CN111354457A - System and method for processing artificial intelligence diagnosis result of medical image - Google Patents
System and method for processing artificial intelligence diagnosis result of medical image Download PDFInfo
- Publication number
- CN111354457A CN111354457A CN201811572352.9A CN201811572352A CN111354457A CN 111354457 A CN111354457 A CN 111354457A CN 201811572352 A CN201811572352 A CN 201811572352A CN 111354457 A CN111354457 A CN 111354457A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- diagnosis result
- result
- doctor
- processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a system for processing the artificial intelligent diagnosis result of a medical image, which comprises an AI diagnosis result list generation module, a parameter display module and an AI diagnosis result list generation module, wherein the AI diagnosis result list generation module defines the content of each column in the AI diagnosis result list based on different AI diagnosis systems and the requirements of doctors and displays the parameter corresponding to a focus below the AI diagnosis result list; the AI diagnosis result processing module is used for automatically marking the diagnosis result when a doctor uses the diagnosis result of the AI diagnosis system; when a doctor finds that the diagnosis result of the AI diagnosis system is wrong, processing the wrong result, and automatically recording the processed data; and the data interface module acquires the diagnosis result marked by the use and the processed data from the data storage module and sends the diagnosis result and the processed data to the AI diagnosis system. The invention also discloses a method for processing the artificial intelligence diagnosis result of the medical image. The invention enables the AI diagnosis system to improve the diagnosis result, improves the diagnosis efficiency of doctors and reduces the cost.
Description
Technical Field
The invention relates to the field of medical information, in particular to a system and a method for processing an artificial intelligence diagnosis result of a medical image.
Background
With the development of information technology and the construction of medical informatization, many medical institution imaging departments have been installed and deployed with medical imaging structured reporting systems and medical imaging AI (artificial intelligence) diagnostic systems, such as a pulmonary nodule AI diagnostic system, a bone age measurement AI diagnostic system, a prostate AI diagnostic system, and the like. Currently, these systems have the following problems in use: for the AI diagnosis result with the wrong operation, the doctor generally ignores or revises the diagnosis result after confirming the error, and the AI diagnosis system cannot acquire the revision information, so that the wrong data can be frequently sent to the doctor, the doctor diagnosis reagent is consumed, the continuous diagnosis result of the doctor is influenced, the doctor efficiency is reduced, and the diagnosis cost is increased.
Disclosure of Invention
In view of the above, the present invention provides a system and a method for processing a medical image artificial intelligence diagnosis result, which can solve the problems in the prior art that an AI diagnosis system often sends a wrong diagnosis result to a doctor due to the fact that the wrong diagnosis data modified by the doctor cannot be fed back to the AI diagnosis system, so that the diagnosis efficiency of the doctor is reduced, and the diagnosis cost is increased.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
in one aspect, the invention provides a system for processing artificial intelligence diagnosis results of medical images, which comprises an artificial intelligence AI diagnosis result list generating module, an AI diagnosis result processing module, a data storage module and a data interface module, wherein the AI diagnosis result list generating module is connected with the AI diagnosis result processing module and is used for defining the content of each column in the AI diagnosis result list based on different AI diagnosis systems and requirements of doctors and displaying various parameters corresponding to a focus below the AI diagnosis result list; the AI diagnosis result processing module is respectively connected with the AI diagnosis result list generating module and the data storage module and is used for automatically marking the diagnosis result when a doctor uses the diagnosis result of the AI diagnosis system; when a doctor finds that the diagnosis result of the AI diagnosis system is wrong, the doctor processes the wrong result, automatically records the processed data and sends the diagnosis result marked by the use and the processed data to the data storage module; the data storage module is respectively connected with the AI diagnostic result processing module and the data interface module and is used for caching the diagnostic result after the use mark and the processed data; and the data interface module is connected with the data storage module and is used for sending the diagnosis result after the use mark and the processed data to the AI diagnosis system.
Preferably, when the doctor finds that the diagnosis result of the AI diagnosis system is wrong, the wrong result is processed, including: when the error result belongs to a correction type error, the doctor modifies the focus area and/or the focus related parameter; and when the error result does not belong to the correction type error, the doctor refuses to use the error result, and at the moment, the AI diagnosis result processing module is also used for automatically refusing to mark the diagnosis result refused to be used, and meanwhile, the AI diagnosis result is subjected to blurring display in an AI diagnosis result list and is arranged in an unconventional attention area of the AI diagnosis result list.
Preferably, the AI diagnostic result processing module further includes: and the display unit is used for arranging the diagnosis results after the marks are used above the AI diagnosis result list in sequence according to time sequence.
Preferably, the AI diagnostic result processing module further includes: and the cancellation operation unit is used for automatically recording the cancellation operation when the doctor needs to revise the diagnosis result corresponding to the use mark or the rejection mark, and generating a revisable state for the doctor to revise the diagnosis result corresponding to the use mark or the rejection mark.
