CN113870968A

CN113870968A - Medical image report generation method and device, computer equipment and storage medium

Info

Publication number: CN113870968A
Application number: CN202111069596.7A
Authority: CN
Inventors: 朱子戌; 张丽红; 张少伟
Original assignee: Shanghai United Imaging Healthcare Co Ltd
Current assignee: Shanghai United Imaging Healthcare Co Ltd
Priority date: 2021-09-13
Filing date: 2021-09-13
Publication date: 2021-12-31

Abstract

The application relates to a medical image report generation method and device, computer equipment and a storage medium. The method comprises the steps of analyzing image data of a patient to obtain focus information and a disease type of the patient, obtaining a section image of a focus part of the patient according to the focus information and the image data, obtaining pathological description information from a preset pathological knowledge base according to the disease type and the focus information, adding the pathological description information and the section image to an initial report template, obtaining an audit result after auditing the added initial report template, and generating a medical image report of the patient according to the audit result. In the process of generating the medical image report, the focus information, the disease type, the section image and the pathological description information are obtained by the automatic analysis of the medical terminal, so that the method can efficiently generate the medical image report and can avoid the problem of inaccurate generation of the medical image report caused by insufficient experience of doctors.

Description

Medical image report generation method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of medical imaging technologies, and in particular, to a method and an apparatus for generating a medical imaging report, a computer device, and a storage medium.

Background

With the progress of society and the continuous development of economic level, the medical science and technology level is also rapidly improved, how to reduce the burden of doctors through medical science and technology and artificial intelligence, improve the medical experience of patients, and is the target of medical science and technology enterprises.

In the current medical system, after the patient performs the image scanning, an image report is generally issued, and the image report of the patient mainly includes: patient, scan information, imaging performance, imaging diagnosis, image findings, physician and date information, etc. The process of generating such visual reports includes: after registration, the patient enters the department of the attending doctor to start an examination item and pay for examination; generating an image of a patient scanning area through a post-processing algorithm after the examination is finished; a doctor selects an image with a focus by observing the image and places the image into an iconography expression area of a report; the doctor observes the size and the position of the focus of the patient according to the representation of the imaging, and judges the pathological type and the like; doctors can complete the writing of reports of imaging performance, diagnosis and the like according to the types of pathology.

However, the output efficiency of the above image report is very low, and the workload of the doctor is very large with the proliferation of the patients.

Disclosure of Invention

In view of the above, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for generating a medical image report, which can improve output efficiency.

In a first aspect, a method for generating a medical image report includes:

analyzing the image data of a patient to obtain the focus information and the disease type of the patient;

obtaining a section image of the focus part of the patient according to the focus information and the image data;

acquiring pathological description information from a preset pathological knowledge base according to the disease type and the focus information;

and adding the pathological description information and the section image to an initial report template, acquiring an auditing result obtained after auditing the added initial report template, and generating a medical image report of the patient according to the auditing result.

In one embodiment, the analyzing the image data of the patient to obtain the lesion information and the disease type of the patient includes:

performing focus analysis on image data of a patient to obtain focus information of the patient;

and carrying out disease analysis on the focus information to obtain the disease type of the patient.

In one embodiment, the obtaining a sectional image of the lesion site of the patient according to the lesion information and the image data includes:

carrying out three-dimensional model reconstruction on the image data to obtain a three-dimensional tissue structure image;

and performing section processing on the tissue structure image according to the focus information to obtain a section image corresponding to the focus part.

In one embodiment, the generating a medical image report of the patient according to the audit result includes:

if the audit result is that the audit is passed, adding the signature of the doctor and the current time to the added initial report template to obtain the medical image report;

if the audit result is that the audit is not passed, new pathological description information and/or a new section image are obtained again, the new pathological description information and/or the new section image are updated to the added initial report template, the audit result after the updated initial report template is audited is obtained, and a medical image report of the patient is generated according to the audit result.

In one embodiment, the method further comprises:

acquiring medical information of the patient from registration information of the patient;

adding the patient's medical information to a blank report template, generating the initial report template.

In one embodiment, the pathology description information includes: descriptive information of the imaging performance and/or descriptive information of the imaging diagnosis.

