CN112786162A - System and method for designing structured report template based on sub-template semantic relation - Google Patents
System and method for designing structured report template based on sub-template semantic relation Download PDFInfo
- Publication number
- CN112786162A CN112786162A CN202011589066.0A CN202011589066A CN112786162A CN 112786162 A CN112786162 A CN 112786162A CN 202011589066 A CN202011589066 A CN 202011589066A CN 112786162 A CN112786162 A CN 112786162A
- Authority
- CN
- China
- Prior art keywords
- cde
- template
- semantic
- structured report
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000003745 diagnosis Methods 0.000 claims abstract description 144
- 238000003384 imaging method Methods 0.000 claims abstract description 28
- 230000001575 pathological effect Effects 0.000 claims abstract description 24
- 230000000877 morphologic effect Effects 0.000 claims abstract description 20
- 201000010099 disease Diseases 0.000 claims description 31
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 31
- 210000000056 organ Anatomy 0.000 claims description 25
- 210000003484 anatomy Anatomy 0.000 claims description 24
- 230000003902 lesion Effects 0.000 claims description 16
- 238000002372 labelling Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 44
- 210000001519 tissue Anatomy 0.000 description 17
- 206010056342 Pulmonary mass Diseases 0.000 description 12
- 210000000481 breast Anatomy 0.000 description 8
- 210000004907 gland Anatomy 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 208000014674 injury Diseases 0.000 description 6
- 210000004072 lung Anatomy 0.000 description 6
- 238000003058 natural language processing Methods 0.000 description 6
- 230000008733 trauma Effects 0.000 description 6
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 5
- 208000007536 Thrombosis Diseases 0.000 description 4
- 210000001015 abdomen Anatomy 0.000 description 4
- 210000000038 chest Anatomy 0.000 description 4
- 210000004351 coronary vessel Anatomy 0.000 description 4
- 230000002496 gastric effect Effects 0.000 description 4
- 230000003211 malignant effect Effects 0.000 description 4
- 210000005075 mammary gland Anatomy 0.000 description 4
- 210000004877 mucosa Anatomy 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 210000002784 stomach Anatomy 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 208000034656 Contusions Diseases 0.000 description 2
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 2
- 210000000988 bone and bone Anatomy 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 210000002318 cardia Anatomy 0.000 description 2
- 230000009519 contusion Effects 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 201000005202 lung cancer Diseases 0.000 description 2
- 208000020816 lung neoplasm Diseases 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003387 muscular Effects 0.000 description 2
- 238000013188 needle biopsy Methods 0.000 description 2
- 210000001187 pylorus Anatomy 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000004962 physiological condition Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/117—Tagging; Marking up; Designating a block; Setting of attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/189—Automatic justification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides a system for designing a structured report template based on sub-template semantic relation, which comprises a CDE semantic marking module, a semantic marking module and a display module, wherein the CDE semantic marking module semantically marks each control based on the attribute of each control in each CDE, and the semantic marking comprises morphological expression, pathological morphological characteristics, a logical relation between two CDEs in front and back and a matching relation between the CDE and an external system; the correlation module automatically correlates all CDEs matched with the image examination item based on semantic marks when a doctor opens a certain imaging structured report, and automatically loads the CDE with a logical relation with the diagnosis data based on the diagnosis data of the CDE filled by the doctor; and the template generation module typesets all automatically associated CDEs and all automatically loaded CDEs according to the order filled by doctors, generates an image structured report template and outputs a diagnosis result. The invention also discloses a method for designing the structured report template based on the sub-template semantic relation. The invention improves the efficiency of writing reports and the diagnosis quality of doctors.
Description
Technical Field
The invention relates to the field of medical information, in particular to a system and a method for designing a structured report template based on sub-template semantic relation.
Background
The image structured report is the main development trend of the imaging diagnosis informatization tool. Structuring not only controls the quality of diagnosis, but also generates a large amount of tagged data that can be used for analysis for discovery of new knowledge.
Various kinds of cde (common data element) elements are widely used as basic description elements of image diagnosis reports. Taking MRRT (management of Radiology template) report advocated by RSNA (North American society of Radiology) as an example, even the report design tool obtained by the inventor is designed, and the existing various CDEs can be dynamically applied to combine into a new report template. The report template is characterized in that the report template can be stored in an XML format for free exchange.
This type of template design approach has two significant drawbacks: first, the efficiency of writing reports in actual work is not always good because the imaging diagnosis knowledge is too complex to provide a general-purpose tool for setting the logic built in the template. Second, since there is no gold standard for defining the data dimension range and the built-in logic for a diagnosis report (a report of a non-single disease type) common to parts, it is necessary to list as many CDEs related to an image as possible on the report in order to express complete image discovery. This not only results in a bulky layout, but also is inefficient in filling. Since there are many possible CDEs for each tissue/organ and some are mutually exclusive, the method of listing CDEs as much as possible cannot be implemented in all scenarios.
In the case of smaller number of patients in europe and america and generally higher physician quality, the contradiction of reporting efficiency using MRRT is insignificant, but in china such inefficient templates are hardly acceptable to imaging physicians.
How to build the inference logic as much as possible while keeping the report template size as small as possible is very important for improving the diagnosis efficiency and the diagnosis quality, which is also the core pursuit of report template design.
Disclosure of Invention
In view of the above, the main objective of the present invention is to provide a system and a method for designing a structured report template based on sub-template semantic relations, which can solve the problems of low writing efficiency and low diagnosis efficiency caused by huge image structured report layout in the prior art.
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 designing a structured report template based on sub-template semantic relation, which comprises a CDE semantic marking module, an association module and a template generation module, wherein the CDE semantic marking module is connected with the association module and is used for semantically marking each control based on the attribute of each control in each CDE (sub-template common data element), and the semantic marking comprises morphological expression, pathological morphological characteristics, a logical relation between two CDEs in front and back and a matching relation between the CDE and an external system; the correlation module is respectively connected with the CDE semantic marking module and the template generating module and is used for automatically correlating all CDEs matched with the image examination items based on semantic marks when a doctor opens a certain imaging structured report, and automatically loading the CDEs with logical relations with the diagnosis data based on the diagnosis data of the CDEs filled by the doctor; and the template generation module is connected with the association module and used for typesetting all automatically associated CDEs and all automatically loaded CDEs according to the order filled by doctors, generating an image structured report template and outputting a diagnosis result.