Preferably, the AI diagnostic result processing module further includes: and the recording unit is used for automatically recording the sequenced diagnosis results and displaying the sequenced diagnosis results in the AI diagnosis result list when the doctor manually sequences the diagnosis results according to the requirements.
In another aspect, the present invention further provides a method for processing the artificial intelligence diagnosis result of the medical image, including: the AI diagnosis result list generation module defines the content of each column in the AI diagnosis result list based on different AI diagnosis systems and the requirements of doctors, and displays various parameters corresponding to the focus below the AI diagnosis result list; when a doctor uses the diagnosis result of the AI diagnosis system, the AI diagnosis result processing module automatically marks the diagnosis result; when a doctor finds that the diagnosis result of the AI diagnosis system is wrong, the doctor processes the wrong result, automatically records the processed data and sends the diagnosis result marked by the use and the processed data to the data storage module; the data storage module caches the diagnosis result after the use of the mark and the processed data; and the data interface module sends the diagnosis result after the use mark and the processed data to the AI diagnosis system.
Preferably, when the doctor finds that the diagnosis result of the AI diagnosis system is wrong, the wrong result is processed, including: when the error result belongs to a correction type error, the doctor modifies the focus area and/or the focus related parameter; and when the error result does not belong to the correction type error, the doctor refuses to use the error result, and at the moment, the AI diagnosis result processing module is also used for automatically refusing to mark the diagnosis result refused to be used, and meanwhile, the AI diagnosis result is subjected to blurring display in the AI diagnosis result list and is arranged in an unconventional attention area of the AI diagnosis result list.
Preferably, the method further comprises: the display unit in the AI diagnostic result processing module arranges the diagnostic results marked with the markers above the AI diagnostic result list in chronological order.
Preferably, the method further comprises: when the doctor needs to revise the diagnosis result corresponding to the use mark or the rejection mark, the cancellation operation unit in the AI diagnosis result processing module automatically records the cancellation operation, and generates a revisable state for the doctor to revise the diagnosis result corresponding to the use mark or the rejection mark.
Preferably, the method further comprises: when the doctor manually sorts the diagnosis results according to the requirements, the recording unit in the AI diagnosis result processing module automatically records the sorted diagnosis results and displays the sorted diagnosis results in the AI diagnosis result list.
The invention has the technical effects that:
1. because the invention has set up AI diagnostic result tabulation and produced the module, AI diagnostic result processing module, data interface module, AI diagnostic result processing module process AI diagnostic result, use AI result correctly, and mark, incorrect AI result, correct or refuse to use and mark wrong result, send the data after processing to AI diagnostic system through the data interface module, for AI diagnostic system to improve the diagnostic result, continue the iteration, raise the diagnostic efficiency of doctor, has reduced the diagnostic cost; meanwhile, the diagnosis result marked to be rejected is subjected to blurring display in an AI diagnosis result list and is arranged in an unconventional concerned area of the AI diagnosis result list, so that the diagnosis idea of a doctor is prevented from being interfered;
2. because the display unit is arranged, the diagnosis results marked by the use can be sequentially arranged above the AI diagnosis result list according to the time sequence, so that the operation of a doctor is facilitated and the diagnosis is clear at a glance;
3. because the cancel operation unit is arranged, when a doctor needs to revise the diagnosis result corresponding to the use mark or the rejection mark, the cancel operation is automatically recorded, and the diagnosis result corresponding to the use mark or the rejection mark is generated into a revisable state for the doctor to revise, so that the system is more humanized, and the operation is more convenient and faster;
4. because the recording unit is arranged, when a doctor manually sorts the diagnosis results according to the requirements, the sorted diagnosis results are automatically recorded and displayed in the AI diagnosis result list, and the diagnosis results can be preferentially displayed in the AI diagnosis result list according to the severity of the focus, so that the system is more flexible.
