CN112420147A - System and method for real-time communication between image AI result and structured report desktop - Google Patents
System and method for real-time communication between image AI result and structured report desktop Download PDFInfo
- Publication number
- CN112420147A CN112420147A CN202011292736.2A CN202011292736A CN112420147A CN 112420147 A CN112420147 A CN 112420147A CN 202011292736 A CN202011292736 A CN 202011292736A CN 112420147 A CN112420147 A CN 112420147A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- correction data
- data
- cloud server
- 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.)
- Granted
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
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
-
- 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
- G16H50/20—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
Abstract
The invention provides a desktop real-time communication system of an image AI result and a structured report, which comprises a prediction result calling module, an AI cloud server module and a prediction result display module, wherein when a doctor opens the image structured report of a patient, the prediction result calling module transmits examination parameters to the AI cloud server module; the AI cloud server module loads the prediction result of the patient to an AI browser interface; the corrected data sending module sends a corrected prediction result (defined as corrected data) to the AI cloud server module; the AI cloud server module generates an XML file in a preset format based on the correction data and sends prompt information to the data extraction module; after receiving the prompt message, the data extraction module automatically downloads the XML file; and the result dynamic display module displays the analyzed correction data to a structured report interface in real time. The invention also discloses a method for real-time communication between the image AI result and the structured report desktop. The invention can feed back the correction data of the doctor to the structured report interface in real time, improves the working efficiency of the doctor and simultaneously enables the image AI model to be continuously iterated.
Description
Technical Field
The invention relates to the field of medical information, in particular to a system and a method for real-time communication between an image AI result and a structured report desktop.
Background
The image AI model can generate a large number of measured values and key images, and is particularly suitable for extracting physiological and pathological image characteristics in the first stage of image diagnosis. The image structured report is a diagnosis knowledge base which embeds diagnosis data dimension and diagnosis inference logic into a report template, each data element of the report template has clear medical meaning, and the inference logic is compiled according to gold standard or expert consensus. The image structured report is particularly suitable for reasoning work after extracting physiological characteristics and pathological characteristics of the image, including reference diagnosis/differential diagnosis and knowledge reasoning of cross-clinical departments. The front-back integration of the image AI model and the image structured report product is a very reasonable application.
The prediction result output by the video AI is not always very accurate, and in the actual diagnosis work, the video doctor operates the report while viewing the image using a double screen. If the imaging physician finds errors in the classification and measurement of the imaging AI model, the imaging physician modifies the results of these analyses on the image processing software provided by the imaging AI model provider. The modification results in a series of automatic calculations and new image AI results. Doctors must require that these modified messages be entered into the report immediately and then shut down after the results are satisfactory. Doctors can not accept transmission through a non-real-time protocol at all, and can wait for several minutes to see a final report result; or if the corrected result cannot be fed back to the image structure report in real time, the doctor mostly abandons the adjustment in the image AI for the reason of work, and selects to directly perform the adjustment on the clinical report, thus affecting the continuous iteration of the image AI model.
At present, the communication method for integrating the image AI models of different manufacturers and the third-party structured report has three limitations in the integrated communication scheme: firstly, after the image AI model completes all image analysis work, all image characteristics are pushed to an image structured report at one time; secondly, the method mostly adopts an HL7 message mechanism and does not adopt real-time communication; after the doctor modifies the image again, the doctor needs to manually modify attributes such as measurement values in the image structured report, and the work efficiency is reduced.
