A review process labeling storage and reproduction method and system
By labeling the review process in the three-dimensional breast ultrasound diagnostic system, the problem that the existing technology cannot record and reproduce the diagnostic process is solved, the detailed recording and interactive operation of the diagnostic process is realized, and the diagnostic work is improved. Convenience and accuracy, suitable for a variety of medical occasions.
Patent Information
- Application Number
- CN202110235191.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-03-03
- Publication Date
- 2024-12-10
- Estimated Expiration
- 2041-03-03
AI Technical Summary
The existing three-dimensional breast ultrasound diagnosis system cannot effectively record and reproduce the doctor's review process, which makes it difficult to record the complexity and details of the diagnosis process, affecting the diagnosis of difficult diseases, patient follow-up visits, collaborative examinations, evidence collection for doctor-patient disputes and diagnosis teaching, etc. The demand for occasions increases the work burden of doctors.
The review process labeled storage reproduction method is used to split the review process into scenes arranged in time, digitally encode and label naming, form a scene label library, and use feature value retrieval and matching to realize parameter-by-parameter replication of the review process. Now, it supports interactive operations and high-speed distribution.
It realizes detailed recording and interactive operation of the diagnostic process, reduces storage media consumption, provides efficient reproduction and collaborative operation capabilities, and is suitable for patients' follow-up visits, collaborative examinations, evidence collection for medical and patient disputes, and training and teaching, which significantly improves the The convenience and accuracy of diagnostic work.
Smart Images

Figure CN113130087B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of medical diagnosis process recording, and specifically relates to a review process labeling storage and reproduction method and system. Background Art
[0002] The 3D breast ultrasound diagnostic system workstation is a computer software system that analyzes the image data obtained by the 3D breast ultrasound scanning station and draws diagnostic conclusions. The ultrasound diagnostic system workstation can be used together with the ultrasound diagnostic system scanning station, or it can be used alone as a diagnostic aid and medical research system.
[0003] The results of 3D breast ultrasound scanning mainly include volume data of different parts of the left and right breasts. Reviewing these data requires reconstruction of volumetric 3D images and sections, including the coronal plane parallel to the front of the human body, the cross-section plane orthogonal to the human body, and the sagittal plane orthogonal to the human body. These data are included in the patient's examination data.
[0004] The process of observing, marking, studying and reporting the patient's examination data on the workstation is an important part of the doctor's diagnosis. Traditional workstation software mainly focuses on the reconstruction imaging technology of the examination image, but not the work process, and does not adequately record the doctor's work practice. The review process in these work practices, namely reading the image, optimizing the image, and processing the marking and measurement process, is the core work of the diagnosis.
[0005] Often, we require more than just a diagnosis result, but also pay close attention to the process of diagnosis. For example, in the diagnosis of difficult diseases, follow-up visits for patients, collaborative examinations, evidence collection for medical disputes, workstation training, and diagnostic teaching, we need to reproduce and repeatedly review the review process. However, the existing ultrasound diagnostic system does not provide direct means in this regard, which not only makes it impossible to meet the urgent needs of the above-mentioned occasions, but also causes the loss of valuable medical experience and medical resources.
[0006] The process of a doctor reviewing an examination is closely related to the doctor's experience, the nature of the case itself, and diagnostic research activities. There is no unified standard process that can be recorded, and the doctor's diagnostic behavior is difficult to express in words. When recording is needed, screen recording, video recording, etc. can generally be used. However, recording not only requires additional equipment or software, but also requires learning new operations, which adds a greater burden to the already heavy diagnostic work and cannot be carried out regularly. The point is that screen recording and video recording alone cannot reflect the details of the diagnosis. Summary of the invention
[0007] In view of the above-mentioned problems existing in the prior art, the present invention proposes a method and system for labeling, storing and reproducing the review process, which can digitally encode the review process and record and apply it. It can not only record the review details but also enable interactive operations, thereby greatly facilitating doctors' diagnosis, research, auditing, training and teaching.