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 structural diagram of a system for processing artificial intelligence diagnosis results of medical images according to a first embodiment of the present invention;
fig. 2 is a schematic diagram illustrating an AI diagnosis result list interface in a system for processing medical image artificial intelligence diagnosis results according to a first embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a DICOM image lesion area labeled by an AI diagnosis system in a system for processing medical image artificial intelligence diagnosis results according to a first embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a diagnosis result of an AI diagnosis system modified by a doctor in a system for processing artificial intelligence diagnosis results of medical images according to a first embodiment of the present invention;
fig. 5 is a schematic diagram illustrating an AI diagnosis result list after a doctor rejects an AI diagnosis result operation in the system for processing medical image artificial intelligence diagnosis results according to the first embodiment of the present invention;
FIG. 6 is a diagram illustrating a system for processing results of artificial intelligence diagnosis of medical images according to a second embodiment of the present invention;
fig. 7 is a schematic diagram illustrating a list interface for sorting AI diagnosis results after marking in a system for processing medical image artificial intelligence diagnosis results according to a second embodiment of the present invention;
FIG. 8 is a schematic structural diagram of a system for processing results of artificial intelligence diagnosis of medical images according to a third embodiment of the present invention;
FIG. 9 is a schematic diagram illustrating the cancellation of the use of the mark when the use of the mark is revised again in the system for processing the results of the artificial intelligence diagnosis of the medical image according to the third embodiment of the invention;
FIG. 10 is a diagram illustrating a system for processing results of artificial intelligence diagnosis of medical images according to a fourth embodiment of the present invention;
fig. 11 is a schematic diagram illustrating a list of diagnosis results after a doctor manually sorts the diagnosis results in the system for processing medical image artificial intelligence diagnosis results according to the fourth embodiment of the present invention;
FIG. 12 is a flowchart of a method for processing results of artificial intelligence diagnosis of medical images according to a fifth embodiment of the present invention;
fig. 13 is a schematic diagram illustrating an AI diagnosis result list interface in the method for processing medical image artificial intelligence diagnosis results according to the fifth embodiment of the present invention;
fig. 14 is a schematic diagram illustrating labeling of a DICOM image lesion area by an AI diagnosis system in a method for processing medical image artificial intelligence diagnosis results according to a fifth embodiment of the present invention;
fig. 15 is a schematic diagram illustrating a diagnosis result of the AI diagnosis system modified by a doctor in the method for processing medical image artificial intelligence diagnosis results according to the fifth embodiment of the present invention;
fig. 16 is a schematic diagram illustrating an AI diagnosis result list after a doctor rejects an AI diagnosis result operation in the method for processing medical image artificial intelligence diagnosis results according to the fifth embodiment of the present invention;
fig. 17 is a schematic diagram of a list interface for sorting AI diagnosis results after marking in the method for processing medical image artificial intelligence diagnosis results according to the fifth embodiment of the present invention;
FIG. 18 is a diagram illustrating the cancellation of use marks when the use marks are re-modified in a system for processing results of artificial intelligence diagnosis of medical images according to a third embodiment of the present invention;
fig. 19 is a schematic diagram illustrating a list of diagnosis results obtained after a doctor manually sorts the diagnosis results in the system for processing medical image artificial intelligence diagnosis results according to the fourth 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 structural diagram of a system for processing artificial intelligence diagnosis results of medical images according to a first embodiment of the present invention; as shown in fig. 1, the system includes an artificial intelligence AI (artificial intelligence) diagnosis result list generating module 10, an AI diagnosis result processing module 20, a data storage module 30, and a data interface module 40, wherein,
an AI diagnosis result list generating module 10 connected to the AI diagnosis result processing module 20, for defining the content of each column in the AI diagnosis result list based on the requirements of different AI diagnosis systems and doctors, and displaying various parameters corresponding to the focus below the AI diagnosis result list;
the AI diagnosis system is an artificial intelligent auxiliary diagnosis system, is developed by a large number of manufacturers in China, can be applied to various hospitals, can assist doctors in diagnosing the DICOM image focus, and improves the diagnosis quality and efficiency of the doctors.
Fig. 2 is a schematic diagram illustrating an AI diagnosis result list interface in a system for processing medical image artificial intelligence diagnosis results according to a first embodiment of the present invention; as shown in fig. 2, this is an AI diagnosis result list of fracture, each column in the list is set to 6 columns according to the AI diagnosis system of fracture and the requirements of doctors, the list is respectively a serial number, a name, a source (supplier of the AI diagnosis system), time, description and a position, and various parameters for setting fracture are displayed below the list.
The AI diagnosis result processing module 20 is respectively connected with the AI diagnosis result list generating module 10 and the data storage module 30, and is used for automatically marking the diagnosis result when a doctor uses the diagnosis result of the AI diagnosis system; when a doctor finds that the diagnosis result of the AI diagnosis system is wrong, the doctor processes the wrong result, automatically records the processed data and sends the diagnosis result marked by the use and the processed data to the data storage module 30;
fig. 2 is a schematic diagram illustrating an AI diagnosis result list interface in a system for processing medical image artificial intelligence diagnosis results according to a first embodiment of the present invention; as shown in fig. 2, the diagnosis result with the serial number 3 is the result used by the doctor, and a mark of √ is added in front of the serial number 3 to indicate that the doctor uses the diagnosis result, and the diagnosis result can be viewed and displayed with priority in the later period; the form of the use mark can be a circle or a dot, which is not limited herein; when the doctor finds that the diagnosis result is wrong, the doctor processes the mistake, for example, the diagnosis result with the serial number 5 is wrong, the rib is supposed to be of the 5 th class, the doctor can modify the result, and the modified data is recorded.
The data storage module 30 is respectively connected with the AI diagnostic result processing module 20 and the data interface module 40, and is used for caching the diagnostic result after the use mark and the processed data;
for example, as shown in fig. 2, if the diagnosis result with serial number 5 is wrong and the rib should be of type 5, the doctor can modify the result, record the modified data, and display the modified data in the AI diagnosis result list.
And the data interface module 40 is connected with the data storage module 30 and is used for sending the diagnosis result after the use mark and the processed data to the AI diagnosis system.
