System and method for dynamically generating structured reports in imaging diagnosis services

Abstract

The present invention provides a system for dynamically generating structured reports in imaging diagnosis services, including a CDE selection module that selects a CDE set that matches the purpose of the examination based on the relevant information of the patient, and displays all CDE sets that match the examination items on the imaging structured report interface for doctors to select and fill in; a CDE search module that extracts the keywords of the anatomical parts and the keywords of the imaging manifestations in the diagnostic data corresponding to the current CDE set when the doctor completes the filling of each CDE set, and searches for the next CDE set associated with the keywords of the anatomical parts and the keywords of the imaging manifestations for the doctor to fill in; until the description of the patient's imaging manifestations is completed; an imaging structured report generation module outputs the final diagnosis conclusion. The present invention also discloses a method for dynamically generating structured reports in imaging diagnosis services. The present invention can dynamically organize the structured report interface to ensure the efficiency and quality of filling in the diagnostic report.

Description

Technical Field

[0001] The present invention relates to the field of medical information, and more specifically, to a system and method for dynamically generating structured reports in imaging diagnosis services. Background Art

[0002] In the field of imaging diagnostic reports, all current diagnostic templates are prepared in advance before writing the report, and cannot dynamically generate report components based on imaging manifestations and diagnostic analysis. This is true for personalized text templates used in copy / paste mode, structured reports for single diseases, and even foreign templates that support voice input and step-by-step descriptions based on anatomical locations.

[0003] In a general diagnostic report of a large area (such as an upper abdominal CT scan), multiple organs are involved, and the description and diagnosis of multiple diseases may be involved. Especially in the case of comorbidities and complications, the imaging manifestations may be very complex, and the diagnostic conclusions are also very complex. It is inconvenient to describe the imaging manifestations in the order of organs or disease types.

[0004] If all possibilities are laid out flat on the report interface, the size of the general report template will be very large, which is not only inefficient but also affects the diagnostic doctor's thinking. It is also not feasible to only select some common imaging manifestations to be included in the template for description. Because the various imaging manifestations of a large-scale general report appear randomly, it is difficult to cover them with one or a few fixed templates. If the content of the template is too limited, the completeness of the report content will be limited, affecting the quality of diagnosis. Summary of the invention

[0005] In view of this, the main purpose of the present invention is to provide a system and method for dynamically generating structured reports in imaging diagnosis services, which can solve the problems of incomplete imaging report content, low diagnostic quality and inconvenient operation caused by fixed diagnostic templates in the prior art.

[0006] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0007] On the one hand, the present invention provides a system for dynamically generating structured reports in image diagnosis services, including a CDE selection module, a CDE search module and an image structured report generation module, wherein the CDE selection module is connected to the CDE search module and is used to select a CDE (structured report sub-template common data structure ... element) set for the doctor to fill in, and all CDE sets matching the examination items are displayed at the corresponding position of the image structured report interface for the doctor to choose and fill in; wherein, the CDE set is composed of at least one sub-CDE; the relevant information of the patient is: examination site, examination item, examination purpose, gender, and age; a CDE search module is connected to the CDE search module and the image structured report generation module respectively, and is used to extract the keywords of the anatomical site and the keywords of the imaging manifestation in the diagnostic data corresponding to the current CDE set when the doctor completes the filling of a CDE set, and based on the keywords of the anatomical site and the keywords of the imaging manifestation, search for the next CDE set associated with the keywords of the anatomical site and the keywords of the imaging manifestation, and display it in the image structured report interface for the doctor to fill in; until the description of the patient's imaging manifestation is completed; the image structured report generation module is connected to the CDE search module, and is used to generate natural language from the diagnostic data in sequence based on the order of the CDE sets filled in by the doctor, and output the final diagnosis conclusion.

[0008] Preferably, the CDE search module also includes an association unit, which is used to automatically associate the next CDE set when the association frequency between the current and the next CDE set is greater than a first preset threshold, and display it on the image structured report interface for the doctor to continue filling in after the doctor completes filling in the previous CDE set.

[0009] Preferably, the system also includes a CDE template generation module, which is connected to the CDE search module, and is used to automatically generate a new CDE set template when the combined usage frequency of a certain N CDE set is greater than a second preset threshold, and store the new CDE set template in the database of the image structured report; where N≥2.

[0010] Preferably, the system also includes a mapping module, which is connected to the CDE search module, and is used to automatically map the diagnostic data corresponding to the CDE set previously filled in by the doctor into the structured report template fixed for a specific disease when a CDE set completely matches the structured report template fixed for a specific disease.

[0011] Preferably, the mapping module also includes an insertion unit for automatically extracting a CDE set that matches the keywords of the anatomical part and the pathological data based on the keywords of the anatomical part and the pathological data, and inserting it into a structured report template fixed for a specific disease for the doctor to fill in.

[0012] On the other hand, the present invention also provides a method for dynamically generating structured reports in imaging diagnosis services, including: when a doctor opens the patient's imaging structured report interface, the CDE selection module selects a CDE (structured report sub-template common data element) set that matches the examination purpose based on the patient's relevant information for the doctor to fill in, and displays all CDE sets that match the examination items at the corresponding position of the imaging structured report interface for the doctor to select and fill in; wherein the CDE set is composed of at least one sub-CDE; the patient's relevant information is: examination site, examination item, examination purpose, gender, and age; when the doctor completes the filling of each CDE set, the CDE search module extracts the keywords of the anatomical site and the keywords of the imaging manifestation in the diagnostic data corresponding to the current CDE set, and based on the keywords of the anatomical site and the keywords of the imaging manifestation, searches for the next CDE set associated with the keywords of the anatomical site and the keywords of the imaging manifestation, and displays it on the imaging structured report interface for the doctor to fill in; until the description of the patient's imaging manifestation is completed; the imaging structured report generation module generates natural language from the diagnostic data in sequence based on the order of the CDE sets filled in by the doctor, and outputs the final diagnostic conclusion.

