Method for storing ultrasonic film with voice
By using ultrasound movie storage method with voice in ultrasound examination, real-time recording of patient feedback and doctor scan image explanation, the problem of separation of real-time voice entry and scanning process in ultrasound examination in the prior art is solved, and diagnostic efficiency and accuracy are improved.
Patent Information
- Application Number
- CN202510137000.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-07
- Publication Date
- 2025-06-06
AI Technical Summary
In existing ultrasound examinations, real-time voice input, voice manipulation and voice filling reports are separated from the ultrasound scanning process, resulting in low diagnostic efficiency and poor accuracy, which is not conducive to doctors' burden reduction.
It provides an ultrasonic movie storage method with voice. It stores ultrasonic movies through an ultrasonic system and records audio data, writes ultrasonic movies, audio data and corresponding data structures into the database, real-time recording of patient feedback and doctors’ scan image explanation.
It improves the understanding and explanation of the movie during playback, improves the work efficiency of doctors and the accuracy of diagnosis, provides more comprehensive information and better clinical data, and helps to better diagnose and treat diseases.
Smart Images

Figure CN120108616A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of ultrasonic medical treatment, and in particular to a method for storing ultrasonic films with voice. Background Art
[0002] At present, ultrasound imaging is a non-invasive imaging technology widely used in medical diagnosis and monitoring. Ultrasound examination has become an important diagnostic tool in modern medicine due to its unique safety, real-time and versatility. The storage and reading of ultrasound images is a core part of ultrasound examination. The stored ultrasound movies and images can be measured again during playback, image processing, etc.
[0003] However, although real-time voice input, voice control and voice report filling have reduced the doctors' operation and filling work, in actual work, the ultrasound scanning process, real-time voice report filling, ultrasound scanning work and report filling are completed separately. On the one hand, if the report is filled in real time, the scanning doctor needs to have clinical diagnosis ability. On the other hand, if the ultrasound scan and the report are separated, the doctor who fills in the report can only analyze and diagnose through the stored movies and pictures, which is out of touch with the environment and patients of the ultrasound scan at that time, which brings great inconvenience to the diagnosis operation, reduces the efficiency of ultrasound examination, and is not conducive to reducing the burden on doctors.
[0004] Therefore, in order to overcome the above technical problems, the present invention provides an ultrasound movie storage method with voice. Summary of the invention
[0005] The present invention provides a method for storing ultrasound movies with voice, which can help doctors record patients' feedback and doctors' scan image interpretation in real time through the storage of ultrasound movies with voice, improve the understanding of the movie and the interpretation effect during playback; effectively improve the doctors' work efficiency, improve the accuracy of diagnosis, and provide more comprehensive information and better clinical data in scientific research and clinical diagnosis; provide doctors with more efficient, faster and more accurate data information, and help better diagnose and treat diseases.
[0006] A method for storing ultrasonic movies with voice, comprising:
[0007] Step 1: Store the ultrasound movie based on the ultrasound system and record the audio data. At the same time, write the ultrasound movie, audio data and corresponding data structure into the database;
[0008] Step 2: When the ultrasound movie needs to be replayed, the target ultrasound movie and target audio data are determined in the database according to the selected target;
[0009] Step 3: Play back the target ultrasound movie and target audio data.
[0010] Preferably, a method for storing ultrasound movies with voice, in step 1, storing ultrasound movies based on an ultrasound system and recording audio data, and at the same time, writing the ultrasound movies, audio data and corresponding data structures into a database, including:
[0011] Configure the recording function for the ultrasound system, and when the configuration is successful, switch to the image mode to be scanned, and start the storage function to store the ultrasound movie, and at the same time, determine whether the recording function is turned on;
[0012] According to the judgment result, the storage file and the corresponding data structure are written into the database.