For example, the diagnostic result marked with the "√" mark in front of the serial number 3 in the above example and the modified data of the diagnostic result with the serial number 5 are sent to the AI diagnostic system for the AI diagnostic system to perform the improvement processing, so as to reduce the unnecessary data result sent to the doctor.
When a doctor finds that a diagnosis result of the AI diagnosis system is wrong, the doctor processes the wrong result, and the method comprises the following steps: when the error result belongs to a correction type error, the doctor modifies the focus area and/or the focus related parameter; and when the error result does not belong to the correction type error, the doctor refuses to use the error result, and at the moment, the AI diagnosis result processing module is also used for automatically refusing to mark the diagnosis result refused to be used, and meanwhile, the AI diagnosis result is subjected to blurring display in an AI diagnosis result list and is arranged in an unconventional attention area of the AI diagnosis result list.
The doctor modifies the error diagnosis result of the AI diagnosis system, corrects the focus area, measures the length, the angle and the like by opening the DICOM image editing area, and then records and displays the focus area, the measure length, the angle and the like in the AI diagnosis result list again;
fig. 3 is a schematic diagram illustrating a DICOM image lesion area labeled by an AI diagnosis system in a system for processing medical image artificial intelligence diagnosis results according to a first embodiment of the present invention; fig. 4 is a schematic diagram illustrating a diagnosis result of an AI diagnosis system modified by a doctor in a system for processing artificial intelligence diagnosis results of medical images according to a first embodiment of the present invention; as shown in fig. 3 and 4, the diagnosis result of the prostate AI diagnosis system is modified, the diagnosis error 1 is corrected, the correction can be directly performed in the DICOM image browsing area, and the modification result is fed back to the AI diagnosis system, so that the AI diagnosis system performs improvement processing.
Fig. 5 is a schematic diagram illustrating an AI diagnosis result list after a doctor rejects an AI diagnosis result operation in a system for processing a medical image artificial intelligence diagnosis result according to an embodiment of the present invention; as shown in fig. 5, the diagnostic results with the numbers 5 and 6 are rejected for use, displayed in gray font in the AI diagnostic result list, and set below all the diagnostic results, so as not to be in common focus on the area.
The embodiment of the invention is provided with an AI diagnosis result list generation module, an AI diagnosis result processing module and a data interface module, wherein the AI diagnosis result processing module processes the AI diagnosis result, correctly uses and marks the AI result, corrects or refuses to use and marks the incorrect result when the AI result is incorrect, and sends the processed data to the AI diagnosis system through the data interface module for the AI diagnosis system to improve and continuously iterate the diagnosis result, thereby improving the diagnosis efficiency of a doctor and reducing the diagnosis cost; meanwhile, the diagnosis result marked to be rejected is displayed in a blurring mode in the AI diagnosis result list and is arranged in an unconventional concerned area of the AI diagnosis result list, and therefore the diagnosis thought of a doctor is prevented from being interfered.
Example two
Fig. 6 is a schematic structural diagram of a system for processing artificial intelligence diagnosis results of medical images according to a second embodiment of the present invention, and as shown in fig. 6, the AI diagnosis result processing module 20 further includes: a display unit 202 for arranging the diagnosis results marked with the markers above the AI diagnosis result list in chronological order.
Fig. 7 is a schematic diagram illustrating a list interface for sorting AI diagnosis results after marking in a system for processing medical image artificial intelligence diagnosis results according to a second embodiment of the present invention; as shown in fig. 7, when the diagnosis result with the number 1 is used, the diagnosis result is arranged at the top of all the diagnosis results in the AI diagnosis result list, which is convenient for the doctor to view preferentially.
The embodiment of the invention is provided with the display unit, and the diagnosis results marked by the marks can be arranged above the AI diagnosis result list in sequence according to time sequence, so that the operation of a doctor is facilitated and the display unit is clear at a glance.
EXAMPLE III
FIG. 8 is a schematic structural diagram of a system for processing results of artificial intelligence diagnosis of medical images according to a third embodiment of the present invention; as shown in fig. 8, the AI diagnostic result processing module 202 further includes: and a cancel operation unit 204, configured to automatically record a cancel operation when the doctor needs to revise the diagnosis result corresponding to the use flag or the reject flag, and generate a revisable state for the doctor to revise the diagnosis result corresponding to the use flag or the reject flag.
FIG. 9 is a schematic diagram illustrating the cancellation of the use of the mark when the use of the mark is revised again in the system for processing the results of the artificial intelligence diagnosis of the medical image according to the third embodiment of the invention; as shown in fig. 9, when the doctor clicks the right button on the diagnosis result with the serial number 3 to display the "cancel use mark", the cancel operation is automatically recorded, and the diagnosis result with the serial number 3 is generated into a modifiable state for the doctor to modify.
The embodiment of the invention is provided with the canceling operation unit, when a doctor needs to revise the diagnosis result corresponding to the use mark or the rejection mark, the canceling operation is automatically recorded, and the diagnosis result corresponding to the use mark or the rejection mark is generated into a revisable state for the doctor to revise, so that the system is more humanized and the operation is more convenient.
