A method and device for labeling and managing medical data
By acquiring and labeling a variety of medical data, the problem of low efficiency in operating room data management is solved, the rapid positioning and display of data is achieved, and the efficiency of surgical data utilization and information sharing is improved.
Patent Information
- Application Number
- CN202011105709.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-10-15
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2040-10-15
AI Technical Summary
The existing technology has business function defects and technical bottlenecks in operating room data management, which cannot enable doctors to view patient medical records, diagnostic data and vital sign data in real time during the operation, resulting in inefficient data viewing.
By obtaining multiple types of medical data (image, video, audio, control instructions, operation instructions, etc.) and performing tag management, associating different types of data, generating tags based on automatic signal recognition and preset operations, and storing them on the backend server , realize the positioning and display of data.
It improves the efficiency of viewing medical data, allows doctors to quickly find the required marking locations during review, and achieves the maximum utilization of surgical data and information sharing.
Smart Images

Figure CN112365960B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of medical data management, and in particular to a medical data tag management method and device. Background Art
[0002] The operating room is a relatively closed treatment environment, but the various data generated in the operating room are also valuable medical resources. Traditional operating rooms are unable to informatize these resources and collect, store and share them with the outside world. With the development of informatization in hospital operating rooms, there is an urgent need to share surgical medical equipment information, surgical process videos, and surgical imaging data with the outside world. Based on various data in the operating room, it is feasible to carry out artificial intelligence diagnosis, surgical teaching, remote medical consultation and other surgical data interaction.
[0003] At present, there are still few studies and achievements covering the acquisition, processing, transmission, storage, information management, service management and other aspects of surgical dynamic images such as surgical process videos and surgical imaging materials in the operating room. Most solutions have business function defects and technical implementation bottlenecks, which can hardly meet the hospital's requirements for the development of operating room informatization. The main deficiencies are as follows:
[0004] Doctors can only see certain recorded information and cannot view the patient's medical history, previous examination data, diagnostic data, doctor's orders, medication status and other relevant information in real time. For example, when replaying the surgical video, they cannot see the vital signs data and anesthesia receipts at the time, which is not conducive to comprehensive diagnosis and teaching. In addition, the current solution only saves surgical data such as videos and images generated in the operating room, which means that when viewing the data later, it is often necessary to traverse the entire data, resulting in low efficiency. Summary of the invention
[0005] In response to the defects in the prior art, the present invention proposes a marking management method and device for medical data. This solution implements a solution for obtaining multiple different types of medical data and integrating the different types of medical data. In addition, in order to mark the medical data in a targeted manner, the row markings of the data by the doctor during the treatment process are also obtained. When the medical data is reviewed later, the required marking location can be easily found for viewing, thereby improving the efficiency of data viewing.
[0006] Specifically, the present invention proposes the following specific embodiments:
[0007] The embodiment of the present invention provides a method for tag management of medical data, including:
[0008] Acquire various types of medical data during the medical process; wherein the types include: image type, video type, audio type, control instruction type, and operation instruction type;
[0009] Obtaining the doctor's marking of the medical data during the medical process;
[0010] Associating the medical data of different types in the same medical process, and associating the corresponding medical data with the tags and storing them in the back-end server;
[0011] When a playback request including a mark is obtained, positioning of all medical data associated with the mark is completed.
[0012] In a specific embodiment, the mark is generated based on automatic recognition of signals during the medical procedure; and / or is generated based on acquisition of the doctor performing a preset operation during the medical procedure.
[0013] In a specific embodiment, the “based on automatic signal recognition during the medical process” includes: recognizing audio signals during the medical process, and performing content recognition on speech during the medical process;
[0014] The preset operations include: touch input operation, pedal input operation, and operation of acquiring electronic tag information.
[0015] In a specific embodiment, the method further comprises:
[0016] When a viewing request is obtained, determining the medical data and the mark corresponding to the viewing request;
[0017] The determined medical data and the mark are displayed on a display interface.
[0018] In a specific embodiment, the method further comprises:
[0019] When the medical data and the mark are displayed on the display interface, when the mark is triggered, the medical data associated with the triggered mark is displayed.
[0020] The embodiment of the present invention further provides a medical data tag management device, including:
[0021] A data acquisition module, used to acquire various types of medical data during the medical process; wherein the types include: image type, video type, audio type, control instruction type, and operation instruction type;
[0022] An identification acquisition module, used to acquire the doctor's mark on the medical data during the medical process;
[0023] A processing module, used for associating the medical data of different types in the same medical process, and associating the corresponding medical data with the tags and storing them in a back-end server;
[0024] The playback module is used to complete the positioning of all medical data associated with the mark when a playback request including the mark is obtained.