In one embodiment, the lesion information includes: the size, position, density, symmetry and edge definition of the focus part.

In a second aspect, an apparatus for generating a medical image report includes:

the analysis module is used for analyzing the image data of the patient to obtain the focus information and the disease type of the patient;

the determining module is used for obtaining a section image of the focus part of the patient according to the focus information and the image data;

the first acquisition module is used for acquiring pathological description information from a preset pathological knowledge base according to the disease type and the focus information;

and the first generation module is used for adding the pathological description information and the section image into an initial report template, acquiring an audit result obtained after the added initial report template is audited, and generating a medical image report of the patient according to the audit result.

In a third aspect, a computer device comprises a memory storing a computer program and a processor implementing the method of the first aspect when the processor executes the computer program.

In a fourth aspect, a computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the method of the first aspect described above.

According to the method, the device, the computer equipment and the storage medium for generating the medical image report, the focus information and the disease type of the patient are obtained by analyzing the image data of the patient, the section image of the focus part of the patient is obtained according to the focus information and the image data, the pathological description information is obtained from the preset pathological knowledge base according to the disease type and the focus information, the pathological description information and the section image are added to the initial report template, the auditing result obtained after the added initial report template is audited is obtained, and the medical image report of the patient is generated according to the auditing result. In the process of generating the medical image report, the focus information, the disease type, the section image and the pathological description information are obtained by automatically analyzing by the medical terminal, the preset pathological knowledge base contains comprehensive pathological description information, accurate pathological description information can be quickly searched from the preset pathological knowledge base according to the specific disease type and the focus information, and doctors do not need to intervene in the process from analysis to searching of the pathological description information, namely the content of the medical image report is determined without depending on the experience of doctors, so that the method can efficiently and automatically generate the medical image report and reduce the workload of the doctors.

Drawings

FIG. 1 is a diagram of an exemplary medical imaging report generation process;

FIG. 2 is a flow diagram illustrating a method for generating a medical imaging report according to one embodiment;

FIG. 2A is a diagram illustrating a default pathology knowledge base in accordance with an embodiment;

FIG. 2B is a diagram illustrating a medical imaging report, according to an embodiment;

FIG. 3 is a schematic flow chart illustrating an implementation manner of S101 in the embodiment of FIG. 2;

FIG. 3A is a schematic structural view of lesion analysis;

FIG. 3B is a schematic structural view of lesion analysis;

FIG. 3C is a schematic diagram of disease analysis;

FIG. 3D is a schematic diagram of the structure of disease analysis;

FIG. 4 is a flowchart illustrating an implementation manner of S102 in the embodiment of FIG. 2;

FIG. 5 is a flow diagram illustrating a method for generating a medical imaging report according to one embodiment;

FIG. 6 is a flow diagram illustrating a method for generating a medical imaging report according to one embodiment;

FIG. 7 is a flow diagram illustrating a method for generating a medical imaging report according to one embodiment;

FIG. 8 is a flow diagram illustrating a method for generating a medical imaging report according to one embodiment;

FIG. 9 is a block diagram showing an exemplary embodiment of a medical image report generation apparatus;

FIG. 10 is a block diagram showing an exemplary embodiment of a medical image report generation apparatus;

FIG. 11 is a block diagram showing an exemplary embodiment of a medical image report generation apparatus;

FIG. 12 is a block diagram showing an exemplary embodiment of a medical imaging report generation apparatus;

FIG. 13 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The method for generating a medical image report provided by the present application can be applied to an application environment as shown in fig. 1, wherein a medical terminal 102 is connected to a medical scanning device 104, and the medical scanning device 104 scans a body part of a patient to obtain image data; the medical terminal 102 acquires image data from the medical scanning device 104 and generates a medical image report of the patient based on the image data. The medical scanning device 104 may be various types of scanning devices, such as Computed Tomography (CT), Magnetic Resonance scanning (MR), and so on. The medical terminal 102 may be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices.

Those skilled in the art will appreciate that the application environment shown in fig. 1 is only a block diagram of a portion of the structure associated with the present application and does not constitute a limitation on the application environment to which the present application is applied, and that a particular application environment may include more or less components than those shown in the drawings, or may combine certain components, or have a different arrangement of components.