Disclosure of Invention
In view of the above, the main objective of the present invention is to provide a desktop real-time communication system and method for image AI results and structured reports, which establishes a set of real-time communication mechanism between an image AI model and an image structured report, and can solve the problem in the prior art that a doctor cannot automatically synchronize a corrected result to the image structured report after correcting the image AI results due to non-real-time communication.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
on one hand, the invention provides a desktop real-time communication system of an image AI result and a structured report, which comprises a prediction result calling module, an AI cloud server module, a correction data sending module, a data extraction module, a data analysis module and a result dynamic display module, wherein the prediction result calling module is connected with the AI cloud server module and is used for automatically calling an AI browser when a doctor opens the image structured report of a patient and transmitting an inspection parameter to the AI cloud server module through the AI browser; the AI cloud server module is respectively connected with the prediction result calling module, the correction data sending module and the data extraction module and is used for loading the prediction result of the patient to an AI browser interface for the doctor to check based on the examination parameters; the correction data sending module is connected with the AI cloud server module and used for sending the corrected prediction result to the AI cloud server module through the AI browser after the doctor corrects the prediction result; the corrected prediction result is defined as correction data, at the moment, the AI cloud server module is further used for generating an XML file in a preset format after performing relevant calculation based on the correction data, storing the XML file in a preset directory, forming prompt information and sending the prompt information to the data extraction module in real time; the data extraction module is respectively connected with the AI cloud server module and the data analysis module and is used for automatically calling a related function of the image structured report through the AI browser and extracting preset parameters after receiving the prompt information, downloading an XML file based on the preset parameters and sending the XML file to the data analysis module; the data analysis module is respectively connected with the data extraction module and the result dynamic display module and is used for analyzing the correction data based on the XML file and sending the analyzed correction data to the result dynamic display module; and the result dynamic display module is connected with the data analysis module and used for receiving the analyzed correction data and displaying the analyzed correction data to a corresponding control of the image structured report interface in real time for a doctor to check.
Preferably, the system further comprises a data storage module connected to the result dynamic display module for storing the analyzed correction data after the doctor submits the final image structured report.
In another aspect, the present invention further provides a method for real-time communication between an image AI result and a structured report desktop, comprising: when a doctor opens an image structured report of a patient, the prediction result calling module automatically calls an AI browser and transmits the examination parameters to the AI cloud server module through the AI browser; the AI cloud server module loads the prediction result of the patient to an AI browser interface for the doctor to check based on the examination parameters; after the doctor corrects the prediction result, the corrected prediction result is sent to the AI cloud server module by the corrected data sending module through the AI browser; the corrected prediction result is defined as correction data, at the moment, the AI cloud server module performs related calculation based on the correction data to generate an XML file in a preset format, stores the XML file in a preset directory, forms prompt information and sends the prompt information to the data extraction module in real time; after receiving the prompt message, the data extraction module automatically calls a related function of the image structured report through the AI browser, extracts a preset parameter, downloads an XML file based on the preset parameter, and sends the XML file to the data analysis module; the data analysis module analyzes the correction data based on the XML file and sends the analyzed correction data to the result dynamic display module; and the result dynamic display module receives the analyzed correction data, and displays the analyzed correction data to a corresponding control of the image structured report interface in real time for a doctor to check.
Preferably, the method further comprises: and the data storage module is used for storing the analyzed correction data after the doctor submits the final image structured report.
The invention has the technical effects that:
because the correction data sending module, the data extraction module, the data analysis module and the result dynamic display module are arranged in the invention, when a doctor corrects a prediction result, the correction data sending module sends the corrected prediction result (defined as correction data) to the AI cloud server module through the AI browser; the AI cloud server module generates an XML file with a preset format and sends prompt information to the data extraction module in real time after performing relevant calculation based on the correction data; after receiving the prompt message, the data extraction module automatically calls a related function of the image structured report through the AI browser, extracts a preset parameter, and downloads an XML file based on the preset parameter; the data analysis module analyzes the correction data; the result dynamic display module displays the analyzed correction data in a corresponding control of an image structured report interface in real time, so that the result adjusted by a doctor can be automatically synchronized into the image structured report in real time, the manual secondary input is avoided, the system is in real-time communication, the doctor is prevented from waiting, and the working efficiency of the doctor is improved; the doctor corrects the processing result of the image AI, continuous iteration can be performed on the image AI model, and the diagnosis precision of the image AI is improved; meanwhile, the data storage module is arranged in the invention, so that analyzed correction data can be stored after a doctor submits a final image structured report for subsequent continuous calling, and the doctor operation and the subsequent system development are facilitated.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a schematic diagram illustrating a system structure of real-time communication between an image AI result and a structured report desktop according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an interface of two-sided image AI prediction results for examining items as breast molybdenum targets in a system for real-time communication of image AI results and a structured report desktop according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a bilateral image structured report interface for examining a breast molybdenum target as an item in a system for real-time communication between an image AI result and a structured report desktop according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a system for real-time communication between an image AI result and a structured report desktop according to a second embodiment of the invention;