Preferably, the system further comprises a CDE database module connected to the template generation module, and configured to draw a position map of the organ and the tissue based on the morphology of the organ and the tissue, mark each anatomical region on the position map, mark a disease type corresponding to the anatomical region with a graph of a different shape, and store the disease type separately.
Preferably, the association module further comprises an extraction unit, configured to, when the CDE having a matching relationship with the external system is opened by the doctor, automatically extract relevant data of the external system and display the relevant data in a relevant control of the CDE for the doctor to view.
Preferably, the template generation module further includes a first statistical unit for setting a diagnosis result corresponding to the diagnosis data based on the diagnosis data when a frequency with which a certain CDE is used is greater than a first preset threshold.
Preferably, the template generating module further comprises a second statistical unit for setting a diagnosis result corresponding to the diagnosis data based on the diagnosis data when the lesion descriptions of the N sites all use the same CDE; wherein, N is a second preset threshold.
Preferably, the template generating module further comprises a detecting unit, configured to automatically abandon the generation of the visual representation and the diagnostic grammar of a certain CDE when the CDE is not edited.
In another aspect, the present invention further provides a method for designing a structured report template based on sub-template semantic relation, comprising: the CDE semantic labeling module semantically labels each control based on the attribute of each control in each CDE (sub-template common data element), wherein the semantic labels comprise morphological expression, pathological morphological characteristics, a logical relationship between two CDEs before and after, and a matching relationship between the CDE and an external system; when a doctor opens a certain imaging structured report, the association module automatically associates all CDEs matched with the imaging examination item based on the semantic mark, and automatically loads the CDE with a logical relation with the diagnosis data based on the diagnosis data of the CDE filled by the doctor; and the template generation module typesets all automatically associated CDEs and all automatically loaded CDEs according to the order filled by doctors, generates an image structured report template and outputs a diagnosis result.
Preferably, the method further comprises: the CDE graph database module is used for drawing a position graph of the organ and the tissue based on the shape of the organ and the tissue, marking each anatomical part on the position graph, marking the disease type corresponding to the anatomical part by graphs in different shapes, and storing the graphs independently.
Preferably, the method further comprises: when a doctor opens the CDE which has a matching relationship with the external system, the extraction unit in the association module automatically extracts the related data of the external system and displays the related data in the related control of the CDE for the doctor to view.
Preferably, the method further comprises: when the frequency of a certain CDE being used is greater than a first preset threshold, a first statistical unit in the template generation module sets the diagnosis result corresponding to the diagnosis data based on the diagnosis data.
Preferably, the method further comprises: when the lesion descriptions of the N parts all use the same CDE, a second statistical unit in the template generation module sets the diagnosis result corresponding to the diagnosis data based on the diagnosis data; wherein, N is a second preset threshold.
Preferably, the method further comprises: when a certain CDE is not edited, the detection unit in the template generation module automatically abandons the generation of the image expression and the diagnosis grammar of the CDE.
The invention has the technical effects that:
1. because the CDE semantic marking module, the association module and the template generation module are arranged in the invention, the CDE semantic marking module semantically marks each control based on the attribute of each control in each CDE, when a doctor opens a certain imaging structured report, the association module automatically associates all CDEs matched with the imaging examination item based on the semantic marking, and automatically loads the CDE with a logical relation with the diagnosis data based on the diagnosis data of the CDE filled by the doctor; the template generation module typesets all automatically associated CDEs and all automatically loaded CDEs according to the order filled by doctors, generates an image structuralized report template and outputs a diagnosis result, the system carries out semantic marking on various attributes of the CDEs, and is matched with external system information in the imaging examination process, so that the data dimensionality is limited no matter in the special disease field or the general part field, the image report template with sufficient diagnostic logic is built in, the infinite increase of data dimension caused by stacking CDE by inexperienced image structured report template creators is avoided, in the general diagnosis field without gold standard (such as the situation that the CT flat scan of the upper abdomen may involve various diseases of the middle organ), the imaging structured report template with applicable data dimension and higher filling efficiency can be provided, so that the diagnosis efficiency and the diagnosis quality are improved;
2. because the CDE database module is arranged, the position maps of organs and tissues can be drawn based on the forms of the organs and the tissues, the position maps are marked on all anatomical parts, the disease types corresponding to the anatomical parts are marked by the graphs in different shapes, the disease types and the names of the anatomical parts possibly associated with the CDE can be recorded by using graph data logics, the CDE database module is convenient for a doctor to check, and the visibility is higher;
3. because the extraction unit is arranged, when a doctor opens the CDE which is matched with the external system, the relevant data of the external system can be automatically extracted and displayed in the relevant control of the CDE, so that the time for the doctor to input and search the diagnosis data is saved, and the system is more intelligent;
4. because the first statistical unit is arranged, when the frequency of using a certain CDE is greater than the first preset threshold (for example, ten times), the diagnosis result corresponding to the diagnosis data can be set based on the diagnosis data, so that the step of editing the diagnosis result by a doctor is omitted, and meanwhile, the diagnosis logic is sufficient, and the diagnosis precision is improved;
5. because the second statistical unit is arranged, when the lesion descriptions of a plurality of positions use the same CDE, the diagnosis result corresponding to the diagnosis data can be set based on the diagnosis data; the diagnosis result can be automatically generated, the memory of a doctor is reduced, and the doctor can operate conveniently;
6. because the invention sets up the detecting element, when a certain CDE is not edited, give up the image representation and diagnosis grammar of this CDE automatically and produce, has avoided the description of the unnecessary image representation, make the system more humanized.