[0013] Preferably, a method for storing ultrasound movies with voice, writing the storage file and the corresponding data structure into a database according to the judgment result, comprises:
[0014] The judgment results include:
[0015] When the recording function is turned on, the ultrasound movie is saved and the audio data is recorded. At the same time, the ultrasound movie and the audio data are written into the database as storage files and corresponding data structures;
[0016] When the recording function is not turned on, the ultrasound movie is saved and, at the same time, the ultrasound movie is written into the database as a storage file and a corresponding data structure.
[0017] Preferably, a method for storing ultrasound movies with voice, the data structure includes: patient ID, examination ID, doctor information, movie ID and recording ID.
[0018] Preferably, a method for storing an ultrasound movie with voice, in step 2, when the ultrasound movie needs to be played back, a target ultrasound movie and target audio data are determined in a database according to a selected target, including:
[0019] When the ultrasound movie needs to be replayed, a selected target is obtained, and a target ultrasound movie to be replayed is located according to the selected target;
[0020] Read the movie identifier of the target ultrasound movie, and input the movie identifier into the database for matching to determine whether there is a recording file that matches the movie identifier;
[0021] When there is a recording file that matches the movie identifier, the target audio data corresponding to the recording file is obtained, and at the same time, the target ultrasound movie and the target audio data are used as playback targets;
[0022] When there is no recording file matching the electronic sound identifier, the target ultrasound movie is used as the playback target.
[0023] Preferably, a method for storing an ultrasound movie with voice, in step 3, playing back the target ultrasound movie and the target audio data, comprises:
[0024] Get the start time of the target audio data;
[0025] Reading the first frame of the image frame set in the target ultrasound movie;
[0026] The start time is mapped to the first frame as the playback start point, and the target audio data and the target ultrasound movie are played back simultaneously according to the mapping result.
[0027] Preferably, a method for storing an ultrasound movie with voice, when simultaneously playing back target audio data and a target ultrasound movie, comprises:
[0028] The playback speed of the target ultrasound movie is adjusted according to the playback speed requirement, and the playback speed of the target audio data is independent of the playback speed of the target ultrasound movie and is a normal playback speed.
[0029] Preferably, a method for storing an ultrasound movie with voice, in step 3, playing back the target ultrasound movie and the target audio data, comprises:
[0030] Obtaining a target method for playing back a target ultrasound movie and target audio data;
[0031] Among them, the target methods include:
[0032] The first mode is used to play back the target ultrasound movie and the target audio data simultaneously;
[0033] The second method is used to play back the target audio data alone;
[0034] The third method is used to play back the target ultrasound movie alone.
[0035] Preferably, a method for storing ultrasound movies with voice also includes, when playing back the target audio data, identifying recording keywords, and determining the target report in the report knowledge base according to the recording keywords, and displaying it in the report knowledge base UI, including:
[0036] Loading target audio data and preprocessing the target audio data to obtain pure target audio data;
[0037] Performing speech recognition on the pure target audio data to obtain an audio text of the pure target audio data;
[0038] Remove irrelevant information from the audio text to obtain the target audio text, traverse the target audio text in the keyword vocabulary, and extract the recording keywords of the target audio text according to the traversal results;
[0039] Match the recording keywords to the report knowledge base to determine whether the recording keywords are stored in the report knowledge base;
[0040] When the recording keyword is stored in the report knowledge base, the recording keyword and the entry corresponding to the recording keyword are loaded, and the recording keyword and the entry corresponding to the recording keyword are displayed in the report knowledge base UI;
[0041] When the recording keyword is not stored in the report knowledge base, the recording keyword is loaded and displayed in the report knowledge base UI.
[0042] Preferably, a method for storing ultrasonic movies with speech, before traversing the target audio text in a keyword word library, comprises:
[0043] The data structure of the predefined keyword database includes a number of keyword IDs and corresponding keywords;
[0044] Several keyword IDs and corresponding keywords are stored in a preset file, and the preset file is loaded into a memory to obtain a preset keyword set, wherein a keyword thesaurus is formed based on the preset keyword set.
