistency and stability of marking quality can be guaranteed, the marking quality can be guaranteed, objective scientific evaluation indexes can be obtained, and subsequent machine learning model construction is facilitated.
In another preferred embodiment, the method further comprises the steps of:
when the manual labeling result of any labeling user on any medical image is consistent with the reference labeling result, adding 1 to the correct labeling number of the user;
and when the correct marking number of the marking users is larger than a preset threshold value, adding the marking users into a doctor user library.
The excellent labeling users are added into the doctor user library, when the qualified labeling users have the medical practitioner certificates, the formal doctor users can be applied, the report signing and issuing qualification is achieved, the problems of serious shortage and overload work of the existing doctor users can be solved, the existing report signing and issuing pressure is greatly relieved, and the report signing and issuing efficiency is improved.
Referring to fig. 4, a schematic structural diagram of a medical image-based report issuing apparatus according to an embodiment of the present invention includes:
an AI interpretation result acquisition module 101, configured to acquire an AI interpretation result of a medical image when receiving a report issuance instruction regarding the medical image; wherein the AI interpretation results of the medical image comprise negative results and positive results;
a first manual interpretation result obtaining module 102, configured to request a manual interpretation result of the medical image from any doctor user when the AI interpretation result of the medical image is determined to be a negative result;
a first report issuing module 103, configured to issue a report sheet regarding the medical image and identify a negative result in the report sheet when the AI interpretation result of the medical image is determined to be a negative result and the manual interpretation result of the medical image by the doctor user is consistent with the AI interpretation result;
a second manual interpretation result obtaining module 104, configured to request manual interpretation results of the medical images from any two doctor users when the AI interpretation results of the medical images are judged to be positive results;
and the second report issuing module 105 is configured to issue a report sheet about the medical image and identify a positive result in the report sheet when the AI interpretation result of the medical image is determined to be a negative result and the manual interpretation results of the two doctor users on the medical image are both consistent with the AI interpretation result.
The implementation process and the working principle of the report issuing device based on the medical image according to the embodiment of the present invention may refer to any one of the above descriptions of the report issuing method based on the medical image, and are not described herein again.
Another embodiment of the present invention provides a medical image-based report issuing apparatus, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the medical image-based report issuing method according to any of the above embodiments of the present invention when executing the computer program.
Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, the apparatus on which the computer-readable storage medium is located is controlled to execute the medical image-based report issuing method according to any one of the above-mentioned embodiments.
Fig. 5 is a schematic structural diagram of a report issuing apparatus based on medical images according to another embodiment of the present invention. The medical image-based report issuing apparatus includes: at least one processor 11, such as a CPU, at least one network interface 14 or other user interface 13, a memory 15, at least one communication bus 12, the communication bus 12 being used to enable connectivity communications between these components. The user interface 13 may optionally include a USB interface, and other standard interfaces, wired interfaces. The network interface 14 may optionally include a Wi-Fi interface as well as other wireless interfaces. The memory 15 may comprise a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 15 may optionally comprise at least one memory device located remotely from the aforementioned processor 11.
In some embodiments, the memory 15 stores elements, executable modules or data structures, or a subset thereof, or an expanded set thereof:
an operating system 151 containing various system programs such as a battery management system and the like for implementing various basic services and processing hardware-based tasks;
and (5) a procedure 152.
Specifically, the processor 11 is configured to call the program 152 stored in the memory 15 to execute the medical image-based report issuing method according to the above embodiment, for example, step S11 shown in fig. 1. Alternatively, the processor 11, when executing the computer program, implements the functions of each module/unit in the above device embodiments, for example, the AI interpretation result obtaining module 101.
Illustratively, the computer program may be partitioned into one or more modules/units, stored in the memory and executed by the processor to accomplish the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program in the medical image-based report issuing apparatus.
The medical image based report issuing device may include, but is not limited to, a processor 11, a memory 15. It will be understood by those skilled in the art that the schematic diagram is merely an example of a medical image-based report issuing apparatus and does not constitute a limitation of a medical image-based report issuing apparatus, and may include more or fewer components than those shown, or some components in combination, or different components, for example, the medical image-based report issuing apparatus may further include an input-output device, a network access device, a bus, etc.
The Processor 11 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the processor 11 is the control center of the medical image based report issuing apparatus, and various interfaces and lines are used to connect the various parts of the entire medical image based report issuing apparatus.