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 diagram illustrating a system structure for designing a structured report template based on sub-template semantic relations according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating a system structure for designing a structured report template based on sub-template semantic relations according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram of an interface of a CDE description of a morphological manifestation in a system for designing a structured report template based on sub-template semantic relations according to a second embodiment of the present invention;
FIG. 4 is a diagram illustrating a system structure for designing a structured report template based on sub-template semantic relation according to a third embodiment of the present invention;
FIG. 5 is a schematic diagram of an interface of an external system in a system for designing a structured report template based on sub-template semantic relation, which is a pathological system, according to a third embodiment of the invention;
FIG. 6 is a schematic interface diagram of a CDE corresponding to an external system in a system for designing a structured report template based on sub-template semantic relation according to a third embodiment of the present invention;
FIG. 7 is a schematic diagram illustrating an interface of an external system, namely an image AI system, in the system for designing a structured report template based on sub-template semantic relation according to a third embodiment of the present invention;
FIG. 8 is a schematic diagram illustrating an interface of a CDE corresponding to an image AI system as an external system in a system for designing a structured report template based on sub-template semantic relation according to a third embodiment of the present invention;
FIG. 9 is a schematic interface diagram of a CDE corresponding to an external system in a system for designing a structured report template based on sub-template semantic relation according to a third embodiment of the invention;
FIG. 10 is a diagram illustrating a system structure for designing a structured report template based on sub-template semantic relations according to a fourth embodiment of the present invention;
FIG. 11 is a diagram illustrating a system structure for designing a structured report template based on sub-template semantic relations according to a fifth embodiment of the present invention;
FIG. 12 is a diagram illustrating a mammary gland left breast multi-part reference asymmetric CDE interface in a system for designing a structured report template based on sub-template semantic relation according to a fifth embodiment of the invention;
FIG. 13 is a schematic diagram of a CDE interface of gland components in a system for designing a structured report template based on sub-template semantic relation according to a fifth embodiment of the invention;
FIG. 14 is a diagram illustrating a system architecture for designing a structured report template based on sub-template semantic relations according to a sixth embodiment of the invention;
FIG. 15 illustrates a flowchart of a method for designing a structured report template based on sub-template semantic relations in accordance with a seventh embodiment of the invention;
FIG. 16 is a schematic diagram of an interface depicting gastric lesions with a CDE of morphological representation in a method of designing a structured report template based on sub-template semantic links according to a seventh embodiment of the invention;
FIG. 17 is a diagram illustrating an interface of an external system as a pathological system in the method for designing a structured report template based on sub-template semantic relation according to the seventh embodiment of the present invention;
FIG. 18 is a schematic interface diagram of a CDE corresponding to an external system as a pathological system in the method for designing a structured report template based on sub-template semantic relation according to the seventh embodiment of the present invention;
FIG. 19 is a diagram illustrating an interface of an external system, which is an image AI system, in the method for designing a structured report template based on sub-template semantic relations according to the seventh embodiment of the present invention;
FIG. 20 is a schematic diagram illustrating an interface of a CDE corresponding to an external system being an image AI system in the method for designing a structured report template based on sub-template semantic relation according to the seventh embodiment of the invention;
FIG. 21 is a schematic diagram of an interface of a CDE corresponding to an external system as a clinical system in the method for designing a structured report template based on sub-template semantic relation according to the seventh embodiment of the invention;
FIG. 22 is a diagram illustrating a mammary gland left breast multiple part referencing asymmetric CDE interface in a method for designing a structured report template based on sub-template semantic relation according to a seventh embodiment of the invention;
fig. 23 shows a schematic diagram of a gland component CDE interface in a method for designing a structured report template based on sub-template semantic relation according to the seventh 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 diagram illustrating a system structure for designing a structured report template based on sub-template semantic relations according to an embodiment of the present invention; as shown in fig. 1, the system includes: a CDE semantic labeling module 10, an association module 20, and a template generation module 30, wherein,
the CDE semantic labeling module 10 is connected to the association module 20, and is configured to semantically label each control based on an attribute of each control in each CDE (sub-template common data element), where the semantic labeling includes morphological expression, pathological morphological characteristics, a logical relationship between two CDEs before and after, and a matching relationship between a CDE and an external system;
for example, the CDE represented by morphology, the system uses RADLEX and SNOMED ontologies to describe CDE objects and lower-level data attributes, and the universality is stronger.
The logical relationship between the two CDEs can be exemplified by: if the doctor fills in a certain control in the previous CDE, certain controls in the subsequent CDE are automatically inactivated (for example, the controls become grey and can not be edited), so that the doctor is prompted that the controls do not need to be edited, and the editing efficiency of the doctor is improved.
The association module 20 is respectively connected with the CDE semantic mark module 10 and the template generation module 30, and is used for automatically associating all CDEs matched with the image examination items based on semantic marks when a doctor opens a certain imaging structured report, and automatically loading CDEs having a logical relationship with the diagnosis data based on the diagnosis data of the CDEs filled by the doctor;
and the template generating module 30 is connected with the associating module 20 and is used for typesetting all automatically associated CDEs and all automatically loaded CDEs according to the order filled by the doctor, generating an image structured report template and outputting a diagnosis result.
The generated image structured report template may be displayed in a list form at a corresponding position of the image structured report interface, or may be displayed in a tiled form, which is not limited herein.
In different CDEs, for some parts which are complicated in imaging performance and difficult to use limited structural description, clear corresponding relations are established with a specific NLP analysis method according to the CDE semantic meaning, so that the information is also accurately structured and labeled.
For example: under the condition of special complexity of certain lesions, external physical trauma and internal other diseases, the complexity is high under the existing CDE logic, the physical trauma and the internal lump are described, and more association description is not performed temporarily, and a plurality of simple CDEs are continuously used for simply and combinatively describing that 'trauma at a certain part, skin XX, contusion of bones, influence on a lung, and XX lump in the lung need to be performed by combination of XXX scheme'. In this case, in the simple CDE, the known codes are configured to correspond to NLPs, so as to perform NLP analysis.