[0045] Compared with the prior art, the present invention has the following beneficial effects:
[0046] The storage of ultrasound movies with voice can help doctors record patients' feedback and doctors' scan image explanations in real time, improve the understanding of the movie and the effect of the explanation during playback; effectively improve doctors' work efficiency and the accuracy of diagnosis, and provide more comprehensive information and better clinical data in scientific research and clinical diagnosis; provide doctors with more efficient, faster and more accurate data information to help better diagnose and treat diseases.
[0047] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in this application document.
[0048] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0050] Figure 1This is a flow chart of a method for storing ultrasound movies with voice in an embodiment of the present invention;
[0051] Figure 2 This is a flow chart of step 1 in a method for storing ultrasound movies with voice in an embodiment of the present invention;
[0052] Figure 3 A flowchart of extracting key words from recordings and generating a target report in a method for storing ultrasound movies with voice in an embodiment of the present invention;
[0053] Figure 4 This is a UI interface diagram of a report knowledge base in an ultrasound movie storage method with voice in an embodiment of the present invention. DETAILED DESCRIPTION
[0054] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.
[0055] In one embodiment, a method for storing ultrasound movies with voice is provided, such as Figure 1 As shown, including:
[0056] Step 1: Store the ultrasound movie based on the ultrasound system and record the audio data. At the same time, write the ultrasound movie, audio data and corresponding data structure into the database;
[0057] Step 2: When the ultrasound movie needs to be replayed, the target ultrasound movie and target audio data are determined in the database according to the selected target;
[0058] Step 3: Play back the target ultrasound movie and target audio data.
[0059] In this embodiment, a recording function is provided to store recordings while storing ultrasound movies backwards, generate recording files, and generate data structures related to ultrasound movies and recordings, including: patient ID, examination ID, doctor information, movie ID, recording ID, etc., to facilitate subsequent management and retrieval.
[0060] In this embodiment, the stored ultrasound movie files and recording files and the data structure data related thereto are stored in a database to ensure the integrity and consistency of the data.
[0061] In this embodiment, simultaneous recording and playback of movie playback is provided: the recording is played synchronously during movie playback (the image data obtained by real-time scanning and stored in the memory is re-displayed on the ultrasound device at a certain speed).
[0062] In this embodiment, when movie playback or recording playback is provided: separate movie playback or separate recording playback is implemented.
[0063] In this embodiment, the ultrasound system also supports the export function of ultrasound movies and audio data, and can export the saved ultrasound movies and audio data.
[0064] The beneficial effects of the above technical solution are: the storage of ultrasound movies with voice can help doctors record patients' feedback and doctors' scan image explanations in real time, improve the understanding and explanation effect of the movie during playback; effectively improve doctors' work efficiency, improve the accuracy of diagnosis, and provide more comprehensive information and better clinical data in scientific research and clinical diagnosis; provide doctors with more efficient, faster and more accurate data information to help better diagnose and treat diseases.
[0065] In one embodiment, a method for storing ultrasound movies with voice is provided, such as Figure 2 As shown, in step 1, the ultrasound movie is stored based on the ultrasound system, and audio data is recorded. At the same time, the ultrasound movie, audio data and corresponding data structure are written into the database, including:
[0066] Configure the recording function for the ultrasound system, and when the configuration is successful, switch to the image mode to be scanned, and start the storage function to store the ultrasound movie, and at the same time, determine whether the recording function is turned on;
[0067] According to the judgment result, the storage file and the corresponding data structure are written into the database.
[0068] Wherein, according to the judgment result, the storage file and the corresponding data structure are written into the database, including:
[0069] The judgment results include:
[0070] When the recording function is turned on, the ultrasound movie is saved and the audio data is recorded. At the same time, the ultrasound movie and the audio data are written into the database as storage files and corresponding data structures;
[0071] When the recording function is not turned on, the ultrasound movie is saved and, at the same time, the ultrasound movie is written into the database as a storage file and a corresponding data structure.
