A cloud platform-based medical image data sharing system

Abstract

This invention discloses a cloud-based medical image data sharing system, comprising terminal devices and a medical cloud platform. The terminal devices communicate with the medical cloud platform via a communication network. The terminal devices include field devices and remote devices. The medical cloud platform includes a data communication module and a data sharing module. Field devices collect user medical data and send it to the medical cloud platform. Remote devices interact with the field devices. The data sharing module includes functions for storing medical data, collecting user feedback, and filtering historical medical data from all stored medical data based on the medical data and user feedback. It then shares the corresponding remote devices with the field devices. By connecting the field devices and remote devices through the medical cloud platform, remote doctors and field doctors can share patient medical data, improving diagnostic accuracy and efficiency.

Description

Technical Field

[0001] This invention relates to the field of medical cloud platform technology, and more specifically to a medical image data sharing system based on a cloud platform. Background Technology

[0002] With the improvement of medical and health technology, more and more medical instruments are being used. Nowadays, many difficult and complicated diseases can be diagnosed through medical imaging. This makes a more convenient, faster and more accurate medical imaging diagnosis mode a goal that people look forward to. However, in some economically underdeveloped areas, due to the limited medical level, misdiagnosis and missed diagnosis still occur, which leads to delays in patients' conditions and prevents them from receiving timely diagnosis and treatment.

[0003] In recent years, with the development of wireless communication technology, internet technology, and the Internet of Things (IoT) technology, telemedicine diagnostic technology has become an important means to solve the aforementioned problems. However, in existing technologies, how to accurately and quickly identify suitable target patients for telemedicine diagnosis remains a problem that needs to be overcome. Summary of the Invention

[0004] The purpose of this invention is to provide a medical image data sharing system based on a cloud platform.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] A cloud-based medical image data sharing system includes terminal devices and a medical cloud platform. The terminal devices communicate with the medical cloud platform via a communication network. The terminal devices include field devices and remote devices. The medical cloud platform includes a data communication module and a data sharing module.

[0007] The field equipment is used to collect users' medical data and send the medical data to the medical cloud platform.

[0008] Remote devices are used to exchange data with field devices.

[0009] The data communication module is used to receive medical data from multiple terminal devices in real time and transmit the medical data to the data sharing module.

[0010] The data sharing module includes functions for storing medical data, collecting user feedback information, and filtering historical medical data that matches the current medical data from all stored medical data based on the medical data and user feedback information, and sharing the remote devices corresponding to the historical medical data with the field devices.

[0011] The field equipment is also used to select any idle remote device from all the remote devices shared with the data sharing module for data interaction.

[0012] As a further aspect of the present invention, the medical data includes the patient's identity information, the detection site, medical images, and on-site diagnostic analysis videos.

[0013] As a further aspect of the present invention: the patient's identity information includes department information and personal information, and the personal information includes height, weight, age and gender.

[0014] As a further aspect of the present invention, the data sharing module operates as follows:

[0015] 1. Store newly added medical data and create data tags for the stored medical data. The data tags include identity tags, body part tags, medical image tags, department tags, and treatment tags.

[0016] II. Obtaining Feature Data from Current Medical Data. Feature data includes on-site diagnostic analysis videos and disease keyword datasets.

[0017] Third, identify historical medical data in all stored historical medical data that have at least four identical data tags to the current medical data.

[0018] Fourth, play the on-site diagnostic analysis video of the identified historical medical data in sequence, and obtain user feedback data on the on-site diagnostic analysis video.

[0019] V. Based on user feedback data regarding the on-site diagnostic analysis video, calculate the user's satisfaction rating H for the current on-site diagnostic analysis video.

[0020] 6. Filter out historical medical data that matches the current medical data.

[0021] 7. Share the corresponding remote devices with the appropriate historical medical data with the field devices.