[0013] Preferably, the method also includes: when the association frequency between the current and subsequent CDE sets is greater than a first preset threshold, after the doctor completes filling in the previous CDE set, the association unit in the CDE search module automatically associates the subsequent CDE set and displays it in the image structured report interface for the doctor to continue filling in.

[0014] Preferably, the method also includes: when the combined usage frequency of a certain N CDE sets is greater than a second preset threshold, the CDE template generation module automatically generates a new CDE set template and stores the new CDE set template in the database of the image structured report; wherein N≥2.

[0015] Preferably, the method also includes: when a CDE set completely matches a structured report template for a specific disease, the mapping module automatically maps the diagnostic data corresponding to the CDE set previously filled in by the doctor into the structured report template for a specific disease.

[0016] Preferably, the method also includes: an insertion unit in the mapping module automatically extracts a CDE set that matches the keywords of the anatomical part and the pathological data based on the keywords of the anatomical part and the pathological data, and inserts it into a structured report template fixed for a specific disease for the doctor to fill in.

[0017] Technical effects of the present invention:

[0018] 1. Since the present invention provides a CDE search module and an image structured report generation module, when a doctor opens the patient's image structured report interface, the CDE selection module selects a CDE set that matches the purpose of the examination based on the patient's relevant information. When the doctor completes filling in a CDE set, the CDE search module searches for the next CDE set associated with the keywords of the anatomical site and the keywords of the image manifestation, and displays it on the image structured report interface for the doctor to fill in; until the description of the patient's imaging manifestation is completed; the system can use semantics to dynamically combine CDE components based on the structured report's CDE module and the imaging manifestation, between the CDE module and the diagnosis conclusion, and between the CDE modules. According to the patient's personalized imaging manifestations and personalized diagnosis requirements, the structured report interface can be dynamically organized, which can avoid the loss of description details due to limited fixed templates, and avoid the huge template interface required to cover all possibilities, while ensuring the filling efficiency and quality of the diagnosis report;

[0019] 2. Since the present invention is provided with an association unit, when the association frequency of the first and second CDE sets is greater than the first preset threshold, after the doctor completes filling in the first CDE set, the second CDE set can be automatically associated and displayed in the image structured report interface for the doctor to continue filling in, making the system more perfect and the dynamically generated structured template more accurate;

[0020] 3. Since the present invention is provided with a CDE template generation module, when the combined use frequency of a certain N CDE sets is greater than the second preset threshold, a new CDE set template is automatically generated, and the new CDE set template is stored in the database of the image structured report for later template calls, and the most suitable structured template is dynamically generated according to the personalized needs of a single business, and the structured tags can be saved under the premise of ensuring efficiency, laying the foundation for subsequent continuous improvement;

[0021] 4. Since the present invention is provided with a mapping module, when a certain CDE set completely matches a structured report template for a specific disease, after the doctor changes to use the structured report template for a specific disease, the diagnostic data corresponding to the CDE set previously filled in by the doctor is automatically mapped to the structured report template for a specific disease, thereby improving the speed at which the doctor writes reports and making the system more user-friendly;

[0022] 5. Since the present invention is provided with an insertion unit, it can automatically extract a CDE set that matches the keywords of the anatomical part and the pathological data based on the keywords of the anatomical part and the pathological data, and insert it into a structured report template fixed for a specific disease for doctors to fill in. This makes it convenient for doctors to temporarily insert a structured description to express unexpected findings, facilitates doctors' operation, and makes the system more versatile. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0024] Figure 1 A schematic diagram of the system structure for dynamically generating structured reports in an imaging diagnosis service according to the first embodiment of the present invention is shown;

[0025] Figure 2 A schematic diagram of a CDE interface in which the examination item is a chest CT scan and the clinical diagnosis is a suspected fracture in a system for dynamically generating a structured report in an imaging diagnosis service according to the first embodiment of the present invention is shown;

[0026] Figure 3 A schematic diagram of a CDE interface for searching for descriptions of fracture properties after a fracture is found in a system for dynamically generating structured reports in an imaging diagnosis service according to a first embodiment of the present invention is shown;

[0027] Figure 4 A schematic diagram of a CDE interface describing the location of a lung nodule lesion when a lung nodule is found in a system for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 1 of the present invention is shown;

[0028] Figure 5 A schematic diagram of a CDE interface describing the properties of a pulmonary nodule when a pulmonary nodule is found in a system for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 1 of the present invention is shown;

[0029] Figure 6 A schematic diagram of a CDE interface describing the size of a lung nodule when a lung nodule is found in a system for dynamically generating a structured report in an imaging diagnosis service according to the first embodiment of the present invention is shown;

[0030] Figure 7 A schematic diagram of the system structure for dynamically generating structured reports in an imaging diagnosis service according to a second embodiment of the present invention is shown;

[0031] Figure 8 A schematic diagram of the system structure for dynamically generating structured reports in an imaging diagnosis service according to a third embodiment of the present invention is shown;

[0032] Fig. 9 A schematic diagram of the system structure for dynamically generating structured reports in an imaging diagnosis service according to a fourth embodiment of the present invention is shown;

[0033] Fig.10 A schematic diagram of the system structure for dynamically generating structured reports in an imaging diagnosis service according to a fifth embodiment of the present invention is shown;