[0008] The present invention adopts the following technical solution: a method for labeling, storing and reproducing a review process, comprising the steps of:
[0009] S1. Break the review process into a series of scenarios arranged in time;
[0010] S2, encoding the information contained in a series of scenes to digitize the scene information;
[0011] S3, labeling and storing the digitized scenes to form a scene label library;
[0012] S4, searching by using the feature value as a parameter to match and extract the corresponding scene tag in the scene tag library;
[0013] S5. Reproduce the digitized scene information corresponding to the scene tag extracted by matching parameter by parameter.
[0014] As a preferred solution, the steps between step S3 and step S4 further include:
[0015] A. receiving a transmitted scene tag and digitized scene information corresponding to the scene tag;
[0016] B. Storing the received scene tags and the digitized scene information corresponding to the scene tags in a scene tag library.
[0017] As a preferred solution, step S3 further includes the following steps: adding, deleting, modifying, and checking the tag main entity, or changing the value of a single tag record field.
[0018] As a preferred solution, the scene information includes review object information, review action information, review environment information and review instruction information, wherein:
[0019] Review object information: including patient information and examination data;
[0020] Review action information: including operation action information when using the functions provided by the ultrasound workstation;
[0021] Review environment information: including image arrangement, whether the image is scaled, and image viewing angle information;
[0022] Review instructions: Includes comments during the review process.
[0023] As a preferred solution, the functions provided by the ultrasound workstation include free reading of images, marking and measurement, and the annotation information includes annotation frame lines, annotation symbols, annotations and recordings.
[0024] As a preferred solution, the DICOM protocol is used to digitize the review object information.
[0025] As a preferred solution, the feature values include average features, attribute features and additional features, wherein:
[0026] Average feature: The scene feature value matched with the string feature value used in scene encoding;
[0027] Attribute features: including keywords, values, and storage time information of scene coding;
[0028] Additional features: Includes a string entered by the user.
[0029] Accordingly, a review process labeling storage and reproduction system is also provided, comprising a scene division module, a scene encoding module, a label recording module, a feature retrieval module and an interactive replay module;
[0030] A scenario partitioning module, which is used to split the review process into a series of scenarios arranged in time;
[0031] A scene encoding module is used to encode the information contained in a series of scenes to digitize the scene information;
[0032] A label recording module is used to label and store the digitized scenes to form a scene label library;
[0033] A feature retrieval module is used to perform retrieval using feature values as parameters to match and extract corresponding scene tags in a scene tag library;
[0034] The interactive replay module is used to reproduce the digitized scene information corresponding to the matched extracted scene labels parameter by parameter.
[0035] As a preferred solution, it also includes a data receiving module for receiving the transmitted scene tags and the digitized scene information corresponding to the scene tags; the tag recording module is also used to store the received scene tags and the digitized scene information corresponding to the scene tags in the scene tag library.
[0036] As a preferred solution, an editing module is also included for adding, deleting, modifying and checking the tag main entity, or changing the value of a single tag record field.
[0037] The beneficial effects of the present invention are:
[0038] 1. Digitally encoding, recording and applying the review process can not only record the review details, but also enable interactive operations, thus greatly facilitating doctors' diagnosis, research, auditing, training and teaching.
[0039] 2. The review process in the reproduction is fully parameterized, so you can interrupt, change and other interactive operations at any time without affecting the subsequent reproduction process.
[0040] 3. The content in the scene tag library does not contain the pixel data of the image itself, so it can be distributed at high speed, thereby achieving real-time replay. A pair of ultrasound workstations that replay each other can better collaborate.
[0041] 4. The recorded results can be used in patient follow-up visits, collaborative examinations, evidence collection for medical disputes, training and teaching, etc. Compared with ordinary video or screen recordings, it has significant advantages such as low storage medium consumption, accurate content, and interactivity. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0043] Figure 1 It is a flowchart of a method for labeling, storing and reproducing a review process;
[0044] Figure 2 It is a structural diagram of a review process labeling storage and reproduction system. DETAILED DESCRIPTION
[0045] The following describes the embodiments of the present invention through specific embodiments, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.