FIG. 5 is a flowchart illustrating a method for real-time communication between an image AI result and a structured report desktop according to a third embodiment of the invention;
FIG. 6 is a schematic diagram of an AI prediction result interface of a two-sided image of breast molybdenum target as an inspection item in a desktop real-time communication method of an AI result and a structured report according to a third embodiment of the invention;
fig. 7 is a schematic diagram of a structured report interface of two-sided image of breast molybdenum target for examination item in the method of real-time communication between an AI result and a structured report desktop according to the third embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Example one
Fig. 1 is a schematic diagram illustrating a system structure of real-time communication between an image AI result and a structured report desktop according to an embodiment of the present invention; as shown in fig. 1, the system includes: a prediction result calling module 10, an AI cloud server module 20, a correction data sending module 30, a data extracting module 40, a data analyzing module 50 and a result dynamic display module 60, wherein,
the prediction result calling module 10 is connected with the AI cloud server module 20, and is used for automatically calling an AI browser when the doctor opens the image structured report of the patient, and transmitting the examination parameters to the AI cloud server module 20 through the AI browser;
the AI browser is generally a dedicated browser of an AI manufacturer, and browsing of image AI results generally uses a dedicated image browser of the image AI manufacturer;
the examination parameters are mainly the examination number of the patient, and the examination parameters can be configured arbitrarily according to the requirements of the medical institution, and other examination parameters, such as the age, name, and the like of the patient, can be added in addition to the examination number, and are not limited herein.
The AI cloud server module 20 is respectively connected with the prediction result calling module 10, the correction data sending module 30 and the data extraction module 40, and is used for loading the prediction result of the patient to an AI browser interface for the doctor to check based on the examination parameters;
at present, more and more image diagnosis links use an image AI model, the image AI model can automatically generate marks, classifications and measured values of key image features, and the identification and calculation work can greatly reduce the labor intensity of people.
The correction data sending module 30 is connected to the AI cloud server module 20, and is configured to send the corrected prediction result to the AI cloud server module 20 through the AI browser after the doctor corrects the prediction result;
the prediction result of the image AI is not always correct, for example, a doctor adjusts/modifies the boundary of a positive lesion, corrects the prediction result or the DICOM image to show that the lesion is increased, the attribute of the lesion is modified, the lesion is deleted, and the like, and the corrected prediction result can be sent to the AI cloud server module by the correction data sending module in real time.
Wherein the corrected prediction result is defined as correction data, and at this time,
fig. 2 is a schematic diagram of an interface of a bilateral breast molybdenum target image AI prediction result in a system for real-time communication between an image AI result and a structured report desktop according to an embodiment of the present invention, where the right side of the interface is the prediction result of the bilateral breast molybdenum target image AI, and a doctor can correct the prediction result and then click and submit the prediction result, so that correction data is sent to an AI cloud server module.
The AI cloud server module 20 is further configured to generate an XML file in a preset format after performing relevant calculation based on the correction data, store the XML file in a preset directory, form prompt information, and send the prompt information to the data extraction module 40 in real time;
the AI cloud server module can recalculate and predict screenshots of the key images, various indexes of lesion morphology and the like, and generate an XML file in a preset format. The link can continuously iterate the image AI model, and the diagnosis precision of the image AI model is improved.
The XML file includes a plurality of iconography representations, each of which is described in a fixed structured format, and in general, the predetermined format may be defined as: code, data name, value, for example: v47, name, short diameter, unit cm, 0.3. The preset format can be set individually according to the requirements of the medical institution, and is not limited herein.
The data extraction module 40 is respectively connected with the AI cloud server module 20 and the data analysis module 50, and is configured to, after receiving the prompt information, automatically call a relevant function of the image structured report through the AI browser and extract a preset parameter, download an XML file based on the preset parameter, and send the XML file to the data analysis module 50;
the prompting information is a related function which informs the data extraction module to trigger the image structured report after the AI cloud server module generates the XML file, and the data extraction module triggers the image structured report by calling a srrptlaunter.dll program;
the preset parameter is generally a download address of the XML file, and the XML file is downloaded through a Web Service data interface.
The data analysis module 50 is respectively connected with the data extraction module 40 and the result dynamic display module 60, and is used for analyzing the correction data based on the XML file and sending the analyzed correction data to the result dynamic display module 60;
and the result dynamic display module 60 is connected with the data analysis module 50 and is used for receiving the analyzed correction data and displaying the analyzed correction data to a corresponding control of the image structured report interface in real time for a doctor to check.