[0072] In this embodiment, the data structure includes: patient ID, examination ID, doctor information, movie ID and recording ID.
[0073] The working principle and beneficial effects of the above technical solution are: In order to realize the storage of ultrasound movies with voice, the technical solution of using stored ultrasound movies and recording workflow includes the following: first confirm whether the recording function has been configured in the configuration (the preset can set whether to turn on the recording function when storing ultrasound movies); enter the image mode to be scanned, press the storage button, and the ultrasound system starts to store ultrasound movies. At the same time, use a microphone or recording device to collect audio data. After recording is completed, the stored ultrasound movie file and audio file are saved and written into the database together with the related data structure to ensure data consistency.
[0074] In one embodiment, this embodiment provides a method for storing an ultrasound movie with voice. In step 2, when the ultrasound movie needs to be played back, a target ultrasound movie and target audio data are determined in a database according to a selected target, including:
[0075] When the ultrasound movie needs to be replayed, a selected target is obtained, and a target ultrasound movie to be replayed is located according to the selected target;
[0076] Read the movie identifier of the target ultrasound movie, and input the movie identifier into the database for matching to determine whether there is a recording file that matches the movie identifier;
[0077] When there is a recording file that matches the movie identifier, the target audio data corresponding to the recording file is obtained, and at the same time, the target ultrasound movie and the target audio data are used as playback targets;
[0078] When there is no recording file matching the electronic sound identifier, the target ultrasound movie is used as the playback target.
[0079] In this embodiment, during the movie playback process, image measurement, grayscale adjustment, image data feature extraction, etc. can be performed.
[0080] The working principle and beneficial effect of the above technical solution are: after selecting the target ultrasound movie to be played back, according to the CineID (i.e., movie identifier) of the current target ultrasound movie, find the matching recording file (i.e., target audio data), and determine whether the recording file exists. If it exists, the corresponding recording file is played while playing back the target ultrasound movie (image data). The start time of the recording file playback is consistent with the first frame image of the playback movie file, and the playback rate of the recording file is independent of the playback speed of the movie file. Regardless of whether the movie file is manually played back or automatically played at a slow or fast speed, the recording file is played at a normal speed, which helps doctors record the patient's feedback and the doctor's scan image explanation in real time, improves the understanding and explanation effect of the movie during playback, and the attending doctor listens to the scanning doctor's scanning instructions while viewing the ultrasound movie, and understands the pathological characteristics displayed by the image from all aspects, thereby improving the accuracy of diagnosis.
[0081] In one embodiment, a method for storing an ultrasound movie with voice is provided. In step 3, the target ultrasound movie and target audio data are played back, including:
[0082] Get the start time of the target audio data;
[0083] Reading the first frame of the image frame set in the target ultrasound movie;
[0084] The start time is mapped to the first frame as the playback start point, and the target audio data and the target ultrasound movie are played back simultaneously according to the mapping result.
[0085] In this embodiment, the playback rate of the target ultrasound movie is adjusted according to the playback speed requirement, and the playback speed of the target audio data is independent of the playback speed of the target ultrasound movie and is a normal playback speed.
[0086] The beneficial effects of the above technical solution are: helping doctors to record patients' feedback and doctors' scan image interpretation in real time, improving the understanding and interpretation effect of the movie during playback; in scientific research, the synchronous recording of ultrasound movies and audio recordings can provide more comprehensive information for the research, facilitate data analysis and result interpretation, and generate medical teaching videos.
[0087] In one embodiment, a method for storing an ultrasound movie with voice is provided. In step 3, the target ultrasound movie and target audio data are played back, including:
[0088] Obtaining a target method for playing back a target ultrasound movie and target audio data;
[0089] Among them, the target methods include:
[0090] The first mode is used to play back the target ultrasound movie and the target audio data simultaneously;
[0091] The second method is used to play back the target audio data alone;
[0092] The third method is used to play back the target ultrasound movie alone.