[0046] Embodiment 1:
[0047] Reference Figure 1 This embodiment provides a method for labeling, storing and reproducing a review process, which is applied to an ultrasound workstation and includes the following steps:
[0048] S1. Break the review process into a series of scenarios arranged in time;
[0049] S2. Encode the information included in a series of scenarios to digitize the scenario information;
[0050] S3. Name and store the digitized scenarios with tags to form a scenario tag library;
[0051] S4. Retrieve using the eigenvalue as a parameter to match and extract the corresponding scenario tags in the scenario tag library;
[0052] S5. Reproduce the digitized scenario information corresponding to the matched and extracted scenario tags parameter by parameter.
[0053] Specifically:
[0054] The information content of a complete scene includes: review object information, review action information, review environment information, and review instruction information.
[0055] (1). Review object information: including patient data and the scan result information of ultrasonically scanning this patient, i.e., study data. This information is directly digitized using the DICOM protocol.
[0056] (2). Review action information: including the operation action information when the doctor uses the functions provided by the ultrasound workstation. The functions provided by the ultrasound workstation include free image viewing, marking, measuring, etc. This information is digitized using action numbers and each action is attached with attributes such as action duration, action classification, attribution, the product or consequence of the action, etc.
[0057] (3). Review environment information: including the image arrangement method, whether the image is scaled, and the image viewing angle information, etc.
[0058] (4). Review instruction information: including the annotation information of the doctor during the review process. The annotation information includes annotation box lines, annotation symbols, annotations, recordings, etc.
[0059] Take the Xml format as an example for the scenario encoding method:
[0060] <Patient patient>
[0061] <name> name< / name>
[0062] <dob> Date of Birth< / dob>
[0063] <weight> weight< / weight>
[0064] < / Patient patient>
[0065] <Study examination>
[0066] <id> Check ID< / id>
[0067] <type> Check type< / type>
[0068] < / Study Check>
[0069] <Action Action>
[0070] <user> doctor< / user>
[0071] <volume> Scanning area< / volume>
[0072] <layout>Hanging method <layout>
[0073] < / Action Action>
[0074] <Context Environment>
[0075] <scale> Scaling< / scale>
[0076] <port> Image display area< / port>
[0077] <Context Environment>
[0078] <Sign Indicator Data>
[0079] <mouse> Mouse position< / mouse>
[0080] <roiarea> Areas of interest< / roiarea>
[0081] <symbol> Marking symbols< / symbol>
[0082] <note>< / note>
[0083] <record>< / record>
[0084] < / Sign Indicator Data>
[0085] Whether the scene is valid has nothing to do with the information integrity of the scene. The selection of the four aspects and the selection of the information of the aspect content are related to the use of the scene. And the scene can be an empty scene without any information, and the empty scene can exist as a placeholder in a series of scenes.
[0086] At a certain moment, the information set of the above-related content constitutes the scene of the review process of the ultrasound workstation. If any sub-item of the scene content changes, it is considered that the scene has changed. Then, as long as these scenes are recorded, the review process can be recorded. Therefore, we name and manage the scenes, save a series of scene tags as a scene tag library, and complete the scene tagging.
[0087] Furthermore, the tag naming includes internal naming and external naming:
[0088] The internal naming uses a globally unique identifier, and the external naming uses a custom prefix and suffix plus an ordered value.
[0089] The storage method of the scene tags includes manual storage and automatic storage:
[0090] Manual storage means storing according to the user's意愿 at any time. For example, a scene tag button is set on the toolbar, and when the user clicks it, a scene is generated.
[0091] Automatic storage means that the scenes that meet the conditions are automatically stored based on the changes in time, action, environment, etc. For example, if the trigger conditions are marking and deleting marks, all scenes after the user changes the mark will be automatically recorded. The introduction of automatic storage as a supplement to manual storage reduces the steps of user operation and enhances the ease of use of scene coding.