[0034] Fig.11 A flow chart of a method for dynamically generating a structured report in an imaging diagnosis service according to a sixth embodiment of the present invention is shown;

[0035] Fig.12 A schematic diagram of a CDE interface in which the examination item is a chest CT scan and the clinical diagnosis is a suspected fracture in a method for dynamically generating a structured report in an imaging diagnosis service according to a sixth embodiment of the present invention is shown;

[0036] Fig.13 A schematic diagram of a CDE interface for searching for a description of the nature of a fracture when a fracture is found in a method for dynamically generating a structured report in an imaging diagnosis service according to a sixth embodiment of the present invention is shown;

[0037] Fig.14 A schematic diagram of a CDE interface describing the location of a lung nodule lesion when a lung nodule is found in a method for dynamically generating a structured report in an imaging diagnosis service according to a sixth embodiment of the present invention is shown;

[0038] Fig.15 A schematic diagram of a CDE interface describing the properties of a pulmonary nodule when a pulmonary nodule is found in a method for dynamically generating a structured report in an imaging diagnosis service according to a sixth embodiment of the present invention is shown;

[0039] Fig.16 A schematic diagram of a CDE interface describing the size of a lung nodule when a lung nodule is found in a method for dynamically generating a structured report in an imaging diagnosis service according to a sixth embodiment of the present invention is shown. DETAILED DESCRIPTION

[0040] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0041] Embodiment 1

[0042] Figure 1 FIG. 4 shows a schematic diagram of a system structure for dynamically generating a structured report in an imaging diagnosis service according to a first embodiment of the present invention; Figure 1 As shown, the system includes: a CDE selection module 10, a CDE search module 20 and an image structured report generation module 30, wherein:

[0043] The CDE selection module 10 is connected to the CDE search module and is used to select a CDE (structured report sub-template common data element) set that matches the examination purpose based on the relevant information of the patient when the doctor opens the patient's image structured report interface, for the doctor to fill in, and display all CDE sets that match the examination items at the corresponding position of the image structured report interface for the doctor to select and fill in; wherein the CDE set is composed of at least one sub-CDE; the relevant information of the patient is: examination site, examination item, examination purpose, gender, and age;

[0044] Figure 2 A schematic diagram of a CDE interface in a system for dynamically generating structured reports in an imaging diagnosis service according to Embodiment 1 of the present invention is shown, where the examination item is a chest CT scan and the clinical diagnosis is a suspected fracture; Figure 2 As shown, the CDE selection module selects the CDE set of the fracture location according to the examination site, examination items, examination purpose (clinical diagnosis is suspected fracture), gender, and age. The doctor can select the left side, right side, and the number of ribs on the CDE interface; and according to the examination item - chest CT scan, all CDE sets matching the chest CT scan are displayed in the corresponding position of the image structured report interface. For example, the CDE sets matching the chest CT scan include lung nodules, fractures, heart, bronchi, lymph nodes, etc., for the doctor to select the corresponding CDE to fill in according to the patient's imaging findings. The display form can be in the form of a list, which is displayed on the left side of the image structured report interface. Each CDE set is presented to the doctor in a tree-like structure.

[0045] Each CDE set and each sub-CDE are displayed in a structured form.

[0046] The CDE search module 20 is connected to the CDE selection module 10 and the image structured report generation module 30, respectively, and is used to extract the keywords of the anatomical parts and the keywords of the imaging manifestations in the diagnostic data corresponding to the current CDE set when the doctor completes filling in each CDE set, and based on the keywords of the anatomical parts and the keywords of the imaging manifestations, search for the next CDE set associated with the keywords of the anatomical parts and the keywords of the imaging manifestations, and display it on the image structured report interface for the doctor to fill in; until the description of the imaging manifestations of the patient is completely completed;

[0047] The form of extracting keywords of anatomical parts and imaging manifestations in the diagnostic data corresponding to the CDE set may be:

[0048] Two association selections are performed in the tree structure, namely, the selection of keywords for anatomical parts and the selection of keywords for imaging manifestations. This form is a structured tree architecture.

[0049] It can also be: voice recording of a file or typing of a text and using NLP technology for analysis to extract keywords of anatomical parts and keywords of imaging manifestations.

[0050] In each CDE set scenario, doctors can continue with their original input, and the system will default to abandoning the use of the CDE set and still use the traditional free text template (or voice converted into free text) to enter the imaging manifestation part.

[0051] Figure 3 FIG. 1 shows a schematic diagram of a CDE interface for searching for a description of the nature of a fracture when a fracture is found in a system for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 1 of the present invention; Figure 3 As shown, when the doctor completes filling in the fracture CDE, the CDE search module searches for a CDE set associated with the keywords of the anatomical site and the keywords of the imaging manifestations based on the keywords of the anatomical site and the keywords of the imaging manifestations in the diagnostic data, that is, a CDE set describing the nature of the fracture, and automatically displays it in the imaging structured report interface for the doctor to fill in.

[0052] Figure 4 FIG. 1 shows a schematic diagram of a CDE interface describing the location of a lung nodule lesion when a lung nodule is found in a system for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 1 of the present invention; Figure 4 As shown, after the doctor completes the fracture CDE set, if lung nodules are found in the patient's images, the doctor selects the CDE of the lung nodule lesion location from the list on the left side of the image structured report interface to fill in: including left and right lungs, upper, middle and lower pages, etc.