The embodiment of the invention is provided with a CDE semantic marking module, an association module and a template generation module, wherein the CDE semantic marking module semantically marks each control based on the attribute of each control in each CDE, when a doctor opens a certain image structured report, the association module automatically associates all CDEs matched with the image examination item based on the semantic marking, and automatically loads the CDE with a logical relation with the diagnosis data based on the diagnosis data of the CDE filled by the doctor; the template generation module typesets all automatically associated CDEs and all automatically loaded CDEs according to the order filled by doctors, generates an image structuralized report template and outputs a diagnosis result, the system carries out semantic marking on various attributes of the CDEs, and is matched with external system information in the imaging examination process, so that the data dimensionality is limited no matter in the special disease field or the general part field, the image report template with sufficient diagnostic logic is built in, the infinite increase of data dimension caused by stacking CDE by inexperienced image structured report template creators is avoided, in the general diagnosis field without gold standard (such as the situation that the CT flat scan of the upper abdomen can involve various diseases of the middle organ), the imaging structured report template with applicable data dimension and higher filling efficiency can be provided, so that the diagnosis efficiency and the diagnosis quality are improved.
Example two
FIG. 2 is a diagram illustrating a system structure for designing a structured report template based on sub-template semantic relations according to a second embodiment of the present invention; as shown in fig. 2, the system further includes a CDE database module 40 connected to the template generating module 30, for drawing a position map of the organ and the tissue based on the morphology of the organ and the tissue, marking each anatomical region on the position map, labeling the disease type corresponding to the anatomical region with graphs of different shapes, and storing the graphs separately.
For example, a zigzag type of label corresponds to a disease type of malignant tumor, a smooth type of label corresponds to a benign tumor, and so on.
Fig. 3 is a schematic interface diagram illustrating CDE description of gastric lesion based on morphological representation in a system for designing a structured report template based on sub-template semantic association according to a second embodiment of the present invention, as shown in fig. 3, the gastric lesion, and the region description area includes:
the large part (stomach body, cardia, pylorus, fundus stomach, etc.)
Elbow (big elbow side, small elbow side)
Inner and outer of membranous layer (muscular layer, mucosa layer, serosa lower layer, serosa outer layer)
The disease type can be shown from the position map on the right.
The embodiment of the invention is provided with the CDE graph database module, can draw the position graphs of organs and tissues based on the shapes of the organs and the tissues, marks all anatomical parts on the position graphs, marks the disease types corresponding to the anatomical parts by graphs in different shapes, and can record the disease types and the names of the anatomical parts possibly associated with CDE by utilizing graph data logic, thereby being convenient for a doctor to check and having higher visibility.
EXAMPLE III
FIG. 4 is a diagram illustrating a system structure for designing a structured report template based on sub-template semantic relation according to a third embodiment of the present invention; as shown in fig. 4, the association module 20 further includes an extraction unit 202, configured to, when a CDE having a matching relationship with an external system is opened by a doctor, automatically extract relevant data of the external system and display the relevant data in a relevant control of the CDE for the doctor to view.
The external system may be a pathological system, an imaging AI system, a clinical system, etc.
FIG. 5 is a schematic diagram of an interface of an external system in a system for designing a structured report template based on sub-template semantic relation, which is a pathological system, according to a third embodiment of the invention; FIG. 6 is a schematic interface diagram of a CDE corresponding to an external system in a system for designing a structured report template based on sub-template semantic relation according to a third embodiment of the present invention;
as shown in figure 5 and figure 6, the case system is to take small pieces from the fundus mucosa of the gastroscope, the case analysis is calcified lumps, and the pu value is equal to 5 cc. The CDE of fig. 6, which is the morphological feature used exclusively to describe the pathological state, is cited only to illustrate the presence of a pathological state, and can be used to describe both normal physiological states and pathological states beyond certain range values, which are considered to describe pathological features.
If the value exceeds the normal value (6cc) set for pu, the test piece is determined to be positive. The pathological result of fig. 5 is pu value equal to 5cc, and the result is automatically shown in CDE of fig. 6.
FIG. 7 is a schematic diagram illustrating an interface of an external system, namely an image AI system, in the system for designing a structured report template based on sub-template semantic relation according to a third embodiment of the present invention; FIG. 8 is a schematic diagram illustrating an interface of a CDE corresponding to an image AI system as an external system in a system for designing a structured report template based on sub-template semantic relation according to a third embodiment of the present invention; as shown in fig. 7, the data management interface of the lung nodule image AI is shown in fig. 8, which is an interface of the lung nodule CDE, the lung nodule CDE is automatically matched with the lung nodule screening image AI of a certain manufacturer, and after receiving the result of the image AI, the CDEs and corresponding results of a plurality of lung nodules are automatically added to the image structured report.
FIG. 9 is a schematic interface diagram of a CDE corresponding to an external system in a system for designing a structured report template based on sub-template semantic relation according to a third embodiment of the invention; as shown in fig. 9, matching of the CDE with the clinical system, automatically extracting clinical context information and populating a corresponding control of the CDE, for example, a lung cancer screening report, requires providing relevant clinical information as shown in fig. 9.
The embodiment of the invention is provided with the extraction unit, when a doctor opens the CDE which has a matching relation with the external system, the relevant data of the external system can be automatically extracted and displayed in the relevant control of the CDE, so that the time for the doctor to input and search the diagnosis data is saved, and the system is more intelligent.
Example four
FIG. 10 is a diagram illustrating a system structure for designing a structured report template based on sub-template semantic relations according to a fourth embodiment of the present invention; as shown in fig. 10, the template generating module 30 further includes a first statistical unit 302 for setting a diagnostic result corresponding to a certain CDE based on the diagnostic data when the frequency with which the diagnostic data is used is greater than a first preset threshold.
For example: chest lung nodule CDE references more than 10 (first preset threshold): the setting of the first preset threshold is personalized according to medical institutions and medical knowledge, and is not limited herein.
If 8 of the 4 classes have Lung-RADS scores of more than or equal to, the diagnosis result comprises multiple and malignant, and generation of multiple malignant Lung is not excluded, and further CT examination is recommended. Needle biopsy if necessary. "
If the Lung-RADS scores are all less than or equal to 3 types, the diagnosis is that the property is undetermined, and the reexamination is recommended after 6 months. "
If the Lung-RADS scores are less than or equal to 1 category, the diagnosis is that the benign possibility is high, and the reexamination is recommended after 1 month. "
Wherein setting a diagnosis result corresponding to the diagnosis data based on the diagnosis data is performed according to a medical institution and medical knowledge.