[0022] As a further aspect of the present invention, the process of obtaining user feedback data on the on-site diagnostic analysis video is as follows:

[0023] (1) Acquire the voice stream data and video stream data generated by the user during the playback of the on-site diagnostic analysis video, as well as the user's instruction to switch the current on-site diagnostic analysis video.

[0024] (2) Determine whether an instruction to switch the current on-site diagnostic analysis video has been received. If yes, assign 1 to the feature quantity SW that reflects the instruction; otherwise, assign 0 to SW.

[0025] As a further aspect of the present invention: the calculation process of the user's satisfaction rating value H for the current on-site diagnostic analysis video is as follows:

[0026] (1) Perform speech recognition on the on-site diagnosis analysis video, extract the keywords that match the feature data in the disease keyword dataset, and count their number N1.

[0027] (2) Perform video action recognition on the on-site diagnostic analysis video. Extract the gestures and actions that represent the user's feedback to the current on-site diagnostic analysis video, and count their number N2.

[0028] (3) Identify the on-site diagnostic analysis video. Determine the duration t during which the user focuses on the current on-site diagnostic analysis video.

[0029] (4) Get the value of SW.

[0030] (5) Calculate the current user's satisfaction rating H for the on-site diagnostic analysis video using the following formula:

[0031]

[0032] In the formula, H represents the user's satisfaction rating of the current on-site diagnostic analysis video, H≥0, and the larger the value of H, the higher the user's satisfaction with the current on-site diagnostic analysis video. This represents the user's attention level on the current on-site diagnostic analysis video. k1 represents the influence factor of voice feedback on the overall acceptance evaluation result. k2 represents the influence factor of posture and movement feedback on the overall acceptance evaluation result. k3 represents the influence factor of attention level on the overall acceptance evaluation result. a1 represents the score of a single keyword in the voice feedback. a2 represents the score of a single posture and movement in the posture and movement feedback. a3 represents the score of attention level.

[0033] As a further aspect of the present invention, the method for calculating the user's attention duration t for the current on-site diagnostic analysis video is as follows:

[0034]

[0035] In the formula, t1 represents the duration of direct eye contact during the playback of the current on-site diagnostic analysis video, numbered t2 represents the duration of eye-closed contact during the playback of the current on-site diagnostic analysis video, numbered t3 represents the duration of head-down contact during the playback of the current on-site diagnostic analysis video, numbered t4 represents the duration of head-turning contact during the playback of the current on-site diagnostic analysis video, numbered t4 represents the duration of head-turning contact during the playback of the current on-site diagnostic analysis video, and T is the total playback duration of the current on-site diagnostic analysis video.

[0036] As a further aspect of the present invention: the user's posture and actions in providing feedback on the on-site diagnostic analysis video include nodding, clapping, pointing the hand at the playback interface, and head tilting or turning the head from a non-direct gaze state to a direct gaze state during playback.

[0037] As a further aspect of the present invention, the process of filtering out historical medical data that matches the current medical data is as follows:

[0038] Set a high threshold H for H L and a low threshold H W High threshold H L This indicates that the user approves the current threshold value of the on-site diagnostic analysis video, H. W This indicates that the user does not accept the current threshold value of the on-site diagnostic analysis video. W >0.

[0039] When H≥H L At that time, the historical medical data corresponding to the current on-site diagnostic analysis video is regarded as the most suitable historical medical data.

[0040] H W ≤H≤H L At that time, the historical medical data corresponding to the current on-site diagnostic analysis video is regarded as general adapted historical medical data.

[0041] Create a best-fit data table and a general-fit data table. Enter the best-fit historical medical data into the best-fit data table, and the general-fit historical medical data into the general-fit data table. If the best-fit data table contains 3 sets of data, stop filtering and use these 3 sets as the historical medical data that matches the current medical data. If the best-fit data table contains fewer than 3 sets of data, but the general-fit data table contains 5 sets of data, stop filtering and use all data from both the best-fit and general-fit data tables as the historical medical data that matches the current medical data.

[0042] The present invention has at least one of the following beneficial effects:

[0043] This invention relates to a cloud-based medical image data sharing system. By connecting on-site and remote devices through a medical cloud platform, it enables remote doctors to share patient medical data with on-site doctors, thereby assisting on-site doctors in diagnosing and treating patients, improving diagnostic accuracy and efficiency.

[0044] The data sharing module in the cloud-based medical imaging data sharing system of this invention can quickly and accurately find compatible remote devices, which can effectively improve treatment efficiency. Attached Figure Description

[0045] The invention will now be further described with reference to the accompanying drawings.

[0046] Figure 1 This is a schematic diagram of the modules of the cloud-based medical image data sharing system of the present invention;

[0047] Figure 2This is a flowchart of the data sharing module in this invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] In one specific embodiment of the present invention, a cloud-based medical image data sharing system is disclosed, including terminal devices and a medical cloud platform, such as... Figure 1 As shown. The terminal devices communicate with the medical cloud platform via a communication network. The terminal devices include field devices and remote devices. The medical cloud platform includes a data communication module and a data sharing module.

[0050] Field devices are used to collect users' medical data and send it to the medical cloud platform. For example, field devices may include various devices such as user information registration devices, communication devices, multi-parameter monitoring devices, respiratory function monitoring devices, intracranial pressure monitoring devices, fetal heart rate monitoring devices, CT scanners, and camera devices. Specifically, the medical data includes patient identity information, examination sites, medical images, and on-site diagnostic analysis videos. Patient identity information includes department information and personal information, including height, weight, age, and gender. The field devices communicate with the medical cloud platform via a communication network, sending the patient's identity information, examination sites, medical images, and on-site diagnostic analysis videos to the medical cloud platform. The field devices are also used to select any idle remote device from all remote devices shared with the data sharing module for data interaction.

[0051] Remote devices are used for data interaction with field devices. It should be noted that remote devices must include at least communication devices capable of communicating with both the medical cloud platform and the field devices. When field devices interact with selected remote devices, the data interaction can be achieved through network communication.

[0052] It should be noted that the above communication networks include, but are not limited to, wired networks, GSM networks, GPRS networks, CDMA and other wireless transmission networks.

[0053] The data communication module is used to receive medical data from multiple terminal devices in real time and transmit the medical data to the data sharing module.

[0054] The data sharing module includes functions for storing medical data, collecting user feedback information, and filtering historical medical data that matches the current medical data from all stored medical data based on the medical data and user feedback information, and sharing the remote devices corresponding to the historical medical data with the field devices.

[0055] It should be noted that, please refer to... Figure 2 The data sharing module in this invention operates as follows:

[0056] 1. Store newly added medical data and create data tags for the stored medical data. Data tags include identity tags, body part tags, medical image tags, department tags, and treatment tags. Based on the identity tag, determine if the current patient's identity already appears in historical medical data. If it does, update the corresponding other tags. If not, create an empty user tag for the current patient. The treatment tag includes all feasible treatment methods.

[0057] II. Obtaining Feature Data from Current Medical Data. Feature data includes on-site diagnostic analysis videos and a dataset of disease-related keywords. The disease-related keyword dataset should include at least: keywords reflecting the severity of the condition, keywords reflecting the type of condition, keywords reflecting the department involved in the condition, and high-frequency keywords from the videos.

[0058] Third, identify historical medical data in all stored historical medical data that have at least four identical data tags to the current medical data.

[0059] IV. Play the identified historical medical data on-site diagnostic analysis videos in sequence and obtain user feedback data on the on-site diagnostic analysis videos. In this invention, user feedback mainly includes the following aspects: (1) Changes in the user's facial expressions while watching the video. (2) Direct discussions by the user about the video. For example, discussing the severity of the illness in the video, various treatment methods and effects, etc. (3) Gestures made by the user while watching the video. For example, if a user points directly at the video playback device to prompt other users to pay attention, this reflects that the user is concerned about the currently playing video. (4) The duration of the user's attention while watching a certain video. (5) The user's request to switch the currently playing video. This directly reflects the user's dissatisfaction with the video.

[0060] The process of obtaining user feedback data on on-site diagnostic analysis videos is as follows:

[0061] (1) Acquire the voice stream data and video stream data generated by the user during the playback of the on-site diagnostic analysis video, as well as the user's instruction to switch the current on-site diagnostic analysis video.

[0062] (2) Determine whether an instruction to switch the current on-site diagnostic analysis video has been received. If yes, assign 1 to the feature quantity SW that reflects the instruction; otherwise, assign 0 to SW.

[0063] V. Based on user feedback data regarding the on-site diagnostic analysis video, calculate the user's satisfaction rating H for the current on-site diagnostic analysis video.

[0064] The calculation process for the user's satisfaction rating H for the current on-site diagnostic analysis video is as follows:

[0065] (1) Perform speech recognition on the on-site diagnosis analysis video, extract the keywords that match the feature data in the disease keyword dataset, and count their number N1.

[0066] (2) Perform video action recognition on the on-site diagnostic analysis video. Extract the gestures and actions that represent the user's feedback to the current on-site diagnostic analysis video, and count their number N2.

[0067] User gestures and actions in response to on-site diagnostic analysis videos include nodding, clapping, pointing at the playback interface with their hand, and head movements such as looking up or turning their head from a non-direct gaze to a direct gaze.

[0068] (3) Identify the on-site diagnostic analysis video. Determine the duration t during which the user focuses on the current on-site diagnostic analysis video.

[0069] The method for calculating the user's attention duration t for the current on-site diagnostic analysis video is as follows:

[0070]

[0071] In the formula, t1 represents the duration of direct eye contact during the playback of the current on-site diagnostic analysis video, numbered t2 represents the duration of eye-closed contact during the playback of the current on-site diagnostic analysis video, numbered t3 represents the duration of head-down contact during the playback of the current on-site diagnostic analysis video, numbered t4 represents the duration of head-turning contact during the playback of the current on-site diagnostic analysis video, numbered t4 represents the duration of head-turning contact during the playback of the current on-site diagnostic analysis video, and T is the total playback duration of the current on-site diagnostic analysis video.

[0072] In this invention, when calculating the duration of user attention to a video, both the time spent directly watching the video and the time spent in a non-directly watching state are considered. This embodiment primarily obtains a relatively accurate attention duration by removing the time spent in a non-attentive state and then averaging it with the time spent in an attentive state.

[0073] (4) Get the value of SW.

[0074] (5) Calculate the current user's satisfaction rating H for the on-site diagnostic analysis video using the following formula:

[0075]

[0076] In the formula, H represents the user's satisfaction rating of the current on-site diagnostic analysis video, H≥0, and the larger the value of H, the higher the user's satisfaction with the current on-site diagnostic analysis video. This represents the user's attention level on the current on-site diagnostic analysis video. k1 represents the influence factor of voice feedback on the overall acceptance evaluation result. k2 represents the influence factor of posture and movement feedback on the overall acceptance evaluation result. k3 represents the influence factor of attention level on the overall acceptance evaluation result. a1 represents the score of a single keyword in the voice feedback. a2 represents the score of a single posture and movement in the posture and movement feedback. a3 represents the score of attention level.

[0077] In this embodiment, speech recognition, image recognition, and video action recognition technologies are used to extract various types of feedback information from the user's voice stream data and video stream data. After these feedback information are quantified by the method provided in this embodiment, an evaluation result reflecting the user's approval of the current video can be obtained.

[0078] 6. Filter out historical medical data that matches the current medical data.