[0025] In a specific embodiment, the mark is generated based on automatic recognition of signals during the medical procedure; and / or is generated based on acquisition of the doctor performing a preset operation during the medical procedure.
[0026] In a specific embodiment, the “based on automatic signal recognition during the medical process” includes: recognizing audio signals during the medical process and performing content recognition on speech during the medical process;
[0027] The preset operations include: touch input operation, pedal input operation, and operation of acquiring electronic tag information.
[0028] In a specific embodiment, the device further comprises:
[0029] A display module, for determining the medical data and the mark corresponding to the viewing request when a viewing request is obtained;
[0030] The determined medical data and the mark are displayed on a display interface.
[0031] In a specific embodiment, the device further comprises:
[0032] A trigger module is used to display the medical data and the mark on the display interface, and when the mark is triggered, display the medical data associated with the triggered mark.
[0033] Therefore, the embodiments of the present invention have the following advantages:
[0034] This solution implements the acquisition of multiple different types of medical data and the integration of different types of medical data. In addition, in order to mark the medical data in a targeted manner, the doctor's marking of the data during the treatment process is also obtained. This way, when reviewing the medical data later, the required marking location can be easily found for viewing, which improves the efficiency of data viewing. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0036] Figure 1 A schematic diagram of a flow chart of a medical data tag management method proposed in an embodiment of the present invention;
[0037] Figure 2 A schematic diagram of a specific flow of generating a mark in a mark management method for medical data proposed in an embodiment of the present invention;
[0038] Figure 3 A schematic diagram of the structure of a medical data tag management device proposed in an embodiment of the present invention;
[0039] Figure 4 A schematic diagram of the structure of a medical data tag management device proposed in an embodiment of the present invention;
[0040] Figure 5 A schematic diagram of the structure of a medical data tag management device proposed in an embodiment of the present invention. DETAILED DESCRIPTION
[0041] In the following, various embodiments of the present disclosure will be described more fully. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather the present disclosure should be understood to cover all adjustments, equivalents and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.
[0042] The terms used in the various embodiments of the present disclosure are only used for the purpose of describing specific embodiments and are not intended to limit the various embodiments of the present disclosure. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the meanings commonly understood by ordinary technicians in the field to which the various embodiments of the present disclosure belong. The terms (such as the terms defined in the generally used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments of the present disclosure.
[0043] Example 1
[0044] Embodiment 1 of the present invention discloses a method for tagging and managing medical data. Figure 1 As shown, the following steps are included:
[0045] Step 101, acquiring various types of medical data in a medical process; wherein the types include: image type, video type, audio type, control instruction type, and operation instruction type;
[0046] Specifically, considering that the current general medical data acquisition is not comprehensive in terms of data types, audio data is generally not acquired. However, in the case of surgical applications, there are conversations between consulting experts and operating room doctors. These audio information is very important in subsequent teaching. The system records the equipment audio and the consultation conversation audio by adding an audio processing module to achieve the most comprehensive collection of surgical data. For this reason, audio data is also acquired in this solution. There are various ways to acquire medical data, and there are different acquisition methods according to different data types. For example, image type and video type data can be acquired through a camera, and audio type data can be acquired through a sound pickup device or a recording device. For example, control instruction type medical data is data for controlling oxygen supply time, oxygen supply concentration, temperature control, etc., and operation instruction type medical data is data for operating equipment, etc. No matter what type of medical data, it is data related to medical care collected during the medical process, including medical process record data, as well as environment and operation data and control data of medical equipment. In this way, data loss can be avoided as much as possible and medical data as comprehensive as possible in the medical process can be obtained.
[0047] Step 102: Obtain the doctor's mark on the medical data during the medical process;
[0048] The mark is generated based on automatic recognition of signals during the medical process; and / or is generated based on the doctor performing a preset operation during the medical process.
[0049] Furthermore, the “based on automatic signal recognition during the medical process” includes: recognizing audio signals during the medical process and content recognition of speech during the medical process;
[0050] The preset operations include: touch input operation, pedal input operation, and operation of acquiring electronic tag information.
[0051] Specifically, the recording time of medical processes, such as surgical processes, is generally long. For medical teaching or consultation discussions, how to quickly locate some key content can be more efficient. In this solution, doctors can generate marks during the operation through voice, gestures, foot pedals, screenshots, control instructions (zoom, zoom), scene signals (video movement, brightness changes), etc., and the key points marked by subsequent marks will be updated in the surgical data and saved in the surgical back-end database. When other doctors view the surgical data later, they will see the marks made by the doctor of the operation on the key points of the operation, thereby guiding and reminding other doctors of precautions and surgical points during the operation, and sharing surgical experience; providing rich clinical basis for intelligent medical care, refined surgery, and standardization of surgical processes, thereby maximizing the use of surgical data.