The embodiment of the invention provides the first statistical unit, when the frequency of using a certain CDE is greater than the first preset threshold (for example, ten times), the diagnosis result corresponding to the diagnosis data can be set based on the diagnosis data, the step of editing the diagnosis result by a doctor is omitted, and meanwhile, the diagnosis logic is sufficient, and the diagnosis precision is provided.
EXAMPLE five
FIG. 11 is a diagram illustrating a system structure for designing a structured report template based on sub-template semantic relations according to a fifth embodiment of the present invention; as shown in fig. 11, the template generating module 30 further includes a second statistical unit 304, configured to set a diagnosis result corresponding to the diagnosis data based on the diagnosis data when the lesion descriptions of the N sites all use the same CDE; wherein, N is a second preset threshold.
For example, when multiple coronary artery sites are described, if thrombus CDE and stent CDE are cited in all 3 sites (the second preset threshold is 3), the diagnosis is established and statistics are generated, and "thrombus is found in all 3 coronary artery sites, stent treatment is recommended, and the detailed description shows the performance. The setting of the second preset threshold is personalized according to medical institutions and medical knowledge, and is not limited herein.
FIG. 12 is a diagram illustrating a mammary gland left breast multi-part reference asymmetric CDE interface in a system for designing a structured report template based on sub-template semantic relation according to a fifth embodiment of the invention; FIG. 13 is a schematic diagram of a CDE interface of gland components in a system for designing a structured report template based on sub-template semantic relation according to a fifth embodiment of the invention; as shown in fig. 12, if the left breast rich part of the breast refers to an asymmetric CDE (check out the "asymmetric" preceding box), then the "non-uniform gland" is automatically selected in the gland component CDE, as shown in fig. 13.
The embodiment of the invention is provided with a second statistical unit, when the lesion descriptions of a plurality of parts all use the same CDE, the diagnosis result corresponding to the diagnosis data can be set based on the diagnosis data; the diagnosis result can be automatically generated, the memory of the doctor is reduced, and the doctor can operate conveniently.
EXAMPLE six
FIG. 14 is a diagram illustrating a system architecture for designing a structured report template based on sub-template semantic relations according to a sixth embodiment of the invention; as shown in fig. 14, the template generating module 30 further includes a detecting unit 306, which is used to automatically abandon the generation of the image representation and the diagnosis grammar of a certain CDE when the CDE is not edited.
For example, after the chest fracture CDE is added to the image structured report, if the doctor does not edit the CDE, the doctor judges that the CDE is not used, and the image representation and the generation of the diagnosis grammar of the CDE are automatically abandoned.
The embodiment of the invention is provided with the detection unit, when a certain CDE is not edited, the generation of the image expression and the diagnosis grammar of the CDE is automatically abandoned, the unnecessary description of the image expression is avoided, and the system is more humanized.
EXAMPLE seven
FIG. 15 illustrates a flowchart of a method for designing a structured report template based on sub-template semantic relations in accordance with a seventh embodiment of the invention; as shown in fig. 15, the method includes the steps of:
step S701, the CDE semantic marking module semantically marks each control based on the attribute of each control in each CDE (sub-template common data element), wherein the semantic marking comprises morphological expression, pathological morphological characteristics, a logical relation between two CDEs in front and back, and a matching relation between the CDE and an external system;
for example, the CDE represented by morphology, the system uses RADLEX and SNOMED ontologies to describe CDE objects and lower-level data attributes, and the universality is stronger.
The logical relationship between the two CDEs can be exemplified by: if the doctor fills in a certain control in the previous CDE, certain controls in the subsequent CDE are automatically inactivated (for example, the controls become grey and can not be edited), so that the doctor is prompted that the controls do not need to be edited, and the editing efficiency of the doctor is improved.
Step S702, when a doctor opens a certain imaging structured report, the correlation module automatically correlates all CDEs matched with the imaging examination item based on the semantic mark, and automatically loads the CDE having a logical relationship with the diagnosis data based on the diagnosis data of the CDE filled by the doctor;
and step S703, the template generation module typesets all the automatically associated CDEs and all the automatically loaded CDEs according to the order filled by the doctor, generates an image structured report template and outputs a diagnosis result.
The generated image structured report template may be displayed in a list form at a corresponding position of the image structured report interface, or may be displayed in a tiled form, which is not limited herein.
In different CDEs, for some parts which are complicated in imaging performance and difficult to use limited structural description, clear corresponding relations are established with a specific NLP analysis method according to the CDE semantic meaning, so that the information is also accurately structured and labeled.
For example: under the condition of special complexity of certain lesions, external physical trauma and internal other diseases, the complexity is high under the existing CDE logic, the physical trauma and the internal lump are described, and more association description is not performed temporarily, and a plurality of simple CDEs are continuously used for simply and combinatively describing that 'trauma at a certain part, skin XX, contusion of bones, influence on a lung, and XX lump in the lung need to be performed by combination of XXX scheme'. In this case, in the simple CDE, the known codes are configured to correspond to NLPs, so as to perform NLP analysis.
Wherein, the method also comprises: the CDE graph database module is used for drawing a position graph of the organ and the tissue based on the shape of the organ and the tissue, marking each anatomical part on the position graph, marking the disease type corresponding to the anatomical part by graphs in different shapes, and storing the graphs independently.
For example, a zigzag type of label corresponds to a disease type of malignant tumor, a smooth type of label corresponds to a benign tumor, and so on.
Fig. 16 is a schematic diagram illustrating an interface of a CDE description of a morphological expression in a method for designing a structured report template based on sub-template semantic relation according to a seventh embodiment of the present invention, as shown in fig. 16, the gastric lesion, and the region description area includes:
the large part (stomach body, cardia, pylorus, fundus stomach, etc.)
Elbow (big elbow side, small elbow side)
Inner and outer of membranous layer (muscular layer, mucosa layer, serosa lower layer, serosa outer layer)
The disease type can be shown from the position map on the right.
Wherein, the method also comprises: when a doctor opens the CDE which has a matching relationship with the external system, the extraction unit in the association module automatically extracts the related data of the external system and displays the related data in the related control of the CDE for the doctor to view.