Example four
FIG. 10 is a diagram illustrating a system for processing results of artificial intelligence diagnosis of medical images according to a fourth embodiment of the present invention; as shown in fig. 10, the AI diagnostic result processing module 20 further includes: and the recording unit 206 is used for automatically recording the sequenced diagnosis results and displaying the sequenced diagnosis results in an AI diagnosis result list when the doctor manually sequences the diagnosis results according to the requirements.
Fig. 11 is a schematic diagram illustrating a list of diagnosis results after a doctor manually sorts the diagnosis results in the system for processing medical image artificial intelligence diagnosis results according to the fourth embodiment of the present invention; as shown in fig. 11, the doctor manually sorts the AI diagnosis results according to the size of the lung nodules, the lung nodules are arranged at the top with a large volume, and the recording unit 206 automatically records the sorted diagnosis results and displays the diagnosis results in the AI diagnosis result list.
The embodiment of the invention is provided with the recording unit, when a doctor manually sorts the diagnosis results according to the requirements, the sorted diagnosis results are automatically recorded and displayed in the AI diagnosis result list, and the diagnosis results can be preferentially displayed in the AI diagnosis result list according to the severity of the focus, so that the system is more flexible.
EXAMPLE five
FIG. 12 is a flowchart of a method for processing results of artificial intelligence diagnosis of medical images according to a fifth embodiment of the present invention; as shown in fig. 12, the method includes the steps of:
step S501, an AI diagnosis result list generation module defines the content of each column in the AI diagnosis result list based on different AI diagnosis systems and the requirements of doctors, and displays various parameters corresponding to the focus below the AI diagnosis result list;
fig. 13 is a schematic diagram illustrating an AI diagnosis result list interface in the method for processing medical image artificial intelligence diagnosis results according to the fifth embodiment of the present invention; as shown in fig. 13, this is an AI diagnosis result list of fracture, each column in the list is set to 6 columns according to the AI diagnosis system of fracture and the requirements of doctors, the list is respectively a serial number, a name, a source (supplier of the AI diagnosis system), time, description and a position, and various parameters for setting fracture are displayed below the list.
Step S502, when the doctor uses the diagnosis result of the AI diagnosis system, the AI diagnosis result processing module automatically marks the diagnosis result; when a doctor finds that the diagnosis result of the AI diagnosis system is wrong, the doctor processes the wrong result, automatically records the processed data and sends the diagnosis result marked by the use and the processed data to the data storage module;
fig. 13 is a schematic diagram illustrating an AI diagnosis result list interface in the method for processing medical image artificial intelligence diagnosis results according to the fifth embodiment of the present invention; as shown in fig. 13, the diagnosis result with the serial number 3 is the result used by the doctor, and a mark of √ is added before the serial number 3, which indicates that the doctor uses the diagnosis result and can be viewed and displayed with priority in the later period; the form of the use mark can be a circle or a dot, which is not limited herein; when the doctor finds that the diagnosis result is wrong, the doctor processes the mistake, for example, the diagnosis result with the serial number 5 is wrong, the rib is supposed to be of the 5 th class, the doctor can modify the result, and the modified data is recorded.
Step S503, the data storage module caches the diagnosis result after the use mark and the processed data;
for example, as shown in fig. 13, if the diagnosis result with serial number 5 is wrong and the rib should be of type 5, the doctor can modify the result, record the modified data, and display the modified data in the AI diagnosis result list.
In step S504, the data interface module sends the diagnosis result after using the mark and the processed data to the AI diagnosis system.
For example, the diagnostic result marked with the "√" mark in front of the serial number 3 in the above example and the modified data of the diagnostic result with the serial number 5 are sent to the AI diagnostic system for the AI diagnostic system to perform the improvement processing, so as to reduce the unnecessary data result sent to the doctor.
When a doctor finds that a diagnosis result of the AI diagnosis system is wrong, the doctor processes the wrong result, and the method comprises the following steps: when the error result belongs to a correction type error, the doctor modifies the focus area and/or the focus related parameter; and when the error result does not belong to the correction type error, the doctor refuses to use the error result, and at the moment, the AI diagnosis result processing module is also used for automatically refusing to mark the diagnosis result refused to be used, and meanwhile, the AI diagnosis result is subjected to blurring display in an AI diagnosis result list and is arranged in an unconventional attention area of the AI diagnosis result list.
The doctor modifies the error diagnosis result of the AI diagnosis system, corrects the focus area, measures the length, the angle and the like by opening the DICOM image editing area, and then records and displays the focus area, the measure length, the angle and the like in the AI diagnosis result list again;
fig. 14 is a schematic diagram illustrating labeling of a DICOM image lesion area by an AI diagnosis system in a method for processing medical image artificial intelligence diagnosis results according to a fifth embodiment of the present invention; fig. 15 is a schematic diagram illustrating a diagnosis result of the AI diagnosis system modified by a doctor in the method for processing medical image artificial intelligence diagnosis results according to the fifth embodiment of the present invention; as shown in fig. 14 and 15, the diagnosis result of the prostate AI diagnosis system is modified, the diagnosis error 1 is corrected, the correction can be directly performed in the DICOM image browsing area, and the modification result is fed back to the AI diagnosis system, so that the AI diagnosis system performs improvement processing.