[0052] In addition, during the operation, some special audio clips often mark the occurrence or end of certain events. Effectively detecting these special audio events can assist in the establishment and positioning of the medical video index structure. Therefore, tags can also be generated based on these special audio events. In the surgical video, the voice signals from the doctor's microphone and the consultation center and the audio signals of the equipment are the two most important audio data. Generally speaking, the doctor's microphone explanation often occurs at the beginning of the operation or at critical moments or surgical exchanges, and the equipment alarm sound may occur unexpectedly during the operation. In this way, in actual application scenarios, tags can also be generated by monitoring the doctor's microphone and the equipment alarm sound.
[0053] In addition, in order to better identify audio data or perform speech recognition, audio events can be detected. The audio signal sampling rate is 16KHz, one sampling point is 16 bits, and it is mono. When extracting audio frame features, the mean and variance features of the audio zero-crossing rate are used as judgment values to implement audio type recognition (speech, music, background noise, etc.) and special audio event detection (device alarm sound). By distinguishing speech, device alarm sound and background noise from the audio, removing the interference of music and noise, and improving the overall performance of the algorithm, the changes in audio follow the changes in video content. If a switch occurs from speech to music or from music to speech, it often means that the content of the video presentation has changed.
[0054] For another example, when the patient enters the operating room, the time point when the scanner reads the RFID tag on the patient's wristband is used as the timestamp of the video system to effectively locate the time when the operation started. The time when the operation was performed can be effectively located by performing video motion detection on the surgical field and the laparoscope's video images. The time of extracorporeal changes can be effectively located by monitoring the surgical field control signal. The time when abnormalities or important nodes occur can be marked by taking screenshots of the video, etc. In this case, tags can also be generated based on the information obtained from the RFID tag on the wristband.
[0055] Thus, for example Figure 2 As shown, the medical process is taken as a right hip replacement as an example for explanation, which includes the following steps:
[0056] Step 1: Cut the skin, subcutaneous tissue, and fascia lata;
[0057] Step 2: Cut the femoral neck and remove the femoral head;
[0058] Step 3: Treat the acetabulum;
[0059] Step 4: Place the prosthesis;
[0060] Step 5: Open the medullary cavity with a bone hammer and inject the mixed bone cement into the femoral medullary cavity;
[0061] Step 6: Reposition the hip joint and drain tube;
[0062] During the implementation of each step, the above events can be used to generate markers to record the time nodes. These times can be input by the doctor's touch or foot pedal. By marking on the timeline, the nodes where each step occurs can be quickly located.
[0063] Step 103: Associating the medical data of different types in the same medical process, and associating the corresponding medical data with the tags and storing them in the back-end server.
[0064] Step 104: When a playback request including a mark is obtained, all medical data associated with the mark are located. Specifically, for example, when reviewing an operation, the corresponding marked data and operation instructions and other conditions can be quickly located at the data site related to the operation at that time.
[0065] In addition, currently, general medical data is scattered and independent, and not sufficiently correlated. For example, in existing solutions, medical data such as video data cannot be synchronized to other scenes at the time when replaying video data. For example, when a doctor replays a laparoscopic surgery, it is difficult or impossible to locate the operating technique of the surgeon at the time, because the surgical field and the laparoscope are not related. In this solution, by associating different types of medical data in the same medical process, the signals connected to the system can be associated, providing mixed recordings such as encoding methods, video quality and bit rate, and sound / image synchronization timestamps. Information of all scenes at the time can be seen during playback.
[0066] Based on the above steps, this solution also includes:
[0067] When a viewing request is obtained, determining the medical data and the mark corresponding to the viewing request;
[0068] The determined medical data and the mark are displayed on a display interface.
[0069] Specifically, after establishing the associated table items of various types of medical data and identifiers, the identifiers can be displayed together with the various types of medical data when they need to be retrieved later. For example, when retrieving the record of operation 1, various medical data of operation 1 will be displayed, including video data, audio data, instrument operation data, and data from various sensors, as well as consultation data, including remote consultation data, etc., all of which are displayed in association, and the identifiers in each medical data are displayed together. For example, the identifiers can include the start of the operation, the end of the operation, a key node in the operation, etc. In this way, when viewing the data, you can fully see all the relevant medical data, and you can also view the data according to the identifier, without having to read it from beginning to end, and you can effectively grasp the key points, which improves efficiency.
[0070] Furthermore, for easier viewing, the method further includes:
[0071] When the medical data and the mark are displayed on the display interface, when the mark is triggered, the medical data associated with the triggered mark is displayed.