The memory 15 may be used to store the computer programs and/or modules, and the processor 11 may implement various functions of the medical image-based report issuing apparatus by operating or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory 15 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 15 may include a high speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein the modules/units integrated with the medical image-based report issuing device may be stored in a computer-readable storage medium if implemented in the form of software functional units and sold or used as independent products. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, etc. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (9)
1. A medical image-based report issuing method, comprising the steps of:
when a report issuing instruction about any medical image is received, acquiring an AI interpretation result of the medical image; wherein the AI interpretation results of the medical image comprise negative results and positive results;
when the AI interpretation result of the medical image is judged to be a negative result, requesting the manual interpretation result of the medical image from any doctor user;
when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation result of the medical image by the doctor user is consistent with the AI interpretation result, issuing a report sheet about the medical image and marking the negative result in the report sheet;
when the AI interpretation result of the medical image is judged to be a positive result, requesting the manual interpretation result of the medical image from any two doctor users;
when the AI interpretation result of the medical image is judged to be a positive result, and the manual interpretation results of the two doctor users on the medical image are consistent with the AI interpretation result, a report sheet about the medical image is issued, and the positive result is marked in the report sheet;
the medical image is generated by:
dividing an original scanning image of a pathological section into n small pictures, and calculating a pathological index of each small picture in the n small pictures; wherein, n is more than or equal to 10^10 and more than or equal to 10;
acquiring the pathological index of each small picture in the n small pictures, and taking the front m small pictures with the highest pathological index in the n small pictures as the medical image; wherein, m is more than or equal to 50 and more than or equal to 5.
2. A medical image-based report issuance method according to claim 1, said method further comprising the steps of:
and when the AI interpretation result of the medical image is judged to be a positive result and the manual interpretation result of at least one doctor user to the medical image is inconsistent with the AI interpretation result in the two doctor users, sending an interpretation request or an organization discussion request of the medical image to other doctor users or expert doctor users.
3. A medical image-based report issuance method according to claim 2, said method further comprising the steps of:
when the results of the manual interpretation of the medical image by the other doctor users or the expert doctor users are received, a report sheet about the medical image is issued, and the results of the manual interpretation of the medical image by the other users or the expert users are indicated in the report sheet.
4. A medical image-based report issuance method according to claim 2, said method further comprising the steps of:
and when final manual interpretation results sent by the two doctor users and the other doctor users or specialist users after discussion are received, a report sheet about the medical image is issued, and the final interpretation results are indicated in the report sheet.
5. The medical image-based report issuance method according to claim 1, wherein the AI interpretation result of the medical image is obtained after being interpreted by a preset classifier, and the classifier is trained by a plurality of medical images marked with reference annotation results; the reference labeling result is determined by the manual labeling results of a labeling users; wherein a is more than or equal to 1.
6. The medical image-based report issuance method according to claim 5, further comprising the steps of:
when the manual labeling result of any labeling user on any medical image is consistent with the reference labeling result, adding 1 to the correct labeling number of the user;
and when the correct marking number of the marking users is larger than a preset threshold value, adding the marking users into a doctor user library.
7. A medical image-based report issuance apparatus, comprising:
the AI interpretation result acquisition module is used for acquiring the AI interpretation result of a medical image when a report issuing instruction about the medical image is received; wherein the AI interpretation results of the medical image comprise negative results and positive results;
the first manual interpretation result acquisition module is used for requesting the manual interpretation result of the medical image to any doctor user when the AI interpretation result of the medical image is judged to be a negative result;
the first report issuing module is used for issuing a report sheet about the medical image and marking a negative result in the report sheet when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation result of the medical image by the doctor user is consistent with the AI interpretation result;
the second manual interpretation result acquisition module is used for requesting the manual interpretation result of the medical image from any two doctor users when the AI interpretation result of the medical image is judged to be a positive result;
the second report issuing module is used for issuing a report sheet about the medical image and identifying a positive result in the report sheet when the AI interpretation result of the medical image is judged to be a negative result and the manual interpretation results of the two doctor users on the medical image are consistent with the AI interpretation result;
the medical image is generated by:
dividing an original scanning image of a pathological section into n small pictures, and calculating a pathological index of each small picture in the n small pictures; wherein, n is more than or equal to 10^10 and more than or equal to 10;
acquiring the pathological index of each small picture in the n small pictures, and taking the front m small pictures with the highest pathological index in the n small pictures as the medical image; wherein, m is more than or equal to 50 and more than or equal to 5.
8. A medical image based report issuing apparatus comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the medical image based report issuing method according to any one of claims 1-6 when executing the computer program.
9. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the medical image-based report issuing method according to any one of claims 1 to 6.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811261521.7A CN109509541B (en) | 2018-10-26 | 2018-10-26 | Report issuing method and device based on medical image |
| PCT/CN2019/073339 WO2020082638A1 (en) | 2018-10-26 | 2019-01-28 | Pathological annotation method and device for medical images, report issuing method and device based on medical images, and computer readable storage medium |
| US16/628,683 US11094411B2 (en) | 2018-10-26 | 2019-01-28 | Methods and devices for pathologically labeling medical images, methods and devices for issuing reports based on medical images, and computer-readable storage media |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811261521.7A CN109509541B (en) | 2018-10-26 | 2018-10-26 | Report issuing method and device based on medical image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109509541A CN109509541A (en) | 2019-03-22 |
| CN109509541B true CN109509541B (en) | 2020-07-07 |
Family
ID=65746950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811261521.7A Active CN109509541B (en) | 2018-10-26 | 2018-10-26 | Report issuing method and device based on medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109509541B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11094411B2 (en) * | 2018-10-26 | 2021-08-17 | Guangzhou Kingmed Center for Clinical Laboratory Co., Ltd. | Methods and devices for pathologically labeling medical images, methods and devices for issuing reports based on medical images, and computer-readable storage media |
| CN111063422A (en) * | 2019-12-26 | 2020-04-24 | 北京推想科技有限公司 | Medical image labeling method, device, equipment and medium |
| CN114280014A (en) * | 2021-11-30 | 2022-04-05 | 杭州迪英加科技有限公司 | Independent accounting reagent for AI interpretation |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103926687A (en) * | 2013-01-16 | 2014-07-16 | 索尼公司 | Image Acquisition Apparatus, Image Acquisition Method, And Information Processing Program |
| 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 |
-
2018
- 2018-10-26 CN CN201811261521.7A patent/CN109509541B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103926687A (en) * | 2013-01-16 | 2014-07-16 | 索尼公司 | Image Acquisition Apparatus, Image Acquisition Method, And Information Processing Program |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109509541A (en) | 2019-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109509541B (en) | Report issuing method and device based on medical image | |
| CN109446370A (en) | Pathology mask method and device, the computer readable storage medium of medical image | |
| US20230154142A1 (en) | Fundus color photo image grading method and apparatus, computer device, and storage medium | |
| US11967181B2 (en) | Method and device for retinal image recognition, electronic equipment, and storage medium | |
| CN115730605B (en) | Data analysis method based on multidimensional information | |
| US11756199B2 (en) | Image analysis in pathology | |
| CN109461147B (en) | Pathological labeling method and device applied to FOV picture of mobile terminal | |
| CN109473160A (en) | The mark qualification of medical image determines method and device | |
| CN114240883B (en) | Chromosome image processing method and system | |
| CN111784665A (en) | OCT image quality assessment method, system and device based on Fourier transform | |
| US20200320291A1 (en) | Techniques to determine document recognition errors | |
| CN113707304A (en) | Triage data processing method, device, equipment and storage medium | |
| CN110971673B (en) | Computer device and method for acquiring user activity of deep learning platform | |
| CN112801940A (en) | Model evaluation method, device, equipment and medium | |
| CN116030950B (en) | Medical data integration management method | |
| WO2020082638A1 (en) | Pathological annotation method and device for medical images, report issuing method and device based on medical images, and computer readable storage medium | |
| CN104546013A (en) | Method and device for processing breast ultrasound image and ultrasonic machine | |
| CN113642667A (en) | Enhancement strategy determination method and device, electronic equipment and storage medium | |
| CN113688886A (en) | Image classification method, device and storage medium | |
| CN114582519B (en) | Hospital follow-up method and device based on multi-source data and terminal equipment | |
| CN109545346B (en) | Unilateral capability evaluation method and device of detection system | |
| CN111062977B (en) | Sample data generation method and device, computer equipment and storage medium | |
| WO2024108396A1 (en) | Method and apparatus for measuring hemodynamic heterogeneity and computer device | |
| CN114020687A (en) | User retention analysis method, device, equipment and storage medium | |
| CN118069896A (en) | Power consumption data processing method and device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Che Shuanlong Inventor after: Luo Pifu Inventor after: Liu Si Inventor after: Li Yinghua Inventor after: Qiu Weisong Inventor after: Su Juming Inventor before: Che Shuanlong Inventor before: Luo Pifu Inventor before: Liu Si Inventor before: Li Yinghua Inventor before: Qiu Weisong Inventor before: Su Juming |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221031 Address after: Room 332, Building (3), No. 10, Spiral Third Road, International Biological Island, Huangpu District, Guangzhou, Guangdong 510700 Patentee after: Guangzhou Jinyili Pharmaceutical Technology Co.,Ltd. Address before: 510000, No. 2429, Xingang East Road, Guangzhou, Guangdong, Haizhuqu District Patentee before: GUANGZHOU KINGMED CENTER FOR CLINICAL LABORATORY |