Fig. 3 is a schematic diagram of a bilateral image structured report interface for examining a breast molybdenum target as an item in a system for real-time communication between an image AI result and a structured report desktop according to an embodiment of the present invention; as shown in fig. 3, the predicted result or the corrected data of the breast molybdenum target bilateral image AI are displayed in the corresponding controls of the image structured report interface, such as the number, size, etc. of the tumor mass, for the doctor to view and submit the final image report.
The transmission of the prediction result of the image AI to the image structured report is completed in the AI cloud server module in advance, and the prediction result is displayed when the application of the image structured report terminal is opened; the corrected data is fed back to the image structured report from the AI cloud server module in real time, and after the corrected data is submitted from the doctor, the generation of the XML file, the calling of the function, the downloading of the XML file and the display of the corrected data after the analysis are finished within 2-3 seconds, so that the real-time communication and the real-time feedback are realized in the whole closed-loop feedback process.
The embodiment of the invention is provided with a correction data sending module, a data extraction module, a data analysis module and a result dynamic display module, wherein when a doctor corrects a prediction result, the correction data sending module sends the corrected prediction result (defined as correction data) to the AI cloud server module through the AI browser; the AI cloud server module generates an XML file with a preset format and sends prompt information to the data extraction module in real time after performing relevant calculation based on the correction data; after receiving the prompt message, the data extraction module automatically calls a related function of the image structured report through the AI browser, extracts a preset parameter, and downloads an XML file based on the preset parameter; the data analysis module analyzes the correction data; the result dynamic display module displays the analyzed correction data in a corresponding control of an image structured report interface in real time, so that the result adjusted by a doctor can be automatically synchronized into the image structured report in real time, the manual secondary input is avoided, the system is in real-time communication, the doctor is prevented from waiting, and the working efficiency of the doctor is improved; the doctor corrects the processing result of the image AI, can continuously iterate the image AI model, and improves the diagnosis precision of the image AI.
Example two
FIG. 4 is a schematic diagram of a system for real-time communication between an image AI result and a structured report desktop according to a second embodiment of the invention; as shown in fig. 4, the system further includes a data storage module 70 connected to the result dynamic display module 60, for storing the analyzed correction data after the doctor submits the final image structured report, so as to be called continuously.
The data storage module is arranged in the embodiment of the invention, so that analyzed correction data can be stored after a doctor submits a final image structured report for subsequent continuous calling, and the doctor operation and the subsequent system development are facilitated.
EXAMPLE III
FIG. 5 is a flowchart illustrating a method for real-time communication between an image AI result and a structured report desktop according to a third embodiment of the invention; as shown in fig. 5, the method comprises the steps of:
step S301, when a doctor opens an image structured report of a patient, a prediction result calling module automatically calls an AI browser and transmits examination parameters to an AI cloud server module through the AI browser;
the AI browser is generally a dedicated browser of an AI manufacturer, and browsing of image AI results generally uses a dedicated image browser of the image AI manufacturer;
the examination parameters are mainly the examination number of the patient, and the examination parameters can be configured arbitrarily according to the requirements of the medical institution, and other examination parameters, such as the age, name, and the like of the patient, can be added in addition to the examination number, and are not limited herein.
Step S302, the AI cloud server module loads the prediction result of the patient to an AI browser interface for the doctor to check based on the examination parameters;
at present, more and more image diagnosis links use an image AI model, the image AI model can automatically generate marks, classifications and measured values of key image features, and the identification and calculation work can greatly reduce the labor intensity of people.
Step S303, after the doctor corrects the prediction result, the corrected data sending module sends the corrected prediction result to the AI cloud server module through the AI browser;
the prediction result of the image AI is not always correct, for example, a doctor adjusts/modifies the boundary of a positive lesion, corrects the prediction result or the DICOM image to show that the lesion is increased, the attribute of the lesion is modified, the lesion is deleted, and the like, and the corrected prediction result can be sent to the AI cloud server module by the correction data sending module in real time.
Wherein the corrected prediction result is defined as correction data;
fig. 6 is a schematic diagram of an interface of a bilateral breast molybdenum target image AI prediction result as an inspection item in the method for real-time communication between an image AI result and a structured report desktop according to the third embodiment of the present invention, and as shown in fig. 6, the prediction result of the bilateral breast molybdenum target image AI is on the right side of the interface, and a doctor can correct the prediction result and then click and submit the correction result, so that correction data is sent to the AI cloud server module.