[0093] In one embodiment, a method for storing ultrasound movies with voice is provided, such as Figure 3 As shown, it also includes, when playing back the target audio data, identifying the recording keywords, and determining the target report in the report knowledge base according to the recording keywords, and displaying it in the report knowledge base UI, including:
[0094] Loading target audio data and preprocessing the target audio data to obtain pure target audio data;
[0095] Performing speech recognition on the pure target audio data to obtain an audio text of the pure target audio data;
[0096] Remove irrelevant information from the audio text to obtain the target audio text, traverse the target audio text in the keyword vocabulary, and extract the recording keywords of the target audio text according to the traversal results;
[0097] Match the recording keywords to the report knowledge base to determine whether the recording keywords are stored in the report knowledge base;
[0098] When the recording keyword is stored in the report knowledge base, the recording keyword and the entry corresponding to the recording keyword are loaded, and the recording keyword and the entry corresponding to the recording keyword are displayed in the report knowledge base UI;
[0099] When the recording keyword is not stored in the report knowledge base, the recording keyword is loaded and displayed in the report knowledge base UI.
[0100] In this embodiment, before traversing the target audio text in the keyword thesaurus, it includes: predefining the data structure of the keyword thesaurus, wherein the data structure of the keyword database includes a number of keyword IDs and corresponding keywords; storing the number of keyword IDs and the corresponding keywords in a preset file, and loading the preset file into the memory to obtain a preset keyword set, wherein the keyword thesaurus is constructed based on the preset keyword set.
[0101] In this embodiment, the report knowledge base UI is displayed as follows: Figure 4 shown.
[0102] In this embodiment, in the report module, keyword recognition technology is used to identify keywords in the recording, and the keywords are combined with the knowledge base function to display the keyword information on the report's knowledge base template interface (i.e., the report knowledge base UI), and the doctor can select information to insert into the report.
[0103] The working principle and beneficial effects of the above technical solution are: first, predefine the data structure of the keywords to be extracted (keyword thesaurus, which can be expanded to store more data information), which contains the keyword ID and the keyword itself, store all keyword data in a file, load it into memory, and obtain a predefined keyword set.
[0104] Enter the report mode, load the recording file under the current Application and perform preprocessing (noise reduction) (i.e., preprocess the target audio data), use the existing speech recognition API to convert the recorded speech into text (i.e., perform speech recognition on the pure target audio data to obtain the audio text of the pure target audio data), remove stop words, symbols, etc. (i.e., irrelevant information) in the file, and then extract and identify all the keywords in the text (traverse the predefined keyword set, check whether the speech text contains these keywords, and extract the included keywords), compare the ID of the identified keyword with the existing knowledge base file, and display them together in the report's knowledge base UI. The doctor can select the available text to edit the report, and use the recorded speech keyword recognition technology to perform keyword recognition on the scanning doctor's description to generate a report keyword knowledge base template, so that the doctor can complete the diagnosis report faster and more accurately.
[0105] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A method for storing ultrasonic movies with voice, characterized in that: include: Step 1: Store the ultrasound movie based on the ultrasound system and record the audio data. At the same time, write the ultrasound movie, audio data and corresponding data structure into the database; Step 2: When the ultrasound movie needs to be replayed, the target ultrasound movie and target audio data are determined in the database according to the selected target; Step 3: Play back the target ultrasound movie and target audio data.
2. The method for storing ultrasonic movies with voice according to claim 1, characterized in that: In step 1, the ultrasound movie is stored based on the ultrasound system, and the audio data is recorded. At the same time, the ultrasound movie, the audio data and the corresponding data structure are written into the database, including: Configure the recording function for the ultrasound system, and when the configuration is successful, switch to the image mode to be scanned, and start the storage function to store the ultrasound movie, and at the same time, determine whether the recording function is turned on; According to the judgment result, the storage file and the corresponding data structure are written into the database.