[0053] Figure 5 FIG. 1 shows a schematic diagram of a CDE interface describing the properties of a pulmonary nodule when a pulmonary nodule is found in a system for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 1 of the present invention; Figure 5 As shown, based on the diagnostic data of CDE of the location of lung nodules, the CDE search module extracts the keywords of anatomical parts and imaging manifestations in the diagnostic data corresponding to the current CDE set, and based on the keywords of anatomical parts and imaging manifestations, searches for the next CDE set associated with the keywords of the anatomical parts and the keywords of the imaging manifestations - CDE describing the nature of lung nodules: location map and number of lymph node metastases, etc., for doctors to fill in.

[0054] Figure 6 FIG. 1 shows a schematic diagram of a CDE interface describing the size of a lung nodule when a lung nodule is found in a system for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 1 of the present invention; Figure 6As shown, based on the diagnostic data of CDE of the nature of lung nodules, the CDE search module extracts the keywords of anatomical parts and imaging manifestations in the diagnostic data corresponding to the current CDE set, and based on the keywords of anatomical parts and imaging manifestations, searches for the next CDE set associated with the keywords of the anatomical parts and the keywords of the imaging manifestations - CDE describing the size of lung nodules: including the maximum long axis, short axis, volume, CT value, etc., for doctors to fill in, and repeats the above steps in a cycle until the description of the patient's imaging manifestations is completed.

[0055] If no abnormalities are found in the patient's images, the imaging diagnosis report will be completed directly.

[0056] The image structured report generation module 30 is connected to the CDE search module and is used to generate natural language from the diagnostic data in sequence based on the order of the CDE set filled in by the doctor, and output the final diagnostic conclusion.

[0057] In the general reporting business of large anatomical parts, due to the complexity of the business scenarios, the content scale and scope of the templates are difficult to control in advance, so it is difficult to use structured reports, and it is also difficult to retain data labels for continuous improvement based on big data analysis. This system introduces the technology of dynamically generating templates, so that the most suitable structured templates can be dynamically generated according to the personalized needs of a single business, and structured labels can be saved while ensuring efficiency, laying the foundation for subsequent continuous improvement. This system is used to dynamically generate structured report templates in the core part of the imaging diagnosis report - the description chapter of imaging findings. The semantics of the structured report between the CDE module and the imaging manifestations, between the CDE module and the diagnostic conclusions, and between the CDE modules are used to dynamically combine CDE components. The structured report interface is dynamically organized according to the patient's personalized imaging manifestations and personalized diagnosis needs.

[0058] The embodiment of the present invention provides a CDE search module and an image structured report generation module. When the doctor opens the patient's image structured report interface, the CDE selection module selects a CDE set that matches the examination purpose based on the patient's relevant information. When the doctor completes filling out each CDE set, the CDE search module searches for the next CDE set associated with the keywords of the anatomical site and the keywords of the imaging manifestations, and displays it on the image structured report interface for the doctor to fill out; until the description of the patient's imaging manifestations is completed; the system can use semantics based on the CDE module of the structured report and the imaging manifestations, between the CDE module and the diagnosis conclusion, and between the CDE modules. The architecture of the CDE components can be dynamically combined. According to the patient's personalized imaging manifestations and personalized diagnosis needs, the structured report interface can be dynamically organized, which can avoid the loss of description details due to limited fixed templates, and avoid the huge template interface required to cover all possibilities, while ensuring the efficiency and quality of filling out the diagnosis report.

[0059] Embodiment 2

[0060] Figure 7 FIG. 4 shows a schematic diagram of a system structure for dynamically generating a structured report in an imaging diagnosis service according to a second embodiment of the present invention; Figure 7 As shown, the CDE search module 20 also includes an association unit 202, which is used to automatically associate the next CDE set when the association frequency between the current and the next CDE set is greater than a first preset threshold, and display it on the image structured report interface for the doctor to continue filling in after the doctor completes filling in the previous CDE set.

[0061] For example, the current CDE set is a CDE set describing lung nodules, and the next CDE set is a CDE set describing abnormal lymph nodes. When the correlation frequency of these two CDE sets is greater than a first preset threshold, for example, the frequency of these two CDE sets appearing together is greater than 100 times, then when the CDE set describing lung nodules is completed, the CDE set describing abnormal lymph nodes is automatically displayed on the image structured report interface for the doctor to continue filling in.

[0062] The setting of the first preset threshold is determined according to the needs of the medical institution and medical knowledge, and no limitation is made here.

[0063] An embodiment of the present invention provides an association unit. When the association frequency between the current and subsequent CDE sets is greater than a first preset threshold, after the doctor completes filling in the previous CDE set, the subsequent CDE set can be automatically associated and displayed on the image structured report interface for the doctor to continue filling in, thereby making the system more complete and the dynamically generated structured template more accurate.

[0064] Embodiment 3

[0065] Figure 8 FIG. 4 shows a schematic diagram of a system structure for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 3 of the present invention; Figure 8 As shown, the system also includes a CDE template generation module 40, which is connected to the CDE search module 20 and is used to automatically generate a new CDE set template when the combined usage frequency of a certain N CDE set is greater than a second preset threshold, and store the new CDE set template in the database of the image structured report for subsequent extraction and use; wherein N≥2.

[0066] For example, if the frequency of using the combination of CDE describing the fracture location and CDE describing the fracture nature is greater than 100 times, a new CDE set template will be automatically generated. If the relevant imaging description of the fracture is called later, the template will be automatically called out for the doctor to fill in.

[0067] Therefore, by the same token, the largest image structured report is also the largest CDE set, and each CDE set is also composed of many sub-CDEs.

[0068] The setting of the second preset threshold is determined according to the needs of the medical institution and medical knowledge, and no limitation is made here.

