CN112562816A - System and method for correspondence and evaluation of diagnosis result and pathological result of tumor image report - Google Patents
System and method for correspondence and evaluation of diagnosis result and pathological result of tumor image reportDownload PDFInfo
- Publication number
- CN112562816A CN112562816ACN202011268228.0ACN202011268228ACN112562816ACN 112562816 ACN112562816 ACN 112562816ACN 202011268228 ACN202011268228 ACN 202011268228ACN 112562816 ACN112562816 ACN 112562816A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- result
- code
- image
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The invention relates to the field of medical information, in particular to a system and a method for correspondence and evaluation of a diagnosis result and a pathological result of a tumor image report.
Background
The image diagnosis report corresponds to the clinical end result of the patient, is a closed-loop feedback link of the work of an imaging doctor, and is a core means for finding diagnosis cognitive defects and improving diagnosis confidence. The imaging diagnosis of the tumor is high in complexity, has a large influence on a clinical treatment scheme, has a large influence on the mind and body of a patient, is more beneficial and is the key point of attention in the imaging diagnosis result feedback link. The diagnosis results reported by the tumor images often correspond to pathological results.
At present, no automatic method exists for the correspondence between the image diagnosis result and the pathological result, and the correspondence is generally completed by manual sampling of doctors with certain seniority arranged in an image department. The complexity of this service is: some patients have image examination but no pathological examination; patients with pathological results are not always subjected to image examination; patients with pathological results, the imaging examination does not necessarily diagnose the disease, and may be physical examination; different term systems are used between the image diagnosis conclusion and the pathological result, semantic understanding exists, manual judgment needs experience, and the manual and sampling method is low in efficiency and has many errors.
Disclosure of Invention
In view of the above, the present invention is directed to a system and a method for associating and evaluating a diagnosis result and a pathological result of a tumor image report, which can solve the problems of low work efficiency and high error rate caused by the manual and sampling correspondence between the diagnosis result and the pathological result and the different terminology systems used between the diagnosis result and the pathological result in the prior art.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
on one hand, the invention provides a system for correspondence and evaluation of tumor image report diagnosis results and pathological results, which comprises a pathological module, an image report screening module, a first extraction module, a second extraction module, a diagnosis quality judgment module and a judgment result display module, wherein the pathological module is respectively connected with the image report screening module and the second extraction module and is used for storing relevant data of pathological examination of a patient; the image report screening module is respectively connected with the pathology module and the first extraction module and is used for screening all tumor image structured reports of the parts of the image examination items of the patient in a preset time period, including the material-taking parts of the pathology examination, based on the pathology examination of the patient, and independently storing each tumor image structured report; wherein the pathological examination does not include intraoperative frozen pathological examination; the first extraction module is respectively connected with the image report screening module and the diagnosis quality judgment module and is used for identifying an image examination part and a diagnosis result based on each tumor image structured report, wherein the diagnosis result comprises a first disease type and a first diagnosis type, and extracting a code of the image examination part and a code of the first diagnosis type; the second extraction module is respectively connected with the pathology module and the diagnosis quality judgment module and is used for identifying a material taking part and a pathology result of the pathology examination based on relevant data of the pathology examination, wherein the pathology result comprises a second disease type and a second diagnosis type, and extracting a code of the material taking part and a code of the second diagnosis type; the diagnosis quality judgment module is respectively connected with the first extraction module, the second extraction module and the judgment result display module and is used for judging the conformity of the diagnosis result, and the judgment rule is as follows: when the code of the image inspection part does not correspond to the code of the material-taking part, the output judgment result is: the diagnosis result is non-compliance; when the code of the image examination part corresponds to the code of the material taking part and the first disease type is matched with the second disease type, outputting a judgment result as follows: the diagnosis result is coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, but the code of the first diagnosis type corresponds to the code of the second diagnosis type, the output judgment result is: the diagnosis result is partial coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, and the code of the first diagnosis type is not matched with the code of the second diagnosis type, the output judgment result is as follows: the diagnosis result is non-compliance; and the judgment result display module is connected with the diagnosis quality judgment module and used for receiving the judgment result and displaying the judgment result in the patient list for a doctor to check.
Preferably, when the diagnosis results are plural, the first extraction module further includes a diagnosis result screening unit, configured to select a diagnosis result meeting a preset condition based on the preset condition, define the diagnosis result meeting the preset condition as a first diagnosis result, and send a code of the first diagnosis type in each first diagnosis result to the diagnosis quality judgment module; at this time, the diagnosis quality judgment module is further configured to respectively judge the compliance of each first diagnosis result, and output the judgment result with the highest compliance to the judgment result display module.
Preferably, the diagnosis quality judgment module further comprises a marking unit, which is used for automatically marking the tumor image structured report when the code of the image examination part and/or the code of the material-taking part cannot be received, and sending the marked result to the judgment result display module; at this time, the judgment result display module is further configured to display the labeled result in the patient list for a doctor to view.
Preferably, the judgment result display module further includes an error prompt unit, configured to automatically display the pathological result corresponding to the tumor image structured report with the diagnosis result of partial coincidence or the diagnosis result of non-coincidence in a corresponding view angle of the patient list for a doctor to view.
On the other hand, the invention also provides a method for corresponding and evaluating the diagnosis result and the pathological result of the tumor image report, which comprises the following steps: the pathology module stores data related to a pathological examination of a patient; the image report screening module screens all tumor image structured reports of the parts of the image examination items of the patient in a preset time period, including the material-taking parts of the pathological examination, based on the pathological examination of the patient, and stores each tumor image structured report separately; wherein the pathological examination does not include intraoperative frozen pathological examination; the first extraction module identifies an image examination part and a diagnosis result based on each tumor image structured report, wherein the diagnosis result comprises a first disease type and a first diagnosis type, and extracts the code of the image examination part and the code of the first diagnosis type; the second extraction module identifies a material drawing part and a pathological result of the pathological examination based on the relevant data of the pathological examination, wherein the pathological result comprises a second disease type and a second diagnosis type, and extracts the code of the material drawing part and the code of the second diagnosis type; the diagnosis quality judgment module judges the conformity of the diagnosis result, and the judgment rule is as follows: when the code of the image inspection part does not correspond to the code of the material-taking part, the output judgment result is: the diagnosis result is non-compliance; when the code of the image examination part corresponds to the code of the material taking part and the first disease type is matched with the second disease type, outputting a judgment result as follows: the diagnosis result is coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, but the code of the first diagnosis type corresponds to the code of the second diagnosis type, the output judgment result is: the diagnosis result is partial coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, and the code of the first diagnosis type is not matched with the code of the second diagnosis type, the output judgment result is as follows: the diagnosis result is non-compliance; and the judgment result display module receives the judgment result and displays the judgment result in the patient list for a doctor to check.