Step S304, after the AI cloud server module further performs related calculation based on the correction data, generating an XML file in a preset format, storing the XML file in a preset directory, forming prompt information, and sending the prompt information to the data extraction module in real time;
the AI cloud server module can recalculate and predict screenshots of the key images, various indexes of lesion morphology and the like, and generate an XML file in a preset format. The link can continuously iterate the image AI model, and the diagnosis precision of the image AI model is improved.
The XML file includes a plurality of iconography representations, each of which is described in a fixed structured format, and in general, the predetermined format may be defined as: code, data name, value, for example: v47, name, short diameter, unit cm, 0.3. The preset format can be set individually according to the requirements of the medical institution, and is not limited herein.
Step S305, after receiving the prompt message, the data extraction module automatically calls the related function of the image structured report through the AI browser and extracts the preset parameters, downloads the XML file based on the preset parameters, and sends the XML file to the data analysis module;
the prompting information is a related function which informs the data extraction module to trigger the image structured report after the AI cloud server module generates the XML file, and the data extraction module triggers the image structured report by calling a srrptlaunter.dll program;
the preset parameter is generally a download address of the XML file, and the XML file is downloaded through a Web Service data interface.
Step S306, the data analysis module analyzes the correction data based on the XML file and sends the analyzed correction data to the result dynamic display module;
and step S307, the result dynamic display module receives the analyzed correction data, and displays the analyzed correction data to a corresponding control of the image structured report interface in real time for a doctor to check.
Fig. 7 is a schematic diagram of a structured report interface of two-sided image of breast molybdenum target as an inspection item in a desktop real-time communication method of image AI results and structured report according to a third embodiment of the present invention; as shown in fig. 7, the predicted result or the corrected data of the breast molybdenum target bilateral image AI are displayed in the corresponding controls of the image structured report interface, such as the number, size, etc. of the tumor mass, for the doctor to view and submit the final image report.
The transmission of the prediction result of the image AI to the image structured report is completed in the AI cloud server module in advance, and the prediction result is displayed when the application of the image structured report terminal is opened; the corrected data is fed back to the image structured report from the AI cloud server module in real time, and after the corrected data is submitted from the doctor, the generation of the XML file, the calling of the function, the downloading of the XML file and the display of the corrected data after the analysis are finished within 2-3 seconds, so that the real-time communication and the real-time feedback are realized in the whole closed-loop feedback process.
Wherein, the method also comprises: and after the doctor submits the final image structured report, the data storage module stores the analyzed correction data for subsequent continuous calling.
According to the embodiment of the invention, after a doctor corrects a prediction result, the corrected data sending module sends the corrected prediction result (defined as correction data) to the AI cloud server module through the AI browser; the AI cloud server module generates an XML file with a preset format and sends prompt information to the data extraction module in real time after performing relevant calculation based on the correction data; after receiving the prompt message, the data extraction module automatically calls a related function of the image structured report through the AI browser, extracts a preset parameter, and downloads an XML file based on the preset parameter; the data analysis module analyzes the correction data; the result dynamic display module displays the analyzed correction data in a corresponding control of an image structured report interface in real time, so that the result adjusted by a doctor can be automatically synchronized into the image structured report in real time, the manual secondary input is avoided, the system is in real-time communication, the doctor is prevented from waiting, and the working efficiency of the doctor is improved; the doctor corrects the processing result of the image AI, continuous iteration can be performed on the image AI model, and the diagnosis precision of the image AI is improved; meanwhile, the data storage module in the embodiment of the invention can store the analyzed correction data after the doctor submits the final image structured report for subsequent continuous calling, thereby facilitating the doctor operation and the subsequent system development.