[0069] An embodiment of the present invention provides a CDE template generation module. When the combined usage frequency of a certain N CDE sets is greater than a second preset threshold, a new CDE set template is automatically generated, and the new CDE set template is stored in the database of the image structured report for later template calls. The most suitable structured template is dynamically generated according to the personalized needs of a single business, and structured labels can be saved while ensuring efficiency, laying the foundation for subsequent continuous improvement.

[0070] Embodiment 4

[0071] Fig. 9 FIG. 4 shows a schematic diagram of a system structure for dynamically generating a structured report in an imaging diagnosis service according to a fourth embodiment of the present invention; Fig. 9 As shown, the mapping module 50 is connected to the CDE search module 20, and is used to automatically map the diagnostic data corresponding to the CDE set previously filled in by the doctor into the structured report template fixed for a specific disease when a certain CDE set completely matches the structured report template fixed for a specific disease.

[0072] Among them, the fixed structured report template for special diseases is also a CDE template, which is just an inherent template for special diseases that has been set in advance in the image structured report.

[0073] If a CDE set completely matches a structured report template for a specific disease, the reasoning logic of the structured report template for the specific disease can be automatically used to generate partial diagnostic conclusions.

[0074] An embodiment of the present invention provides a mapping module. When a CDE set completely matches a structured report template for a specific disease, after the doctor switches to using the structured report template for a specific disease, the diagnostic data corresponding to the CDE set previously filled in by the doctor is automatically mapped losslessly to the structured report template for the specific disease, thereby improving the speed at which the doctor writes reports and making the system more user-friendly.

[0075] Embodiment 5

[0076] Fig.10 FIG. 4 shows a schematic diagram of a system structure for dynamically generating a structured report in an imaging diagnosis service according to a fifth embodiment of the present invention; Fig.10 As shown, the mapping module 50 also includes an insertion unit 502, which is used to automatically extract a CDE set matching the keywords of the anatomical part and the pathological data from the image structured report interface based on the keywords of the anatomical part and the pathological data, and insert it into a structured report template fixed for a specific disease for the doctor to fill in.

[0077] The embodiment of the present invention is provided with an insertion unit, which can automatically extract a CDE set that matches the keywords of the anatomical part and the pathological data based on the keywords of the anatomical part and the pathological data, and insert it into a structured report template fixed for a specific disease for doctors to fill in. This makes it convenient for doctors to temporarily insert a structured description to express unexpected findings, facilitates doctors' operation, and makes the system more versatile.

[0078] Embodiment 6

[0079] Fig.11 FIG. 4 shows a flow chart of a method for dynamically generating a structured report in an imaging diagnosis service according to a sixth embodiment of the present invention; Fig.11 As shown, the method comprises the following steps:

[0080] Step S601, when the doctor opens the patient's image structured report interface, the CDE selection module selects a CDE (structured report sub-template common data element) set that matches the examination purpose based on the relevant information of the patient for the doctor to fill in, and displays all CDE sets that match the examination items at the corresponding position of the image structured report interface for the doctor to select and fill in; wherein the CDE set consists of at least one sub-CDE;

[0081] Fig.12A schematic diagram of a CDE interface is shown in which the examination item is a chest CT scan and the clinical diagnosis is a suspected fracture in the method for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 6 of the present invention; Fig.12 As shown, the CDE selection module selects the CDE set of the fracture location according to the examination site, examination items, examination purpose (clinical diagnosis is suspected fracture), gender, and age. The doctor can select the left side, right side, and the number of ribs on the CDE interface; and according to the examination item - chest CT scan, all CDE sets matching the chest CT scan are displayed in the corresponding position of the image structured report interface. For example, the CDE sets matching the chest CT scan include lung nodules, fractures, heart, bronchi, lymph nodes, etc., for the doctor to select the corresponding CDE to fill in according to the patient's imaging findings. The display form can be in the form of a list, which is displayed on the left side of the image structured report interface. Each CDE set is presented to the doctor in a tree-like structure.

[0082] Each CDE set and each sub-CDE are displayed in a structured form.

[0083] Step S602: when the doctor completes filling in a CDE set, the CDE search module extracts the keywords of the anatomical parts and the keywords of the imaging manifestations in the diagnostic data corresponding to the current CDE set, and searches for the next CDE set associated with the keywords of the anatomical parts and the keywords of the imaging manifestations based on the keywords of the anatomical parts and the keywords of the imaging manifestations, and displays it on the imaging structured report interface for the doctor to fill in; until the description of the imaging manifestations of the patient is completed;

[0084] The form of extracting keywords of anatomical parts and imaging manifestations in the diagnostic data corresponding to the CDE set may be:

[0085] Two association selections are performed in the tree structure, namely, the selection of keywords for anatomical parts and the selection of keywords for imaging manifestations. This form is a structured tree architecture.

[0086] It can also be: voice recording of a file or typing of a text and using NLP technology for analysis to extract keywords of anatomical parts and keywords of imaging manifestations.

[0087] In each CDE set scenario, doctors can continue with their original input, and the system will default to abandoning the use of the CDE set and still use the traditional free text template (or voice converted into free text) to enter the imaging manifestation part.

[0088] Fig.13FIG. 4 is a schematic diagram showing a CDE interface for searching for a description of the nature of a fracture when a fracture is found in a method for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 6 of the present invention; Fig.13 As shown, when the doctor completes filling in the fracture CDE, the CDE search module searches for a CDE set associated with the keywords of the anatomical site and the keywords of the imaging manifestations based on the keywords of the anatomical site and the keywords of the imaging manifestations in the diagnostic data, that is, a CDE set describing the nature of the fracture, and automatically displays it in the imaging structured report interface for the doctor to fill in.