[0072] Specifically, still taking the above example, for example, if the mark 1 corresponds to a key node or stage in the operation, when the mark 1 is clicked by mouse or touch, the data related to the mark 1 will be displayed, that is, the medical data of a key node or stage in the operation, so as to facilitate the viewing of medical data.
[0073] Example 2
[0074] In order to further illustrate the present invention, the second embodiment of the present invention further discloses a medical data tag management device, such as Figure 3 As shown, including:
[0075] The data acquisition module 201 is used to acquire various types of medical data during the medical treatment process; wherein the types include: image type, video type, audio type, control instruction type, and operation instruction type;
[0076] The identification acquisition module 202 is used to obtain the doctor's mark on the medical data during the medical process;
[0077] A processing module 203 is used to associate the medical data of different types in the same medical process, and associate the corresponding medical data with the tags and store them in a backend server;
[0078] The playback module 204 is used to obtain a playback request including a mark and complete the positioning of all medical data associated with the mark.
[0079] In a specific embodiment, the mark is generated based on automatic recognition of signals during the medical procedure; and / or is generated based on acquisition of the doctor performing a preset operation during the medical procedure.
[0080] In a specific embodiment, the “based on automatic signal recognition during the medical process” includes: recognizing audio signals during the medical process and performing content recognition on speech during the medical process;
[0081] The preset operations include: touch input operation, pedal input operation, and operation of acquiring electronic tag information.
[0082] In a specific embodiment, Figure 4 As shown, it also includes:
[0083] A display module 204, configured to determine the medical data and the mark corresponding to the viewing request when a viewing request is obtained;
[0084] The determined medical data and the mark are displayed on a display interface.
[0085] In a specific embodiment, Figure 5 As shown, it also includes:
[0086] The trigger module 205 is used to display the medical data and the mark on the display interface, and when the mark is triggered, display the medical data associated with the triggered mark.
[0087] Those skilled in the art will appreciate that the accompanying drawings are merely schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present invention.
[0088] Those skilled in the art will appreciate that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.
[0089] The above serial numbers of the present invention are only for description and do not represent the advantages or disadvantages of the implementation scenarios.
[0090] The above disclosure is only a few specific implementation scenarios of the present invention, but the present invention is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the protection scope of the present invention.
Claims
1. A method for labeling and managing medical data. It is characterized in that include: Acquire various types of medical data during the medical process; wherein the types include: image type, video type, audio type, control instruction type, and operation instruction type; Obtaining the doctor's marking of the medical data during the medical process; Associating the medical data of different types in the same medical process, and associating the corresponding medical data with the tags and storing them in the back-end server; When a playback request including a tag is obtained, positioning of all medical data associated with the tag is completed; The mark is generated based on automatic recognition of signals during the medical process; and is generated based on the doctor performing a preset operation during the medical process; The "based on automatic signal recognition during the medical process" includes: recognizing the audio signal during the medical process and performing content recognition on the voice during the medical process; audio types include voice, music and background noise, and special audio events include equipment alarm sounds; extracting audio frame features, using the mean and variance features of the audio zero-crossing rate as judgment values to implement audio type recognition and the special audio event detection according to the judgment; The preset operation includes: an operation of obtaining electronic tag information; The time point of the RFID tag on the patient's wristband is read as the time stamp of the video system to locate the start time of the operation; When a viewing request is obtained, determining the medical data and the mark corresponding to the viewing request; Displaying the determined medical data and the mark on a display interface; When the medical data and the mark are displayed on the display interface, when the mark is triggered, the medical data associated with the triggered mark is displayed.
2. A medical data tag management device, It is characterized in that include: A data acquisition module, used to acquire various types of medical data during the medical process; wherein the types include: image type, video type, audio type, control instruction type, and operation instruction type; An identification acquisition module, used to acquire the doctor's mark on the medical data during the medical process; A processing module, used for associating the medical data of different types in the same medical process, and associating the corresponding medical data with the tags and storing them in a back-end server; A playback module, for completing the positioning of all medical data associated with the tag when a playback request including the tag is obtained; A display module, for determining the medical data and the mark corresponding to the viewing request when a viewing request is obtained; and displaying the determined medical data and the mark on a display interface; A trigger module, configured to display the medical data associated with the triggered mark when the mark is triggered when the medical data and the mark are displayed on the display interface; The mark is generated based on automatic recognition of signals during the medical process; and is generated based on the doctor performing a preset operation during the medical process; The "based on automatic signal recognition during the medical process" includes: recognizing the audio signal during the medical process and recognizing the content of the voice during the medical process; the audio types include voice, music and background noise, and the special audio events include equipment alarm sounds; extracting audio frame features, using the mean and variance features of the audio zero-crossing rate as judgment values to realize audio type recognition and the special audio event detection according to the judgment; The preset operation includes: an operation of acquiring electronic tag information.