Fig. 16 is a schematic diagram illustrating an AI diagnosis result list after a doctor rejects an AI diagnosis result operation in the fifth method for processing medical image artificial intelligence diagnosis results according to the embodiment of the present invention; as shown in fig. 16, the diagnostic results with the numbers 5 and 6 are rejected for use, displayed in gray font in the AI diagnostic result list, and set below all the diagnostic results, so as not to be in common focus.
Wherein, the method also comprises: the display unit in the AI diagnostic result processing module arranges the diagnostic results marked with the markers above the AI diagnostic result list in chronological order.
Fig. 17 is a schematic diagram of a list interface for sorting AI diagnosis results after marking in the method for processing medical image artificial intelligence diagnosis results according to the fifth embodiment of the present invention; as shown in fig. 17, when the diagnosis result with the number 1 is used, the diagnosis result is arranged at the top of all the diagnosis results in the AI diagnosis result list, which is convenient for the doctor to view preferentially.
Wherein, the method also comprises: when the doctor needs to revise the diagnosis result corresponding to the use mark or the rejection mark, the cancellation operation unit in the AI diagnosis result processing module automatically records the cancellation operation, and generates a revisable state for the doctor to revise the diagnosis result corresponding to the use mark or the rejection mark.
FIG. 18 is a schematic diagram illustrating the cancellation of the use of the mark when the use of the mark is modified again in the method for processing the result of the artificial intelligence diagnosis of the medical image according to the fifth embodiment of the invention; as shown in fig. 18, when the doctor clicks the right button on the diagnosis result with the serial number 3 to display the "cancel use flag", the cancel operation is automatically recorded, and the diagnosis result with the serial number 3 is modified by the doctor.
Wherein, the method also comprises: when the doctor manually sorts the diagnosis results according to the requirements, the recording unit in the AI diagnosis result processing module automatically records the sorted diagnosis results and displays the sorted diagnosis results in the AI diagnosis result list.
Fig. 19 is a schematic diagram illustrating a list of diagnosis results obtained after a doctor manually sorts the diagnosis results in the method for processing medical image artificial intelligence diagnosis results according to the fifth embodiment of the present invention; as shown in fig. 19, the doctor manually sorts the AI diagnosis results according to the size of the lung nodules, the lung nodules are arranged at the top in a large size, and the recording unit automatically records the sorted diagnosis results and displays the diagnosis results in the AI diagnosis result list.
The AI diagnosis result processing module in the embodiment of the invention processes the AI diagnosis result, correctly uses and marks the AI result, corrects or refuses to use and marks the incorrect AI result, and sends the processed data to the AI diagnosis system through the data interface module, so that the AI diagnosis system can improve the diagnosis result, continuously iterate, improve the diagnosis efficiency of a doctor and reduce the diagnosis cost; meanwhile, the diagnosis result marked to be rejected is subjected to blurring display in an AI diagnosis result list and is arranged in an unconventional concerned area of the AI diagnosis result list, so that the diagnosis idea of a doctor is prevented from being interfered; the display unit can arrange the diagnosis results marked by the use above the AI diagnosis result list in sequence according to the time sequence, so that the operation of a doctor is facilitated and the diagnosis results are clear at a glance; when the doctor needs to revise the diagnosis result corresponding to the use mark or the rejection mark, the cancellation operation unit automatically records cancellation operation, and generates a revisable state for the doctor to revise according to the diagnosis result corresponding to the use mark or the rejection mark, so that the system is more humanized, and the operation is more convenient and faster; when a doctor manually sorts the diagnosis results according to needs, the recording unit automatically records the sorted diagnosis results and displays the sorted diagnosis results in the AI diagnosis result list, and the diagnosis results can be preferentially displayed in the AI diagnosis result list according to the severity of a focus, so that the system is more flexible.
From the above description, it can be seen that the above-described embodiments of the present invention achieve the following technical effects: because the embodiment of the invention is provided with the AI diagnosis result list generation module, the AI diagnosis result processing module and the data interface module, the AI diagnosis result processing module processes the AI diagnosis result, correctly uses and marks the AI result, corrects or refuses to use and marks the incorrect result when the AI result is incorrect, and sends the processed data to the AI diagnosis system through the data interface module, so that the AI diagnosis system can improve and continuously iterate the diagnosis result, thereby improving the diagnosis efficiency of doctors and reducing the diagnosis cost; meanwhile, the diagnosis result marked to be rejected is subjected to blurring display in an AI diagnosis result list and is arranged in an unconventional concerned area of the AI diagnosis result list, so that the diagnosis idea of a doctor is prevented from being interfered; because the display unit is arranged in the embodiment of the invention, the diagnosis results marked by the use can be arranged above the AI diagnosis result list in sequence according to the time sequence, so that the operation of a doctor is facilitated and the operation is clear at a glance; because the embodiment of the invention is provided with the cancel operation unit, when a doctor needs to revise the diagnosis result corresponding to the use mark or the rejection mark, the cancel operation is automatically recorded, and the diagnosis result corresponding to the use mark or the rejection mark is generated into a revisable state for the doctor to revise, so that the system is more humanized and the operation is more convenient; because the recording unit is arranged in the embodiment of the invention, when a doctor manually sorts the diagnosis results according to the requirements, the sorted diagnosis results are automatically recorded and displayed in the AI diagnosis result list, and the diagnosis results can be preferentially displayed in the AI diagnosis result list according to the severity of the focus, so that the system is more flexible.