FIG. 17 is a diagram illustrating an interface of an external system as a pathological system in the method for designing a structured report template based on sub-template semantic relation according to the seventh embodiment of the present invention; FIG. 18 is a schematic interface diagram of a CDE corresponding to an external system as a pathological system in the method for designing a structured report template based on sub-template semantic relation according to the seventh embodiment of the present invention;
as shown in FIG. 17 and FIG. 18, the case system is to take small pieces from the fundus mucosa of the gastroscope, and the case analysis is calcified lumps, pu value is equal to 5 cc. The CDE of fig. 18, which is a morphological feature specifically used to describe a pathological condition, is cited only to illustrate the presence of a pathological condition, and can be used to describe both normal physiological conditions and pathological conditions outside certain ranges of values beyond which a pathological feature is considered to be described.
If the value exceeds the normal value (6cc) set for pu, the test piece is determined to be positive. The pathological result of fig. 17 is pu value equal to 5cc, and the result is automatically shown in CDE of fig. 18.
FIG. 19 is a diagram illustrating an interface of an external system, which is an image AI system, in the method for designing a structured report template based on sub-template semantic relations according to the seventh embodiment of the present invention; FIG. 20 is a schematic diagram illustrating an interface of a CDE corresponding to an external system being an image AI system in the method for designing a structured report template based on sub-template semantic relation according to the seventh embodiment of the invention; as shown in fig. 19, the data management interface of the lung nodule image AI is shown in fig. 20, which is an interface of the lung nodule CDE, the lung nodule CDE is automatically matched with the lung nodule screening image AI of a certain manufacturer, and after receiving the result of the image AI, the CDEs and corresponding results of a plurality of lung nodules are automatically added to the image structured report.
FIG. 21 is a schematic diagram of an interface of a CDE corresponding to an external system as a clinical system in the method for designing a structured report template based on sub-template semantic relation according to the seventh embodiment of the invention; as shown in fig. 21, matching of the CDE with the clinical system, automatically extracting clinical context information and populating a corresponding control of the CDE, for example, a lung cancer screening report, requires providing relevant clinical information as shown in fig. 21.
Wherein, the method also comprises: when the frequency of a certain CDE being used is greater than a first preset threshold, a first statistical unit in the template generation module sets the diagnosis result corresponding to the diagnosis data based on the diagnosis data.
For example: chest lung nodule CDE references more than 10 (first preset threshold): the setting of the first preset threshold is personalized according to medical institutions and medical knowledge, and is not limited herein.
If 8 of the 4 classes have Lung-RADS scores of more than or equal to, the diagnosis result comprises multiple and malignant, and generation of multiple malignant Lung is not excluded, and further CT examination is recommended. Needle biopsy if necessary. "
If the Lung-RADS scores are all less than or equal to 3 types, the diagnosis is that the property is undetermined, and the reexamination is recommended after 6 months. "
If the Lung-RADS scores are less than or equal to 1 category, the diagnosis is that the benign possibility is high, and the reexamination is recommended after 1 month. "
Wherein setting a diagnosis result corresponding to the diagnosis data based on the diagnosis data is performed according to a medical institution and medical knowledge.
Wherein, the method also comprises: when the lesion descriptions of the N parts all use the same CDE, a second statistical unit in the template generation module sets the diagnosis result corresponding to the diagnosis data based on the diagnosis data; wherein, N is a second preset threshold.
For example, when multiple coronary artery sites are described, if thrombus CDE and stent CDE are cited in all 3 sites (the second preset threshold is 3), the diagnosis is established and statistics are generated, and "thrombus is found in all 3 coronary artery sites, stent treatment is recommended, and the detailed description shows the performance. The setting of the second preset threshold is personalized according to medical institutions and medical knowledge, and is not limited herein.
FIG. 22 is a diagram illustrating a mammary gland left breast multiple part referencing asymmetric CDE interface in a method for designing a structured report template based on sub-template semantic relation according to a seventh embodiment of the invention; FIG. 23 is a schematic diagram of a gland component CDE interface in a method for designing a structured report template based on sub-template semantic relation according to a seventh embodiment of the invention; as shown in fig. 22, if the left breast rich part of the breast refers to an asymmetric CDE (check out the "asymmetric" preceding box), then the "non-uniform gland" is automatically selected in the gland component CDE, as shown in fig. 23.
Wherein, the method also comprises: when a certain CDE is not edited, the detection unit in the template generation module automatically abandons the generation of the image expression and the diagnosis grammar of the CDE.
For example, after the chest fracture CDE is added to the image structured report, if the doctor does not edit the CDE, the doctor judges that the CDE is not used, and the image representation and the generation of the diagnosis grammar of the CDE are automatically abandoned.
The CDE semantic marking module semantically marks each control based on the attribute of each control in each CDE, when a doctor opens a certain imaging structured report, the correlation module automatically correlates all CDEs matched with the imaging examination item based on the semantic marking, and automatically loads the CDE having a logical relation with the diagnosis data based on the diagnosis data of the CDE filled by the doctor; the template generation module typesets all automatically associated CDEs and all automatically loaded CDEs according to the order filled by doctors, generates an image structuralized report template and outputs a diagnosis result, the system carries out semantic marking on various attributes of the CDEs, and is matched with external system information in the imaging examination process, so that the data dimensionality is limited no matter in the special disease field or the general part field, the image report template with sufficient diagnostic logic is built in, the infinite increase of data dimension caused by stacking CDE by inexperienced image structured report template creators is avoided, in the general diagnosis field without gold standard (such as the situation that the CT flat scan of the upper abdomen may involve various diseases of the middle organ), the imaging structured report template with applicable data dimension and higher filling efficiency can be provided, so that the diagnosis efficiency and the diagnosis quality are improved; the CDE graph database module in the embodiment of the invention can draw the position graphs of organs and tissues based on the forms of the organs and the tissues, mark the position graphs on all anatomical parts, mark the disease types corresponding to the anatomical parts with graphs in different shapes, and record the disease types and the names of the anatomical parts possibly associated with CDE by utilizing graph data logic, thereby being convenient for a doctor to check and having higher visibility; according to the extraction unit in the embodiment of the invention, when a doctor opens the CDE which is in a matching relation with the external system, the relevant data of the external system can be automatically extracted and displayed in the relevant control of the CDE, so that the time for the doctor to input and search the diagnosis data is saved, and the system is more intelligent; in the first statistical unit in the embodiment of the present invention, when the frequency of a certain CDE being used is greater than a first preset threshold (for example, ten times), the diagnostic result corresponding to the diagnostic data may be set based on the diagnostic data, so that the step of a doctor editing the diagnostic result is omitted, and meanwhile, the diagnostic logic is sufficient, and the diagnostic accuracy is provided; the second statistical unit in the embodiment of the present invention may set the diagnosis result corresponding to the diagnosis data based on the diagnosis data when the same CDE is used for lesion descriptions of a plurality of sites; the diagnosis result can be automatically generated, the memory of a doctor is reduced, and the doctor can operate conveniently; when a certain CDE is not edited, the detection unit in the embodiment of the invention automatically abandons the generation of the image expression and the diagnosis grammar of the CDE, avoids the description of unnecessary image expression and ensures that the system is more humanized.
