Method and Device for Detecting Microembolic Signals in Doppler Ultrasound Signals Using Artificial Intelligence

Abstract

According to one aspect of the present invention, a method for providing information on whether a microembolus exists within a target using Doppler ultrasound is provided, comprising the steps of: obtaining a first Doppler ultrasound measurement result by using a first probe on a measurement target area of ​​the target; obtaining a preprocessed first Doppler ultrasound measurement result by preprocessing the first Doppler ultrasound measurement result by a processor; determining whether an MES exists from the preprocessed first Doppler ultrasound measurement result by using a first artificial intelligence algorithm by the processor; and providing information regarding a microembolus within the target according to whether an MES exists by the processor.

Description

Technology Field

[0001] The present invention relates to a method and apparatus for detecting microembolic signals (MES) from Doppler ultrasound signals using artificial intelligence. Background Technology

[0002] An embolus is a substance that travels along the bloodstream within a blood vessel and blocks it; it can appear in various forms, such as blood clots, fatty tissue, air bubbles, or other foreign substances. If such an embolus blocks a blood vessel, it can cause serious conditions such as stroke, pulmonary embolism, and myocardial infarction.

[0003] Microemboluses are very small and do not present with distinct clinical symptoms in the early stages; however, due to their continuous accumulation or migration, they have the potential to cause fatal diseases in the long term. These microemboluses appear as MES on Doppler ultrasound imaging and are utilized as early predictive indicators for embolism formation, vascular occlusion, and cancer metastasis.

[0004] Conventional Doppler ultrasound devices are bulky, heavy, and expensive, and require skilled medical personnel, making them difficult for patients to use individually. To overcome these limitations, there is a need to develop a highly portable Doppler ultrasound device that can be easily used by non-experts. The problem to be solved

[0005] The present invention aims to provide a method and system for detecting MES from Doppler ultrasonic signals using artificial intelligence. means of solving the problem

[0006] A representative configuration of the present invention for achieving the above objective is as follows.

[0007] According to one aspect of the present invention, a method for providing information on whether a microembolic signal exists within a target object using Doppler ultrasound is provided, comprising the steps of: obtaining a first Doppler ultrasound measurement result by using a first probe on a measurement target area of ​​the target object; obtaining a preprocessed first Doppler ultrasound measurement result by preprocessing the first Doppler ultrasound measurement result by a processor; determining whether a microembolic signal (MES) exists from the preprocessed first Doppler ultrasound measurement result by using a first artificial intelligence algorithm by the processor; and providing information regarding the microembolic signal within the target object according to the presence or absence of the MES by the processor.

[0008] According to another aspect of the present invention, an MES detection device is provided comprising: a sensor module including a first probe; a storage for storing a first artificial intelligence algorithm; and a processor that uses the first probe on a measurement target area of ​​an object to obtain a first Doppler ultrasonic measurement result, preprocesses the first Doppler ultrasonic measurement result to obtain a preprocessed first Doppler ultrasonic measurement result, uses the first artificial intelligence algorithm to determine the presence of an MES from the preprocessed first Doppler ultrasonic measurement result, and provides information regarding microembolisms within the object according to the presence of the MES.

[0009] In addition to this, other methods for implementing the present invention, other devices, and non-transient computer-readable recording media for recording a computer program for executing said methods are further provided. Effects of the invention

[0010] According to the present invention, the presence of MES can be determined quickly and accurately by utilizing artificial intelligence in signals obtained through Doppler ultrasound, thereby contributing to the early diagnosis and prevention of microembolism-related diseases.

[0011] According to the present invention, by combining a highly portable and easy-to-use Doppler ultrasound device with artificial intelligence technology, it is possible for even ordinary people who are not medical professionals to easily utilize it to enable continuous health monitoring at home. Brief explanation of the drawing

[0012] FIG. 1 is a block diagram of an MES detection device according to one embodiment of the present invention. FIG. 2 is a flowchart illustrating the operation method of an MES detection device according to one embodiment of the present invention. FIG. 3 is a flowchart showing the preprocessing step among the operation methods of an MES detection device according to one embodiment of the present invention. FIG. 4 illustrates a learning method of an artificial intelligence algorithm used in the operation method of an MES detection device according to one embodiment of the present invention. FIG. 5 is a flowchart for changing the amplitude threshold and the duration threshold as MES is detected during the operation method of an MES detection device according to one embodiment of the present invention. FIG. 6 is a flowchart illustrating the operation method of an MES detection device having a blood vessel location recognition function according to one embodiment of the present invention. Specific details for implementing the invention

[0013] The following detailed description of the invention refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that various embodiments of the invention are different but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be modified from one embodiment to another without departing from the spirit and scope of the invention. It should also be understood that the location or arrangement of individual components within each embodiment may be modified without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not meant to be limiting, and the scope of the invention should be understood to encompass the scope claimed by the claims and all equivalents thereof. Similar reference numerals in the drawings indicate identical or similar components across various aspects.

[0014] Terms such as "first," "second," etc., may be used to describe various components, but said components should not be limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component. The term "and / or" includes a combination of a plurality of related described items or any of a plurality of related described items.

[0015] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0016] The terms used in this application are used merely to describe specific embodiments and are not intended to limit the invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "having" are intended to specify the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0017] In this regard, terms such as "approximately" and "substantially" as used throughout the specification are used to mean at or near the stated value when inherent manufacturing and material tolerances are presented in the said meaning, and are used to prevent unscrupulous infringers from unfairly exploiting the disclosure in which precise or absolute values ​​are mentioned to aid in understanding the invention. As used throughout the specification of the invention, terms such as "step of" or "step of" do not mean "step for."

[0018] In this specification, the term "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware.

[0019] Some of the operations or functions described herein as being performed by a terminal, device, or device may instead be performed by a server connected to said terminal, device, or device. Likewise, some of the operations or functions described as being performed by a server may also be performed by a terminal, device, or device connected to said server.

[0020] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0021] Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings. In order to facilitate an overall understanding of the present invention, the same reference numerals are used for identical components in the drawings, and redundant descriptions of identical components are omitted.

[0022] FIG. 1 is a block diagram of an MES detection device according to one embodiment of the present invention.

[0023] Referring to FIG. 1, the MES detection device (100) may include a sensor module (110), a processor (120), an operation control module (130), and storage (140). According to an embodiment, the MES detection device (100) may be implemented as a wearable device or a surgical device. According to an embodiment, the MES detection device (100) may be performed in real time.

[0024] According to an embodiment, the sensor module (110) may include probes. One or more probes may be used, and each probe may be utilized according to a specific purpose. For example, the sensor module (110) may include a first probe (112) and / or a third probe (114).