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 (10)
1. A system for processing the artificial intelligent diagnosis result of medical image is characterized by comprising an artificial intelligent AI diagnosis result list generating module, an AI diagnosis result processing module, a data storage module and a data interface module, wherein,
the AI diagnosis result list generation module is connected with the AI diagnosis result processing module and is used for defining the content of each column in the AI diagnosis result list based on the requirements of different AI diagnosis systems and doctors and displaying various parameters corresponding to the focus below the AI diagnosis result list;
the AI diagnosis result processing module is respectively connected with the AI diagnosis result list generating module and the data storage module and is used for automatically marking the diagnosis result when a doctor uses the diagnosis result of the AI diagnosis system; when a doctor finds that the diagnosis result of the AI diagnosis system is wrong, the doctor processes the wrong result, automatically records the processed data and sends the diagnosis result marked by the use and the processed data to the data storage module;
the data storage module is respectively connected with the AI diagnostic result processing module and the data interface module and is used for caching the diagnostic result after the use mark and the processed data;
and the data interface module is connected with the data storage module and is used for sending the diagnosis result after the use mark and the processed data to the AI diagnosis system.
2. The system for processing the results of artificial intelligence ("AI") diagnosis of medical images according to claim 1, wherein the processing of the erroneous results when the doctor finds that the AI diagnosis system has an erroneous diagnosis result comprises: when the error result belongs to a correction type error, the doctor modifies the focus area and/or the focus related parameter; and when the error result does not belong to the correction type error, the doctor refuses to use the error result, and at the moment, the AI diagnosis result processing module is also used for automatically refusing to mark the diagnosis result refused to be used, and meanwhile, the AI diagnosis result is subjected to blurring display in the AI diagnosis result list and is arranged in an unconventional attention area of the AI diagnosis result list.
3. The system for processing the results of artificial intelligence medical image diagnosis recited in claim 1, wherein the AI diagnosis result processing module further comprises: and the display unit is used for arranging the diagnosis results marked by the use marks above the AI diagnosis result list in sequence according to time sequence.
4. The system for processing the medical image artificial intelligence diagnosis result as claimed in claim 2, wherein the AI diagnosis result processing module further comprises: and the cancellation operation unit is used for automatically recording cancellation operation when the doctor needs to revise the diagnosis result corresponding to the use mark or the rejection mark, and generating a revisable state for the doctor to revise the diagnosis result corresponding to the use mark or the rejection mark.
5. The system for processing the results of artificial intelligence medical image diagnosis recited in claim 1, wherein the AI diagnosis result processing module further comprises: and the recording unit is used for automatically recording the sequenced diagnosis results and displaying the sequenced diagnosis results in the AI diagnosis result list when a doctor manually sequences the diagnosis results according to requirements.
6. A method for processing the results of artificial intelligence diagnosis of medical images is characterized by comprising the following steps:
the AI diagnosis result list generation module defines the content of each column in the AI diagnosis result list based on different AI diagnosis systems and the requirements of doctors, and displays various parameters corresponding to the focus below the AI diagnosis result list;
when a doctor uses the diagnosis result of the AI diagnosis system, the AI diagnosis result processing module automatically marks the diagnosis result; when a doctor finds that the diagnosis result of the AI diagnosis system is wrong, the doctor processes the wrong result, automatically records the processed data and sends the diagnosis result marked by the use and the processed data to a data storage module;
the data storage module caches the diagnosis result after the use mark and the processed data;
and the data interface module sends the diagnosis result after the use mark and the processed data to the AI diagnosis system.
7. The method for processing the results of the artificial intelligence medical image diagnosis as claimed in claim 6, wherein the processing the false results when the doctor finds that the diagnosis results of the AI diagnosis system are false comprises: when the error result belongs to a correction type error, the doctor modifies the focus area and/or the focus related parameter; and when the error result does not belong to the correction type error, the doctor refuses to use the error result, and at the moment, the AI diagnosis result processing module is also used for automatically refusing to mark the diagnosis result refused to be used, and meanwhile, the AI diagnosis result is subjected to blurring display in the AI diagnosis result list and is arranged in an unconventional attention area of the AI diagnosis result list.
8. The method for processing the result of artificial intelligence diagnosis of medical image as claimed in claim 6, wherein the method further comprises: the display unit in the AI diagnostic result processing module arranges the diagnostic results marked by the use marks above the AI diagnostic result list in sequence according to time sequence.
9. The method for processing the result of artificial intelligence diagnosis of medical image as claimed in claim 7, wherein the method further comprises: when the doctor needs to revise the diagnosis result corresponding to the use mark or the rejection mark, a cancellation operation unit in the AI diagnosis result processing module automatically records cancellation operation, and generates a revisable state for the doctor to revise the diagnosis result corresponding to the use mark or the rejection mark.
10. The method for processing the result of artificial intelligence diagnosis of medical image as claimed in claim 6, wherein the method further comprises: and when the doctor manually sorts the diagnosis results according to the requirements, a recording unit in the AI diagnosis result processing module automatically records the sorted diagnosis results and displays the sorted diagnosis results in the AI diagnosis result list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811572352.9A CN111354457A (en) | 2018-12-21 | 2018-12-21 | System and method for processing artificial intelligence diagnosis result of medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811572352.9A CN111354457A (en) | 2018-12-21 | 2018-12-21 | System and method for processing artificial intelligence diagnosis result of medical image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111354457A true CN111354457A (en) | 2020-06-30 |
Family
ID=71197400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811572352.9A Pending CN111354457A (en) | 2018-12-21 | 2018-12-21 | System and method for processing artificial intelligence diagnosis result of medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111354457A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114783575A (en) * | 2022-04-20 | 2022-07-22 | 北京中捷互联信息技术有限公司 | Medical image processing system and method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07129542A (en) * | 1993-10-29 | 1995-05-19 | Kao Corp | Diagnostic result displaying device |
| CN108022626A (en) * | 2016-11-02 | 2018-05-11 | 哈尔滨光凯科技开发有限公司 | A kind of remote doctor system of internet medical services |
| CN108831533A (en) * | 2018-06-20 | 2018-11-16 | 腾讯科技（深圳）有限公司 | A kind of image processing method, device, system, terminal and storage medium |
-
2018
- 2018-12-21 CN CN201811572352.9A patent/CN111354457A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07129542A (en) * | 1993-10-29 | 1995-05-19 | Kao Corp | Diagnostic result displaying device |
| CN108022626A (en) * | 2016-11-02 | 2018-05-11 | 哈尔滨光凯科技开发有限公司 | A kind of remote doctor system of internet medical services |
| CN108831533A (en) * | 2018-06-20 | 2018-11-16 | 腾讯科技（深圳）有限公司 | A kind of image processing method, device, system, terminal and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114783575A (en) * | 2022-04-20 | 2022-07-22 | 北京中捷互联信息技术有限公司 | Medical image processing system and method |
| CN114783575B (en) * | 2022-04-20 | 2023-09-29 | 广州唯顶软件科技有限公司 | Medical image processing system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2021203679A1 (en) | A system for use by a medical professional, for diagnosing a cause of a patient medical condition and for providing a patient medical condition report, including a diagnosis and treatment | |
| US8634611B2 (en) | Report generation support apparatus, report generation support system, and medical image referring apparatus | |
| JP5982368B2 (en) | Report creation | |
| US9280818B2 (en) | Medical report writing support system, medical report writing unit, and medical image observation unit | |
| CN111145853A (en) | Application system and method of image structured report to artificial intelligence diagnosis result | |
| US11776150B2 (en) | Systems and methods for detecting laterality of a medical image | |
| CN111063422A (en) | Medical image labeling method, device, equipment and medium | |
| CN110931095A (en) | System and method based on DICOM image annotation and structured report association | |
| CN110853739A (en) | Image management display method, device, computer equipment and storage medium | |
| CN113159195A (en) | Ultrasonic image classification method, system, electronic device and storage medium | |
| CN112562816A (en) | System and method for correspondence and evaluation of diagnosis result and pathological result of tumor image report | |
| CN111354457A (en) | System and method for processing artificial intelligence diagnosis result of medical image | |
| CN111986217B (en) | Image processing method, device and equipment | |
| US20160291847A1 (en) | Method and Apparatus for Providing Application Context Tag Communication Framework | |
| US11682135B2 (en) | Systems and methods for detecting and correcting orientation of a medical image | |
| CN116052848B (en) | Data coding method and system for medical imaging quality control | |
| CN111402983A (en) | Cognitive disorder imaging automation reporting system and method thereof | |
| CN110197722B (en) | AI-CPU system platform | |
| JP2010124943A (en) | Medical image management device | |
| JP2007236726A (en) | Image management method and apparatus | |
| CN110610756A (en) | Method for realizing automatic classified printing of films based on DICOM image information | |
| CN114724704A (en) | Method and system for displaying diagnosis path in real time in structured report writing | |
| Bergström | Automated setup of display protocols | |
| CN101196962A (en) | Image information indication method of medicine imaging system | |
| CN111968111A (en) | Method and device for identifying visceral organs or artifacts of CT (computed tomography) image |
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 |