[0089] Fig.14 FIG. 4 is a schematic diagram of a CDE interface describing the location of a pulmonary nodule lesion when a pulmonary nodule is found in a method for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 6 of the present invention; Fig.14 As shown, after the doctor completes the fracture CDE set, if lung nodules are found in the patient's images, the doctor selects the CDE of the lung nodule lesion location from the list on the left side of the image structured report interface to fill in: including left and right lungs, upper, middle and lower pages, etc.

[0090] Fig.15 FIG. 4 is a schematic diagram of a CDE interface for describing the properties of a pulmonary nodule when a pulmonary nodule is found in a method for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 6 of the present invention; Fig.15 As shown, based on the diagnostic data of CDE of the location of lung nodules, the CDE search module extracts the keywords of anatomical parts and imaging manifestations in the diagnostic data corresponding to the current CDE set, and based on the keywords of anatomical parts and imaging manifestations, searches for the next CDE set associated with the keywords of the anatomical parts and the keywords of the imaging manifestations - CDE describing the nature of lung nodules: location map and number of lymph node metastases, etc., for doctors to fill in.

[0091] Fig.16 FIG. 4 is a schematic diagram of a CDE interface describing the size of a pulmonary nodule when a pulmonary nodule is found in a method for dynamically generating a structured report in an imaging diagnosis service according to Embodiment 6 of the present invention; Fig.16 As shown, based on the diagnostic data of CDE of the nature of lung nodules, the CDE search module extracts the keywords of anatomical parts and imaging manifestations in the diagnostic data corresponding to the current CDE set, and based on the keywords of anatomical parts and imaging manifestations, searches for the next CDE set associated with the keywords of the anatomical parts and the keywords of the imaging manifestations - CDE describing the size of lung nodules: including the maximum long axis, short axis, volume, CT value, etc., for doctors to fill in, and repeats the above steps in a cycle until the description of the patient's imaging manifestations is completed.

[0092] If no abnormalities are found in the patient's images, the imaging diagnosis report will be completed directly.

[0093] Step S603, the image structured report generation module generates natural language from the diagnostic data in sequence based on the order of the CDE set filled in by the doctor, and outputs the final diagnostic conclusion.

[0094] In the general reporting business of large anatomical parts, due to the complexity of the business scenarios, the content scale and scope of the templates are difficult to control in advance, so it is difficult to use structured reports, and it is also difficult to retain data labels for continuous improvement based on big data analysis. This system introduces the technology of dynamically generating templates, so that the most suitable structured templates can be dynamically generated according to the personalized needs of a single business, and structured labels can be saved while ensuring efficiency, laying the foundation for subsequent continuous improvement. This system is used to dynamically generate structured report templates in the core part of the imaging diagnosis report - the description chapter of imaging findings. The semantics of the structured report between the CDE module and the imaging manifestations, between the CDE module and the diagnostic conclusions, and between the CDE modules are used to dynamically combine CDE components. The structured report interface is dynamically organized according to the patient's personalized imaging manifestations and personalized diagnosis needs.

[0095] Among them, the method also includes: when the association frequency between the current and subsequent CDE sets is greater than a first preset threshold, after the doctor completes filling in the previous CDE set, the association unit in the CDE search module automatically associates the subsequent CDE set and displays it in the image structured report interface for the doctor to continue filling in.

[0096] For example, the current CDE set is a CDE set describing lung nodules, and the next CDE set is a CDE set describing abnormal lymph nodes. When the correlation frequency of these two CDE sets is greater than a first preset threshold, for example, the frequency of these two CDE sets appearing together is greater than 100 times, then when the CDE set describing lung nodules is completed, the CDE set describing abnormal lymph nodes is automatically displayed on the image structured report interface for the doctor to continue filling in.

[0097] The setting of the first preset threshold is determined according to the needs of the medical institution and medical knowledge, and no limitation is made here.

[0098] The method also includes: when the combined usage frequency of a certain N CDE sets is greater than a second preset threshold, the CDE template generation module automatically generates a new CDE set template and stores the new CDE set template in the database of the image structured report; wherein N≥2.

[0099] For example, if the frequency of using the combination of CDE describing the fracture location and CDE describing the fracture nature is greater than 100 times, a new CDE set template will be automatically generated. If the relevant imaging description of the fracture is called later, the template will be automatically called out for the doctor to fill in.

[0100] Therefore, by the same token, the largest image structured report is also the largest CDE set, and each CDE set is also composed of many sub-CDEs.

[0101] The setting of the second preset threshold is determined according to the needs of the medical institution and medical knowledge, and no limitation is made here.

[0102] Among them, the method also includes: when a CDE set completely matches the structured report template for a specific disease, the mapping module automatically maps the diagnostic data corresponding to the CDE set previously filled in by the doctor into the structured report template for a specific disease.

[0103] Among them, the fixed structured report template for special diseases is also a CDE template, which is just an inherent template for special diseases that has been set in advance in the image structured report.

[0104] If a CDE set completely matches a structured report template for a specific disease, the reasoning logic of the structured report template for the specific disease can be automatically used to generate partial diagnostic conclusions.

[0105] The method also includes: the insertion unit in the mapping module automatically extracts the CDE set that matches the keywords of the anatomical part and the pathological data based on the keywords of the anatomical part and the pathological data, and inserts it into a structured report template fixed for a specific disease for the doctor to fill in.