[0079] The process of filtering out historical medical data that matches the current medical data is as follows:

[0080] Set a high threshold H for H L and a low threshold H W High threshold H L This indicates that the user approves the current threshold value of the on-site diagnostic analysis video, H. W This indicates that the user does not accept the current threshold value of the on-site diagnostic analysis video. W >0.

[0081] When H≥H L At that time, the historical medical data corresponding to the current on-site diagnostic analysis video is regarded as the most suitable historical medical data.

[0082] H W ≤H≤H L At that time, the historical medical data corresponding to the current on-site diagnostic analysis video is regarded as general adapted historical medical data.

[0083] Create a best-fit data table and a general-fit data table. Enter the best-fit historical medical data into the best-fit data table, and the general-fit historical medical data into the general-fit data table. If the best-fit data table contains 5 sets of data, stop filtering and use these 5 sets as the historical medical data that matches the current medical data. If the best-fit data table contains fewer than 5 sets of data, but the general-fit data table contains 10 sets of data, stop filtering and use all data from both the best-fit and general-fit data tables as the historical medical data that matches the current medical data.

[0084] 7. Share the corresponding remote devices with the appropriate historical medical data with the field devices.

[0085] Field devices can view the corresponding remote devices and their working status on the shared module of the medical cloud platform, which includes an idle state and a working state. An idle state indicates that the remote device has no specific medical task and no other field devices are interacting with it. A working state indicates the opposite. Field devices can choose to communicate with devices in the idle state to exchange medical data. For example, doctors on the remote device can provide treatment suggestions, treatment plans, disease insights, and analyses based on the matched historical medical data.

[0086] Compared to existing technologies, the medical image data sharing system based on the cloud platform of this invention connects on-site and remote devices through a medical cloud platform, enabling remote doctors to share patient medical data with on-site doctors. This allows remote doctors to assist on-site doctors in diagnosing and treating patients, thereby improving the accuracy and efficiency of diagnosis and treatment.

[0087] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A cloud-based medical image data sharing system, characterized in that, It includes terminal devices and a medical cloud platform; the terminal devices communicate with the medical cloud platform through a communication network; the terminal devices include field devices and remote devices; the medical cloud platform includes a data communication module and a data sharing module; The field equipment is used to collect the user's medical data and send the medical data to the medical cloud platform; The remote device is used to interact with the field device; The data communication module is used to receive medical data from multiple terminal devices in real time and transmit the medical data to the data sharing module. The data sharing module is used to store the medical data, collect user feedback information, and filter historical medical data that matches the current medical data from all the stored medical data based on the medical data and user feedback information, and share the remote devices corresponding to the historical medical data with the field devices; The field device is also used to select any one of the remote devices whose working state is idle from all the remote devices shared by the data sharing module for data interaction; The data sharing module operates as follows:

1. Store newly added medical data and establish data tags for the stored medical data, including identity tags, body part tags, medical image tags, department tags, and treatment tags; II. Obtain feature data from current medical data; feature data includes on-site diagnostic analysis videos and disease keyword datasets; Third, identify historical medical data in all stored historical medical data that have no fewer than four identical data tags to the current medical data; 4. Play the on-site diagnostic analysis video of the identified historical medical data in sequence, and obtain user feedback data on the on-site diagnostic analysis video; V. Based on user feedback data regarding the on-site diagnostic analysis video, calculate the user's satisfaction rating H for the current on-site diagnostic analysis video; VI. Filter out historical medical data that matches the current medical data; 7. Share the remote devices corresponding to the compatible historical medical data with the field devices; The calculation process for the user's satisfaction rating H for the current on-site diagnostic analysis video is as follows: (1) Perform speech recognition on the on-site diagnosis analysis video, extract keywords that match the feature data in the disease keyword dataset, and count their number N1; (2) Perform video action recognition on the on-site diagnostic analysis video; extract the posture actions that represent the user's feedback to the current on-site diagnostic analysis video, and count their number N2; (3) Identify the on-site diagnostic analysis video; determine the user's attention duration t for the current on-site diagnostic analysis video; (4) Obtain the value of SW, where SW is a feature quantity of the instruction to switch the current on-site diagnostic analysis video. SW=1 indicates that the instruction to switch the current on-site diagnostic analysis video has been received, and SW=0 indicates that the instruction to switch the current on-site diagnostic analysis video has not been received. (5) Calculate the user's satisfaction rating H for the current on-site diagnostic analysis video using the following formula: ； In the formula, H represents the user's rating of the current on-site diagnostic analysis video, H≥0, and the larger the value of H, the higher the user's rating of the current on-site diagnostic analysis video; T is the total playback time of the current on-site diagnostic analysis video. k1 represents the user's attention concentration on the current on-site diagnostic analysis video; k2 represents the influence factor of voice information feedback on the overall recognition evaluation result; k3 represents the influence factor of attention concentration on the overall recognition evaluation result; a1 represents the score of a single keyword in the voice information feedback; a2 represents the score of a single posture in the posture feedback; a3 represents the score of attention concentration.