[0092] The structure of the scene tag library formed by the stored scene tags is similar to that of a general relational database. Review objects, review actions, review environments, and review instructions are all entities that use the internal name of the tag main entity as the primary reference foreign key.
[0093] Therefore, step S3 may be followed by the following steps: adding, deleting, modifying, and checking the tag main entity, or changing the value of a single tag record field.
[0094] Furthermore, the steps between step S3 and step S4 include:
[0095] A. receiving a transmitted scene tag and digitized scene information corresponding to the scene tag;
[0096] B. Storing the received scene tags and the digitized scene information corresponding to the scene tags in a scene tag library.
[0097] It can receive scene tag contents transmitted from other ultrasound workstations. The transmission unit can be a single scene tag library or a single scene tag. It should be noted that in addition to receiving scene tag contents transmitted from other ultrasound workstations, the scene tag contents of this workstation can also be sent to other ultrasound workstations. The exported data can be carried by the network or external storage media such as hard disk and USB flash drive, and imported into the scene tag library on the workstation.
[0098] Furthermore, the feature value is used as a parameter for retrieval to match and extract the corresponding scene tag in the scene tag library, and the feature value includes average feature, attribute feature and additional feature:
[0099] (1) Average feature: The scene feature value matched by the string feature value used in scene encoding is adopted. Scenes with the same feature value have similarity in related parameters. Fuzzy retrieval of scenes is realized. Take the observation direction and observation point in scene encoding as an example: extract the string generated by connecting the direction and observation point parameters, and extract the feature value. Thus, users can retrieve a series of scene labels produced at the same or similar angles. In medical teaching, it is easy to find similar demonstration cases for students.
[0100] (2) Attribute characteristics: including the keywords, values and storage time information of the scene code, which enables accurate retrieval of the scene.
[0101] (3) Additional features: including strings entered by users. This enables user-defined logical retrieval of scenarios.
[0102] Furthermore, the process of reproducing the parameters of the continuously matched scene tags on the workstation is called replay. When the matched scene tags come from this workstation, it is the replay of the review process of this workstation. When the matched scene tags come from other workstations, it is the replay of the review process of other workstations. It can be divided into real-time collaborative replay and non-real-time replay according to different real-time performance.
[0103] Among them, because the review process in the replay is fully parameterized, it can be interrupted, changed, and other interactive operations at any time without affecting the subsequent replay process. And because the scene tag does not contain the pixel data of the image itself, it can be distributed at high speed, thereby achieving real-time replay. A pair of workstations that replay each other constitute a collaborative operation.
[0104] In medical education, the review process of a typical examination by an expert can be generated into a set of scene tags and replayed in medical education. During the replay, students can see the steps and process of the expert's review at that time. They can also cut into their own operations in a reproduced scene at any time, and continue to return to the replay process of the original scene after the operation.
[0105] Through the above solution, the doctor's review process can be fully recorded, and the recorded results can be used in patient follow-up, collaborative examination, evidence collection for medical disputes, training and teaching, etc. Compared with ordinary video or screen recording data, it has significant advantages such as low storage medium consumption, accurate content, and interactivity.
[0106] Embodiment 2:
[0107] Reference Figure 2 ,This embodiment provides a review process labeling storage and reproduction system, including a scene division module, a scene encoding module, a label recording module, a feature retrieval module and an interactive replay module;
[0108] A scenario partitioning module, which is used to split the review process into a series of scenarios arranged in time;
[0109] A scene encoding module is used to encode the information contained in a series of scenes to digitize the scene information;
[0110] A label recording module is used to label and store the digitized scenes to form a scene label library;
[0111] A feature retrieval module is used to perform retrieval using feature values as parameters to match and extract corresponding scene tags in a scene tag library;
[0112] The interactive replay module is used to reproduce the digitized scene information corresponding to the matched extracted scene labels parameter by parameter.