[0106] The CDE search module and the image structured report generation module in the embodiment of the present invention, when the doctor opens the patient's image structured report interface, the CDE selection module selects a CDE set that matches the purpose of the examination based on the relevant information of the patient. When the doctor completes filling out each CDE set, the CDE search module searches for the next CDE set associated with the keywords of the anatomical site and the keywords of the imaging manifestation, and displays it on the image structured report interface for the doctor to fill out; until the description of the patient's imaging manifestation is completed; the system can be based on the relationship between the CDE module of the structured report and the imaging manifestation, and between the CDE module and the diagnosis The conclusions and CDE modules use a semantically dynamic architecture that can combine CDE components. According to the patient's personalized imaging manifestations and personalized diagnosis needs, the structured report interface is dynamically organized, which can avoid the loss of description details due to limited fixed templates and the huge template interface required to cover all possibilities, while ensuring the efficiency and quality of filling out the diagnosis report. The association unit in the embodiment of the present invention, when the association frequency between the current and subsequent CDE sets is greater than the first preset threshold, can automatically associate the subsequent CDE set after the doctor completes the filling of the previous CDE set, and display it in the image structured report interface. The page is for doctors to continue filling in, making the system more complete and the dynamically generated structured template more accurate; the CDE template generation module in the embodiment of the present invention automatically generates a new CDE set template when the combined usage frequency of a certain N CDE sets is greater than the second preset threshold, and stores the new CDE set template in the database of the image structured report for later template calls, and dynamically generates the most suitable structured template according to the personalized needs of a single business, and can save structured tags while ensuring efficiency, laying the foundation for subsequent continuous improvement; the mapping module in the embodiment of the present invention, when a certain CDE set is matched with a fixed structured report for a specific disease When the template is completely matched, after the doctor changes to using the structured report template fixed for a specific disease, the diagnostic data corresponding to the CDE set filled out by the doctor in advance will be automatically mapped to the structured report template fixed for a specific disease, thereby improving the speed at which the doctor writes reports and making the system more user-friendly; the insertion unit in the embodiment of the present invention can automatically extract the CDE set that matches the keywords and pathological data of the anatomical part based on the keywords and pathological data of the anatomical part, and insert it into the structured report template fixed for the specific disease for the doctor to fill in, thereby facilitating the doctor to temporarily insert a structured description to express unexpected findings, facilitating the doctor's operation, and making the system more versatile.

[0107] From the above description, it can be seen that the above-mentioned embodiments of the present invention achieve the following technical effects: the embodiments of the present invention set up a CDE search module and an image structured report generation module. When the doctor opens the patient's image structured report interface, the CDE selection module selects a CDE set that matches the purpose of the examination based on the relevant information of the patient. When the doctor completes filling in a CDE set, the CDE search module searches for the next CDE set associated with the keywords of the anatomical part and the keywords of the imaging manifestation, and displays it on the image structured report interface for the doctor to fill in; until the description of the patient's imaging manifestations is completed; the system can be based on the structured report. The semantics of the CDE module and the imaging manifestations, between the CDE module and the diagnosis conclusion, and between the CDE modules are used to dynamically combine the CDE components. According to the patient's personalized imaging manifestations and personalized diagnosis needs, the structured report interface is dynamically organized, which can avoid the loss of description details due to limited fixed templates and the huge template interface required to cover all possibilities, while ensuring the efficiency and quality of filling out the diagnosis report. The embodiment of the present invention provides an association unit. When the association frequency of the previous and subsequent CDE sets is greater than a first preset threshold, the next CDE set can be automatically associated after the doctor completes the filling of the previous CDE set. The set is displayed in the image structured report interface for the doctor to continue filling in, making the system more complete and the dynamically generated structured template more accurate; the embodiment of the present invention sets a CDE template generation module. When the combined usage frequency of a certain N CDE sets is greater than a second preset threshold, a new CDE set template is automatically generated, and the new CDE set template is stored in the database of the image structured report for subsequent template calls. The most suitable structured template is dynamically generated according to the personalized needs of a single business, and structured tags can be saved under the premise of ensuring efficiency, laying the foundation for subsequent continuous improvement; the embodiment of the present invention sets a mapping module. When a certain CDE set is matched with a specific When the structured report template with a fixed disease completely matches the specified disease, the doctor switches to using the structured report template with a fixed specific disease, and the diagnostic data corresponding to the CDE set previously filled in by the doctor is automatically mapped to the structured report template with a fixed specific disease, thereby improving the speed at which the doctor writes reports and making the system more user-friendly. An embodiment of the present invention provides an insertion unit, which can automatically extract the CDE set that matches the keywords and pathological data of the anatomical part based on the keywords and pathological data of the anatomical part, and insert it into the structured report template with a fixed specific disease for the doctor to fill in, thereby facilitating the doctor to temporarily insert a structured description to express unexpected findings, facilitating the doctor's operation, and making the system more versatile.

[0108] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0109] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A system for dynamically generating structured reports in imaging diagnosis services, characterized in that: It includes CDE selection module, CDE search module and image structured report generation module, among which: The CDE selection module is connected to the CDE search module and is used to select a CDE (structured report sub-template common data element) set that matches the examination purpose based on the relevant information of the patient when the doctor opens the patient's image structured report interface for the doctor to fill in. The doctor can click on the CDE set interface, and all the CDE sets that match the examination items will be displayed at the corresponding position of the image structured report interface for the doctor to select and fill in; wherein, the CDE set is composed of at least one sub-CDE; the relevant information of the patient is: examination site, the examination item, the examination purpose, gender, and age; The CDE search module is connected to the CDE search module and the structured image report generation module, respectively, and is used to extract the keywords of the anatomical parts and the keywords of the imaging manifestations in the diagnostic data corresponding to the current CDE set when the doctor completes filling in each CDE set, and based on the keywords of the anatomical parts and the keywords of the imaging manifestations, search for the next CDE set associated with the keywords of the anatomical parts and the keywords of the imaging manifestations, and display them on the structured image report interface for the doctor to fill in; until the description of the imaging manifestations of the patient is completed; wherein, the forms of extracting the keywords of the anatomical parts and the keywords of the imaging manifestations in the diagnostic data corresponding to the current CDE set are as follows: Two association selections are made in the tree structure, namely, the selection of keywords for anatomical parts and the selection of keywords for imaging manifestations. This form is a structured tree architecture. Input a document by voice or type a text and use NLP technology to analyze it, extracting keywords of anatomical parts and imaging manifestations; Wherein, based on the keyword of the anatomical part and the keyword of the imaging manifestation, the next CDE set associated with the keyword of the anatomical part and the keyword of the imaging manifestation is searched, and the principle thereof is: the architecture of semantically dynamically combining CDE components is used between the CDE module of the structured report and the imaging manifestation, between the CDE module and the diagnosis conclusion, and between the CDE modules; The image structured report generation module is connected to the CDE search module, and is used to generate natural language from the diagnostic data in sequence based on the order of the CDE set filled in by the doctor, and output the final diagnostic conclusion.