3. The method for storing ultrasonic movies with voice according to claim 2, characterized in that: According to the judgment result, the storage file and the corresponding data structure are written into the database, including: The judgment results include: When the recording function is turned on, the ultrasound movie is saved and the audio data is recorded. At the same time, the ultrasound movie and the audio data are written into the database as storage files and corresponding data structures; When the recording function is not turned on, the ultrasound movie is saved and, at the same time, the ultrasound movie is written into the database as a storage file and a corresponding data structure.
4. The method for storing ultrasonic movies with voice according to claim 2, characterized in that: The data structure includes: patient ID, examination ID, doctor information, movie ID, and recording ID.
5. The method for storing ultrasound movies with voice according to claim 1, characterized in that: In step 2, when the ultrasound movie needs to be replayed, the target ultrasound movie and target audio data are determined in the database according to the selected target, including: When the ultrasound movie needs to be replayed, a selected target is obtained, and a target ultrasound movie to be replayed is located according to the selected target; Read the movie identifier of the target ultrasound movie, and input the movie identifier into the database for matching to determine whether there is a recording file that matches the movie identifier; When there is a recording file that matches the movie identifier, the target audio data corresponding to the recording file is obtained, and at the same time, the target ultrasound movie and the target audio data are used as playback targets; When there is no recording file matching the electronic sound identifier, the target ultrasound movie is used as the playback target.
6. The method for storing ultrasonic movies with voice according to claim 1, characterized in that: In step 3, the target ultrasound movie and target audio data are played back, including: Get the start time of the target audio data; Reading the first frame of the image frame set in the target ultrasound movie; The start time is mapped to the first frame as the playback start point, and the target audio data and the target ultrasound movie are played back simultaneously according to the mapping result.
7. The method for storing ultrasound movies with voice according to claim 6, characterized in that: When the target audio data and the target ultrasound movie are played back simultaneously, it includes: The playback speed of the target ultrasound movie is adjusted according to the playback speed requirement, and the playback speed of the target audio data is independent of the playback speed of the target ultrasound movie and is a normal playback speed.
8. The method for storing ultrasound movies with voice according to claim 1, characterized in that: In step 3, the target ultrasound movie and target audio data are played back, including: Obtaining a target method for playing back a target ultrasound movie and target audio data; Among them, the target methods include: The first mode is used to play back the target ultrasound movie and the target audio data simultaneously; The second method is used to play back the target audio data alone; The third method is used to play back the target ultrasound movie alone.
9. The method for storing ultrasound movies with voice according to claim 1, characterized in that: It also includes, when playing back the target audio data, identifying the recording keywords, determining the target report in the report knowledge base according to the recording keywords, and displaying it in the report knowledge base UI, including: Loading target audio data and preprocessing the target audio data to obtain pure target audio data; Performing speech recognition on the pure target audio data to obtain an audio text of the pure target audio data; Remove irrelevant information from the audio text to obtain the target audio text, traverse the target audio text in the keyword vocabulary, and extract the recording keywords of the target audio text according to the traversal results; Match the recording keywords to the report knowledge base to determine whether the recording keywords are stored in the report knowledge base; When the recording keyword is stored in the report knowledge base, the recording keyword and the entry corresponding to the recording keyword are loaded, and the recording keyword and the entry corresponding to the recording keyword are displayed in the report knowledge base UI; When the recording keyword is not stored in the report knowledge base, the recording keyword is loaded and displayed in the report knowledge base UI.
10. The method for storing ultrasonic movies with audio recording according to claim 9, characterized in that: Before traversing the target audio text in the keyword library, including: The data structure of the predefined keyword database includes a number of keyword IDs and corresponding keywords; Several keyword IDs and corresponding keywords are stored in a preset file, and the preset file is loaded into a memory to obtain a preset keyword set, wherein a keyword thesaurus is formed based on the preset keyword set.