[0113] Specifically:
[0114] The system also includes:
[0115] A data receiving module, used for receiving the transmitted scene tag and the digitized scene information corresponding to the scene tag;
[0116] A data sending module, used for sending scene labels and digitized scene information corresponding to the scene labels;
[0117] The tag recording module is further used to store the received scene tags and the digitized scene information corresponding to the scene tags in a scene tag library.
[0118] The system also includes an editing module for adding, deleting, modifying, and checking the tag main entity, or changing the value of a single tag record field.
[0119] It should be noted that the review process labeling storage and reproduction system provided in this embodiment is similar to that in the first embodiment, and will not be described in detail here.
[0120] The embodiments described above are merely descriptions of preferred implementations of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope of the present invention.< / layout> < / layout> It should be noted that the text seems a bit unclear in its original form, especially the repeated tags like <Action动作> which might need further clarification in the source context for a more accurate translation understanding.
Claims
1. A method for labeling, storing and reproducing a review process, characterized in that: Includes steps: S1. Break the review process into a series of scenarios arranged in time; S2, encoding the information contained in a series of scenes to digitize the scene information; S3, labeling and storing the digitized scenes to form a scene label library; S4, searching by using the feature value as a parameter to match and extract the corresponding scene tag in the scene tag library; S5, reproducing the digitized scene information corresponding to the scene tag extracted by matching parameter by parameter; The steps between step S3 and step S4 also include the following steps: A. receiving a transmitted scene tag and digitized scene information corresponding to the scene tag; B. storing the received scene tags and the digitized scene information corresponding to the scene tags in a scene tag library; The scene information includes review object information, review action information, review environment information and review instruction information, wherein: Review object information: including patient information and examination data; Review action information: including operation action information when using the functions provided by the ultrasound workstation; Review environment information: including image arrangement, whether the image is scaled, and image viewing angle information; Review instructions: including comments during the review process; The step S3 also includes the following steps: adding, deleting, modifying, and checking the tag main entity, or changing the value of a single tag record field.
2. A method for labeling, storing and reproducing a review process according to claim 1, characterized in that: The functions provided by the ultrasound workstation include free reading of images, marking and measurement, and the annotation information includes annotation frame lines, annotation symbols, annotations and recordings.
3. According to claim 1, a method for labeling, storing and reproducing a review process, characterized in that: The DICOM protocol is used to digitize the review object information.
4. A method for labeling, storing and reproducing a review process according to claim 1, characterized in that: The feature values include average features, attribute features and additional features, where: Average feature: The scene feature value matched with the string feature value used in scene encoding; Attribute features: including keywords, values, and storage time information of scene coding; Additional features: Includes a string entered by the user.
5. A review process labeling storage and reproduction system, including a scene division module, a scene encoding module, a label recording module, a feature retrieval module and an interactive replay module; A scenario partitioning module, which is used to split the review process into a series of scenarios arranged in time; A scene encoding module is used to encode the information contained in a series of scenes to digitize the scene information; A label recording module is used to label and store the digitized scenes to form a scene label library; A feature retrieval module is used to perform retrieval using feature values as parameters to match and extract corresponding scene tags in a scene tag library; An interactive replay module is used to reproduce the digitized scene information corresponding to the scene tags extracted by matching, parameter by parameter; The scene information includes review object information, review action information, review environment information and review instruction information, wherein: Review object information: including patient information and examination data; Review action information: including operation action information when using the functions provided by the ultrasound workstation; Review environment information: including image arrangement, whether the image is scaled, and image viewing angle information; Review instructions: including comments during the review process; It also includes a data receiving module, which is used to receive the transmitted scene tag and the digitized scene information corresponding to the scene tag; the tag recording module is also used to store the received scene tag and the digitized scene information corresponding to the scene tag in the scene tag library; It also includes an editing module for adding, deleting, modifying, and checking the tag main entity, or changing the value of a single tag record field.