From the above description, it can be seen that the above-described embodiments of the present invention achieve the following technical effects: the embodiment of the invention is provided with a correction data sending module, a data extraction module, a data analysis module and a result dynamic display module, wherein when a doctor corrects a prediction result, the correction data sending module sends the corrected prediction result (defined as correction data) to the AI cloud server module through the AI browser; the AI cloud server module generates an XML file with a preset format and sends prompt information to the data extraction module in real time after performing relevant calculation based on the correction data; after receiving the prompt message, the data extraction module automatically calls a related function of the image structured report through the AI browser, extracts a preset parameter, and downloads an XML file based on the preset parameter; the data analysis module analyzes the correction data; the result dynamic display module displays the analyzed correction data in a corresponding control of an image structured report interface in real time, so that the result adjusted by a doctor can be automatically synchronized into the image structured report in real time, the manual secondary input is avoided, the system is in real-time communication, the doctor is prevented from waiting, and the working efficiency of the doctor is improved; the doctor corrects the processing result of the image AI, continuous iteration can be performed on the image AI model, and the diagnosis precision of the image AI is improved; meanwhile, the data storage module is arranged in the embodiment of the invention, so that the analyzed correction data can be stored after the doctor submits the final image structured report for subsequent continuous calling, and the doctor operation and the subsequent system development are facilitated.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. A system for real-time communication between an image AI result and a structured report desktop is characterized by comprising a prediction result calling module, an AI cloud server module, a correction data sending module, a data extraction module, a data analysis module and a result dynamic display module, wherein,
the prediction result calling module is connected with the AI cloud server module and is used for automatically calling an AI browser when a doctor opens an image structured report of a patient and transmitting examination parameters to the AI cloud server module through the AI browser;
the AI cloud server module is respectively connected with the prediction result calling module, the correction data sending module and the data extraction module, and is used for loading the prediction result of the patient to the AI browser interface for the doctor to check based on the examination parameters;
the correction data sending module is connected with the AI cloud server module and used for sending the corrected prediction result to the AI cloud server module through the AI browser after the doctor corrects the prediction result; wherein the corrected prediction result is defined as correction data, and at this time,
the AI cloud server module is also used for generating an XML file in a preset format after performing relevant calculation based on the correction data, storing the XML file in a preset directory, forming prompt information and sending the prompt information to the data extraction module in real time;
the data extraction module is respectively connected with the AI cloud server module and the data analysis module, and is used for automatically calling a related function of the image structured report through the AI browser and extracting preset parameters after receiving the prompt message, downloading the XML file based on the preset parameters, and sending the XML file to the data analysis module;
the data analysis module is respectively connected with the data extraction module and the result dynamic display module and is used for analyzing the correction data based on the XML file and sending the analyzed correction data to the result dynamic display module;
and the result dynamic display module is connected with the data analysis module and is used for receiving the analyzed correction data and displaying the analyzed correction data to a corresponding control of the image structured report interface in real time for a doctor to check.
2. The system for desktop real-time communication of visual AI results and structured reports of claim 1, further comprising a data storage module, coupled to the results dynamic display module, for storing the parsed correction data after the physician submits the final visual structured report.
3. A method for real-time communication of an image AI result with a structured report desktop, the method comprising:
when a doctor opens an image structured report of a patient, a prediction result calling module automatically calls an AI browser and transmits examination parameters to an AI cloud server module through the AI browser;
the AI cloud server module loads the prediction result of the patient to the AI browser interface for the doctor to check based on the examination parameters;
after the doctor corrects the prediction result, the corrected data sending module sends the corrected prediction result to the AI cloud server module through the AI browser; wherein the corrected prediction result is defined as correction data, and at this time,
the AI cloud server module is also used for generating an XML file in a preset format after performing relevant calculation based on the correction data, storing the XML file in a preset directory, forming prompt information and sending the prompt information to the data extraction module in real time;
after receiving the prompt message, the data extraction module automatically calls a related function of the image structured report through the AI browser and extracts a preset parameter, downloads the XML file based on the preset parameter, and sends the XML file to a data analysis module;
the data analysis module analyzes the correction data based on the XML file and sends the analyzed correction data to a result dynamic display module;
and the result dynamic display module receives the analyzed correction data and displays the analyzed correction data to a corresponding control of the image structured report interface in real time for a doctor to check.