2. The medical image data sharing system based on a cloud platform according to claim 1, characterized in that, The medical data includes the patient's identity information, the area being examined, medical images, and on-site diagnostic analysis videos.

3. A cloud-based medical image data sharing system according to claim 2, characterized in that, The patient's identity information includes department information and personal information, including height, weight, age, and gender.

4. A cloud-based medical image data sharing system according to claim 1, characterized in that, The process of obtaining user feedback data on on-site diagnostic analysis videos is as follows: (1) Acquire the voice stream data and video stream data generated by the user during the playback of the on-site diagnostic analysis video, as well as the user's instruction to switch the current on-site diagnostic analysis video; (2) Determine whether the instruction to switch the current on-site diagnostic analysis video has been received. If yes, assign the value 1 to the feature quantity SW that reflects the instruction; otherwise, assign the value 0 to SW.

5. A cloud-based medical image data sharing system according to claim 1, characterized in that, The method for calculating the user's attention duration t for the current on-site diagnostic analysis video is as follows: ； In the formula, t1 represents the duration of direct viewing by the user during the current on-site diagnostic analysis video playback; t2 represents the duration of time the user's eyes were closed during the current on-site diagnostic analysis video playback; t3 represents the duration the user's head is down during the current on-site diagnostic analysis video; t4 represents the duration of the user's head turning during the current on-site diagnostic analysis video playback.

6. A cloud-based medical image data sharing system according to claim 1, characterized in that, User gestures and actions in response to on-site diagnostic analysis videos include nodding, clapping, pointing at the playback interface with their hand, and head movements such as looking up or turning their head from a non-direct gaze to a direct gaze.

7. A cloud-based medical image data sharing system according to claim 1, characterized in that, The process of filtering out historical medical data that matches the current medical data is as follows: Set a high threshold H for H. L and a low threshold H W The high threshold H L This indicates that the user approves the current threshold value of the on-site diagnostic analysis video, the H... W This indicates that the user does not accept the current threshold value of the on-site diagnostic analysis video. W >0; When H≥H L At that time, the historical medical data corresponding to the current on-site diagnostic analysis video is regarded as the most suitable historical medical data; H W ≤H≤H L At that time, the historical medical data corresponding to the current on-site diagnostic analysis video is regarded as general adapted historical medical data; Create a best-fit data table and a general-fit data table. Enter the best-fit historical medical data into the best-fit data table and the general-fit historical medical data into the general-fit data table. If the most suitable data table contains 3 sets of data, stop filtering and use the 3 sets of data as historical medical data that are suitable for the current medical data; If the most suitable data table has fewer than 3 sets of data, but the general suitable data table has 5 sets of data, stop filtering and use all the data in the most suitable data table and the general suitable data table as historical medical data that can be matched with the current medical data.

Images