Preferably, when the diagnosis result is plural, the method further comprises: a diagnosis result screening unit in the first extraction module selects diagnosis results meeting preset conditions based on the preset conditions, defines the diagnosis results meeting the preset conditions as first diagnosis results, and sends codes of a first diagnosis type in each first diagnosis result to a diagnosis quality judgment module; at this time, the diagnosis quality judgment module is further configured to respectively judge the compliance of each first diagnosis result, and output the judgment result with the highest compliance to the judgment result display module.
Preferably, the method further comprises: when the code of the image inspection part and/or the code of the material taking part cannot be received, a marking unit in the diagnosis quality judgment module automatically marks the tumor image structural report, and sends the marked result to a judgment result display module; at this time, the judgment result display module is further configured to display the labeled result in the patient list for a doctor to view.
Preferably, the method further comprises: and an error prompting unit in the judgment result display module automatically displays the pathological result corresponding to the tumor image structured report with the diagnosis result partially conforming or the diagnosis result non-conforming in the corresponding visual angle of the patient list for the doctor to check.
The invention has the technical effects that:
1. because the invention is provided with the image report screening module, the first extraction module, the second extraction module, the diagnosis quality judgment module and the judgment result display module, the method comprises the steps that all tumor image structuralized reports of material-taking parts of a patient in an image examination item in a certain time period are screened based on pathological examination of the patient, a first extraction module extracts codes of the image examination parts and codes of a first diagnosis type, a second extraction module extracts codes of the material-taking parts and codes of a second diagnosis type, and a diagnosis quality judgment module judges whether a diagnosis result accords with a pathological result or not based on the codes of the image examination parts, the first disease type and the first diagnosis type and respectively corresponds to the codes of the material-taking parts, the second disease type and the codes of the second diagnosis type, and displays the judgment result in a patient list; the contrast of the image diagnosis result and the pathological result in the system is an important means for the image doctor to self-promote through closed-loop feedback, is very important for enhancing confidence and finding knowledge blind spots, has high automation degree and high efficiency compared with the method of arranging personnel sampling and manual contrast in the prior art, realizes the same term system due to the use of international standard knowledge base coding, has quality independent of the subjective ability of people, and has more stable quality for the evaluation of the image structured report;
2. because the invention sets up the screening unit of the diagnostic result, can choose the diagnostic result in accordance with the preset condition, diagnose the quality judging module and carry on the judgement of the conformance to the diagnostic result chosen, regard the evaluation with the highest conformance as the quality judgement, make the system more perfect, the correct rate is higher;
3. because the marking unit is arranged, the tumor image structured report can be marked under the condition that the codes of the image inspection part and/or the codes of the material taking part cannot be received, and the marked result is sent to the judgment result display module; for example, in the image report of the part description of the diagnosis result including the part modifiers such as "side", "periphery", "up" and "down", because the part is difficult to automatically correspond, the image report is labeled, so that the manual checking is facilitated, and the operation of a doctor is facilitated;
4. because the error prompt unit is arranged, the pathological result corresponding to the tumor image structured report with the diagnosis result partially conforming to or the diagnosis result non-conforming to can be automatically displayed in the corresponding visual angle of the patient list for the doctor to check, so that the doctor can conveniently read and refer to the error content of the image report written before, the diagnosis capability of the doctor is improved, and the system is 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 schematic structural diagram of a system for mapping and evaluating a diagnosis result and a pathological result of a tumor image report according to a first embodiment of the invention;
fig. 2 is a schematic view of an interface of a prostate image structured report image in a tumor image report diagnosis result and pathological result correspondence and evaluation system according to a first embodiment of the present invention;
fig. 3 is a schematic diagram of an interface of a prostate image structured report lesion information in a tumor image report diagnosis result and pathological result correspondence and evaluation system according to a first embodiment of the present invention;
fig. 4 is a schematic diagram of an interface of a prostate image structured report image representation and a diagnosis result in a tumor image report diagnosis result and pathological result correspondence and evaluation system according to a first embodiment of the present invention;
fig. 5 is a schematic diagram illustrating an interface of extracting pathological result structural parameters from a pathological module in a tumor image report diagnosis result and pathological result correspondence and evaluation system according to a first embodiment of the present invention;
fig. 6 is a schematic interface diagram illustrating correspondence between a diagnosis result and a pathological result of a tumor image report according to a first embodiment of the present invention and a judgment result displayed by a judgment result display module in an evaluation system;
fig. 7 is a schematic structural diagram of a system for correspondence between a tumor image report diagnosis result and a pathological result and evaluation according to a second embodiment of the invention;
fig. 8 is a schematic structural diagram of a system for correspondence between a tumor image report diagnosis result and a pathological result and evaluation according to a third embodiment of the present invention;
fig. 9 is a schematic structural diagram of a system for correspondence between a tumor image report diagnosis result and a pathological result and evaluation according to a fourth embodiment of the present invention;
FIG. 10 is a flowchart of a method for mapping and evaluating a diagnosis result and a pathological result of a tumor image report according to a fifth embodiment of the present invention;
fig. 11 is a schematic view showing the interface between the prostate image structured report image in the method for correspondence between the diagnosis result and the pathological result of the tumor image report and the evaluation method according to the fifth embodiment of the present invention;
fig. 12 is a schematic diagram illustrating an interface of structured prostate image report lesion information in a method for correspondence between tumor image report diagnosis results and pathological results and evaluation according to a fifth embodiment of the present invention;
fig. 13 is an interface diagram illustrating the correspondence between tumor image report diagnosis results and pathological results and the prostate image structured report image representation and diagnosis results in the evaluation method according to the fifth embodiment of the present invention;
fig. 14 is a schematic interface diagram illustrating an example of correspondence between a tumor image report diagnosis result and a pathological result and an example of extracting a pathological result structural parameter from a pathological module in the method for evaluating the same according to the fifth embodiment of the present invention;
fig. 15 is a schematic interface diagram illustrating correspondence between a diagnosis result and a pathological result of a tumor image report according to a fifth embodiment of the present invention and a judgment result displayed by the judgment result display module in the evaluation method.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Example one
Fig. 1 is a schematic structural diagram of a system for mapping and evaluating a diagnosis result and a pathological result of a tumor image report according to a first embodiment of the invention; as shown in fig. 1, the system includes: a pathology module 10, an image report screening module 20, a first extraction module 30, a second extraction module 40, a diagnosis quality judgment module 50, and a judgment result display module 60, wherein,
the pathology module 10 is respectively connected with the image report screening module 20 and the second extraction module 40, and is used for storing relevant data of pathological examination of the patient;
the relevant data may include basic information of the patient, such as name, age, sex, examination number, and the like, and parameters such as pathological result.
The image report screening module 20 is respectively connected with the pathology module 10 and the first extraction module 30, and is configured to screen all tumor image structured reports of the parts of the image examination items of the patient within a preset time period, which include the material-drawing parts of the pathology examination, based on the pathology examination of the patient, and separately store each tumor image structured report;
wherein the pathological examination does not include intraoperative frozen pathological examination;
a prerequisite of the present system is that the image diagnosis for the tumor class is made and that the image diagnosis report must use a structured report template.
The preset time period can be set according to the requirements of the medical institution, for example, the imaging examination of the patient exists in the current VISIT (hospitalization/outpatient service), and the part in the examination item includes the material-drawing part of the pathological examination, so the image structured report of the imaging examination is included in the contrast range; in another example, if the patient had a previous imaging examination under VISIT within 1 year and the part in the examination item includes the material part for the pathological examination, the image structure report of the imaging examination is included in the contrast range.
A first extraction module 30, respectively connected to the image report screening module 20 and the diagnosis quality judgment module 50, for identifying an image examination part and a diagnosis result based on each tumor image structured report, wherein the diagnosis result includes a first disease type and a first diagnosis type, and extracting a code of the image examination part and a code of the first diagnosis type;
a second extraction module 40, respectively connected to the pathology module 10 and the diagnosis quality judgment module 50, for identifying a material-drawing part and a pathology result of the pathology examination based on data related to the pathology examination, wherein the pathology result includes a second disease type and a second diagnosis type, and extracting a code of the material-drawing part and a code of the second diagnosis type;
since the image description of the image structured report template defines the disease type, the diagnosis type can be reduced to a plurality of reference diagnosis/differential diagnosis types preset in each image structured report template, and the NLP can be accurately captured. The format for the preservation of diagnostic results corresponding to pathological results is: examination site + type of diagnosis; a report may analyze multiple entries of the above diagnostic findings, but with an unchanged format. The default is to put the most likely, most important diagnostic conclusion in the first place, otherwise systematic errors may occur. The diagnostic result tags are all encoded using the RADLEX or SNOMED ontology.
For example, the disease type of the prostate may be adenocarcinoma (acinar adenocarcinoma), ductal adenocarcinoma, urothelial carcinoma, squamous cell carcinoma, adenosquamous carcinoma, while the diagnostic type may be benign, benign-malignant, malignant in situ, malignant primary, malignant, primary secondary, undetermined, and the like.
Wherein the pathology results in the pathology module are encoded using the ICD-O3.2 version. The coding comprises an anatomical part coding and a pathology coding, and the complete ICD-O coding uses a 10-bit coding, such as C34.1, M-8070/33, wherein C represents an anatomical part, 34 represents a lung, and 1 represents an upper lobe; m stands for morphological code, 8070 refers to squamous cell origin, the first 3 refers to carcinoma, the second 3 refers to hypodifferentiation.
If the pathology module itself does not have the code, other information systems are needed to assist in generating the ICD-O code. Wherein the coding for the site is derived from a sample site of extraction provided by the pathology registration system. The pathology code is given from a manual observation microscope.
The diagnosis quality judgment module 50 is respectively connected with the first extraction module 30, the second extraction module 40 and the judgment result display module 60, and is used for judging the conformity of the diagnosis result, and the judgment rule is as follows: when the code of the image inspection part does not correspond to the code of the material-taking part, the output judgment result is: the diagnosis result is non-compliance; when the code of the image examination part corresponds to the code of the material taking part and the first disease type is matched with the second disease type, outputting a judgment result as follows: the diagnosis result is coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, but the code of the first diagnosis type corresponds to the code of the second diagnosis type, the output judgment result is: the diagnosis result is partial coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, and the code of the first diagnosis type is not matched with the code of the second diagnosis type, the output judgment result is as follows: the diagnosis result is non-compliance;
the anatomical part coding of the imaging diagnosis result uses RADLEX coding, which belongs to the component of LOINC coding at present; the loci code for LOINC has been mapped to SNOMED loci code (open mapping); since there is a clear correspondence (public correspondence table) between ICD-O and SNOMED region codes, mapping of the image anatomical region code to the pathological posture code can be accomplished using open-source tools or programming. Since the degree of detail of the iconographic coding often exceeds that of the pathological body coding, the retrospective principle is that the current/superior anatomical region of RADLEX may correspond to the root anatomical region of ICD-O, for example, 34 of C34.1, and the lower small region is not used.
In many cases, the imaging of tumors does not reflect a cytological source, so the imaging results do not correspond to a cytological source of pathology, but only to the "dynamic" coding of the 9 th position following cellular morphology. The full set of this bit code is: 0, benign; 1, benign-malignant, 2, malignant in situ; 3, primary malignancy, 9 malignancy, secondary primary uncertainty; for 0, 1, 2, the diagnosis was considered benign, and 3, 9, the diagnosis was considered malignant. The association of the diagnostic findings of the imaging report with the "dynamic" coding of the pathology is accomplished through a custom table. Some types of diagnosis represent malignancy, some types of diagnosis represent benign, and some types of diagnosis represent benign. Through the diagnosis names and the benign and malignant classification in the user-defined table, the diagnosis result is associated with the dynamic codes in the diagnosis conclusion of the same pathological part, and whether the diagnosis result is correct or not can be clearly judged.
And the judgment result display module 60 is connected with the diagnosis quality judgment module 50 and is used for receiving the judgment result and displaying the judgment result in the patient list for the doctor to check.
Fig. 2 is a schematic view of an interface of a prostate image structured report image in a tumor image report diagnosis result and pathological result correspondence and evaluation system according to a first embodiment of the present invention; as shown in fig. 2, the sagittal line data of the prostate is shown in the DICOM image.
Fig. 3 is a schematic diagram of an interface of a prostate image structured report lesion information in a tumor image report diagnosis result and pathological result correspondence and evaluation system according to a first embodiment of the present invention; as shown in fig. 3, the location of the lesion, DWI and the relevant parameters of the ADC are shown.
Fig. 4 is a schematic diagram of an interface of a prostate image structured report image representation and a diagnosis result in a tumor image report diagnosis result and pathological result correspondence and evaluation system according to a first embodiment of the present invention; as shown in fig. 4, the image structured report automatically generates image representation and diagnosis results based on the image findings and the parameters associated with the lesion. The diagnosis result is as follows: abnormal signals of the left middle transition zone, the left base part peripheral zone, the tip transition zone and the middle peripheral zone of the prostate are considered.
Fig. 5 is a schematic diagram illustrating an interface of extracting pathological result structural parameters from a pathological module in a tumor image report diagnosis result and pathological result correspondence and evaluation system according to a first embodiment of the present invention; as shown in FIG. 5, the pathological results in the pathological module are extracted and displayed in the form of structured parameters.
Fig. 6 is a schematic interface diagram illustrating correspondence between a diagnosis result and a pathological result of a tumor image report according to a first embodiment of the present invention and a judgment result displayed by a judgment result display module in an evaluation system; as shown in fig. 6, the image-structured report diagnosis result of the male patient completely matches the pathological result (the judgment result is displayed on the left side of the work list).
The embodiment of the invention is provided with an image report screening module, a first extraction module, a second extraction module, a diagnosis quality judgment module and a judgment result display module, the method comprises the steps that all tumor image structuralized reports of material-taking parts of a patient in an image examination item in a certain time period are screened based on pathological examination of the patient, a first extraction module extracts codes of the image examination parts and codes of a first diagnosis type, a second extraction module extracts codes of the material-taking parts and codes of a second diagnosis type, and a diagnosis quality judgment module judges whether a diagnosis result accords with a pathological result or not based on the codes of the image examination parts, the first disease type and the first diagnosis type and respectively corresponds to the codes of the material-taking parts, the second disease type and the codes of the second diagnosis type, and displays the judgment result in a patient list; the contrast of the image diagnosis result and the pathological result in the system is an important means for the image doctor to self-promote through closed-loop feedback, is very important for enhancing confidence and finding knowledge blind spots, has high automation degree and high efficiency compared with the method of arranging personnel sampling and manual contrast in the prior art, realizes the same term system due to the use of international standard knowledge base coding, has quality independent of the subjective ability of people, and has more stable quality for the evaluation of the image structured report.
Example two
Fig. 7 is a schematic structural diagram of a system for correspondence between a tumor image report diagnosis result and a pathological result and evaluation according to a second embodiment of the invention; as shown in fig. 7, when the diagnosis results are plural, the first extraction module 30 further includes a diagnosis result screening unit 302, configured to select a diagnosis result meeting a preset condition based on the preset condition, define the diagnosis result meeting the preset condition as a first diagnosis result, and send a code of a first diagnosis type in each first diagnosis result to the diagnosis quality determination module 50; at this time, the process of the present invention,
the diagnosis quality judgment module 50 is further configured to respectively judge the compliance of each first diagnosis result, and output the judgment result with the highest compliance to the judgment result display module 60.
In general, the preset condition is the most possible and important diagnosis result, generally the first two diagnosis results, and other diagnosis results are ignored and are not evaluated; when the diagnosis quality judgment module judges the conformity of each first diagnosis result, the judgment is performed according to the rule of a single diagnosis result, and the judgment result with the highest conformity is output to the judgment result display module 60.
The embodiment of the invention is provided with the diagnosis result screening unit, so that the diagnosis result meeting the preset condition can be selected, the diagnosis quality judgment module judges the conformity of the selected diagnosis result, and the evaluation with the highest conformity is used as the quality judgment, so that the system is more perfect, and the accuracy is higher.
EXAMPLE III
Fig. 8 is a schematic structural diagram of a system for correspondence between a tumor image report diagnosis result and a pathological result and evaluation according to a third embodiment of the present invention; as shown in fig. 8, the diagnosis quality determining module 50 further includes a labeling unit 502, configured to automatically label the tumor image structured report when the code of the image examination portion and/or the code of the material-drawing portion cannot be received, and send the labeled result to the determining result displaying module 60; at this time, the process of the present invention,
the judgment result display module 60 is further configured to display the labeled result in the patient list for the doctor to view.
In the image report of the part modifiers such as 'side', 'periphery', 'up', 'down' and the like in the description of the part of the diagnosis result, because the part is difficult to automatically correspond, the marking unit automatically marks the tumor image structured report, and then manually checks and evaluates the tumor image structured report; for another example, if there is an ambiguous determination result of an anatomical region in a pathological result, the marking unit also marks the anatomical region if there is an imaging examination item under the same VISIT, and then the anatomical region is manually checked and evaluated.
The embodiment of the invention is provided with a marking unit which can mark the tumor image structured report under the condition that the codes of the image inspection part and/or the material taking part can not be received, and send the marked result to the judgment result display module; for example, in the image report of the part description of the diagnosis result including the part modifiers such as "side", "periphery", "up" and "down", since the part is difficult to be automatically corresponded, the image report is labeled for manual checking, which is convenient for the operation of the doctor.
Example four
Fig. 9 is a schematic structural diagram of a system for correspondence between a tumor image report diagnosis result and a pathological result and evaluation according to a fourth embodiment of the present invention; as shown in fig. 9, the determination result display module 60 further includes an error prompt unit 602, configured to automatically display the pathological result corresponding to the tumor image structured report with the diagnosis result of partial coincidence or the diagnosis result of non-coincidence in the corresponding view angle of the patient list for the doctor to view.
Wherein, the judgment result is automatically fed back to an RIS (video information management system) system. For example, for the image examination whose judgment result is "partial coincidence", the pathological result is displayed in the corresponding viewing angle, the doctor who writes the report can check the non-coincidence content to improve the diagnostic ability, and the case can be manually deleted after the checking; for the result of "not matching", the doctor may open the reading again, and after reading, the reading may be hidden from the list, and the various display settings described above may be set according to the requirements of the medical institution, which is not limited herein.
The embodiment of the invention is provided with the error prompt unit, so that the pathological result corresponding to the tumor image structured report with the diagnosis result partially conforming to or non-conforming to can be automatically displayed in the corresponding visual angle of the patient list for the doctor to check, the doctor can conveniently read and refer to the error content of the image report written before, the diagnosis capability of the doctor is improved, and the system is more humanized.
EXAMPLE five
FIG. 10 is a flowchart of a method for mapping and evaluating a diagnosis result and a pathological result of a tumor image report according to a fifth embodiment of the present invention; as shown in fig. 10, the method comprises the steps of:
step S501, a pathology module stores relevant data of pathological examination of a patient;
the relevant data may include basic information of the patient, such as name, age, sex, examination number, and the like, and parameters such as pathological result.
Step S502, the image report screening module screens all tumor image structuralized reports of the parts of the image examination items of the patient in a preset time period, including the material-taking parts of the pathological examination, based on the pathological examination of the patient, and stores each tumor image structuralized report separately;
wherein the pathological examination does not include intraoperative frozen pathological examination;
a prerequisite of the present system is that the image diagnosis for the tumor class is made and that the image diagnosis report must use a structured report template.
The preset time period can be set according to the requirements of the medical institution, for example, the imaging examination of the patient exists in the current VISIT (hospitalization/outpatient service), and the part in the examination item includes the material-drawing part of the pathological examination, so the image structured report of the imaging examination is included in the contrast range; in another example, if the patient had a previous imaging examination under VISIT within 1 year and the part in the examination item includes the material part for the pathological examination, the image structure report of the imaging examination is included in the contrast range.
Step S503, the first extraction module identifies an image examination part and a diagnosis result based on each tumor image structured report, wherein the diagnosis result comprises a first disease type and a first diagnosis type, and extracts the code of the image examination part and the code of the first diagnosis type;
step S504, a second extraction module identifies a material-taking part and a pathological result of the pathological examination based on the relevant data of the pathological examination, wherein the pathological result comprises a second disease type and a second diagnosis type, and extracts a code of the material-taking part and a code of the second diagnosis type;
since the image description of the image structured report template defines the disease type, the diagnosis type can be reduced to a plurality of reference diagnosis/differential diagnosis types preset in each image structured report template, and the NLP can be accurately captured. The format for the preservation of diagnostic results corresponding to pathological results is: examination site + type of diagnosis; a report may analyze multiple entries of the above diagnostic findings, but with an unchanged format. The default is to put the most likely, most important diagnostic conclusion in the first place, otherwise systematic errors may occur. The diagnostic result tags are all encoded using the RADLEX or SNOMED ontology.
For example, the disease type of the prostate may be adenocarcinoma (acinar adenocarcinoma), ductal adenocarcinoma, urothelial carcinoma, squamous cell carcinoma, adenosquamous carcinoma, while the diagnostic type may be benign, benign-malignant, malignant in situ, malignant primary, malignant, primary secondary, undetermined, and the like.
Wherein the pathology results in the pathology module are encoded using the ICD-O3.2 version. The coding comprises an anatomical part coding and a pathology coding, and the complete ICD-O coding uses a 10-bit coding, such as C34.1, M-8070/33, wherein C represents an anatomical part, 34 represents a lung, and 1 represents an upper lobe; m stands for morphological code, 8070 refers to squamous cell origin, the first 3 refers to carcinoma, the second 3 refers to hypodifferentiation.
If the pathology module itself does not have the code, other information systems are needed to assist in generating the ICD-O code. Wherein the coding for the site is derived from a sample site of extraction provided by the pathology registration system. The pathology code is given from a manual observation microscope.
Step S505, the diagnosis quality judgment module judges the compliance of the diagnosis result, and the judgment rule is: when the code of the image inspection part does not correspond to the code of the material-taking part, the output judgment result is: the diagnosis result is non-compliance; when the code of the image examination part corresponds to the code of the material taking part and the first disease type is matched with the second disease type, outputting a judgment result as follows: the diagnosis result is coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, but the code of the first diagnosis type corresponds to the code of the second diagnosis type, the output judgment result is: the diagnosis result is partial coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, and the code of the first diagnosis type is not matched with the code of the second diagnosis type, the output judgment result is as follows: the diagnosis result is non-compliance;
the anatomical part coding of the imaging diagnosis result uses RADLEX coding, which belongs to the component of LOINC coding at present; the loci code for LOINC has been mapped to SNOMED loci code (open mapping); since there is a clear correspondence (public correspondence table) between ICD-O and SNOMED region codes, mapping of the image anatomical region code to the pathological posture code can be accomplished using open-source tools or programming. Since the degree of detail of the iconographic coding often exceeds that of the pathological body coding, the retrospective principle is that the current/superior anatomical region of RADLEX may correspond to the root anatomical region of ICD-O, for example, 34 of C34.1, and the lower small region is not used.
In many cases, the imaging of tumors does not reflect a cytological source, so the imaging results do not correspond to a cytological source of pathology, but only to the "dynamic" coding of the 9 th position following cellular morphology. The full set of this bit code is: 0, benign; 1, benign-malignant, 2, malignant in situ; 3, primary malignancy, 9 malignancy, secondary primary uncertainty; for 0, 1, 2, the diagnosis was considered benign, and 3, 9, the diagnosis was considered malignant. The association of the diagnostic findings of the imaging report with the "dynamic" coding of the pathology is accomplished through a custom table. Some types of diagnosis represent malignancy, some types of diagnosis represent benign, and some types of diagnosis represent benign. Through the diagnosis names and the benign and malignant classification in the user-defined table, the diagnosis result is associated with the dynamic codes in the diagnosis conclusion of the same pathological part, and whether the diagnosis result is correct or not can be clearly judged.
Step S506, the judgment result display module receives the judgment result and displays the judgment result in the patient list for the doctor to check.
Fig. 11 is a schematic view showing the interface between the prostate image structured report image in the method for correspondence between the diagnosis result and the pathological result of the tumor image report and the evaluation method according to the fifth embodiment of the present invention; as shown in fig. 11, the sagittal line data of the prostate is displayed in the DICOM image.
Fig. 12 is a schematic diagram illustrating an interface of structured prostate image report lesion information in a method for correspondence between tumor image report diagnosis results and pathological results and evaluation according to a fifth embodiment of the present invention; as shown in fig. 12, the location of the lesion, DWI and the relevant parameters of the ADC are shown.
Fig. 13 is an interface diagram illustrating the correspondence between tumor image report diagnosis results and pathological results and the prostate image structured report image representation and diagnosis results in the evaluation method according to the fifth embodiment of the present invention; as shown in fig. 13, the image structured report automatically generates image representation and diagnosis results based on the image findings and the parameters associated with the lesion. The diagnosis result is as follows: abnormal signals of the left middle transition zone, the left base part peripheral zone, the tip transition zone and the middle peripheral zone of the prostate are considered.
Fig. 14 is a schematic interface diagram illustrating an example of correspondence between a tumor image report diagnosis result and a pathological result and an example of extracting a pathological result structural parameter from a pathological module in the method for evaluating the same according to the fifth embodiment of the present invention; as shown in FIG. 14, the pathology results in the pathology module are extracted and displayed in the form of structured parameters.
Fig. 15 is a schematic interface diagram illustrating correspondence between a diagnosis result and a pathological result of a tumor image report according to a fifth embodiment of the present invention and a judgment result displayed by the judgment result display module in the evaluation method; as shown in fig. 15, the image-structured report diagnosis result of the male patient completely matches the pathological result (the judgment result is displayed on the left side in the work list).
Wherein, when the diagnosis result is plural, the method further comprises: a diagnosis result screening unit in the first extraction module selects diagnosis results meeting preset conditions based on the preset conditions, defines the diagnosis results meeting the preset conditions as first diagnosis results, and sends codes of a first diagnosis type in each first diagnosis result to a diagnosis quality judgment module; at this time, the process of the present invention,
the diagnosis quality judging module is also used for respectively judging the conformity of each first diagnosis result and outputting the judgment result with the highest conformity to the judgment result display module.
In general, the preset condition is the most possible and important diagnosis result, generally the first two diagnosis results, and other diagnosis results are ignored and are not evaluated; when the diagnosis quality judgment module judges the conformity of each first diagnosis result, the judgment is carried out according to the rule of a single diagnosis result, and the judgment result with the highest conformity is output to the judgment result display module.
Wherein, the method also comprises: when the code of the image inspection part and/or the code of the material taking part cannot be received, a marking unit in the diagnosis quality judgment module automatically marks the tumor image structural report, and sends the marked result to a judgment result display module; at this time, the process of the present invention,
the judgment result display module is also used for displaying the marked result in the patient list for the doctor to check.
In the image report of the part modifiers such as 'side', 'periphery', 'up', 'down' and the like in the description of the part of the diagnosis result, because the part is difficult to automatically correspond, the marking unit automatically marks the tumor image structured report, and then manually checks and evaluates the tumor image structured report; for another example, if there is an ambiguous determination result of an anatomical region in a pathological result, the marking unit also marks the anatomical region if there is an imaging examination item under the same VISIT, and then the anatomical region is manually checked and evaluated.
Wherein, the method also comprises: and an error prompting unit in the judgment result display module automatically displays the pathological result corresponding to the tumor image structured report with the diagnosis result partially conforming or the diagnosis result non-conforming in the corresponding visual angle of the patient list for the doctor to check.
Wherein, the judgment result is automatically fed back to an RIS (video information management system) system. For example, for the image examination whose judgment result is "partial coincidence", the pathological result is displayed in the corresponding viewing angle, the doctor who writes the report can check the non-coincidence content to improve the diagnostic ability, and the case can be manually deleted after the checking; for the result of "not matching", the doctor may open the reading again, and after reading, the reading may be hidden from the list, and the various display settings described above may be set according to the requirements of the medical institution, which is not limited herein.
The image report screening module, the first extraction module, the second extraction module, the diagnosis quality judgment module and the judgment result display module in the embodiment of the invention, the method comprises the steps that all tumor image structuralized reports of material-taking parts of a patient in an image examination item in a certain time period are screened based on pathological examination of the patient, a first extraction module extracts codes of the image examination parts and codes of a first diagnosis type, a second extraction module extracts codes of the material-taking parts and codes of a second diagnosis type, and a diagnosis quality judgment module judges whether a diagnosis result accords with a pathological result or not based on the codes of the image examination parts, the first disease type and the first diagnosis type and respectively corresponds to the codes of the material-taking parts, the second disease type and the codes of the second diagnosis type, and displays the judgment result in a patient list; the contrast of the image diagnosis result and the pathological result in the system is an important means for the image doctor to self-promote through closed-loop feedback, is very important for enhancing confidence and finding knowledge blind spots, has high automation degree and high efficiency compared with the method of arranging personnel sampling and manual contrast in the prior art, realizes the same term system due to the use of international standard knowledge base coding, has quality independent of the subjective ability of people, and has more stable quality for the evaluation of the image structured report; the diagnosis result screening unit in the embodiment of the invention can select the diagnosis result meeting the preset condition, the diagnosis quality judgment module judges the conformity of the selected diagnosis result, and the evaluation with the highest conformity is taken as the quality judgment, so that the system is more complete and the accuracy is higher; the marking unit in the embodiment of the invention can mark the tumor image structured report under the condition that the codes of the image inspection part and/or the material taking part cannot be received, and send the marked result to the judgment result display module; for example, in the image report of the part description of the diagnosis result including the part modifiers such as "side", "periphery", "up" and "down", because the part is difficult to automatically correspond, the image report is labeled, so that the manual checking is facilitated, and the operation of a doctor is facilitated; the error prompt unit in the embodiment of the invention can automatically display the pathological result corresponding to the tumor image structured report of which the diagnosis result is partially or non-conforming in the corresponding view angle of the patient list for the doctor to check, thereby facilitating the doctor to read and reference the error content of the image report written before, laying a cushion for improving the diagnosis capability of the doctor and ensuring 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 an image report screening module, a first extraction module, a second extraction module, a diagnosis quality judgment module and a judgment result display module, the method comprises the steps that all tumor image structuralized reports of material-taking parts of a patient in an image examination item in a certain time period are screened based on pathological examination of the patient, a first extraction module extracts codes of the image examination parts and codes of a first diagnosis type, a second extraction module extracts codes of the material-taking parts and codes of a second diagnosis type, and a diagnosis quality judgment module judges whether a diagnosis result accords with a pathological result or not based on the codes of the image examination parts, the first disease type and the first diagnosis type and respectively corresponds to the codes of the material-taking parts, the second disease type and the codes of the second diagnosis type, and displays the judgment result in a patient list; the contrast of the image diagnosis result and the pathological result in the system is an important means for the image doctor to self-promote through closed-loop feedback, is very important for enhancing confidence and finding knowledge blind spots, has high automation degree and high efficiency compared with the method of arranging personnel sampling and manual contrast in the prior art, realizes the same term system due to the use of international standard knowledge base coding, has quality independent of the subjective ability of people, and has more stable quality for the evaluation of the image structured report; the embodiment of the invention is provided with the diagnosis result screening unit, so that the diagnosis result meeting the preset condition can be selected, the diagnosis quality judgment module judges the conformity of the selected diagnosis result, and the evaluation with the highest conformity is taken as the quality judgment, so that the system is more perfect, and the accuracy is higher; the embodiment of the invention is provided with a marking unit which can mark the tumor image structured report under the condition that the codes of the image inspection part and/or the material taking part can not be received, and send the marked result to the judgment result display module; for example, in the image report of the part description of the diagnosis result including the part modifiers such as "side", "periphery", "up" and "down", because the part is difficult to automatically correspond, the image report is labeled, so that the manual checking is facilitated, and the operation of a doctor is facilitated; the embodiment of the invention is provided with the error prompt unit, so that the pathological result corresponding to the tumor image structured report with the diagnosis result partially conforming to or non-conforming to can be automatically displayed in the corresponding visual angle of the patient list for the doctor to check, the doctor can conveniently read and refer to the error content of the image report written before, the diagnosis capability of the doctor is improved, 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 (8)
1. A system for correspondence and evaluation of tumor image report diagnosis results and pathological results is characterized by comprising a pathological module, an image report screening module, a first extraction module, a second extraction module, a diagnosis quality judgment module and a judgment result display module,
the pathology module is respectively connected with the image report screening module and the second extraction module and is used for storing relevant data of pathological examination of the patient;
the image report screening module is respectively connected with the pathology module and the first extraction module, and is used for screening all tumor image structured reports of parts of an image examination item of the patient in a preset time period, including material-drawing parts of the pathology examination, based on the pathology examination of the patient, and independently storing each tumor image structured report; wherein the pathology examination does not include an intraoperative frozen pathology examination;
the first extraction module is respectively connected with the image report screening module and the diagnosis quality judgment module, and is used for identifying an image examination part and a diagnosis result based on each tumor image structured report, wherein the diagnosis result comprises a first disease type and a first diagnosis type, and extracting a code of the image examination part and a code of the first diagnosis type;
the second extraction module is respectively connected with the pathology module and the diagnosis quality judgment module, and is used for identifying a material-taking part and a pathology result of the pathology examination based on the relevant data of the pathology examination, wherein the pathology result comprises a second disease type and a second diagnosis type, and extracting a code of the material-taking part and a code of the second diagnosis type;
the diagnosis quality judgment module is respectively connected with the first extraction module, the second extraction module and the judgment result display module, and is used for judging the conformity of the diagnosis result, and the judgment rule is as follows: when the code of the image examination part does not correspond to the code of the material taking part, outputting a judgment result as follows: the diagnostic result is non-compliance; when the code of the image examination part corresponds to the code of the material taking part and the first disease type is matched with the second disease type, outputting the judgment result as follows: the diagnosis result is coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, but the code of the first diagnosis type corresponds to the code of the second diagnosis type, the judgment result is output as follows: the diagnostic result is partial coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, and the code of the first diagnosis type does not correspond to the code of the second diagnosis type, outputting the judgment result as follows: the diagnostic result is non-compliance;
and the judgment result display module is connected with the diagnosis quality judgment module and used for receiving the judgment result and displaying the judgment result in a patient list for a doctor to check.
2. The system according to claim 1, wherein when the diagnosis results are plural, the first extraction module further comprises a diagnosis result screening unit configured to select the diagnosis result meeting a preset condition based on a preset condition, define the diagnosis result meeting the preset condition as a first diagnosis result, and send a code of the first diagnosis type in each first diagnosis result to the diagnosis quality determination module; at this time, the diagnosis quality judgment module is further configured to respectively judge the compliance of each first diagnosis result, and output the judgment result with the highest compliance to the judgment result display module.
3. The system for correspondence and evaluation of tumor image report diagnosis results and pathological results according to claim 1, wherein the diagnosis quality determination module further comprises a labeling unit for automatically labeling the tumor image structured report when the codes of the image examination part and/or the material-drawing part cannot be received, and sending the labeled results to the determination result display module; at this time, the judgment result display module is further configured to display the labeled result in the patient list for a doctor to view.
4. The system of claim 1, wherein the determination result display module further comprises an error prompt unit for automatically displaying the pathological result corresponding to the tumor image structured report with the diagnosis result partially corresponding or the diagnosis result non-corresponding in the corresponding view angle of the patient list for a doctor to view.
5. A method for correspondence and evaluation of tumor image report diagnosis results and pathological results is characterized in that the method comprises the following steps:
the pathology module stores data related to a pathological examination of a patient;
the image report screening module screens all tumor image structured reports of the parts of the image examination items of the patient in a preset time period, including the material drawing parts of the pathological examination, based on the pathological examination of the patient, and individually stores each tumor image structured report; wherein the pathology examination does not include an intraoperative frozen pathology examination;
the first extraction module identifies an image examination part and a diagnosis result based on each tumor image structured report, wherein the diagnosis result comprises a first disease type and a first diagnosis type, and extracts the code of the image examination part and the code of the first diagnosis type;
a second extraction module identifies a material drawing part and a pathological result of the pathological examination based on the relevant data of the pathological examination, wherein the pathological result comprises a second disease type and a second diagnosis type, and extracts the code of the material drawing part and the code of the second diagnosis type;
the diagnosis quality judgment module judges the conformity of the diagnosis result, and the judgment rule is as follows: when the code of the image examination part does not correspond to the code of the material taking part, outputting a judgment result as follows: the diagnostic result is non-compliance; when the code of the image examination part corresponds to the code of the material taking part and the first disease type is matched with the second disease type, outputting the judgment result as follows: the diagnosis result is coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, but the code of the first diagnosis type corresponds to the code of the second diagnosis type, the judgment result is output as follows: the diagnostic result is partial coincidence; when the code of the image examination part corresponds to the code of the material taking part, the first disease type is not matched with the second disease type, and the code of the first diagnosis type does not correspond to the code of the second diagnosis type, outputting the judgment result as follows: the diagnostic result is non-compliance;
and the judgment result display module receives the judgment result and displays the judgment result in a patient list for a doctor to check.
6. The method of claim 5, wherein when there are a plurality of diagnosis results, the method further comprises: a diagnosis result screening unit in the first extraction module selects the diagnosis result meeting the preset condition based on a preset condition, defines the diagnosis result meeting the preset condition as a first diagnosis result, and sends the code of the first diagnosis type in each first diagnosis result to the diagnosis quality judgment module; at this time, the diagnosis quality judgment module further judges the conformity of each first diagnosis result, and outputs the judgment result with the highest conformity to the judgment result display module.
7. The method of claim 5, further comprising: when the code of the image inspection part and/or the code of the material taking part cannot be received, a marking unit in the diagnosis quality judgment module automatically marks the tumor image structural report, and sends the marked result to the judgment result display module; at this time, the judgment result display module is further configured to display the labeled result in the patient list for a doctor to view.
8. The method of claim 5, further comprising: and an error prompt unit in the judgment result display module automatically displays the pathological result corresponding to the tumor image structured report with the diagnosis result partially conforming or the diagnosis result non-conforming in a corresponding visual angle of the patient list for a doctor to check.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011268228.0ACN112562816A (en) | 2020-11-13 | 2020-11-13 | System and method for correspondence and evaluation of diagnosis result and pathological result of tumor image report |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011268228.0ACN112562816A (en) | 2020-11-13 | 2020-11-13 | System and method for correspondence and evaluation of diagnosis result and pathological result of tumor image report |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112562816Atrue CN112562816A (en) | 2021-03-26 |
Family
ID=75042217
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011268228.0APendingCN112562816A (en) | 2020-11-13 | 2020-11-13 | System and method for correspondence and evaluation of diagnosis result and pathological result of tumor image report |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112562816A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113053487A (en)* | 2021-04-22 | 2021-06-29 | 薛蕴菁 | Method and device for automatically giving diagnosis suggestions based on structured report historical data |
| CN113130067A (en)* | 2021-04-01 | 2021-07-16 | 上海市第一人民医院 | Intelligent reminding method for ultrasonic examination based on artificial intelligence |
| CN114464311A (en)* | 2021-12-30 | 2022-05-10 | 复旦大学附属中山医院厦门医院 | Information detection method, system, terminal device and storage medium |
| CN114566246A (en)* | 2022-01-25 | 2022-05-31 | 复旦大学附属中山医院厦门医院 | Structured report generation method, system, terminal device and storage medium |
| CN114566245A (en)* | 2022-01-25 | 2022-05-31 | 复旦大学附属中山医院厦门医院 | Information display method, system, terminal device and storage medium |
| CN115132351A (en)* | 2022-06-23 | 2022-09-30 | 三峡大学 | Diagnostic data feedback evaluation system and method based on real world research |
| CN116206749A (en)* | 2023-01-18 | 2023-06-02 | 首都医科大学附属北京儿童医院 | Method and system for converting disease codes |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013175683A1 (en)* | 2012-05-24 | 2013-11-28 | 日本電気株式会社 | Pathological diagnosis results assessment system, pathological diagnosis results assessment method, and pathological diagnosis results assessment device |
| CN108573490A (en)* | 2018-04-25 | 2018-09-25 | 王成彦 | A kind of intelligent read tablet system for tumor imaging data |
| CN109166105A (en)* | 2018-08-01 | 2019-01-08 | 中国人民解放军南京军区南京总医院 | The malignancy of tumor risk stratification assistant diagnosis system of artificial intelligence medical image |
| CN109545302A (en)* | 2018-10-22 | 2019-03-29 | 复旦大学 | A kind of semantic-based medical image report template generation method |
| CN110335657A (en)* | 2019-07-10 | 2019-10-15 | 杭州大伽信息科技有限公司 | Standard compliation pathologic diagnosis of tumor report template generates system and method |
| CN110364236A (en)* | 2019-07-22 | 2019-10-22 | 卫宁健康科技集团股份有限公司 | Intelligent follow-up method, system, equipment and the storage medium of irradiation image report |
| CN110782972A (en)* | 2019-10-29 | 2020-02-11 | 重庆亚德科技股份有限公司 | Medical image archiving and communication system |
| CN111292821A (en)* | 2020-01-21 | 2020-06-16 | 上海联影智能医疗科技有限公司 | Medical diagnosis and treatment system |
| CN111461530A (en)* | 2020-03-30 | 2020-07-28 | 陈卫霞 | Image diagnosis report quality evaluation system and method thereof |
| CN111681737A (en)* | 2020-05-07 | 2020-09-18 | 陈�峰 | Structured report system and method for constructing liver cancer image database |
| CN111899845A (en)* | 2020-06-24 | 2020-11-06 | 北京赛迈特锐医疗科技有限公司 | DICOM image routing management system and method based on image inspection purpose |
| CN111916185A (en)* | 2020-08-17 | 2020-11-10 | 北京赛迈特锐医疗科技有限公司 | Management system and method for providing image data for AI diagnostic model |
- 2020
- 2020-11-13CNCN202011268228.0Apatent/CN112562816A/enactivePending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013175683A1 (en)* | 2012-05-24 | 2013-11-28 | 日本電気株式会社 | Pathological diagnosis results assessment system, pathological diagnosis results assessment method, and pathological diagnosis results assessment device |
| CN108573490A (en)* | 2018-04-25 | 2018-09-25 | 王成彦 | A kind of intelligent read tablet system for tumor imaging data |
| CN109166105A (en)* | 2018-08-01 | 2019-01-08 | 中国人民解放军南京军区南京总医院 | The malignancy of tumor risk stratification assistant diagnosis system of artificial intelligence medical image |
| CN109545302A (en)* | 2018-10-22 | 2019-03-29 | 复旦大学 | A kind of semantic-based medical image report template generation method |
| CN110335657A (en)* | 2019-07-10 | 2019-10-15 | 杭州大伽信息科技有限公司 | Standard compliation pathologic diagnosis of tumor report template generates system and method |
| CN110364236A (en)* | 2019-07-22 | 2019-10-22 | 卫宁健康科技集团股份有限公司 | Intelligent follow-up method, system, equipment and the storage medium of irradiation image report |
| CN110782972A (en)* | 2019-10-29 | 2020-02-11 | 重庆亚德科技股份有限公司 | Medical image archiving and communication system |
| CN111292821A (en)* | 2020-01-21 | 2020-06-16 | 上海联影智能医疗科技有限公司 | Medical diagnosis and treatment system |
| CN111461530A (en)* | 2020-03-30 | 2020-07-28 | 陈卫霞 | Image diagnosis report quality evaluation system and method thereof |
| CN111681737A (en)* | 2020-05-07 | 2020-09-18 | 陈�峰 | Structured report system and method for constructing liver cancer image database |
| CN111899845A (en)* | 2020-06-24 | 2020-11-06 | 北京赛迈特锐医疗科技有限公司 | DICOM image routing management system and method based on image inspection purpose |
| CN111916185A (en)* | 2020-08-17 | 2020-11-10 | 北京赛迈特锐医疗科技有限公司 | Management system and method for providing image data for AI diagnostic model |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113130067A (en)* | 2021-04-01 | 2021-07-16 | 上海市第一人民医院 | Intelligent reminding method for ultrasonic examination based on artificial intelligence |
| CN113130067B (en)* | 2021-04-01 | 2022-11-08 | 上海市第一人民医院 | Intelligent reminding method for ultrasonic examination based on artificial intelligence |
| CN113053487A (en)* | 2021-04-22 | 2021-06-29 | 薛蕴菁 | Method and device for automatically giving diagnosis suggestions based on structured report historical data |
| CN114464311A (en)* | 2021-12-30 | 2022-05-10 | 复旦大学附属中山医院厦门医院 | Information detection method, system, terminal device and storage medium |
| CN114566246A (en)* | 2022-01-25 | 2022-05-31 | 复旦大学附属中山医院厦门医院 | Structured report generation method, system, terminal device and storage medium |
| CN114566245A (en)* | 2022-01-25 | 2022-05-31 | 复旦大学附属中山医院厦门医院 | Information display method, system, terminal device and storage medium |
| CN115132351A (en)* | 2022-06-23 | 2022-09-30 | 三峡大学 | Diagnostic data feedback evaluation system and method based on real world research |
| CN116206749A (en)* | 2023-01-18 | 2023-06-02 | 首都医科大学附属北京儿童医院 | Method and system for converting disease codes |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112562816A (en) | System and method for correspondence and evaluation of diagnosis result and pathological result of tumor image report | |
| US11587184B2 (en) | Computer vision-based claims processing | |
| US7607079B2 (en) | Multi-input reporting and editing tool | |
| US20220172809A9 (en) | Report generating system and methods for use therewith | |
| Zarbo et al. | Error detection in anatomic pathology | |
| US20250241728A1 (en) | Real-time ai for physical biopsy marker detection | |
| US11170891B2 (en) | Image generation from a medical text report | |
| US10586018B2 (en) | Method and system for generating a medical report and computer program product therefor | |
| US20210158936A1 (en) | Medical scan co-registration and methods for use therewith | |
| US20090204437A1 (en) | System and method for improving diagnoses of medical image reading | |
| US20160012319A1 (en) | A context driven summary view of radiology findings | |
| JP2005510326A (en) | Image report creation method and system | |
| US20120278105A1 (en) | Protocol guided imaging procedure | |
| JP7677483B2 (en) | Information processing device, information processing method, and program | |
| WO2019146357A1 (en) | Medical image processing device, method, and program, and diagnosis assistance device, method, and program | |
| WO2022051867A1 (en) | System and method for image quality review of medical images | |
| Chen et al. | Performance of a breast cancer detection AI algorithm using the personal performance in mammographic screening scheme | |
| WO2012081649A1 (en) | Medical system | |
| JP2018063707A (en) | Image analysis system | |
| CN111986182A (en) | Auxiliary diagnosis method, system, electronic device and storage medium | |
| CN107330246A (en) | Introduction method, device and the computer-readable medium of medical image files | |
| CN118155795A (en) | A neurosurgery imaging diagnosis method and system based on graphic recognition | |
| CN104732086A (en) | Computer-assisted disease detection system based on cloud computing | |
| CN114830244A (en) | Temporal disease state comparison using multimodal data | |
| CN112270975A (en) | A labeling and teaching aid system for abdominal CT medical images |
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 | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20210326 | |
| RJ01 | Rejection of invention patent application after publication |