4. The method for real-time communication of video AI results with a structured reporting desktop as claimed in claim 3, further comprising: and the data storage module stores the analyzed correction data after the doctor submits the final image structured report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011292736.2A CN112420147B (en) | 2020-11-18 | 2020-11-18 | System and method for real-time communication between image AI result and structured report desktop |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011292736.2A CN112420147B (en) | 2020-11-18 | 2020-11-18 | System and method for real-time communication between image AI result and structured report desktop |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112420147A true CN112420147A (en) | 2021-02-26 |
| CN112420147B CN112420147B (en) | 2022-03-04 |
Family
ID=74832255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011292736.2A Active CN112420147B (en) | 2020-11-18 | 2020-11-18 | System and method for real-time communication between image AI result and structured report desktop |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112420147B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113449492A (en) * | 2021-06-02 | 2021-09-28 | 杨旗 | Method and system for converting word data generated by post-processing into structured data |
| CN114242197A (en) * | 2021-12-21 | 2022-03-25 | 数坤(北京)网络科技股份有限公司 | Structured report processing method and device and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101876992A (en) * | 2009-11-17 | 2010-11-03 | 中国科学院自动化研究所 | Method for managing image data warehouse |
| US20140156613A1 (en) * | 2012-09-18 | 2014-06-05 | Squash Compression, LLC | Methods and Apparatus for Increasing the Efficiency of Electronic Data Storage and Transmission |
| CN110197715A (en) * | 2019-05-19 | 2019-09-03 | 复旦大学附属华山医院 | A kind of medical image browsing system for read tablet teaching |
-
2020
- 2020-11-18 CN CN202011292736.2A patent/CN112420147B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101876992A (en) * | 2009-11-17 | 2010-11-03 | 中国科学院自动化研究所 | Method for managing image data warehouse |
| US20140156613A1 (en) * | 2012-09-18 | 2014-06-05 | Squash Compression, LLC | Methods and Apparatus for Increasing the Efficiency of Electronic Data Storage and Transmission |
| CN110197715A (en) * | 2019-05-19 | 2019-09-03 | 复旦大学附属华山医院 | A kind of medical image browsing system for read tablet teaching |
Non-Patent Citations (1)
| Title |
|---|
| 孙应实等: "胃癌术前影像学评估的合理选择", 《中国实用外科杂志》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113449492A (en) * | 2021-06-02 | 2021-09-28 | 杨旗 | Method and system for converting word data generated by post-processing into structured data |
| CN113449492B (en) * | 2021-06-02 | 2024-04-19 | 杨旗 | Method and system for converting word data generated by post-processing into structured data |
| CN114242197A (en) * | 2021-12-21 | 2022-03-25 | 数坤(北京)网络科技股份有限公司 | Structured report processing method and device and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112420147B (en) | 2022-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112420147B (en) | System and method for real-time communication between image AI result and structured report desktop | |
| CN107729929B (en) | Method and device for acquiring information | |
| US10372802B2 (en) | Generating a report based on image data | |
| US6735272B1 (en) | Method and system for a customized patient report in imaging systems | |
| US20090169073A1 (en) | Computer implemented method and system for processing images | |
| US20200019823A1 (en) | Medical image analysis method applying machine learning and system thereof | |
| CN111584043B (en) | Intelligent prompting system and method for imaging scanning scheme | |
| US10304564B1 (en) | Methods and systems for displaying an image | |
| CN111145853A (en) | Application system and method of image structured report to artificial intelligence diagnosis result | |
| EP3567600B1 (en) | Improving a runtime environment for imaging applications on a medical device | |
| CN111723277A (en) | Image structured report cloud requirement classification system and method thereof | |
| US20240038351A1 (en) | Machine learning for optimizing ovarian stimulation | |
| CN110827937A (en) | Data display method and system applied to medical field | |
| CN116910561A (en) | Data set construction method and server | |
| CN113657343A (en) | Method and device for generating claim resource data based on machine learning | |
| CN107844102A (en) | Production plan management method and system | |
| CN110335253B (en) | Eye image processing method, device, equipment and computer readable storage medium | |
| JP7278256B2 (en) | Devices, systems and methods for optimizing image acquisition workflows | |
| KR102246603B1 (en) | Method For Converting Health Information And System For Managing Health Information | |
| CN112509674B (en) | DICOM medical image data downloading method, DICOM medical image data downloading system and DICOM medical image data displaying method | |
| US11417421B1 (en) | Electronic health records connectivity | |
| US20100088113A1 (en) | Medical information controller and medical image system | |
| CN111739598A (en) | Data processing method, device, medium and electronic equipment | |
| KR102371037B1 (en) | Programmable electronic medical record system | |
| Pfeifer | Integrating a Novel Eye Imaging System into Clinical Practice: An Open-Source DICOM Simulation Platform |
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 |