2. The system for dynamically generating structured reports in imaging diagnosis services according to claim 1, characterized in that: The CDE search module also includes an association unit, which is used to automatically associate the next CDE set when the association frequency between the current and the next CDE sets is greater than a first preset threshold, and display it on the image structured report interface for the doctor to continue filling in after the doctor completes filling in the previous CDE set.

3. The system for dynamically generating structured reports in imaging diagnosis services according to claim 1 or 2, characterized in that: The system also includes a CDE template generation module, connected to the CDE search module, for automatically generating a new CDE set template when the combined usage frequency of a certain N CDE sets is greater than a second preset threshold, and storing the new CDE set template in a database of image structured reports; Where N≥2.

4. The system for dynamically generating structured reports in imaging diagnosis services according to claim 1, characterized in that: The system also includes a mapping module connected to the CDE search module, which is used to automatically map the diagnostic data corresponding to the CDE set previously filled in by the doctor to the structured report template fixed for a specific disease when a certain CDE set completely matches the structured report template fixed for a specific disease.

5. The system for dynamically generating structured reports in imaging diagnosis services according to claim 4, characterized in that: The mapping module also includes an insertion unit for automatically extracting the CDE set that matches the keywords of the anatomical part and the pathological data based on the keywords of the anatomical part and the pathological data, and inserting it into the structured report template fixed for the specific disease for the doctor to fill in.

6. A method for dynamically generating structured reports in imaging diagnosis services, characterized in that: The method includes: When the doctor opens the patient's image structured report interface, the CDE selection module selects a CDE (structured report sub-template common data element) set that matches the examination purpose based on the patient's relevant information for the doctor to fill in. The doctor can click on the CDE set interface, and all the CDE sets that match the examination items will be displayed at the corresponding position of the image structured report interface for the doctor to choose and fill in; wherein, the CDE set is composed of at least one sub-CDE; the patient's relevant information is: examination site, examination item, the examination purpose, gender, age; When the doctor completes filling in each CDE set, the CDE search module extracts the keywords of the anatomical parts and the keywords of the imaging manifestations in the diagnostic data corresponding to the current CDE set, and based on the keywords of the anatomical parts and the keywords of the imaging manifestations, searches for the next CDE set associated with the keywords of the anatomical parts and the keywords of the imaging manifestations, and displays it on the image structured report interface for the doctor to fill in; until the description of the imaging manifestations of the patient is completed; wherein, the forms of extracting the keywords of the anatomical parts and the keywords of the imaging manifestations in the diagnostic data corresponding to the current CDE set are as follows: Two association selections are made in the tree structure, namely, the selection of keywords for anatomical parts and the selection of keywords for imaging manifestations. This form is a structured tree architecture. Input a document by voice or type a text and use NLP technology to analyze it, extracting keywords of anatomical parts and imaging manifestations; Wherein, based on the keyword of the anatomical part and the keyword of the imaging manifestation, the next CDE set associated with the keyword of the anatomical part and the keyword of the imaging manifestation is searched, and the principle thereof is: the architecture of semantically dynamically combining CDE components is used between the CDE module of the structured report and the imaging manifestation, between the CDE module and the diagnosis conclusion, and between the CDE modules; The image structured report generation module generates natural language from the diagnostic data based on the order of the CDE set filled in by the doctor, and outputs the final diagnostic conclusion.

7. The method for dynamically generating structured reports in imaging diagnosis services according to claim 6, characterized in that: The method also includes: when the association frequency between the two CDE sets is greater than a first preset threshold, after the doctor completes filling in the previous CDE set, the association unit in the CDE search module automatically associates the next CDE set and displays it on the image structured report interface for the doctor to continue filling in.

8. The method for dynamically generating structured reports in imaging diagnosis services according to claim 6 or 7, characterized in that: The method also includes: when the combined usage frequency of a certain N CDE sets is greater than a second preset threshold, the CDE template generation module automatically generates a new CDE set template and stores the new CDE set template in the database of the image structured report; wherein N≥2.

9. The method for dynamically generating structured reports in imaging diagnosis services according to claim 6, characterized in that: The method also includes: when a certain CDE set completely matches a structured report template for a specific disease, the mapping module automatically maps the diagnostic data corresponding to the CDE set previously filled in by the doctor into the structured report template for the specific disease.

10. The method for dynamically generating structured reports in imaging diagnosis services according to claim 9, characterized in that: The method also includes: the insertion unit in the mapping module automatically extracts the CDE set that matches the keywords of the anatomical part and the pathological data based on the keywords of the anatomical part and the pathological data, and inserts it into the structured report template fixed for the specific disease for the doctor to fill in.

Images