From the above description, it can be seen that the above-described embodiments of the present invention achieve the following technical effects: the embodiment of the invention is provided with a CDE semantic marking module, an association module and a template generation module, wherein the CDE semantic marking module semantically marks each control based on the attribute of each control in each CDE, when a doctor opens a certain image structured report, the association module automatically associates all CDEs matched with the image examination item based on the semantic marking, and automatically loads the CDE with a logical relation with the diagnosis data based on the diagnosis data of the CDE filled by the doctor; the template generation module typesets all automatically associated CDEs and all automatically loaded CDEs according to the order filled by doctors, generates an image structuralized report template and outputs a diagnosis result, the system carries out semantic marking on various attributes of the CDEs, and is matched with external system information in the imaging examination process, so that the data dimensionality is limited no matter in the special disease field or the general part field, the image report template with sufficient diagnostic logic is built in, the infinite increase of data dimension caused by stacking CDE by inexperienced image structured report template creators is avoided, in the general diagnosis field without gold standard (such as the situation that the CT flat scan of the upper abdomen may involve various diseases of the middle organ), the imaging structured report template with applicable data dimension and higher filling efficiency can be provided, so that the diagnosis efficiency and the diagnosis quality are improved; the embodiment of the invention is provided with the CDE graph database module, so that the position graphs of organs and tissues can be drawn based on the forms of the organs and the tissues, the position graphs are marked on all anatomical parts, the disease types corresponding to the anatomical parts are marked by graphs in different shapes, the disease types and the names of the anatomical parts possibly associated with CDE can be recorded by utilizing graph data logic, the CDE graph database module is convenient for a doctor to check, and the visibility is higher; the embodiment of the invention is provided with the extraction unit, when a doctor opens the CDE which has a matching relation with the external system, the relevant data of the external system can be automatically extracted and displayed in the relevant control of the CDE, so that the time for the doctor to input and search the diagnosis data is saved, and the system is more intelligent; the embodiment of the invention is provided with the first statistical unit, when the frequency of using a certain CDE is greater than a first preset threshold (for example, ten times), the diagnostic result corresponding to the diagnostic data can be set based on the diagnostic data, so that the step of editing the diagnostic result by a doctor is omitted, meanwhile, the diagnostic logic is sufficient, and the diagnostic accuracy is improved; the embodiment of the invention is provided with a second statistical unit, when the lesion descriptions of a plurality of parts all use the same CDE, the diagnosis result corresponding to the diagnosis data can be set based on the diagnosis data; the diagnosis result can be automatically generated, the memory of a doctor is reduced, and the doctor can operate conveniently; the embodiment of the invention is provided with the detection unit, when a certain CDE is not edited, the generation of the image expression and the diagnosis grammar of the CDE is automatically abandoned, the unnecessary description of the image expression is avoided, and the system is more humanized.
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 (12)
1. A system for designing a structured report template based on sub-template semantic relation is characterized by comprising a CDE semantic labeling module, an association module and a template generation module, wherein,
the CDE semantic labeling module is connected with the association module and is used for semantically labeling each control based on the attribute of each control in each CDE (sub-template common data element), wherein the semantic labeling comprises morphological expression, pathological morphological characteristics, a logical relation between the front CDE and the back CDE and a matching relation between the CDE and an external system;
the correlation module is respectively connected with the CDE semantic mark module and the template generation module and is used for automatically correlating all the CDEs matched with the image examination item based on the semantic marks when a doctor opens a certain imaging structured report, and automatically loading the CDEs having a logical relation with the diagnosis data based on the diagnosis data of the CDEs filled by the doctor;
and the template generation module is connected with the association module and used for typesetting all the automatically associated CDEs and all the automatically loaded CDEs according to the order filled by doctors, generating an image structured report template and outputting a diagnosis result.
2. The system for designing a structured report template based on sub-template semantic relation according to claim 1, further comprising a CDE database module connected to the template generation module for drawing a position map of the organ and the tissue based on the morphology of the organ and the tissue, labeling each anatomical region of the position map, labeling the disease type corresponding to the anatomical region with different shapes of the graphics, and storing the labeled disease type separately.
3. The system for designing a structured report template based on sub-template semantic relation as claimed in claim 1, wherein the association module further comprises an extraction unit for automatically extracting relevant data of the external system and displaying the relevant data in a relevant control of the CDE for a doctor to view when the doctor opens the CDE having a matching relationship with the external system.
4. The system for designing a structured report template based on sub-template semantic link according to claim 1, wherein the template generating module further comprises a first statistical unit for setting the diagnosis result corresponding to a certain CDE based on the diagnosis data when the frequency with which the diagnosis data is used is greater than a first preset threshold.
5. The system for designing a structured report template based on sub-template semantic relation according to claim 1, wherein the template generating module further comprises a second statistical unit for setting the diagnosis result corresponding to the diagnosis data based on the diagnosis data when the same CDE is used for lesion descriptions of N sites; wherein, N is a second preset threshold.
6. The system for designing a structured report template based on sub-template semantic link according to claim 1, wherein the template generating module further comprises a detecting unit for automatically abandoning the generation of the visual representation and the diagnosis grammar of a certain CDE when the CDE is not edited.