[0025] The first probe (112) may be focused on determining the presence of microembolisms by analyzing ultrasonic reflection signals generated from the blood vessels of the subject. This allows for real-time determination of whether microembolisms are present in the bloodstream and can contribute to the early detection of diseases such as embolism or stroke.

[0026] The third probe (114) can be used to determine the location of the blood vessel to be measured. The structure of the blood vessel may vary depending on the anatomical differences of individual patients, and it is essential to precisely determine the location of the blood vessel for accurate MES detection. The third probe (114) can be used to determine the relative location of major blood vessels based on blood flow velocity and direction, and based on this, it can assist the first probe (112) in collecting signals at the optimal measurement point. Through the use of multiple probes, the present invention enables more precise blood flow analysis and minimizes measurement errors that may occur with a single probe. This allows medical personnel to receive more accurate diagnostic information and enables more effective management of the patient's health through real-time monitoring.

[0027] In one embodiment, the results of the Doppler ultrasound analysis may be provided via spectral Doppler ultrasonography. Spectral Doppler ultrasonography is a diagnostic method that can evaluate blood flow velocity by measuring it as a graph and then quantifying it. The results of the spectral Doppler ultrasound analysis may also be provided in the form of a waveform of the Doppler signal. The probe can output information on the velocity and direction of blood flow in the form of a waveform over time, enabling quantitative analysis of the characteristics of flow within the blood vessel. In an embodiment of the present invention, the frequency spectrum of the Doppler waveform is analyzed to extract a pattern of change in blood flow velocity within the blood vessel, and the location of the blood vessel can be determined by searching for a position where a specific flow pattern is maintained consistently. By analyzing the waveform data, characteristics such as blood flow velocity, pulsatility, and turbulence within the blood vessel can be precisely evaluated, thereby enabling more accurate identification of the location of the blood vessel.

[0028] In one embodiment, the results of the Doppler ultrasound analysis may be provided as color Doppler ultrasonography. Color Doppler ultrasonography is a Doppler examination method that determines color according to the direction of blood flow and brightness according to the velocity of blood flow. Color Doppler ultrasonography may be provided along with an image of the measurement target space. The probe can visually represent the relative position of blood vessels within a specific space based on blood flow and can perform the function of exploring blood vessel structures in 2D or 3D space based on the ultrasound probe. In an embodiment of the present invention, the explored blood vessel locations can be expressed in the form of color mapping or velocity vector mapping, and specific blood vessels can be effectively identified by highlighting areas with high blood flow velocity. Furthermore, these image-based analysis results can be utilized to automatically recognize blood vessel structures and select blood vessels to be measured using machine learning and artificial intelligence models.

[0029] In an embodiment of the present invention, the MES can be detected by combining the results of the diaphragm Doppler ultrasound examination and the tone Doppler ultrasound examination, and the location of the blood vessel to be measured can be determined.

[0030] In this specification, the names first probe (112) and third probe (114) are merely formulas to distinguish their respective functions, and they do not necessarily have to be different devices. The same probe may perform both MES detection and identification of the target blood vessel location. Additionally, multiple probes performing the same purpose may be mounted on a single MES detection device. For example, multiple probes may be arranged for the same measurement purpose to increase the reliability of MES detection, or multiple probes may be utilized to enable measurement from various angles to increase the precision of blood vessel location identification.

[0031] According to an embodiment, the probe may be implemented to be embedded in or coupled to the MES detection device (100).

[0032] The probe performs the role of transmitting ultrasonic signals and receiving reflected signals, and measures blood flow velocity by analyzing signals reflected from red blood cells in the bloodstream. The probe measures blood flow velocity using the Doppler effect and has a built-in ultrasonic transducer. Generally, a frequency in the range of 1 MHz to 10 MHz is used. According to one embodiment, an ultrasonic frequency of 2 MHz may be used for measuring cerebral blood flow.

[0033] According to an embodiment, one or more probes may be mounted on the MES detection device (100), and measurement may be performed by selecting an optimal probe based on its relative position to the blood vessel to be measured. In one embodiment, two probes may be mounted on the left and right sides of the MES detection device (100), and MES measurement may be performed using the probe located close to the blood vessel to be measured. In one embodiment, two probes may be mounted on the left and right sides of the MES detection device (100), and MES measurement may be performed using the probe located close to the blood vessel to be measured. It may be configured such that one probe performs blood vessel location search and the other probe performs MES detection. By utilizing multiple probes, signals can be collected from multiple angles, and reliability can be increased. The quality of the data collected during measurement can be analyzed, and if the signal strength of a specific probe is low or distorted, it can be switched to another probe.

[0034] According to an embodiment, the MES detection device (100) may include a support or a fixing band. The support has a structure that does not completely surround the measurement target area in a circular shape, but is fixed or attached only to a part of the measurement target area in the form of a headband. The support may be relatively lightweight and designed to be stably mounted at a specific area. The fixing band has a structure that completely surrounds the measurement target area in a circular shape in the form of a headband and may be designed to more firmly fix the probe. The fixing band may include an elastic material. Both the support and the fixing band may include an adjustable fastening device to allow the probe to change its position and angle during measurement.

[0035] According to the embodiments, the measurement target site may be the head, neck, arm, wrist, chest, thigh, or ankle. The measurement target site may be selected as a location where major blood vessels with active blood flow are situated, and each site may be selected according to the measurement purpose and the application environment. In the case of the head area, transcranial Doppler (TCD) ultrasound can be utilized to measure blood flow within cerebral blood vessels and to detect microembolic signals (MES) in the middle cerebral artery (MCA) and internal carotid artery. In the case of the neck area, carotid artery ultrasound measurement can be used to analyze the blood flow status and the presence of stenosis within the carotid artery, and measurements can be performed so that MES can be detected in the carotid artery before traveling to the brain. In the case of the arm and wrist areas, peripheral artery blood flow is measured, and it can be utilized to evaluate the health status of systemic blood circulation. In particular, blood flow analysis is possible in the radial artery and brachial artery. The chest area can be utilized to monitor blood flow in major arteries (e.g., aorta, subclavian artery, etc.) connected to the heart. The thigh area allows for the analysis of lower extremity blood circulation status by measuring blood flow in the femoral artery and can be useful for detecting lower extremity arterial occlusion and vascular diseases. The ankle area enables blood flow measurement for the detection of Peripheral Artery Disease (PAD) and allows for the assessment of lower extremity blood circulation problems by calculating the Ankle-Brachial Index (ABI). Furthermore, measurement methods for each area may vary depending on the probe placement and fixation method. For example, in the head and neck areas, supports or fixation bands can be used to maintain the probe's position stably, while elastic fixation bands can be used in the wrist or ankle areas to minimize movement during measurement.

[0036] The position and angle of the probe can be adjusted by the motion control module (130), enabling optimal ultrasound measurement of the blood vessel to be measured. Additionally, if the blood vessel to be measured changes or the patient moves, the direction of the probe is automatically adjusted for optimal ultrasound measurement.

[0037] According to an embodiment, the blood vessel to be measured may include the middle cerebral artery (MCA), internal carotid artery (ICA), external carotid artery (ECA), common carotid artery (CCA), brachial artery, subclavian artery, internal thoracic artery, axillary artery, femoral artery, deep femoral artery, radial artery, ulnar artery, subclavian artery, aorta, tibial artery, or dorsalis pedis artery.

[0038] The location of the blood vessel to be measured may be a relative position from the probe. The relative position can be established based on the probe's coordinate system and can be expressed in one of the three commonly used coordinate systems: the Cartesian coordinate system, the polar coordinate system, and the cylindrical coordinate system. When using multiple probes, the relative position can be determined based on the location of one of them or based on their center point.

[0039] In another embodiment, the position and angle of the probe within the MES detection device (100) may be fixed. The position and angle of the probe may be fixed in an optimal state for MES measurement.

[0040] According to an embodiment, the processor (120) may include a CPU (Central Processing Unit) (122) and a NPU (Neural Processing Unit) (124). The CPU (122) may control the overall operation of the MES detection device (100). The CPU (122) may include a single processor core or a plurality of processor cores. The CPU (110) may process or execute programs and / or data stored in storage (300). For example, the CPU (110) may control the function of the NPU (124) by executing programs and / or modules stored in storage (300). The CPU (122) may also implement neural network models using languages ​​such as Java, C / C++, Python, R, and Python-based languages ​​such as TensorFlow, Keras, and PyTorch.

[0041] The processor (120) can store the Doppler ultrasound measurement results obtained through the sensor module (110) in storage. The processor (120) can adjust the position and angle of the probe to obtain an optimal signal by considering the location of the blood vessel to be measured.

[0042] The processor (120) can be controlled to perform preprocessing on the Doppler ultrasound measurement results obtained through the sensor module (110). The processor (120) can convert the obtained Doppler ultrasound measurement results into continuous frames to prevent data loss. The processor (120) applies filtering techniques to remove low-frequency or high-frequency noise and improve signal quality. The processor (120) can convert the signal to emphasize specific patterns (amplitude, duration, etc.) to make the characteristics of the microembolism signal (MES) more distinct.

[0043] The processor (120) can determine relative coordinates by analyzing the location of the blood vessel based on the Doppler ultrasound measurement results. The processor (120) can automatically search for the blood vessel to be measured by considering the flow velocity and direction of the blood vessel. The processor (120) can maintain an optimal measurement environment by dynamically adjusting the position and angle of the probe based on the blood vessel search results through the motion control module (130).

[0044] The processor (120) can evaluate the possibility of a microembolism signal by extracting a feature vector (amplitude, duration, frequency fluctuation, etc.) of the signal analysis signal for MES detection. The processor (120) can classify the signal by applying a signal analysis model based on the first artificial intelligence algorithm (142) and determine whether MES is present. Based on the analysis results, the processor (120) can evaluate the reliability of MES detection by comparing signal strength and patterns.

[0045] The processor (120) can update the amplitude threshold and / or duration threshold used in the preprocessing process according to the MES detection result. The processor (120) can dynamically adjust the amplitude threshold and duration threshold based on the detected MES pattern.

[0046] The processor (120) can perform dynamic threshold variation during the preprocessing process. If the processor (120) determines that MES is present from the Doppler ultrasonic measurement results using the first artificial intelligence algorithm (142), it can lower the first amplitude threshold (146), raise the first duration threshold (148), or lower the first amplitude threshold (146) and raise the first duration threshold (148). The processor (120) can apply the changed first amplitude threshold (146), the changed second duration threshold (148), or the changed first amplitude threshold (146) and the changed second duration threshold (148) in the step of obtaining the preprocessed Doppler ultrasonic measurement results by preprocessing the Doppler ultrasonic measurement results subsequently. The processor (120) can adjust the detection sensitivity by applying the updated thresholds to the new measurement results.

[0047] The processor (120) may provide information regarding microembolisms within the subject depending on the presence or absence of MES. In one embodiment, the information regarding microembolisms may be the presence or absence of microembolisms, the location where microembolisms are found, the frequency of detection of microembolisms, the signal strength of MES, or a combination thereof. In one embodiment, the processor (120) may store the information regarding microembolisms in real time and output analysis results. The processor (120) may support the analysis of changes over time by recording data logs. In one embodiment, the processor (120) may provide information regarding microembolisms within the subject in real time. In one embodiment, the information regarding microembolisms may be used to predict cerebral infarction, myocardial infarction, or cancer metastasis.

[0048] In one embodiment, the processor (120) can perform machine learning of an artificial intelligence algorithm through an NPU (124). The NPU (124) is a processor designed to optimize machine learning operations, including deep learning, and can play a role in accelerating the learning and execution of artificial intelligence algorithms. In particular, it provides high computational efficiency in neural network models that require a large amount of matrix operations and can support faster computational speeds compared to a CPU (122) through parallel processing. In one embodiment, the NPU (124) can be used to perform learning and optimized inference of a first artificial intelligence algorithm (142) and a third artificial intelligence algorithm (144) for analyzing Doppler ultrasonic signals.

[0049] The processor (120) can be used not only to detect MES from Doppler ultrasound signals but also to identify the location of the blood vessel to be measured. The processor (120) evaluates the blood flow velocity and direction by analyzing the probe signal during the process of finding the location of the blood vessel to be measured, and can determine the relative location of the blood vessel more precisely by rapidly processing a large amount of signal data. Through this, the processor (120) can automatically select a probe close to the blood vessel to be measured and can improve the accuracy of MES detection by maintaining optimal blood flow search conditions.

[0050] The processor (120) receives filtered Doppler ultrasound data from the signal preprocessing process as input and performs artificial intelligence-based feature extraction and signal pattern classification, thereby enabling more precise analysis of the characteristics of the signal. Additionally, the processor (120) can be used during the training process of a machine learning model for blood vessel location detection and MES detection, and during real-time data analysis, inference can be performed based on the trained model to quickly determine the presence of MES.

[0051] In one embodiment, a CPU (122) and an NPU (124) may be appropriately combined and utilized depending on the need for real-time analysis and computational performance requirements. That is, in the step of executing a learned model to analyze signals and detect MES, computation can be performed using only the CPU, and an NPU (124) may be additionally utilized when real-time processing is required or large-scale parallel computation is required. Through this, the present invention can enable rapid and efficient diagnosis by optimizing computational performance while increasing the accuracy of neural network-based MES detection.

[0052] According to an embodiment, the NPU (124) can generate a neural network, train or learn the neural network, perform operations based on training data, generate an information signal based on the results of the operation, or retrain the neural network. The NPU (124) is not limited to a specific name and may be a processor for executing the neural network, such as a GPU or TPU.

[0053] According to various embodiments, neural network models may include various types of models such as Convolutional Neural Network (CNN), Region with Convolutional Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restricted Boltzmann Machine (RBM), Fully Convolutional Network, Long Short-Term Memory Network (LSTM), Classification Network, etc., such as GoogleNet, AlexNet, VGG Network, etc., but are not limited to the aforementioned models.

[0054] According to the embodiments, the neural network models of the reinforcement learning agent may include various models such as DQN (Deep Q-Network), DDQN (Double DQN), Dueling DQN, DDPG (Deep Deterministic Policy Gradient), and DDDQN (Dueling Double DQN), but are not limited to the aforementioned models.

[0055] According to an embodiment, the processor (120) may use separate storage (140) for storing programs corresponding to models of the neural network. The processor (120) may further include separate IP (intellectual property) blocks for processing many operations required to run the neural network. For example, the separate IP blocks may further include a GPU (graphical processing unit) or an accelerator for performing specific operations quickly.

[0056] According to an embodiment, the motion control module (130) can control the movement of the MES detection device (100). For example, the motion control module (130) can control the configuration (e.g., shape of the support, length of the support, tightening of the fixing band, position of the probe on the support and / or fixing band, angle of the probe) for moving the MES detection device (100) according to the location of the blood vessel to be measured.

[0057] In one embodiment, the motion control module (130) can cause the first probe (112) or the third probe (114) to move toward the target blood vessel location by adjusting the position and angle of the first probe (112) or the third probe (114). In one embodiment, the processor (120) can adjust the position and angle of the first probe (112) or the third probe (114) through the motion control module (130) based on information regarding the target blood vessel location. In one embodiment, the motion control module (130) can adjust the shape of the support, the length of the support, or the tightness of the fixing band.

[0058] According to an embodiment, the storage (140) is a storage place for storing data and can store an OS (Operating System), various programs, and various data. For example, the storage (140) may correspond to non-volatile memory. The storage (140) may include ROM (Read Only Memory), flash memory, PRAM (Phase-change RAM), MRAM (Magnetic RAM), RRAM (Resistive RAM), FRAM (Ferroelectric RAM), etc. According to an embodiment, the storage (140) may be implemented as an HDD (Hard Disk Drive), SSD (Solid State Drive), etc.

[0059] According to an embodiment, a first artificial intelligence algorithm (142) and a third artificial intelligence algorithm (144) may be stored in the storage (140). The first artificial intelligence algorithm (142) is a neural network model for determining the presence of microembolism signals (MES) in preprocessed Doppler ultrasound measurement results, and can receive preprocessed Doppler ultrasound measurement results as input, analyze the pattern of MES, and provide detection results. The third artificial intelligence algorithm (144) is an algorithm for searching the location of a blood vessel to be measured and determining relative coordinates, and can be used to automatically search for the blood vessel to be measured and set the optimal probe location. These artificial intelligence algorithms may be stored as pre-trained models or designed to be continuously updated when new data is added.

[0060] According to an embodiment, a first amplitude threshold (146) and a first duration threshold (148) may be stored in the storage (140). The first amplitude threshold (146) is a reference value for removing noise based on the amplitude of a signal and can be used to identify only signals with an amplitude above a certain level in a Doppler ultrasonic signal as MES candidates. The first duration threshold (148) is a reference value for determining only signals that persist for a specific time or longer as MES, which filters out instantaneous changes in the signal and enables reliable MES detection. These thresholds may be dynamically updated based on data stored in the storage (140) and real-time analysis results, and may also be adjusted according to user settings to increase detection accuracy.

[0061] In addition, the storage (140) may store an initial training dataset, user-customized threshold settings, patient-specific measurement history, raw data of Doppler ultrasound signals, and analyzed feature vectors. Through this, the reliability of the MES detection results can be verified by comparing them with previously measured data, and it can support long-term monitoring of changes in a specific patient's blood flow pattern. Furthermore, the storage (140) can be linked with a cloud-based storage, allowing real-time diagnostic data to be shared through a connection with a remote medical system, or enabling medical staff to retrieve past data and perform in-depth analysis if necessary.

[0062] In one embodiment, the MES detection device may include a sensor module including a first probe, a storage for storing a first artificial intelligence algorithm, and a processor that uses the first probe on a measurement target area of ​​the target body to obtain a first Doppler ultrasonic measurement result, preprocesses the first Doppler ultrasonic measurement result to obtain a preprocessed first Doppler ultrasonic measurement result, uses the first artificial intelligence algorithm to determine whether there is an MES from the preprocessed first Doppler ultrasonic measurement result, and provides information regarding microembolisms within the target body according to whether there is an MES.

[0063] In one embodiment, the MES detection device may include a sensor module including a first probe, a storage that stores a first artificial intelligence algorithm and a third artificial intelligence algorithm, and a processor that obtains a third Doppler ultrasound measurement result by using the third probe on a measurement target area of ​​a target object, obtains a preprocessed third Doppler ultrasound measurement result by preprocessing the third Doppler ultrasound measurement result, obtains the location of the measurement target blood vessel from the preprocessed third Doppler ultrasound measurement result using the third artificial intelligence algorithm, obtains a first Doppler ultrasound measurement result by directing the first probe toward the location of the measurement target blood vessel of the measurement target area of ​​the target object, obtains a preprocessed first Doppler ultrasound measurement result by preprocessing the first Doppler ultrasound measurement result, determines the presence of MES from the preprocessed first Doppler ultrasound measurement result using the first artificial intelligence algorithm, and provides information regarding microembolisms within the target object according to the presence of MES.

[0064] FIG. 2 is a flowchart illustrating the operation method of an MES detection device according to one embodiment of the present invention.

[0065] The method of operation of the MES detection device of the present invention includes the steps of acquiring a first Doppler ultrasonic measurement result through a sensor module (S110), performing preprocessing of the acquired data (S120), determining the presence of MES using a first artificial intelligence algorithm (S130), and providing information regarding microembolisms within a target object (S140). This method of operation can be performed in real time.

[0066] In the step of acquiring the first Doppler ultrasonic measurement result through the sensor module (S110), the first probe is used on the measurement target area and is used for MES detection.

[0067] In the step of performing preprocessing of acquired data (S120), the data undergoes a preprocessing process to enable effective use of the first artificial intelligence algorithm. In one embodiment, the processor (120) performs noise removal and signal normalization.

[0068] In the step of determining the presence of MES using the first artificial intelligence algorithm (S130), the first artificial intelligence algorithm can detect MES in the preprocessed Doppler ultrasound signal. In one embodiment, the first artificial intelligence algorithm may be trained based on MES clinical data. The MES clinical data may be clinical data labeled with Doppler ultrasound measurement results and whether MES is present. The first artificial intelligence algorithm may be trained to match the presence of MES labeled based on the MES clinical data with the preprocessed Doppler ultrasound measurement results (e.g., second Doppler ultrasound measurement results) based on the MES clinical data. In one embodiment, during the process of training the first artificial intelligence algorithm, the preprocessed second Doppler ultrasound measurement results, which are preprocessed based on the MES clinical data, may be used as training data, and the clinical data regarding the presence of MES may be used as labeling data. In one embodiment, features of MES (e.g., signal amplitude, frequency fluctuation, duration, etc.) may be directly extracted, and machine learning may be performed based thereon.

[0069] In the step of providing information regarding microembolisms within a subject (S140), information regarding microembolisms within the subject may be provided depending on the presence or absence of MES. According to one embodiment, the information regarding microembolisms within the subject may include the presence or absence of microembolisms, the detection frequency of microembolisms, the signal strength of MES, or a combination thereof. Dynamic thresholds may be included as needed. For example, when MES is detected, the first amplitude threshold (146) and the first duration threshold (148) may be dynamically changed, and the updated thresholds may be applied during subsequent detection processes. Additionally, the detected data may be stored in storage (140) and utilized as data for long-term patient monitoring and further analysis.

[0070] FIG. 3 is a flowchart showing the preprocessing step among the operation methods of an MES detection device according to one embodiment of the present invention.

[0071] The step of performing preprocessing of acquired data (S120) in the operation method of the MES detection device of the present invention may include the step of continuously acquiring a first Doppler ultrasonic measurement result as a plurality of Doppler ultrasonic images (S210), the step of extracting a single or plurality of signals from the plurality of Doppler ultrasonic images (S220), the step of filtering a signal having an amplitude less than or equal to a first amplitude threshold from the single or plurality of signals (S230), and / or the step of additionally filtering a signal having a duration longer than a first duration threshold from the filtered single or plurality of signals (S240).

[0072] In the step of continuously acquiring the first Doppler ultrasound measurement results as a plurality of Doppler ultrasound images (S210), a process of acquiring a blood flow signal of the measurement target area using a probe may be performed. In an embodiment of the present invention, the first probe is used for MES detection and measures a continuous blood flow signal. In the signal acquisition process, a plurality of Doppler ultrasound images may be continuously collected, and data may be acquired in an overlapping manner so that the signal can be maintained continuously without data loss. The Doppler ultrasound signal is captured as a continuous image frame, and can be subdivided in a superimposed state to ensure that the signal is not omitted. In one embodiment, the Doppler ultrasound signal is divided into time intervals of 100ms to 200ms, and an overlap of 50% or more between each segment may be applied to prevent continuous data loss. In one embodiment, an overlap of 10% to 90% or more between each segment of the divided Doppler ultrasound signal may be applied to prevent continuous data loss. This enables continuous detection without signal loss even if the MES exists beyond the boundaries of a single frame.

[0073] In the step of extracting a single or multiple signals from multiple Doppler ultrasound images (S220), continuously acquired signals are arranged in chronological order, and frames are merged based on data overlapping with previous segments to extract a single or multiple signals that maintain a flow. Signal amplitude and duration can be standardized to enable consistent analysis in all measurement environments. In one embodiment, the signal can be converted to the frequency domain using a Fourier Transform, and unnecessary noise can be removed by analyzing the frequency spectrum. In particular, since MES signals exhibit patterns in specific frequency bands, MES candidate signals can be more clearly distinguished through signal filtering and frequency analysis.

[0074] In the step of filtering signals having an amplitude below a first amplitude threshold from a single or multiple signals (S230), a high-pass filter may be applied to reduce low-frequency components and external interference included in the signal. In one embodiment, MES candidate signals may be separated by retaining only signals having an amplitude of 1 to 6 dB or more relative to the background blood flow velocity. In one embodiment, MES candidate signals may be separated by retaining only signals having an amplitude of 3 dB or more relative to the background blood flow velocity. In one embodiment, MES candidate signals may be separated by filtering signals having an amplitude of less than 3 dB relative to the background blood flow velocity. In one embodiment, the first amplitude threshold may be 1 to 6 dB. In one embodiment, the first amplitude threshold may be 4 to 5 dB. In one embodiment, the first amplitude threshold may be 3 dB.

[0075] In the step of further filtering (S240) a signal having a duration longer than a first duration threshold among a single or multiple filtered signals, if the duration of the signal is maintained for a specific time (e.g., 0.5 seconds to 1 second) or longer, the signal may be removed as it is highly likely to be a long-term blood flow change or noise. Conversely, instantaneous short signals may be maintained as they are highly likely to be MES. In one embodiment, the first duration threshold may be 0.5 to 2 seconds. In one embodiment, the first duration threshold may be 0.5 to 1 second. In one embodiment, the first duration threshold may be 100 to 1000% of the average signal duration of the MES. In one embodiment, the first duration threshold may be 100 to 500%, 100 to 300%, or 100 to 200% of the average signal duration of the MES. In one embodiment, the average signal duration of the MES may be 0.5 to 1 second. In one embodiment, the average signal duration of the MES may be 0.75 seconds.

[0076] In one embodiment, a multi-frame comparison method may be applied during the signal filtering process, and reliability can be improved by evaluating whether MES candidate signals occur repeatedly within a specific time interval. Additionally, a correction process may be added so that key features (amplitude, duration, frequency fluctuation, etc.) are maintained even after the signal is filtered. Finally, the filtered signal may be output in an analyzable form, and a process of storing the analysis results may be performed. In an embodiment of the present invention, the preprocessed signal is stored in a processor and can be utilized as input data for subsequent artificial intelligence analysis.

[0077] In one embodiment, the steps of performing preprocessing of acquired data (S120) among the operation methods of the MES detection device, continuously acquiring a first Doppler ultrasonic measurement result as a plurality of Doppler ultrasonic images (S210), extracting a single or plurality of signals from the plurality of Doppler ultrasonic images (S220), filtering a signal having an amplitude less than or equal to a first amplitude threshold from the single or plurality of signals (S230), and further filtering a signal having a duration longer than a first duration threshold from the filtered single or plurality of signals (S240) may each be used independently for performing preprocessing, and may also be used in combination.

[0078] FIG. 4 illustrates a learning method of an artificial intelligence algorithm used in the operation method of an MES detection device according to one embodiment of the present invention.

[0079] The first artificial intelligence algorithm may have been trained to match the second Doppler ultrasound measurement results, preprocessed based on MES clinical data, with the presence or absence of labeled MES.

[0080] In one embodiment, training data may be generated after preprocessing a raw signal measured by a probe. In one embodiment, the preprocessing process may be the same as the step of performing preprocessing (S120) on data obtained from a first Doppler ultrasound measurement result. That is, the process may include the step of continuously acquiring a second Doppler ultrasound measurement result as a plurality of Doppler ultrasound images, the step of extracting a single or plurality of signals from the plurality of Doppler ultrasound images, the step of filtering signals having an amplitude less than or equal to a second amplitude threshold from the single or plurality of signals, and the step of further filtering signals having a duration longer than a second duration threshold from the filtered single or plurality of signals. The second amplitude threshold may be equal to the first amplitude threshold. The second duration threshold may be equal to the first duration threshold. A signal obtained by preprocessing Doppler ultrasound measurement results based on clinical data may be used as training data. The training data is divided into specific time intervals (e.g., units of 100 to 200 ms) and may be partially overlapped to maintain signal continuity. Noise is removed from each signal through frequency analysis and filtering, and the signal can be normalized to emphasize the characteristics of MES. Training data may include signal features such as amplitude, frequency fluctuations, and duration. Since MES signals have a relatively higher amplitude than background blood flow, the data can be organized based on signal intensity. Methods such as the Fourier Transform can be applied to analyze how the signal changes within specific frequency bands. Because MES signals occur in short bursts, they can be distinguished based on specific durations. Training data may include Doppler ultrasound data collected from various environments, and the dataset can be classified according to the measurement target area (head, neck, arms, etc.) and blood vessel type (middle cerebral artery, carotid artery, femoral artery, etc.).

[0081] In one embodiment, labeled data serves as ground truth data corresponding to training data and may include information indicating whether each Doppler ultrasound signal contains MES. In embodiments of the present invention, signals may be labeled based on clinical data regarding the presence of MES, enabling a machine learning model to learn the correct patterns. The labeled data may be constructed based on clinical research and analysis by medical experts, and may be classified to distinguish whether a Doppler ultrasound signal is actual MES, normal blood flow, or an artifact. Signals identified as MES may be grouped in detail based on signal intensity, frequency pattern, and duration, allowing them to be clearly distinguished from non-MES signals. To prevent data imbalance during the neural network learning process, the labeled data may be modified in various ways through an augmentation process. In embodiments of the present invention, labeling methods such as binary classification or multi-class classification may be applied. In the case of binary classification, the model may be trained to distinguish whether each Doppler ultrasound signal is MES or non-MES. For multi-classification, the model can be trained to distinguish the severity of MES signals or to differentiate specific signal patterns by subdividing them. MES clinical data may include Doppler ultrasound results collected from neurological and cardiology studies, patient data measured in hospitals, publicly available medical datasets, and self-constructed datasets. This data is labeled to enable neural network models to distinguish between MES signals and normal blood flow signals, and may include feature vectors such as signal amplitude, frequency fluctuations, and duration.

[0082] In one embodiment, the neural network model may utilize a Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), etc. By utilizing a CNN model, features regarding MES and blood vessel locations can be learned from preprocessed Doppler ultrasound image data. By applying an LSTM model, signal change patterns over time can be learned and signal continuity can be reflected. If necessary, a hybrid model combining CNN and LSTM may also be applied. As a loss function, the Cross-Entropy Loss function, etc., can be used during the model training process to evaluate training performance. Algorithms such as Adam and RMSprop can be utilized as optimizers, and optimal results can be derived by adjusting the training speed. The trained model can be evaluated through a validation dataset and a test dataset. Model performance can be evaluated based on metrics such as accuracy, precision, recall, and F1-score.

[0083] FIG. 5 is a flowchart for changing the amplitude threshold and the duration threshold as MES is detected during the operation method of an MES detection device according to one embodiment of the present invention.

[0084] The method of operation of the MES detection device of the present invention may include a procedure for determining whether MES is present (S130) using a first artificial intelligence algorithm or providing information regarding microembolisms within a target object (S140), and then determining whether MES is detected (S310), and if MES is detected, lowering a first amplitude threshold or raising a first duration threshold (S320), and if MES is not detected, maintaining the first amplitude threshold and the first duration threshold (S330).

[0085] In the step of determining whether MES has been detected (S310), a process of verifying whether MES has been detected by analyzing the Doppler ultrasonic signal may be performed. In an embodiment of the present invention, a first artificial intelligence algorithm performs signal analysis, and if MES is detected more than a certain number of times within a specific time, it may be determined that the occurrence of MES appears as a continuous pattern. It may be analyzed whether the detected MES signal is a one-time occurrence or a pattern that occurs continuously. If MES is repeatedly detected for a certain period of time, the amplitude and duration threshold values ​​can be automatically adjusted to reflect the signal characteristics. Conversely, if MES is not detected for a certain period of time, the threshold values ​​may be returned to their default values.

[0086] In the step (S320) of lowering the first amplitude threshold or raising the first duration threshold when MES is detected, a process of determining whether to maintain or adjust the currently set amplitude threshold (first amplitude threshold) and duration threshold (first duration threshold) may be performed. When a new MES pattern is detected, it may be evaluated whether the existing threshold is appropriate for optimizing MES detection. If the existing threshold is too high and some MES signals may be missed, the amplitude threshold may be lowered or the duration threshold may be raised to increase detection sensitivity. Conversely, if necessary to reduce false positives (noise signals), the amplitude threshold may be increased or the duration threshold may be extended. In an embodiment of the present invention, the range of threshold change can be dynamically adjusted, the amplitude threshold may be adjusted within a range of 1 to 6 dB, and the duration threshold may be adjusted within a range of 0.5 to 2 seconds.

[0087] The adjusted threshold value is stored in storage (140) and can be newly reflected during a subsequent analysis process. The detection sensitivity can be optimized by applying the updated threshold value to the Doppler ultrasonic signal collected thereafter. A function to return the threshold value to the default value if the MES is not detected for a certain period of time may also be included. In an embodiment of the present invention, by dynamically optimizing the threshold value by reflecting previous analysis results, it is possible to flexibly respond to signal fluctuations while maintaining the accuracy of MES detection.

[0088] FIG. 6 is a flowchart illustrating the operation method of an MES detection device having a blood vessel location recognition function according to one embodiment of the present invention.

[0089] Another method of operation of the MES detection device of the present invention includes the steps of: obtaining a third Doppler ultrasound measurement result through a sensor module (S410); performing preprocessing of the obtained data (S420); obtaining the location of the blood vessel to be measured using a third artificial intelligence algorithm (S430); obtaining a first Doppler ultrasound measurement result through a sensor module (S440); performing preprocessing of the obtained data (S450); determining the presence of MES using a first artificial intelligence algorithm (S460); and providing information regarding microembolisms within the target body (S470).

[0090] In the step of acquiring the third Doppler ultrasound measurement result through the sensor module (S410), a process of acquiring a signal for blood vessel exploration using a probe may be performed. In one embodiment, the third probe may analyze blood flow patterns to locate the position of the blood vessel to be measured. Since blood vessel structures vary from person to person, it is necessary to precisely locate the blood vessel to be measured. The probe transmits multi-frequency signals to measure the speed and direction of blood flow, and if a constant flow pattern is detected in a specific blood vessel, it can be set as the location of the explored blood vessel. In this step, data may be accumulated for a certain period of time to maintain the continuity of the blood flow signal and may be utilized in a subsequent analysis process.

[0091] In one embodiment, the results of the Doppler ultrasound analysis may be provided via spectral Doppler ultrasonography. Spectral Doppler ultrasonography is a diagnostic method that can evaluate blood flow velocity by measuring it as a graph and then quantifying it. The results of the spectral Doppler ultrasound analysis may also be provided in the form of a waveform of the Doppler signal. In one embodiment, based on the acquired waveform data, the pattern of change in blood flow velocity can be analyzed, and the location of the blood vessel can be determined by searching for a location where a specific flow pattern is maintained at a constant level.

[0092] In one embodiment, the results of the Doppler ultrasound analysis may be provided as color Doppler ultrasonography. Color Doppler ultrasonography is a Doppler examination method that determines color according to the direction of blood flow and brightness according to the velocity of blood flow. Color Doppler ultrasonography may be provided along with an image of the measurement target space. The probe can visually represent the relative position of blood vessels within a specific space based on blood flow and can perform the function of exploring blood vessel structures in 2D or 3D space based on the ultrasound probe.

[0093] In one embodiment, the third Doppler ultrasound measurement result may be obtained from a diacritical Doppler ultrasound result, a tone Doppler ultrasound result, or a combination of a diacritical Doppler ultrasound result and a tone Doppler ultrasound result.

[0094] In the step of performing preprocessing of the acquired data (S420), the acquired third Doppler ultrasound measurement results may be preprocessed to prepare for blood vessel location analysis. In the embodiments of the present invention, various signal processing and normalization techniques may be applied to increase the accuracy of blood vessel location detection, and the goal is to maintain data quality and improve analyzability. In one embodiment, the process of preprocessing the third Doppler ultrasound measurement results may be the same as the process of preprocessing the first Doppler ultrasound measurement results.

[0095] In one embodiment, the third Doppler ultrasound measurement result may be provided as image data that visually represents the direction and velocity of blood flow, and various preprocessing steps may be performed to analyze the data. The preprocessing of the color tone Doppler ultrasound image data may include steps such as image quality enhancement, color correction, spatial alignment, and feature extraction, thereby enabling more accurate analysis of the blood vessel location and optimization of signal processing for MES detection.

[0096] Since color Doppler ultrasound results may contain various types of noise in the medical imaging environment, filtering and image correction processes may be performed to improve signal quality. Gaussian filters or median filters can remove high-frequency noise that may occur in ultrasound images and emphasize continuous blood flow patterns. Binary thresholding and contrast enhancement can improve analysis accuracy by clearly distinguishing blood flow from surrounding tissues. Spatial smoothing techniques can minimize unnecessary background noise while maintaining the uniformity of blood flow.

[0097] Since color Doppler ultrasound results are characterized by color assigned according to the direction of blood flow and brightness changing according to velocity, color correction can be performed to facilitate analysis. "RGB → HSV color space conversion" can convert the RGB (Red-Green-Blue) color space to the HSV (Hue-Saturation-Value) color space to analyze the colors of ultrasound images more effectively. Color mapping analysis can highlight blood flow patterns of specific colors, enabling clearer recognition of the flow in specific blood vessels. Channel separation allows for the separation and analysis of individual color channels to analyze the direction of blood flow based on color information.

[0098] Since tone Doppler ultrasound images can be spatially distorted depending on probe movement and ultrasound measurement angles, alignment and correction processes can be performed for analysis. Geometric transformation can correct image distortion caused by changes in probe position. Region of Interest (ROI) setting allows for the analysis of specific blood vessels by defining an area of ​​interest. Multi-frame alignment tracks the location of blood vessels based on continuous image data and can compensate for image loss in specific frames.

[0099] A process can be performed to analyze the characteristics of blood flow from preprocessed color Doppler ultrasound results and extract features that can be utilized for MES detection. Blood flow velocity-based feature analysis can quantify blood flow velocity based on changes in intensity and hue in color Doppler images, and can detect abnormal turbulence or vascular stenosis by analyzing patterns of blood flow velocity change. Vascular structure-based feature analysis can recognize the shape of blood vessels within the image, extract their diameter and directionality, detect continuous vascular patterns in color Doppler images, and optimize the location of specific vessels. Blood flow direction analysis and MES detection can evaluate the possibility of MES and classify signal characteristics when the blood flow direction changes abruptly or when multiple signal patterns are detected within a specific vessel.

[0100] The preprocessed color tone Doppler ultrasound results can be stored in storage (140) and subsequently utilized in the blood vessel location search and MES detection algorithms.

[0101] When diacritical Doppler ultrasound results (waveform data) and tone Doppler ultrasound results (image data) are mixed, data alignment can be performed to facilitate analysis. By normalizing signal intensity based on blood flow velocity and frequency changes, deviations that may occur depending on the ultrasound measurement environment can be minimized. For image-based data (tone Doppler ultrasound results), color correction and sharpening can be applied, and for waveform data (diacritical Doppler ultrasound results), noise can be minimized by correcting high and low frequency components.

[0102] Filtering techniques can be applied to eliminate external interference and environmental noise that may occur during the measurement process. Signal quality can be improved by applying high-pass filtering and low-pass filtering. By optimizing the signal-to-noise ratio (SNR) in diametric Doppler ultrasound signals, it is possible to retain only the vascular signal and remove background signals.

[0103] If some signals are lost or data intervals are inconsistent in specific sections, interpolation techniques can be applied to supplement the data. Based on the pattern of changes in blood flow velocity, the signal is adjusted to maintain a constant flow, allowing the relative positions of blood vessels to be identified more clearly. Multi-frame analysis can be performed to supplement blood vessel information missed in a single frame using data from consecutive frames.

[0104] In this process, tone Doppler ultrasound image data and diaphragm Doppler ultrasound waveform data are combined to enable comprehensive analysis of vascular structure and blood flow velocity patterns.

[0105] In the step of obtaining the location of the blood vessel to be measured using the third artificial intelligence algorithm (S430), a process of obtaining the final location of the blood vessel to be measured using the third artificial intelligence algorithm based on preprocessed blood vessel location candidate data may be performed. In the embodiment of the present invention, analysis using a neural network model may be performed by considering blood flow velocity, direction, flow pattern, etc., and it may be determined whether a specific blood vessel is a target optimized for MES detection.

[0106] In an embodiment of the present invention, the third artificial intelligence algorithm may apply a neural network model trained for Doppler ultrasound-based blood vessel location detection.

[0107] Training data may include diaphragmatic Doppler ultrasound results and tone Doppler ultrasound results collected based on clinical data. In one embodiment, a fourth Doppler ultrasound measurement result may be used as training data. Location information of the blood vessel to be measured (middle cerebral artery, carotid artery, femoral artery, etc.) and blood flow signal patterns collected from the corresponding blood vessel may be included in the dataset. Since blood vessel data measured in various body parts is included, accurate blood vessel detection in a specific area is enabled.

[0108] As for analysis methods, CNN or LSTM-based image analysis can be considered. CNNs can learn tone Doppler ultrasound data and automatically recognize vascular structures. By applying an LSTM model, diaphragm Doppler ultrasound waveform data can be analyzed to learn continuous changes in blood flow velocity. By combining the results of these two analyses, the neural network model is enabled to determine whether a specific blood vessel is a suitable target for MES detection.

[0109] The labeling data may include the optimal MES measurement vessel location on the cerebral blood flow anatomy data. The relative location of the vessel may be determined based on the probe, and various coordinate system representations, such as Cartesian coordinates, polar coordinates, and cylindrical coordinates, may be applied to indicate the relative location. In one embodiment, the cerebral blood flow anatomy data may be used to optimize vessel location analysis and MES detection using Doppler ultrasound, and may include information on major cerebral blood vessel structures and blood flow patterns. Such data may be configured based on anatomical characteristics such as the anatomical arrangement of cerebral blood vessels, blood flow velocity and direction, and vessel diameter, thereby enabling accurate identification of specific vessels and evaluation of blood flow conditions. In one embodiment, the cerebral blood flow anatomy data may include information on major vessels such as the middle cerebral artery (MCA), anterior cerebral artery (ACA), posterior cerebral artery (PCA), basilar artery (BA), vertebral artery (VA), and carotid artery (ICA, CCA, ECA). These data may include data collected from various age groups and pathological conditions (e.g., stroke, vascular stenosis, etc.) to reflect anatomical variations in individual patients, and can improve the reliability of Doppler ultrasound analysis by providing normal blood flow velocity ranges for each blood vessel.

[0110] After the location of the blood vessel is determined, the third artificial intelligence algorithm can select the optimal blood vessel to be measured by considering signal strength and flow patterns. To select a blood vessel suitable for MES detection, the blood flow strength and pattern of the blood vessel to be measured can be evaluated. If the velocity of blood flow within the blood vessel is too low or irregular, another blood vessel may be selected to increase measurement reliability. The location of the blood vessel can be updated in real time and can be automatically corrected if the measurement environment changes.

[0111] The acquired blood vessel location data and the third artificial intelligence algorithm can be stored in storage (140) and referenced during the subsequent MES detection process. By storing the relative location of the blood vessels, an optimal measurement environment can be maintained when performing repeated inspections at the same measurement site. Subsequently, when MES detection is performed, the probe can be automatically adjusted based on the discovered blood vessel location.

[0112] The steps of obtaining a first Doppler ultrasonic measurement result through a sensor module (S440), performing preprocessing of the obtained data (S450), determining the presence of MES using a first artificial intelligence algorithm (S460), and providing information regarding microembolisms within a target object (S470) may be identical to steps S110 to S140 of FIG. 1. In the step of providing information regarding microembolisms within a target object (S470), the information regarding microembolisms may include the presence of microembolisms, the location where microembolisms are found, the detection frequency of microembolisms, the signal strength of MES, or a combination thereof.

[0113] The embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. In one embodiment, a non-transient computer-readable recording medium may be provided for recording a computer program for executing an MES detection method. The computer-readable recording medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the computer-readable recording medium may be those specifically designed and configured for the present invention or those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. A hardware device may be changed into one or more software modules to perform processing according to the present invention, and vice versa.

[0114] Although the present invention has been described above with reference to specific details such as specific components, limited embodiments, and drawings, this is provided only to aid in a more comprehensive understanding of the invention, and the invention is not limited to the above embodiments, and a person skilled in the art to which the invention belongs can make various modifications and changes from this description.

[0115] Accordingly, the scope of the present invention should not be limited to the embodiments described above, and all scopes equivalent to or equivalently modified from the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the concept of the present invention. Explanation of the symbols

[0116] 100: MES detection device 110: Sensor module 112: 1st probe 114: 2nd probe 120: Processor 122: CPU 124: NPU 130: Operation control module 140: Storage 142: The First Artificial Intelligence Algorithm 144: The Third Artificial Intelligence Algorithm 146: First amplitude threshold 148: First duration threshold

Claims

Claim 1 An MES detection device comprising: a sensor module including a first probe; a storage for storing a first artificial intelligence algorithm; and a processor that uses the first probe on a measurement target area of ​​a target object to obtain a first Doppler ultrasound measurement result, preprocesses the first Doppler ultrasound measurement result to obtain a preprocessed first Doppler ultrasound measurement result, uses the first artificial intelligence algorithm to determine the presence of MES from the preprocessed first Doppler ultrasound measurement result, and provides information regarding microembolisms within the target object according to the presence of MES.

Images