Today, after the patient is scanned, the doctor usually presents an image report of the patient to inform the patient of the image examination result. The image report of the patient mainly comprises: some or all of the patient information, scan information, imaging performance, imaging diagnosis, image findings, doctor and date information, and the like. The medical imaging equipment acquires data images of corresponding areas of different body parts of a patient through imaging methods such as X-ray, magnetic resonance and the like, generally, the data images need to be converted into images for two-dimensional, three-dimensional post-processing and the like which can be browsed and read by a doctor through a medical equipment reconstruction algorithm, the doctor judges information such as a focus position, a focus size, possible pathology and disease types of the patient and the like of the patient by observing the medical images of the patient and combining self experience, expresses the information in an image report of the patient, and finally prints the information into a report or generates an electronic version report to be sent to a medical terminal to be handed to the patient. Most of the current major procedures for generating medical image reports include the following steps:

and S1, after registration of the patient, starting an examination item at the position of the main doctor and paying for examination.

And S2, after the patient is examined by the medical imaging equipment, the medical imaging equipment generates an image of the scanned area of the patient through a reconstruction algorithm and transmits the image to a doctor.

S3, the doctor selects the section image with the focus by observing the images of different sections, and edits the image expression area of the report.

S4, the doctor observes the size and position of the focus of the patient and judges the pathology according to the imaging performance.

And S5, determining the pathological information of the patient according to the size and position of the focus of the patient, judging the pathology and the like by the doctor, and filling the pathological information into the areas of the imaging performance, the imaging diagnosis and the like.

And S6, finishing signing by the doctor, filling in the date, generating a medical image report, and delivering the medical image report to the patient.

According to the process, in the existing medical imaging report generation process, a doctor needs to manually select one layer of section images containing the focus as an imaging representation area of the report by observing and analyzing the multi-layer images scanned and output by the medical imaging equipment; and doctors are required to observe the size, position, pathology and the like of the focus of the patient according to the imaging performance, further determine the pathological information by themselves, and then manually fill the pathological information into the reported imaging performance, imaging diagnosis and other areas. The medical image report generation method needs doctor intervention, increases a lot of workload for doctors, is extremely low in generation efficiency of the medical image report, and is extremely dependent on doctor experience in the process of generating the medical image report, so that the accuracy of the generated medical image report is low for doctors with shallow experience. Based on the problems in the prior art, the present application provides a method for automatically generating a medical image report, which can complete the writing of the medical image report more efficiently and accurately.

In one embodiment, as shown in fig. 2, a method for generating a medical image report is provided, which is described by taking the method as an example of being applied to the medical terminal in fig. 1, and includes the following steps:

s101, analyzing the image data of the patient to obtain the focus information and the disease type of the patient.

Wherein the lesion information includes at least one of type, size, position, density, symmetry, and edge definition of a lesion site. The image data may be image data obtained by scanning a body part of a patient by any type of medical imaging equipment, and may specifically be image data in DICOM format, and an image corresponding to the image data may be a three-dimensional image or a two-dimensional image. The medical imaging device may be a Computed Tomography (CT), a Magnetic Resonance scanning (MR), or the like.

In this embodiment, the medical imaging device may acquire image data of a region corresponding to a lesion of a patient by using an imaging method such as X-ray or magnetic resonance, and store the image data. When a medical image report corresponding to the image data needs to be generated, the medical terminal can be connected to the medical imaging device and acquire the image data of the patient from the medical imaging device according to the information of the patient, or the medical imaging device directly transmits the acquired image data of the patient to the medical terminal connected with the medical imaging device. When the medical terminal acquires the image data of the patient, a corresponding analysis algorithm can be further adopted to analyze based on the image data, so as to obtain an analysis result containing focus information and disease types. Specifically, the medical terminal may pre-construct an analysis network, for example, an analysis network is constructed by using a convolutional neural network algorithm or a machine learning algorithm, the constructed analysis network may be used to analyze the image data to obtain an analysis result including the lesion information and the disease type, the computer device may also pre-construct two analysis networks, different analysis networks are used to perform different content analyses on the image data to obtain different analysis results, for example, a first analysis network and a second analysis network are constructed by using a convolutional neural network, the first analysis network is used to obtain the lesion information based on the image data analysis, and the second analysis network is used to obtain the disease type based on the image data analysis. In practical application, after the computer device acquires the image data, the image data can be input into one constructed analysis network for analysis, or input into two constructed analysis networks for analysis, so as to obtain the focus information and the disease type of the patient.

S102, obtaining a section image of the focus part of the patient according to the focus information and the image data.

When the medical terminal acquires the image data of the patient, a corresponding image reconstruction algorithm can be further adopted to reconstruct the image data to obtain a two-dimensional or three-dimensional image or image, specifically, a plurality of layers of images can be generated, and the images of different layers correspond to the images of different sections of the scanning area. Since all slice images of all layers do not contain the lesion site of the patient, the computer device needs to analyze the lesion information of the patient, further realize the positioning of the lesion site in the multilayer image, so as to judge the size and the position of the lesion, and then screen out the slice images containing the lesion site from the multilayer image according to the size and the position of the lesion, or slice the slice images from the multilayer image at different angles to obtain the slice images containing the lesion site at different angles. It should be noted that the sectional image of the lesion site may be a layer of image, and the layer of image includes a sectional view of the lesion site; the sectional image of the lesion site may also include different layer images including sectional views of the lesion site at different angles. It is understood that the sectional image is obtained in this embodiment, and in practical applications, a three-dimensional image including a lesion site, for example, a VR image, may also be obtained.

And S103, acquiring pathological description information from a preset pathological knowledge base according to the disease type and the focus information.

The preset pathology knowledge base can be a cloud database or a local database. The preset pathology knowledge base includes pathology description information corresponding to different disease types of different focus locations, optionally, the preset pathology knowledge base may also include pathology description information corresponding to different disease types of different focus locations in different scanning modes, for example, as shown in fig. 2A, the preset pathology knowledge base includes pathology description information corresponding to bronchopneumonia and old tuberculosis of a chest in a CT scanning mode, pathology description information corresponding to space occupying disease of a skull in a CT scanning mode and acute cerebral infarction, pathology description information corresponding to different diseases of different locations in other scanning modes (e.g., MR, MI, etc.) (not specifically shown in the figure), and information description of different focus locations in different scanning modes in a normal condition (e.g., normal item description under the chest in fig. 2A). Wherein the pathology description information includes: descriptive information of the imaging performance and/or descriptive information of the imaging diagnosis.

In this embodiment, after the medical terminal obtains the disease type and the lesion information of the patient, the medical terminal may search the corresponding pathological description information from the preset pathological knowledge base according to the disease type and the lesion information, and by combining with the scanning manner corresponding to the image data, for example, referring to the preset pathological knowledge base shown in fig. 2A, when CT scanning is performed on the patient, CT scanning data is obtained, the computer device analyzes the CT scanning data based on the foregoing method, and obtains that the lesion part of the patient is a chest and the disease type of the patient is bronchopneumonia, then the medical terminal searches the pathological description information corresponding to the bronchopneumonia disease of the chest in the CT scanning manner from the preset pathological knowledge base shown in fig. 2A, and the searched pathological description information includes an imaging performance and an imaging diagnosis, where the imaging performance includes contents shown in fig. 2A, for the content of the imaging diagnosis, please refer to fig. 2A, which is not described herein. It should be noted that the item contents included in the preset pathology knowledge base shown in fig. 2A are only an example, for example, some pathology knowledge bases include pathology description information corresponding to different disease types at different focus sites, and information under different scanning modes is not distinguished.

And S104, adding the pathological description information and the section image into the initial report template, acquiring an auditing result obtained after auditing the added initial report template, and generating a medical image report of the patient according to the auditing result.

The initial report template is constructed in advance by a computer device, and includes a plurality of areas to which information is to be added, and titles of corresponding reports, for example, as shown in fig. 2B, the initial report template includes a title of a report (medical image report), a display area of patient information, a display area of scanning information, a display area of imaging performance, a display area of imaging diagnosis, a display area of image viewing, and a display area of doctor signature and time. The display area seen by the image is used for displaying a section image of the focus part, and can display one section image and also can display a plurality of section images at different angles; the display area of the imaging performance and the display area of the imaging diagnosis are used for pathological descriptive information like a patient.

After the medical terminal acquires the pathological description information of a patient and the section image of a focus part, the pathological description information and the section image can be added to a corresponding area in an initial report template to generate an initial report, the initial report is displayed to a doctor, the doctor can check and audit the initial report on the medical terminal to determine whether the imaging findings, the imaging performances and the imaging diagnoses contained in the initial report are accurate, if the audit result is accurate, the doctor inputs own signature on the medical terminal or clicks a button for confirming that the audit is completed to determine that the audit is completed, and the medical terminal automatically adds the signature of the doctor to the initial report to generate the medical image report. Optionally, after the medical terminal generates the initial report, the initial report may also be sent to a user terminal of a doctor, the doctor may view and review the initial report on the user terminal of the doctor, the user terminal may feed back the review result to the medical terminal, and the medical terminal generates the medical image report according to the review result. Optionally, after the medical terminal generates the initial report, the initial report may also be audited in an artificial intelligence manner, and after the audit is completed, the medical image report is automatically generated. The medical terminal can print out the medical image report after generating the medical image report, and can also store the medical image report so as to store the relevant treatment information of the patient. An application scene also exists, if the auditing result is inaccurate, the medical terminal can acquire the relevant information of the patient again for analysis, and the initial report is generated again; alternatively, the doctor may modify the initial report, and the medical terminal modifies the initial report according to the modified content of the doctor and generates a medical image report based on the newly modified initial report.

According to the method for generating the medical image report, the focus information and the disease type of the patient are obtained by analyzing the image data of the patient, the section image of the focus part of the patient is obtained according to the focus information and the image data, the pathological description information is obtained from the preset pathological knowledge base according to the disease type and the focus information, the pathological description information and the section image are added to the initial report template, the auditing result obtained after the added initial report template is audited is obtained, and the medical image report of the patient is generated according to the auditing result. In the process of generating the medical image report, the focus information, the disease type, the section image and the pathological description information are obtained by automatically analyzing by the medical terminal, the preset pathological knowledge base contains comprehensive pathological description information, accurate pathological description information can be quickly searched from the preset pathological knowledge base according to the specific disease type and the focus information, and doctors do not need to intervene in the process from analysis to searching of the pathological description information, namely the content of the medical image report is determined without depending on the experience of doctors, so that the method can efficiently generate the medical image report and can avoid the problem that the generated medical image report is inaccurate due to insufficient experience of the doctors.

Optionally, an implementation manner of the above S101 is provided, as shown in fig. 3, where the above S101 "obtains the lesion information and the disease type of the patient by analyzing the image data of the patient", and includes:

s201, focus information of the patient is obtained by analyzing the image data of the patient.

In this embodiment, as shown in fig. 3A, the medical terminal may construct a lesion analysis network in advance according to a neural network algorithm or a machine learning algorithm, and when the medical terminal acquires image data of a patient, the image data may be directly input into the constructed lesion analysis network for lesion analysis, so as to directly obtain lesion information corresponding to the image data; optionally, in another application, as shown in fig. 3B, the medical terminal may construct a lesion segmentation network and a lesion analysis network in advance according to a neural network algorithm or a machine learning algorithm, when the medical terminal acquires image data of a patient, the image data may be input into the constructed lesion segmentation network to identify and position a lesion site in the image data, so as to obtain a segmentation image including the lesion site, and then the lesion analysis network is used to analyze a lesion in the segmentation image, so as to obtain lesion information including a lesion type, a lesion position, a lesion size, a lesion density, a lesion symmetry, a lesion edge definition, and the like.

S202, disease analysis is carried out on the focus information to obtain the disease type of the patient.

In this embodiment, as shown in fig. 3C, the medical terminal may construct a disease analysis network in advance according to a neural network algorithm or a machine learning algorithm, and when the medical terminal acquires the lesion information, the lesion information may be directly input into the constructed disease analysis network for disease analysis, so as to directly obtain a disease type corresponding to the lesion information, that is, a disease type of a patient; optionally, as shown in fig. 3D, the medical terminal may construct different types of disease analysis networks in advance according to a neural network algorithm or a machine learning algorithm, for example, a blood vessel analysis network, a bone structure analysis network, a perfusion analysis network, a nodule analysis network, a tumor analysis network, and a density analysis network in fig. 3D, and select a corresponding type of analysis network to perform analysis based on lesion information according to a lesion type indicated by the lesion information, for example, as shown in fig. 3D, if the lesion type indicated by the lesion information is a bone structure type, the medical terminal inputs the lesion information into the bone structure analysis network to perform bone structure type disease analysis, so as to obtain a disease type corresponding to the lesion information; if the focus type indicated by the focus information is a blood vessel type, the medical terminal inputs the focus information into a blood vessel analysis network for blood vessel disease analysis, and a disease type corresponding to the focus information is obtained.

Optionally, an implementation manner of the S102 is provided, as shown in fig. 4, the S102 "obtaining a sectional image of a lesion site of a patient according to lesion information and image data" includes:

s301, three-dimensional model reconstruction is carried out on the image data to obtain a three-dimensional tissue structure image.

When the medical terminal acquires the image data of the patient, a corresponding model construction algorithm can be adopted to carry out three-dimensional model reconstruction on the image data, and specifically, the sequence pictures are fused to obtain a high-precision three-dimensional tissue structure image. Optionally, when the medical terminal obtains the three-dimensional model according to model building calculation and reconstruction, the model can be clearly and easily observed through movie-level rendering, so that when a doctor wants to view the image of the three-dimensional model, each tissue structure of the image can be clearly observed; optionally, the medical terminal may further mark a possible lesion position in the three-dimensional tissue structure image, so that a sectional image of the lesion site can be accurately extracted later.

S302, according to the focus information, performing section processing on the tissue structure image to obtain a section image corresponding to the focus part.

The tissue structure image is a multilayer image, and each layer of image does not contain a focus position, so that the tissue structure image needs to be further subjected to section processing, specifically, the focus position in the tissue structure image is positioned according to the focus type, the focus position, the focus size and the like indicated by the focus information, and one layer of image or multiple layers of images containing the focus position are screened from the multilayer image according to the position of the focus position, namely the section image corresponding to the focus position, or the multilayer tissue structure image is subjected to segmentation processing according to the position of the focus position and the focus size, so that a segmentation image containing the focus position is obtained, namely the section image corresponding to the focus position. The section image corresponding to the focus part can be the section image of the focus part with different angles.

In the above embodiment, the medical terminal reconstructs a three-dimensional model and performs slice processing on the image according to the lesion information to obtain a slice image corresponding to the lesion position, so as to implement a method for automatically analyzing the tissue structure image and screening the slice image including the lesion position.

In one application, a doctor needs to review the added initial report template to generate a medical image report, and the process of generating the medical image report is different for different review results, for example, the different process is provided as shown in fig. 5, and the method includes:

and S401, if the audit result is that the audit is passed, adding the signature of the doctor and the current time in the added initial report template to obtain a medical image report.

Wherein, the current time is the auditing time. In this embodiment, if the examination result determined by the doctor is that the examination is passed, it indicates that the pathological description information and the section image added by the medical terminal on the initial report template are accurate, and based on this environment, the doctor can input his/her signature and current time at the corresponding area position of the initial report template to add the doctor information in the medical image report, thereby completing the medical image report. It should be noted that, the doctor may input his/her signature and current time on the computer device by editing, or may input his/her signature and current time by clicking a pull-down menu, which is not limited herein. After the doctor inputs the self signature and the current time, the medical terminal automatically adds the signature and the current time input by the doctor to a corresponding area in the initial report template, and then generates a medical image report.

And S402, if the audit result is that the audit is not passed, acquiring new pathological description information and/or a new section image again, updating the new pathological description information and/or the new section image to the added initial report template, acquiring the audit result after the audit is performed on the updated initial report template, and generating a medical image report of the patient according to the audit result.

If the examination result determined by the doctor is that the examination is not passed, it indicates that the pathology description information and/or the section image added by the medical terminal on the initial report template may have errors or be inaccurate, based on the environment, the doctor may select whether to add the pathology description information and/or the section image on the initial report template again, if the doctor selects to add the pathology description information and/or the section image on the initial report template again, i.e. to obtain the pathology description information and/or the section image again, the doctor inputs a re-examination instruction on the medical terminal, when receiving the re-examination instruction, the medical terminal obtains new pathology description information and/or a new section image again according to the method, and updates the corresponding information in the current initial report template according to the new pathology description information and/or the new section image, for example, the new pathology description information is used to replace the pathology description information in the initial report template, the new section image is used to replace the section image in the initial report template, then the medical terminal obtains the initial report template after the information is updated again, and then the initial report template after the information is updated is fed back to the doctor for re-examination until the examination is passed; if a doctor selects to modify the pathological description information and/or section image on the current initial report template or supplement information on the current initial report template, the doctor can directly edit the content in the initial report template on the medical terminal to complete the modification or supplement of the content, and then the medical terminal generates a medical image report according to the initial report template after the doctor inputs the information. It should be noted that, when the doctor modifies the slice image on the current initial report template, a slice image may be reselected from a plurality of slice images acquired by the previous medical terminal, or a three-dimensional tissue structure image reconstructed by the previous medical terminal may be observed again, and the slice image may be determined therefrom.

In a typical medical image report, information related to a patient is included, and therefore, in one embodiment, a method for obtaining patient information and generating an initial report template including the patient information is provided, as shown in fig. 6, the method includes:

s501, medical information of the patient is acquired from the registration information of the patient.

The medical information includes at least one of the name, sex, age, patient number, past medical history, hospitalization information, etc. of the patient.

The medical terminal may be connected to a medical system of a hospital, such as a Radiology Information System (RIS), and retrieve registration information of a patient therefrom and extract medical information of the patient based on the registration information of the patient.

S502, adding the medical information of the patient to a blank report template to generate an initial report template.

After the medical terminal acquires the medical information of the patient, the medical information can be added to a corresponding area (for example, a report head area) in a blank report template so as to identify the attribute of the medical image report generated later, and a doctor can check the accuracy of the pathological description information and/or section image automatically acquired by the medical terminal conveniently later, so that the checking accuracy can be improved by combining the medical information of the patient, and the accuracy of generating the medical image report can be further improved.

In summary, in the above embodiments, there is provided a method for generating a medical image report, as shown in fig. 7, the method includes:

s601, acquiring medical information of the patient from the registration information of the patient.

S602, adding the medical information of the patient to a blank report template to generate an initial report template.

And S603, acquiring the image data and the scanning information of the patient by connecting the scanning equipment.

S604, performing focus analysis on the image data of the patient to obtain focus information of the patient.

And S605, analyzing the disease of the focus information to obtain the disease type of the patient.

And S606, performing three-dimensional model reconstruction on the image data to obtain a three-dimensional tissue structure image.

And S607, performing section processing on the tissue structure image according to the focus information to obtain a section image corresponding to the focus part.

And S608, acquiring pathological description information from a preset pathological knowledge base according to the disease type, the focus information and the scanning information.

And S609, adding the pathological description information and the section image into the initial report template, and acquiring an audit result of the added initial report template after the doctor audits, wherein if the audit result is that the audit is passed, the step S611 is executed, and if the audit result is that the audit is not passed, the step S612 is executed.

And S611, adding the signature of the doctor and the current time to the added initial report template to obtain a medical image report.

And S612, acquiring new pathological description information and/or a new section image again, updating the new pathological description information and/or the new section image to the added initial report template, and returning to the step of executing S609.

The above steps are all described, and please refer to the above description for details, which are not described herein.

Based on the above method, there is also provided a method for generating a medical image report in practical application, as shown in fig. 8, the method includes the steps of:

s701, patient registration information is obtained by the computer equipment.

S702, when the primary doctor determines that the patient needs to be scanned and examined after the primary diagnosis of the patient, the computer equipment acquires the scanning information and the image data of the medical imaging equipment.

And S703, performing focus analysis by the computer equipment based on the image data to obtain focus information.

S704, the computer device performs a disease analysis (at least one of bone structure analysis, blood vessel analysis, perfusion analysis, nodule analysis, tumor analysis, and density analysis) based on the image data, and obtains a disease type of the patient after performing the above analysis based on the extracted lesion.

S705, the computer device carries out three-dimensional model reconstruction based on the image data to obtain a three-dimensional tissue structure image.

S706, the computer device carries out image section processing on the three-dimensional tissue structure image according to the focus information to obtain a focus multi-angle section view.

And S707, the computer device compares the knowledge base according to the focus information, the scanning mode and the disease type, and extracts the pathological description information from the knowledge base according to the comparison result.

And S708, acquiring pathological description information of the patient and doctor information input by the computer equipment after the doctor reviews the multi-angle section of the focus.

And S708, adding the patient information, the scanning information, the pathological description information, the multi-angle focus cross-sectional drawing and the doctor information to corresponding areas in the blank medical image report by the computer equipment to generate the medical image report.

The detailed description of the above steps is introduced in the above, and please refer to the above contents for details, which are not described herein.

It should be understood that although the various steps in the flow charts of fig. 2-8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-8 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.

In one embodiment, as shown in fig. 9, there is provided a medical image report generation apparatus, including:

the analysis module 11 is configured to analyze image data of a patient to obtain lesion information and a disease type of the patient.

And the determining module 12 is configured to obtain a sectional image of the lesion site of the patient according to the lesion information and the image data.

A first obtaining module 13, configured to obtain pathological description information from a preset pathological knowledge base according to the disease type and the lesion information.

The first generating module 14 is configured to add the pathology description information and the section image to an initial report template, obtain an examination result obtained by examining the added initial report template, and generate a medical image report of the patient according to the examination result.

In an embodiment, as shown in fig. 10, the analysis module 11 specifically includes:

a first analysis unit 111, configured to perform a lesion analysis on image data of a patient to obtain lesion information of the patient;

and a second analysis unit 112, configured to perform disease analysis on the lesion information to obtain a disease type of the patient.

In an embodiment, as shown in fig. 11, the determining module 12 specifically includes:

a reconstruction unit 121, configured to perform three-dimensional model reconstruction on the image data to obtain a three-dimensional tissue structure image;

a section unit 122, configured to perform section processing on the tissue structure image according to the lesion information, so as to obtain a section image corresponding to the lesion position.

In an embodiment, as shown in fig. 12, the generating module 14 specifically includes:

a first generating unit 141, configured to, if the review result is that the review is passed, add the signature of the doctor and the current time to the added initial report template to obtain the medical image report.

And a second generating unit 142, configured to, when the audit result is that the audit is not passed, obtain new pathology description information and/or a new slice image again, update the new pathology description information and/or the new slice image to the added initial report template, obtain an audit result after the audit is performed on the updated initial report template, and generate a medical image report of the patient according to the audit result.

In one embodiment, as shown in fig. 13, the apparatus for generating a medical image report includes:

a second obtaining module 15, configured to obtain medical information of the patient from registration information of the patient;

a second generating module 16, configured to add the medical information of the patient to a blank report template, and generate the initial report template.

For specific limitations of the medical image report generation device, reference may be made to the above limitations of the medical image report generation method, which are not described herein again. All or part of the modules in the medical image report generation device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 13. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of generating a medical imaging report. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 13 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:

The implementation principle and technical effect of the computer device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A method for generating a medical image report, the method comprising:

2. The method of claim 1, wherein the obtaining of the lesion information and the disease type of the patient by analyzing the image data of the patient comprises:

3. The method of claim 1 or 2, wherein obtaining a sectional image of the lesion site of the patient based on the lesion information and the image data comprises:

carrying out three-dimensional model reconstruction on the image data to obtain an organization structure image;

4. The method of claim 1, wherein generating a medical image report of the patient based on the audit result comprises:

5. The method of claim 1, further comprising:

6. The method of claim 1, wherein the pathology description information comprises: descriptive information of the imaging performance and/or descriptive information of the imaging diagnosis.

7. The method of claim 1, wherein the lesion information comprises: the size, position, density, symmetry and edge definition of the focus part.

8. An apparatus for generating a medical image report, the apparatus comprising:

9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.