7. A method for designing a structured report template based on sub-template semantic relations, the method comprising:
the CDE semantic labeling module semantically labels each control based on the attribute of each control in each CDE (sub-template common data element), wherein the semantic labels comprise morphological expression, pathological morphological characteristics, a logical relationship between a front CDE and a back CDE and a matching relationship between the CDE and an external system;
when a doctor opens a certain imaging structured report, the association module automatically associates all the CDEs matched with the imaging examination item based on the semantic mark, and automatically loads the CDEs having a logical relationship with the diagnosis data based on the diagnosis data of the CDEs filled by the doctor;
and the template generation module typesets all the automatically associated CDEs and all the automatically loaded CDEs according to the order filled by doctors, generates an image structured report template and outputs a diagnosis result.
8. The method for designing a structured report template based on sub-template semantic links according to claim 7, further comprising: and the CDE graph database module is used for drawing a position graph of the organ and the tissue based on the shape of the organ and the tissue, marking each anatomical part on the position graph, marking the disease type corresponding to the anatomical part by graphs in different shapes, and storing the graphs independently.
9. The method for designing a structured report template based on sub-template semantic links according to claim 7, further comprising: when a doctor opens the CDE which is in matching relation with the external system, the extraction unit in the association module automatically extracts the related data of the external system and displays the related data in the related control of the CDE for the doctor to view.
10. The method for designing a structured report template based on sub-template semantic links according to claim 7, further comprising: when the frequency of a certain CDE being used is greater than a first preset threshold, a first statistical unit in the template generation module sets the diagnosis result corresponding to the diagnosis data based on the diagnosis data.
11. The method for designing a structured report template based on sub-template semantic links according to claim 7, further comprising: when the same CDE is used for the lesion descriptions of the N parts, a second statistical unit in the template generation module sets the diagnosis result corresponding to the diagnosis data based on the diagnosis data; wherein, N is a second preset threshold.
12. The method for designing a structured report template based on sub-template semantic links according to claim 7, further comprising: when a certain CDE is not edited, the detection unit in the template generation module automatically abandons the generation of the image expression and the diagnosis grammar of the CDE.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011589066.0A CN112786162B (en) | 2020-12-28 | System and method for designing structured report template based on sub-template semantic association |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011589066.0A CN112786162B (en) | 2020-12-28 | System and method for designing structured report template based on sub-template semantic association |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112786162A true CN112786162A (en) | 2021-05-11 |
| CN112786162B CN112786162B (en) | 2024-06-21 |
Family
ID=
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114446467A (en) * | 2021-12-31 | 2022-05-06 | 华中科技大学同济医学院附属协和医院 | Lung function quantitative analysis method based on structured report template |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110931095A (en) * | 2018-09-19 | 2020-03-27 | 北京赛迈特锐医疗科技有限公司 | System and method based on DICOM image annotation and structured report association |
| CN111667897A (en) * | 2020-04-24 | 2020-09-15 | 杭州深睿博联科技有限公司 | Structured report system of image diagnosis result |
| CN111681737A (en) * | 2020-05-07 | 2020-09-18 | 陈�峰 | Structured report system and method for constructing liver cancer image database |
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110931095A (en) * | 2018-09-19 | 2020-03-27 | 北京赛迈特锐医疗科技有限公司 | System and method based on DICOM image annotation and structured report association |
| CN111667897A (en) * | 2020-04-24 | 2020-09-15 | 杭州深睿博联科技有限公司 | Structured report system of image diagnosis result |
| CN111681737A (en) * | 2020-05-07 | 2020-09-18 | 陈�峰 | Structured report system and method for constructing liver cancer image database |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114446467A (en) * | 2021-12-31 | 2022-05-06 | 华中科技大学同济医学院附属协和医院 | Lung function quantitative analysis method based on structured report template |
| CN114446467B (en) * | 2021-12-31 | 2023-09-12 | 华中科技大学同济医学院附属协和医院 | Pulmonary function quantitative analysis method based on structured report template |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109065110B (en) | Method for automatically generating medical image diagnosis report based on deep learning method | |
| US10275876B2 (en) | Methods and systems for automatically selecting an implant for a patient | |
| US20190214118A1 (en) | Automated anatomically-based reporting of medical images via image annotation | |
| US20110075901A1 (en) | Medical image processing apparatus and method and computer-readable recording medium | |
| US10729396B2 (en) | Tracking anatomical findings within medical images | |
| EP2478834A1 (en) | Radiograph interpretation report creation device, method, and program | |
| WO2018042272A1 (en) | Updating probabilities of conditions based on annotations on medical images | |
| CN110517238B (en) | AI three-dimensional reconstruction and human-computer interaction visualization network system for CT medical image | |
| JP6657210B2 (en) | Picture archiving system with text image linking based on text recognition | |
| KR102366290B1 (en) | Medical machine learning system | |
| JP2015208385A (en) | Medical image information system, medical image information processing method and program | |
| JP6945474B2 (en) | Learning data creation support device, learning data creation support method, and learning data creation support program | |
| CN109192261B (en) | Information processing method and device, electronic device and storage medium | |
| US20160350484A1 (en) | Method and apparatus for managing medical metadatabase | |
| US20040181431A1 (en) | Device for generating standardized medical findings | |
| EP2656243B1 (en) | Generation of pictorial reporting diagrams of lesions in anatomical structures | |
| CN113113100B (en) | Method and device for making medical image inspection report | |
| CN112786162A (en) | System and method for designing structured report template based on sub-template semantic relation | |
| CN112786162B (en) | System and method for designing structured report template based on sub-template semantic association | |
| CN111223555B (en) | DICOM expansion method for medical image artificial intelligence auxiliary diagnosis result representation | |
| Kumar et al. | Comparative Study of Liver Segmentation using U-Net and ResNet50 | |
| CN206557778U (en) | System based on graphical writing structured report | |
| CN110534182A (en) | Display methods, display equipment and the storage medium of medical image | |
| Melvin et al. | Visual Question Answering using Data Mining Techniques for Skeletal Scintigraphy in medical domain-VQADMSS | |
| Vo et al. | Multimodal breast lesion classification using cross-attention deep networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |