Intelligent medical imaging parameter recommendation tool

Abstract

An artificial intelligence-assisted ultrasound imaging parameter recommendation tool is disclosed. In one example, an ultrasound imaging system (100) includes a processing circuit (114) having a processor (116) coupled to a memory device (118) storing instructions that, when executed, cause the processing circuit (114) to perform operations including: identifying contextual information about the patient (205), (810); determining multiple imaging parameters (210) based on the contextual information (205), (810); receiving initial image data of an anatomical region obtained using the multiple imaging parameters (210); presenting multiple initial images (805a), (805b), (805c) based on the initial image data; receiving user input to select a preferred image (805b) from the multiple images (805a), (805b), (805c), the preferred image (805b) having been obtained using a set of preferred imaging parameters (905); and configuring an ultrasound probe (106) to receive additional image data of the anatomical region using the set of preferred imaging parameters (905).

Description

Technical Field

[0001] The embodiments of the subject matter disclosed herein relate to ultrasound imaging, and more specifically, to providing recommendations for ultrasound imaging parameters based on contextual information about an ultrasound scan. Background Technology

[0002] During a medical imaging scan, a technician (such as an ultrasound physician) acquires multiple medical images of the patient to measure or detect various aspects of the anatomical features present within the medical images. The acquisition parameters used to acquire the medical images (e.g., frequency, acquisition angle, dynamic power, gain, compound imaging, etc.) affect the quality of the resulting medical images and are therefore selected by the technician to optimize the image quality. Summary of the Invention

[0003] The embodiment relates to an ultrasound imaging system. The ultrasound imaging system includes: a transducer configured to transmit and receive ultrasound signals; a matching layer configured to have acoustic impedance between a tissue to be imaged and a material of the transducer; a damping block configured to absorb ultrasound energy; and processing circuitry. The processing circuitry includes a processor coupled to a memory device storing instructions that, when executed, cause the processing circuitry to perform operations including: identifying contextual information about a patient being scanned using ultrasound; determining multiple imaging parameters using a machine learning model and based on the contextual information; receiving initial image data of an anatomical region obtained by the transducer using the multiple imaging parameters, wherein the initial image data is obtained using an ultrasound probe at a fixed position above the anatomical region; and presenting multiple initial images on a display device of the ultrasound imaging system based on the initial image data, wherein each initial image corresponds to a set of imaging parameters from the multiple imaging parameters. The operation includes: receiving user input to select a preferred image from a plurality of initial images, the preferred image having been obtained using a set of preferred imaging parameters from a plurality of imaging parameters. The operation also includes: configuring the ultrasound probe to receive additional image data of the anatomical region from the transducer using the set of preferred imaging parameters.

[0004] Another embodiment relates to a medical imaging system including processing circuitry having a processor coupled to a memory device storing instructions that, when executed, cause the processing circuitry to perform operations. The operations include: identifying contextual information about a patient during a medical imaging scan; determining multiple sets of imaging parameters using a machine learning model and based on the contextual information; receiving initial image data of an anatomical region obtained using the multiple sets of imaging parameters, wherein the initial image data is obtained using an ultrasound probe at a fixed position above the anatomical region; presenting multiple initial images on a display device of the medical imaging system based on the initial image data, wherein each initial image corresponds to a set of imaging parameters from the multiple sets of imaging parameters; receiving user input selecting a preferred image from the multiple initial images, the preferred image having been obtained using the set of preferred imaging parameters from the multiple sets of imaging parameters; and configuring the medical imaging system to receive additional image data of the anatomical region using the set of preferred imaging parameters.

[0005] Another embodiment relates to a method. The method includes: identifying contextual information about a patient being scanned using ultrasound by processing circuitry of an ultrasound imaging system. The method includes: determining multiple imaging parameters by the processing circuitry using a machine learning model and based on the contextual information. The method includes: receiving initial image data of an anatomical region obtained using the multiple imaging parameters by the processing circuitry, wherein the initial image data is obtained using an ultrasound probe at a fixed position above the anatomical region. The method includes: presenting multiple initial images on a display device of the ultrasound imaging system based on the initial image data, wherein each initial image corresponds to a set of imaging parameters from the multiple imaging parameters. The method includes: receiving user input from the processing circuitry to select a preferred image from the multiple initial images, the preferred image having been obtained using the set of preferred imaging parameters from the multiple imaging parameters. The method includes: configuring the ultrasound probe to receive additional image data of the anatomical region by the processing circuitry using the set of preferred imaging parameters.

[0006] This overview is merely illustrative and is not intended to be limiting in any way. Other aspects, inventive features, and advantages of the apparatus or process described herein will become apparent from the detailed description set forth herein in conjunction with the accompanying drawings, wherein like reference numerals refer to like elements. Attached Figure Description

[0007] Figure 1 This is a block diagram of an ultrasound imaging system according to an example implementation.

[0008] Figure 2It is based on the example implementation plan. Figure 1 A block diagram of the artificial intelligence (AI) circuitry used in an ultrasound imaging system.

[0009] Figure 3 This is an example of how to use the example implementation scheme. Figure 1 A flowchart of a method for providing recommended imaging parameters during ultrasound scanning of an ultrasound imaging system.

[0010] Figure 4 This is an example of training based on the example implementation scheme. Figure 3 The flowchart shows the method using an artificial intelligence (AI) model during the process.

[0011] Figure 5 This is a block diagram illustrating offline and online training of an AI model based on an example implementation.

[0012] Figure 6 This is an example of the use of the example implementation scheme in... Figure 3 The flowchart describes a method for collecting ultrasound data using recommended imaging parameters provided during the process.

[0013] Figure 7 This is an example of an implementation scheme based on the example. Figure 4 A flowchart illustrating the training process of the AI ​​model during the method.

[0014] Figure 8 This is an example of a user interface that displays multiple ultrasound images obtained using a set of recommended ultrasound imaging parameters, based on an example implementation.

[0015] Figure 9 It is based on the example implementation plan. Figure 8 An example of one of multiple ultrasound images and a corresponding set of recommended ultrasound imaging parameters displayed on the user interface.

[0016] Figure 10 It is a response to receiving an application based on the example implementation scheme. Figure 8 An example of a user interface generated by selecting one of multiple ultrasound images displayed on the user interface. Detailed Implementation

[0017] Referring generally to the accompanying drawings, systems and methods for providing recommended medical imaging parameters are disclosed. More specifically, the systems and methods described herein include training machine learning models to recommend medical imaging parameters based on received contextual information about a medical imaging procedure. For example, contextual information may include patient-related information, procedure-related information, operator preferences, and so on.

[0018] In existing ultrasound imaging systems that rely on general knowledge and user preferences, the ultrasound scanner is typically preset for different applications. The user then adjusts the parameters for each individual case to achieve the desired image quality. In the case of expert users, such existing systems require additional time and effort to modify parameters based on the expert user's preferences and knowledge. However, for inexperienced users, understanding which parameters to change and to what extent is not always straightforward. Furthermore, incorrect imaging parameters can lead to reduced image quality and visibility of the target area.

[0019] Therefore, while existing systems include preset image acquisition parameters assigned to various applications, such systems do not include user preferences or information about the patient that may affect image quality. For example, in women's healthcare, factors such as body mass index (BMI), gestational age, application, and desired anatomical view can affect the image quality obtained using a specific set of acquisition parameters. Furthermore, users may have different preferences regarding image quality and the visibility of internal organs in the image.

[0020] Therefore, after selecting appropriate preset image acquisition parameters using existing technology, expert users can change these parameters in real time during ultrasound scans to achieve the desired image quality. However, inexperienced users rely on images acquired using preset image acquisition parameters because they typically lack the knowledge to appropriately modify acquisition parameters based on patient information and do not have the experience to develop their own preferences regarding image acquisition.

[0021] However, the systems and methods described herein offer a technical solution to existing systems by providing a dynamic imaging parameter recommendation tool configured to achieve improved image quality during medical imaging procedures. Furthermore, by recording specific user usage patterns (e.g., changes in imaging parameters made by the user in different applications), the systems described herein are configured to continuously adjust the tool so that these recommendations take into account user preferences, as preferences can change over time and across applications. Unlike existing technologies, the systems and methods disclosed herein provide a flexible ultrasound imaging workflow by generating multiple sets of recommended imaging parameters based on personalized patient information. That is, multiple variations of the imaging parameter options recommended to the operator allow for variations between operator preferences, patient preferences, examination purposes, ultrasound protocols, etc.

[0022] The specific implementations described herein address technical problems by providing enhanced data integration and analysis capabilities, offering specific technical solutions for simplifying and refining the generation and transmission of ultrasound images. The systems described herein are implemented to improve the way data is synthesized and utilized regarding ultrasound scans to provide high-quality images based on the data. By integrating data related to specific procedures, technicians, patients, etc., these systems provide real-time intelligent recommendations regarding imaging parameters to be used during ultrasound scans. For example, various implementations can provide recommendations to the ultrasound physician based on patient information such as age, BMI, blood pressure, and gestational age. Therefore, this method provides specific technical improvements to various technical problems, including those described herein.

[0023] The system described herein further reduces processing power by simultaneously performing various processing operations to provide intelligent recommendations regarding image acquisition parameters, rather than performing multiple processing operations individually and consuming unnecessary processing power. Furthermore, the system described herein generates recommended imaging parameters for use by sonographers to perform complete and high-quality ultrasound scans given various contextual information (e.g., sonographer preferences, patient history, etc.). That is, the system described herein is trained to identify the imaging parameters required to obtain a high-quality scan in a given ultrasound procedure, thereby ensuring that the scan is completed before attempting to process the ultrasound images. This consideration of contextual information when generating recommended imaging parameters to be used during an ultrasound scan reduces processing power by avoiding the collection of unnecessary ultrasound data and submitting incomplete and / or low-quality scans (which may require the sonographer to capture additional images during consecutive scans).

[0024] Before turning to the accompanying drawings, which detail certain exemplary embodiments, it should be understood that this disclosure is not limited to the details or methods set forth in the specification or illustrated in the drawings. It should also be understood that the terminology used herein is for descriptive purposes only and should not be construed as limiting.

[0025] refer to Figure 1 A schematic diagram of an ultrasound imaging system 100 is shown. The ultrasound imaging system 100 can be used in medical settings (e.g., hospitals, clinics, etc.), for example by an ultrasound physician, technician, or other clinician certified to collect ultrasound data from patients. Although the system and methods are described herein in the context of the ultrasound imaging system 100, it should be understood that the medical imaging parameter recommendation tool described herein can be implemented using any of a variety of medical imaging systems (e.g., medical resonance imaging, X-ray, computed tomography, positron emission tomography, etc.).

[0026] An example of a procedure performed using the ultrasound imaging system 100 could be fetal ultrasound. Fetal ultrasound can be early pregnancy ultrasound, mid-pregnancy ultrasound, late pregnancy ultrasound, or any other ultrasound scan configured to monitor and assess fetal anatomy. In some implementations, fetal ultrasound can be configured to determine the due date, assess placental size and location, confirm normal fetal anatomy, detect heartbeat, and so on. During fetal ultrasound, the sonographer may follow a specific imaging protocol based on contextual information about the patient and / or fetus (e.g., patient's age, gestational age, patient's medical history, patient's BMI, patient's blood pressure, patient's family health history, etc.). Contextual information can provide insights into the likelihood of detecting certain birth defects (such as heart defects, spina bifida, cleft lip and palate, Down syndrome, etc.) during fetal ultrasound. Therefore, given the contextual information and the likelihood of certain birth defects based on it, a patient-specific imaging protocol ensures a comprehensive capture of the fetus through ultrasound data.

[0027] In at least one embodiment, the sonographer collects ultrasound data by navigating a probe (e.g., probe 106, as described below) above the patient's uterus until a sufficient number of ultrasound images are collected. The collected images are stored in a central storage device (e.g., memory 118) and analyzed by the sonographer. The sonographer generates a set of measurements (e.g., 50 to 100 records) based on the images, and these images and measurements are jointly reviewed by an obstetrician. Any clinical findings / conclusions are provided in the report submitted to the patient's medical record by the obstetrician.

[0028] like Figure 1 As shown, the ultrasound imaging system 100 includes a transmit beamformer 102, a transmitter 104, a probe 106, a receiver 110, and a receive beamformer 112.

[0029] Transmit beamformer 102 can be a hardware beamformer or a software beamformer. In embodiments where transmit beamformer 102 is a hardware beamformer, transmit beamformer 102 may include one or more of a graphics processing unit (GPU), a microprocessor, a central processing unit (CPU), a digital signal processor (DSP), or any other type of processor capable of performing logical operations. Transmit beamformer 102 may be configured to perform conventional beamforming techniques as well as techniques such as backtrack transmit beamforming (RTB). Alternatively, in embodiments where transmit beamformer 102 is a software beamformer, a processor (e.g., processor 116, as described below) may be configured to perform some or all of the functions associated with transmit beamformer 102.

[0030] The probe 106 may be a linear array probe, a curved array probe, a sector probe, or any other type of probe configured to acquire two-dimensional (2D) B-mode data, 2D color flow data, M-mode data, three-dimensional (3D) data, four-dimensional (4D) data, or any other type of ultrasound data. Alternatively or additionally, the probe 106 may be any type of probe configured to acquire 2D B-mode data and data corresponding to another ultrasound mode of blood flow velocity in the direction of the detected vessel axis. In some embodiments, the probe 106 may include a positioning sensor configured to detect the positioning of the probe 106 relative to one or more reference locations. That is, when identifying the anatomical structure being imaged, the positioning sensor may continuously track the movement (e.g., rotation, translation, orientation, etc.) of the probe 106 relative to its position. For example, the anatomical structure being imaged may be identified as the fetal skull at a first location of the probe 106. The positioning sensor may then track the movement of the probe 106 relative to the fetal skull to identify successive positions of the probe 106. In some implementations, the positioning sensor may transmit position data to be stored within the ultrasound imaging system 100 (e.g., in memory 118).

[0031] The probe 106 may include a transducer configured to transmit and receive ultrasonic signals. In some embodiments, such as Figure 1 As shown, probe 106 includes signal element 108. Signal element 108 may be arranged as a transducer array, and in some embodiments may be arranged as a one-dimensional (1D) or 2D array. Transmit beamformer 102 and transmitter 104 drive signal element 108 to transmit pulsed ultrasound signals into the body of a subject (e.g., a patient). For example, during a fetal examination, an ultrasound physician or other clinician may navigate probe 106 near the patient's uterus such that signal element 108 in probe 106 transmits pulsed ultrasound signals into the patient's uterus. The pulsed ultrasound signals are then backscattered from anatomical structures within the body, such as blood cells or muscle tissue, to produce an echo returning to signal element 108. That is, the signal element 108 may include: a transducer configured to transmit and receive ultrasound signals; a matching layer configured to have acoustic impedance between the tissue to be imaged and the material of the transducer (e.g., such that pulsed electronic signals can be backscattered from anatomical structures in the body and received by the signal element 108 as an echo); and a damping block configured to absorb ultrasound energy.

[0032] Receiver 110 receives the echo from probe 106 and converts the echo into an electrical signal. The electrical signal then passes through receiver beamformer 112, which generates ultrasound data based on the electrical signal. As described above with reference to transmit beamformer 102, receiver beamformer 112 can be a hardware beamformer or a software beamformer. In embodiments where receiver beamformer 112 is a hardware beamformer, receiver beamformer 112 may include one or more of a GPU, microprocessor, CPU, DSP, or any other type of processor capable of performing logical operations. Receiver beamformer 112 may be configured to perform conventional beamforming techniques as well as techniques such as backtrack transmit beamforming (RTB). Alternatively, in embodiments where receiver beamformer 112 is a software beamformer, a processor (e.g., processor 116 as described below) may be configured to perform some or all of the functions associated with receiver beamformer 112.

[0033] Although the transmitting beamformer 102, transmitter 104, receiver 110 and receiving beamformer 112 are in Figure 1 While components of the ultrasound imaging system 100, which are shown as different from probe 106, are included, it should be understood that in some embodiments, probe 106 may include electronic circuitry configured to perform the functions of each of the transmit beamformer 102, transmitter 104, receiver 110, and / or receive beamformer 112. That is, all or part of the transmit beamformer 102, transmitter 104, receiver 110, and / or receive beamformer 112 may be located within probe 106.

[0034] Still referencing Figure 1 The ultrasound imaging system 100 is shown as including processing circuitry 114. As shown, processing circuitry 114 may include at least one processor 116, memory 118, image processing circuitry 120, and artificial intelligence (AI) circuitry 122. In this way, processing circuitry 114 may be configured or constructed to execute or implement the instructions, commands, and / or control processes described herein with respect to processor 116, memory 118, image processing circuitry 120, and AI circuitry 122. Although in Figure 1 While shown separately from probe 106, it should be understood that processing circuitry 114 may be part of probe 106. For example, processing circuitry 114 may be housed in the handheld housing of probe 106 (e.g., in the case where probe 106 is a wireless probe).

[0035] Processor 116 may include a CPU, GPU, microprocessor, DSP, general-purpose single-chip or multi-chip processor, field-programmable gate array (FPGA), or any other type of processor capable of performing logical operations. A general-purpose processor may be a microprocessor or any conventional processor or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. In some embodiments, processor 116 may be shared by multiple circuits (e.g., the circuitry of processor 116 may include or otherwise share the same processor, and in some example embodiments, the processor may execute instructions stored or otherwise accessed via different regions of memory 118). Alternatively or additionally, processor 116 may be configured to perform or otherwise perform certain operations independently of one or more coprocessors. In some embodiments, two or more processors may be bus-coupled to enable independent, parallel, pipelined, or multi-threaded instruction execution. All such variations are intended to fall within the scope of this disclosure.

[0036] Processor 116 may be configured to control transmit beamformer 102, transmitter 104, receiver 110, and receive beamformer 112. Processor 116 may also communicate electronically with probe 106. For the purposes of this disclosure, the term "electronic communication" may be defined to include both wired and wireless communication.

[0037] In some embodiments, processor 116 may be configured to control probe 106 during data acquisition. That is, processor 116 can control data acquisition by controlling which signal element in signal element 108 is active and by controlling the shape of the beam emitted from probe 106. Alternatively or additionally, processor 116 may include a composite demodulator configured to demodulate radio frequency (RF) data acquired by probe 106 and generate raw data. According to other embodiments, demodulation of the RF data may be performed by another component of the ultrasound imaging system 100. Processor 116 may perform the processing operations described herein according to a variety of selectable ultrasound modes.

[0038] Depending on the operating mode of the ultrasound imaging system 100, the processor 116 can process ultrasound data acquired by the probe 106 to generate 2D or 3D image data. For example, operating modes may include B-mode, color flow Doppler mode, M-mode, color M-mode, spectral Doppler, elastography, TVI, strain, strain rate, etc. Various of these operating modes can be configured to, for example, convert ultrasound data from beam space coordinates (e.g., received from the receiving beamformer 112) to display space coordinates (e.g., such that the ultrasound data can be displayed as image data). In some embodiments, the operating modes may allow video processing by the processor 116, enabling the real-time display of a series of images (e.g., processed ultrasound data) during a scan session / procedure performed on a patient. The operator of the ultrasound imaging system 100 (e.g., an ultrasound physician) can switch between various modes to acquire a variety of ultrasound data and perform a complete scan of the anatomical region of interest. For example, the operator can switch between modes using a user interface 130 (e.g., using physical controls, interface input representing physical controls, etc.). While the terms “image” or “multiple images” are used herein for illustrative purposes, it should be understood that such terms encompass still images as well as videos, clips, or series of images for each still image. For example, in some embodiments, an image or multiple images may include a 1- to 2-second clip derived from image data.

[0039] When receiver 110 receives an echo signal from probe 106, processor 116 performs processing operations in real time. For the purposes of this disclosure, the term "real time" is defined as including procedures performed without any intentional delay. As an illustrative and non-limiting example, in some cases, ultrasound imaging system 100 may acquire images at a real-time volumetric rate of 7 to 20 volumes per second. However, it should be understood that the real-time volumetric rate may depend on the length of time taken to acquire each volume of data used for display. Thus, ultrasound imaging system 100 may be configured to acquire 2D data of an anatomical region at a faster rate than 3D data of the same anatomical region, since acquiring the volume of 3D data takes longer than acquiring the same volume of 2D data. Similarly, when ultrasound imaging system 100 acquires a relatively large amount of data, the real-time volumetric rate may be slower than a smaller amount of data. For example, during an abdominal scan, the real-time volumetric rate may be slower if the patient is an adult than if the patient is an infant, because the amount of data for an adult is larger than that for an infant (e.g., because the abdomen of an adult is larger than that of an infant). Therefore, some specific embodiments of the ultrasound imaging system 100 may have a real-time volume rate faster than 20 volumes / second, while other specific embodiments of the ultrasound imaging system 100 may have a real-time volume rate slower than 7 volumes / second.

[0040] In some embodiments, the ultrasound imaging system 100 may include multiple processors configured to perform the processing operations / functionality described in reference processor 116. For example, in such embodiments, a first processor among the multiple processors may be configured to demodulate and decimate RF signals, while a second processor among the multiple processors may be configured to further process the RF data before displaying an image representing the data. It should be understood that other embodiments may use different processor arrangements.

[0041] Processor 116 can also communicate electronically with display device 132, enabling processor 116 to process ultrasound data acquired by probe 106 and generate images for display on display device 132 (e.g., ultrasound images 805a to 805c, as referred to below). Figure 8 (As described).

[0042] like Figure 1 As shown, the processing circuitry 114 also includes a memory 118. The memory 118 may be configured to, for example, store processed data acquired by the ultrasound imaging system 100 (e.g., ultrasound data collected by probe 106, user input received by user interface 130, etc.). For example, the memory 118 may be a hospital picture archiving and communication system (PACS). The memory 118 (e.g., memory, memory cell, storage device, etc.) may include one or more devices (e.g., RAM, ROM, flash memory, hard disk storage, etc.) for storing data and / or computer code to perform or facilitate the processes, layers, and modules described in this application. The memory 118 may be or include tangible, non-transient volatile memory or non-volatile memory. The memory 118 may also include database components, object code components, script components, or any other type of information structure for supporting the activities and information structures described in this application.

[0043] In various embodiments, the memory 118 may have different capacities (e.g., storage space) in the implementation of the ultrasound imaging system 100. For example, the memory 118 may be configured to store at least 60 minutes of ultrasound data. The ultrasound data may be stored in the memory 118 such that the ultrasound data can be retrieved according to the order / time of data acquisition. That is, the ultrasound data may be stored together with a timestamp indicating the time when the ultrasound data was collected, and can be retrieved starting from the earliest time the ultrasound data was collected.

[0044] The processing circuitry 114 also includes an image processing circuitry 120 and an AI circuitry 122. Both the image processing circuitry 120 and the AI ​​circuitry 122 are configured to facilitate the provision of recommended imaging parameters during ultrasound scanning, as described herein.

[0045] Image processing circuitry 120 is configured to receive image data acquired by the transducer of probe 106 during an ultrasound scan. Image data refers to ultrasound data collected by probe 106 when performing an ultrasound examination on a patient. For example, image data may be collected during fetal ultrasound and may therefore include various images of the patient's uterus and the fetal anatomical structures contained therein. Image processing circuitry 120 may include multiple deep learning-based models configured to analyze the image data. For example, image processing circuitry may be configured to identify views from which it captures image data, anatomical structures or other features captured by the image data, the presence of pathology in the image data, and so on. Image processing circuitry 120 may be configured to identify anatomical structures using one or more algorithms (e.g., image processing algorithms such as edge detection, machine learning models, deep neural networks, etc.). In some embodiments, image processing circuitry 120 may identify anatomical features, such as bones, blood vessels, organs, etc., based on the shape, relative proximity, apparent depth, orientation, etc., of the features described in the image data.

[0046] As described in more detail below, AI circuit 122 can be configured to base its operation on contextual information about the medical imaging procedure (e.g., context information 205, such as...). Figure 2 (as shown) to recommend medical imaging parameters (e.g., imaging parameter 210, such as...) Figure 2 (As shown). For example, during a fetal ultrasound performed using the ultrasound imaging system 100, the AI ​​circuit 122 can be configured to recommend at least one of the following for image acquisition based on the patient's age, gestational age, patient's BMI, the application of the ultrasound imaging system 100, etc.: frequency, acquisition angle, dynamic power, gain, or composite imaging settings.

[0047] The ultrasound imaging system 100 may also include an external database 128 and a user interface 130. The external database 128 refers to a database from which the processing circuitry 114 (e.g., AI circuitry 122) can retrieve information for providing recommended imaging parameters during ultrasound scanning. For example, the external database 128 may be a medical information database. A medical information database may store clinical guidelines, standard practices, medical literature, medical textbooks, published studies, previous case studies, etc. Depending on the specific implementation of the ultrasound imaging system 100 and / or the procedures performed therefrom, the AI ​​circuitry 122 may retrieve clinical guidelines, standard practices, medical literature, medical textbooks, published studies, and previous case studies relevant to the specific implementation and / or procedures. For example, if the ultrasound imaging system 100 is used in a hospital setting to perform an early pregnancy fetal ultrasound on a patient with a BMI of 28.0, the AI ​​circuitry 122 may retrieve clinical guidelines and standard practices relevant to that hospital setting and the early pregnancy fetal ultrasound. Continuing with this example, AI circuit 122 can also retrieve information from medical literature, medical textbooks, published studies, and previous case studies related to fetal anatomy and the risk of having a high BMI during pregnancy.

[0048] Ultrasound examiners or other clinicians can use the user interface 130 to control the operation of the ultrasound imaging system 100. For example, the ultrasound examiner can use the user interface 130 to control the input of patient data, change scanning or display parameters, adjust the segmentation of anatomical features depicted in the ultrasound images, and / or select various other modes, operations, parameters, etc., of the ultrasound imaging system 100. In some embodiments, the user interface 130 may include off-the-shelf consumer electronics devices, such as smartphones, tablets, laptops, etc. For the purposes of this disclosure, the term "off-the-shelf consumer electronics device" is defined as an electronic device designed and developed for general consumer use rather than specifically designed for use in a medical setting. Alternatively, in other embodiments, the user interface 130 may be an electronic device designed and developed for use in a medical setting.

[0049] According to some embodiments, the user interface 130 may be physically separated from the rest of the ultrasound imaging system 100 (e.g., transmit beamformer 102, transmitter 104, probe 106, receiver 110, receive beamformer 112, processing circuitry 114, and / or external database 128). The user interface 130 may communicate with the processor 116 via wireless protocols such as Wi-Fi, Bluetooth, wireless local area network (WLAN), near-field communication, etc. According to some embodiments, the user interface 130 may communicate with the processor 116 via an application programming interface (API).

[0050] In some implementations, the user interface 130 may include one or more physical controls, such as buttons, sliders, knobs, mice, keyboards, trackballs, hard keys linked to specific actions, soft keys configurable to control different functions, etc. Figure 1 As shown, the user interface 130 may also include a display device 132. In some embodiments, the display device 132 may be configured to display a graphical user interface (GUI) based on instructions from the memory 118. The GUI may include user interface icons representing commands and instructions related to the operation of the ultrasound imaging system 100. The user interface icons of the GUI may be configured such that a user (e.g., an ultrasound physician, clinician, etc.) can select a specific user interface icon to activate a specific function controlled by the GUI. For example, various user interface icons may be used to represent windows, menus, buttons, cursors, scroll bars, etc. That is, the physical controls of the user interface 130 may be included as separate hardware components, as user interface icons displayed on the display device 132, or as a combination of hardware components and user interface icons. As described below, Figure 10 An example of GUI 1000 is given, in which at least some physical controls of user interface 130 are represented by various user interface icons.

[0051] In some embodiments, display device 132 may include a touch-sensitive display device or a touchscreen. According to such embodiments, the touchscreen may be configured to interact with a GUI displayed by display device 132, allowing a user (e.g., an ultrasound physician) to interact with the GUI via the touchscreen. The touchscreen may be a single-point touchscreen configured to detect a single contact point at a time, or a multi-point touchscreen configured to detect multiple contact points at a time. For embodiments where the touchscreen is a multi-point touchscreen, the touchscreen may be configured to detect multi-point gestures involving contact from two or more fingers of the user at a time. The touchscreen may be a resistive touchscreen, a capacitive touchscreen, or any other type of touchscreen configured to receive input from a stylus or one or more fingers of the user. According to some embodiments, the touchscreen may be an optical touchscreen that uses techniques such as infrared light or light of other frequencies to detect one or more contact points initiated by the user. In some embodiments, the touchscreen may be incorporated as part of display device 132 or may be separate from display device 132. User interface 130 may also include a proximity sensor configured to detect objects and / or gestures within a predetermined distance (e.g., five feet, six inches, ten centimeters, etc.) of the proximity sensor. In various implementations, the proximity sensor may be positioned on the display device 132 or as part of a touchscreen separate from the display device 132.

[0052] Now for reference Figure 2The AI ​​circuitry 122 of the ultrasound imaging system 100 is shown in more detail. As illustrated, the AI ​​circuitry 122 receives context information 205 regarding an ultrasound scan. In some embodiments, the context information 205 includes parameters about the patient undergoing the ultrasound scan, such as the patient's body mass index (BMI), the patient's age, or gestational age. In some instances, the context information 205 may be exemplified as a display of context information 810, such as... Figure 8 As shown. Contextual information 205 may include any of several factors that influence the image quality of the images generated during an ultrasound scan. For example, in addition to parameters about the patient (e.g., BMI, patient age, gestational age, etc.), contextual information 205 may include information about the application of the ultrasound scan. For example, if the ultrasound scan is a fetal echocardiogram, the required image quality may differ from that required for routine early pregnancy fetal ultrasound in order to adequately capture cardiac anatomy.

[0053] Context information 205 can be used as input to AI algorithm 124. In some implementations, AI algorithm 124 can be a Bayesian neural network. For example... Figure 2 As shown, AI algorithm 124 is configured to generate imaging parameters 210 based on received context information 205. In some instances, imaging parameters 210 may be exemplified as a display of imaging parameters 905, such as... Figure 9 As shown. Imaging parameters 210 may include at least one of the following for image acquisition during ultrasound scanning: frequency, acquisition angle, dynamic power, gain, composite imaging settings, etc. Figure 2 In an example implementation of the AI ​​circuit 122 shown, if the context information 205 includes a BMI of 28.0, the AI ​​algorithm 124 may recommend imaging parameters 210, which are configured to detect cardiac defects, neural tube defects, or any other abnormalities in the fetal anatomy that may be caused by a high BMI.

[0054] In some implementations, information about historical ultrasound scans performed by an expert sonographer (e.g., a sonographer with specific qualifications, a sonographer with many years of experience, etc.) can be used to train the AI ​​algorithm 124. For example, an expert sonographer might perform an early pregnancy fetal ultrasound on a 34-year-old patient at 12 weeks of gestation with a BMI of 28.0. Parameters about the early pregnancy fetal ultrasound (e.g., gestational age of 12 weeks, patient age of 34 years, BMI of 28.0) can be stored (e.g., in memory 118) as context information 205. Furthermore, imaging parameters used by the expert sonographer during the early pregnancy fetal ultrasound can be stored (e.g., in memory 118) as imaging parameters 210 corresponding to the context information 205. In some instances, the imaging parameters used by the expert sonographer refer to the acquisition parameters of the ultrasound probe (e.g., probe 106) at the moment when the image quality is approved by the expert sonographer (e.g., when the expert sonographer instructs the ultrasound imaging system 100 to "freeze"). This information about historical ultrasound scans can be used to train the AI ​​algorithm 124 such that when the contextual information 205 about the ultrasound scan includes at least one of the following: an ultrasound scan performed at 12 weeks, a patient age of 34 years, or a BMI of 28.0, the AI ​​algorithm 124 can be configured to recommend imaging parameters 210 based on imaging parameters 210 used by an expert sonographer when performing an ultrasound scan with the same contextual information 205.

[0055] refer to Figure 3 A flowchart illustrating a method 300 for providing recommended imaging parameters during an ultrasound scan using an ultrasound imaging system is shown. In at least one embodiment, the ultrasound imaging system referred to in method 300 is the one described above. Figure 1 and Figure 2 The ultrasound imaging system 100 is described, and the method 300 can be implemented by the ultrasound imaging system 100. In some embodiments, the method 300 can be implemented as a memory of the ultrasound imaging system 100 (such as...). Figure 1 Executable instructions in memory 118.

[0056] Before starting the collection of ultrasound data, method 300 can begin when an operator (e.g., an ultrasound physician, technician, or other clinician) is authenticated as an authorized user of the ultrasound imaging system 100. In some embodiments, the operator may authenticate themselves as an authorized user of the ultrasound imaging system 100 by logging into a portal associated with the environment in which the ultrasound imaging system 100 is implemented (e.g., a hospital or other healthcare provider), such as an online application accessible via user interface 130. For example, the operator may log in using a unique identifier (e.g., username, password, biometric scan, PIN, etc.).

[0057] After operator authentication, the operator of ultrasound imaging system 100 can input patient and / or procedure-specific information into ultrasound imaging system 100 before collecting ultrasound data. For example, the operator can submit patient information (e.g., identification information such as name, date of birth, social security number, etc., and / or medical information such as medical history, family medical history, current diagnosis, etc.) via user interface 130. In some embodiments, the operator can select a patient from a patient list (e.g., patients associated with a predetermined procedure to be performed by the operator) and can import patient information into ultrasound imaging system 100 (e.g., from a database associated with the environment in which ultrasound imaging system 100 is implemented, such as a hospital). The information input by the operator at the start of method 300 may include contextual information 205 (e.g., patient's BMI, patient age, gestational age, etc.) and can therefore be used by ultrasound imaging system 100 to determine recommended ultrasound imaging parameters, as described herein.

[0058] In addition to patient information, the operator may also enter (e.g., as text input) or otherwise select (e.g., from a program dropdown list) the program the operator is preparing to perform. For example, the operator may enter or select "echocardiography" as the program. Additionally, the operator may enter or otherwise select any known pathology or other medical condition that may be relevant to the program. For example, the operator may be performing fetal echocardiography on a pregnant patient in response to the patient having a high BMI, and such information may be entered into the ultrasound imaging system 100 before collecting ultrasound data. In this way, the ultrasound imaging system 100 may be configured to recommend ultrasound imaging parameters as described herein, specific to data that may be relevant to fetal echocardiography (e.g., adequate imaging of the fetal heart).

[0059] like Figure 3 As shown, at step 305, method 300 may include: identifying context information related to the ultrasound scan being performed by ultrasound imaging system 100. The context information identified at step 305 may be context information 205, as described above. That is, the context information may include patient-related information (e.g., patient's BMI, patient's age, gestational age, etc.) and / or procedure-related information (e.g., the type of ultrasound scan being performed, the settings for the ultrasound scan being performed, the ultrasound physician performing the ultrasound scan, etc.). In some embodiments, the context information may be identified from information input by the operator of ultrasound imaging system 100, as described above, before initiating the collection of ultrasound data.

[0060] At step 310, the machine learning model can be used to determine imaging parameters based on the contextual information identified at step 305. In some embodiments, step 310 can be performed by AI circuit 122, such as... Figure 2 As shown. That is, at step 305, AI algorithm 124 can be used to determine imaging parameters 210 based on context information 205. The imaging parameters determined at step 310 can refer to multiple imaging parameters. That is, multiple imaging parameters can include first imaging parameters, second imaging parameters, third imaging parameters, etc. For example, the first imaging parameters can include: a frame rate of 48 frames per second, a frequency of 5.0 MHz, a power of -1 dB, a gain of 0 dB, a compression of 60 dB, a persistence of 0.7, and a depth of 12.0 cm; while the second imaging parameters can include: a frame rate of 52 frames per second, a frequency of 5.4 MHz, a power of 0 dB, a gain of -1 dB, a compression of 55 dB, a persistence of 0.5, and a depth of 9.0 cm.

[0061] In some implementation schemes, as referenced above Figure 2 As described, a machine learning model for determining imaging parameters at step 310 can be trained using interaction history associated with multiple users of the ultrasound imaging system 100 (e.g., expert sonographers). In such embodiments, the machine learning model can be configured to identify historical image data (e.g., including multiple imaging parameters for obtaining historical image data) from the interaction history associated with at least a portion of the context information received at step 305. The machine learning model can then determine the multiple imaging parameters at step 310 based on the multiple imaging parameters used to obtain the historical image data. For example, if the context information received at step 305 includes a BMI of 28.0, the interaction history may include one or more ultrasound scans involving a patient with a BMI of 28.0. Therefore, the machine learning model can identify the imaging parameters at step 310 based on the imaging parameters used during one or more ultrasound scans of a patient with a BMI of 28.0 involving the interaction history.

[0062] Image data can be obtained at step 315 using the imaging parameters determined at step 310. In some embodiments, the image data is obtained by a transducer of probe 106. The image data obtained at step 315 refers to image data of an anatomical region (e.g., the uterus and the fetal anatomy contained therein) using each of the multiple imaging parameters determined at step 310. That is, if step 310 includes determining a first imaging parameter, a second imaging parameter, and a third imaging parameter, the image data received at step 315 may include image data obtained using the first imaging parameter, image data obtained using the second imaging parameter, and image data obtained using the third imaging parameter.

[0063] In some instances, image data is acquired while the user (e.g., the operator of the ultrasound imaging system 100) holds the probe 106 in a fixed position above the anatomical region for a predetermined amount of time (e.g., three to six seconds). Therefore, while the probe 106 is held in a fixed position above the anatomical region, the ultrasound imaging system 100 is configured to switch between multiple imaging parameters (e.g., a first, second, and third imaging parameter) determined at step 310, such that the image data received at step 315 includes image data acquired using each of the multiple imaging parameters determined at step 310. For example, the image data received at step 315 may refer to ultrasound images 805a, 805b, and 805c, such as... Figure 8 As shown and described in more detail below.

[0064] At step 320, the image data received at step 315 is presented to the user. In some embodiments, the image data (e.g., ultrasound images 805a to 805c) may be presented to the user via the display device 132 of the user interface 130. For example, the image data may be presented via GUI 800, such as... Figure 8 As shown and described in more detail below. In some instances, presenting image data at step 320 includes presenting multiple (e.g., three) dynamic cyclic images depicting the anatomical region.

[0065] According to various implementations of the AI ​​algorithm 124, which is a Bayesian neural network, the image data may include a probability associated with each image included in the image data. For example, in the case where the image data includes ultrasound images 80a to 805c, each of ultrasound images 805a, 805b, and 805c may correspond to a probability determined by the Bayesian neural network. This probability represents the likelihood that each set of imaging parameters used to capture the corresponding image data (e.g., each of ultrasound images 805a, 805b, and 805c) will be used by a specialist sonographer during an ultrasound scan. That is, for example, a first set of imaging parameters may be used to obtain ultrasound image 805a, and the Bayesian neural network may determine a 70% corresponding probability based on historical image data. A second set of imaging parameters may be used to obtain ultrasound image 805b, and the Bayesian neural network may determine a 90% corresponding probability based on historical image data. A third set of imaging parameters may be used to obtain ultrasound image 805c, and the Bayesian neural network may determine an 80% corresponding probability based on historical image data. Therefore, a set of ultrasound imaging parameters can be used to obtain ultrasound image 805b; this set of ultrasound imaging parameters is more likely to be used by a specialist sonographer during an ultrasound scan compared to each of the sets of ultrasound imaging parameters used to obtain ultrasound images 805a and 805c. In such embodiments, each of the probabilities (e.g., 70%, 90%, and 80%) can be presented at step 320 along with the corresponding image data (e.g., ultrasound images 805a, 805b, and 805c, respectively).

[0066] Furthermore, in some implementations, the Bayesian neural network can be configured to identify subsets of image data received at step 315 based on probabilities associated with the image data. For example, the Bayesian neural network can be configured to identify subsets of image data corresponding to a probability of 70% or higher. Continuing this example, a subset of image data can be presented to the user at step 320, such that only image data corresponding to a probability of 70% or higher is presented to the user.

[0067] At step 325, method 300 includes receiving a selection of an image (e.g., a preferred image) from the image data presented to the user at step 320. For example, such as Figure 10 As shown, users can access the interface via GUI 800 (e.g., as...). Figure 8Ultrasound image 805b is selected from the ultrasound images 805a to 805c presented (as shown). Alternatively, if step 320 includes presenting three dynamically looping images to the user, step 325 may include receiving a selection of one of the three dynamically looping images from the user. Then, as described below with reference to step 420 of method 400, the user input (e.g., the selection of an image) is stored in a manner associated with a profile corresponding to the user (e.g., in memory 118). In some embodiments, the selection received at step 325 may be stored via at least one of the following: cloud storage, a storage device (e.g., memory 118), or a server associated with the environment implementing the ultrasound imaging system 100.

[0068] Based on the selection received at step 325, additional image data is received at step 330 using imaging parameters associated with the selected image. That is, probe 106 can be configured to receive additional image data from the transducer of an anatomical region (e.g., the uterus and the fetal anatomical structures contained therein). In this way, the ultrasound scan continues at step 330 by collecting additional image data using selected compositional imaging acquisition parameters (e.g., a set of preferred imaging parameters corresponding to a preferred image selected by the user). For example, if the image selected at step 325 is ultrasound image 805b (e.g., ultrasound images 805a to 805c) from image data presented via GUI 800, additional image data can be received using imaging parameters included in the display of imaging parameters 905 associated with ultrasound image 805b, such as... Figure 9 and Figure 10 As shown.

[0069] refer to Figure 4 A flowchart illustrating method 400 for training an AI model used during method 300 is shown. In at least one embodiment, the AI ​​model referred to by method 400 is the one described above. Figure 1 and Figure 2 The AI ​​circuit 122 described herein includes an AI algorithm 124, and method 400 can be implemented by an ultrasound imaging system 100. In some embodiments, method 400 can be implemented as a memory of the ultrasound imaging system 100 (such as...). Figure 1 Executable instructions in memory 118.

[0070] like Figure 4 As shown, method 400 may begin at step 405 by collecting expert user / ultrasound physician data. The expert user / ultrasound physician data collected at step 405 may include information about historical ultrasound scans performed by the expert ultrasound physician, as referenced above. Figure 2As described above, expert user / ultrasound examiner data may include any parameters that may affect image quality during an ultrasound scan. For example, expert user / ultrasound examiner data may include contextual information about the patient (e.g., age, gestational age, BMI, etc.), the application of the ultrasound scan (e.g., echocardiography, early pregnancy fetal ultrasound scan, etc.), user preferences regarding image acquisition, and so on. Expert user / ultrasound examiner data may be collected at step 405 by AI circuitry 122 using interaction history associated with multiple users (e.g., expert users / ultrasound examiners) of ultrasound imaging system 100, making it possible to use such data to pre-train AI models (e.g., AI algorithm 124) (e.g., as referenced above). Figure 2 (As described).

[0071] At step 410, the AI ​​model (e.g., AI algorithm 124) is trained to receive information (e.g., context information 205) and recommend image acquisition parameters (e.g., imaging parameters 210) based on the received information. In other words, at step 410, the AI ​​model is trained to recommend image acquisition parameters (e.g., imaging parameters 210) based on information such as context information 205. Figure 2 The inputs shown and described above generate the outputs. Furthermore, to provide flexibility during ultrasound scanning, the AI ​​model can be configured to recommend multiple options regarding each component imaging parameter (e.g., the imaging parameters determined at step 310 of method 300) based on the input (e.g., context information 205). In some instances, the AI ​​model is a Bayesian neural network configured to recommend multiple options. That is, the Bayesian neural network is configured to provide a statistical distribution of the outputs, rather than generating a single output (e.g., a set of imaging parameters) for a given input (e.g., context information about the ultrasound scan). Therefore, the Bayesian neural network generates multiple outputs (e.g., multiple sets of image parameters) and a probability associated with each of the multiple outputs, as described above with reference to step 320 of method 300.

[0072] After being trained at step 410 to recommend image acquisition parameters based on the received information, the AI ​​model can be mounted on the ultrasound scanner at step 415 for general use. That is, general use refers to the use of an AI model compatible with each user of the ultrasound imaging system 100 (e.g., non-user-specific). In some embodiments, the ultrasound scanner mentioned at step 415 may be probe 106, as described above.

[0073] At step 420, an ultrasound scanner with an AI model installed for general use (e.g., from step 415) is used to acquire data for a specific duration and for a specific user of the ultrasound imaging system 100. That is, once a user (e.g., an operator, ultrasound physician, technician, etc.) logs in or otherwise accesses the ultrasound imaging system 100 (e.g., as described above with reference to method 300), the ultrasound imaging system 100 can identify the specific user. The specific user can then perform one or more ultrasound scans using the ultrasound scanner with the AI ​​model installed for general use. In this way, the ultrasound imaging system 100 (e.g., AI circuitry 122) can monitor the user's use of the ultrasound scanner during one or more ultrasound scans over a specific duration (e.g., a duration of three ultrasound scans, one month, 100 ultrasound scans, one year, etc.).

[0074] At step 425, the AI ​​model is retrained based on the data obtained at step 420 to learn the user preferences of each specific user. In some implementations, retraining the AI ​​model to learn the user preferences of each specific user includes: firstly, receiving permission from the specific user to retrain the AI ​​model using the user preferences of that specific user (e.g., Figure 5 (See step 422 shown). As an example, AI circuit 122 can be configured to monitor the usage of an ultrasound scanner with an AI model installed for general use by a specific user for three months. Then, after three months and with the specific user's permission, AI circuit 122 can be configured to retrain the AI ​​model (e.g., AI algorithm 124) based on the specific user's learned preferences and behaviors.

[0075] After retraining the AI ​​model at step 425 to learn user preferences, the retrained AI model is used at step 430 to recommend image acquisition parameters to a specific user when that user is online (e.g., when performing a real-time ultrasound scan using the ultrasound imaging system 100). That is, a profile associated with a specific user can be identified during continuous ultrasound scans, and the retrained AI model can be configured to recommend image acquisition parameters based on the identified profile for that specific user. In this way, the retrained AI model can be configured to provide recommended imaging parameters during ultrasound scans during method 300, as described above.

[0076] refer to Figure 5 Examples are shown in Figure 4 The method involves a block diagram of offline and online training of the AI ​​model. That is, Figure 5The two training phases (e.g., offline training and online training) of the AI ​​model during method 400 (e.g., AI algorithm 124) are described. In this way, AI algorithm 124 can be configured to generate output (e.g., such as...) Figure 2 When considering the imaging parameters shown and described above (210), user-specific preferences are taken into account.

[0077] like Figure 5 As shown, offline training of the AI ​​model includes steps 405 and 410 of method 400. Offline training uses a dataset collected from expert users of the ultrasound imaging system 100 to train an algorithm (e.g., AI algorithm 124) to recommend a set of acquisition parameters. More specifically, and as described above, at step 405, historical image data is identified from the interaction history of expert users with the ultrasound imaging system 100 (e.g., expert / ultrasound physician data collected at step 405 of method 400 described above). Then, at step 410, the AI ​​model is trained using contextual information (e.g., contextual information 205) and imaging parameters (e.g., imaging parameters 210) associated with the historical image data. Offline training of the AI ​​model (e.g., steps 405 and 410 of method 400) prepares the AI ​​model for general use when mounted on an ultrasound scanner at step 415 of method 400.

[0078] After mounting the AI ​​model on the ultrasound scanner for general use at step 415, online training of the AI ​​model is shown as including steps 420 and 425 of method 400. As described above, data for a specific user over a specific duration is acquired at step 420. Furthermore, and as... Figure 5 As shown, step 420 may include storing user selections of images (e.g., image selection from step 325 of method 300) and user profiles. That is, user selections of images may be acquired over a specific duration and stored together with a profile of a specific user. In some embodiments, user selections may be stored via at least one of the following: cloud storage, a storage device (e.g., memory 118), or a server associated with the environment in which the ultrasound imaging system is implemented.

[0079] Figure 5 It also includes receiving authorization (e.g., a license) from the user at step 422 for training the model based on the configuration file. That is, as referenced above. Figure 4As described, retraining the AI ​​model to learn user preferences for each specific user may include: first, receiving permission from the specific user to retrain the AI ​​model based on the user preferences of that specific user. After receiving permission at step 422, online training includes: training the AI ​​model at step 425 using a selection of stored images (e.g., the selection of images from step 325 of method 300). In this way, online training includes retraining the AI ​​model to learn user preferences for each specific user. In summary, offline training is configured to train the AI ​​model for general (e.g., non-user-specific) use on a large dataset of historical interactions with the ultrasound imaging system 100. Then, online training takes into account the learned user preferences, such that the AI ​​model can provide more accurate outputs (e.g., imaging parameters 210) based on the specific user of the ultrasound imaging system 100.

[0080] refer to Figure 6 A flowchart illustrating a method 600 for collecting ultrasound data using recommended imaging parameters provided during method 300 is shown, as referenced above. Figure 3 As described. In at least one embodiment, the ultrasound imaging system referred to by method 600 is the one described above. Figure 1 and Figure 2 The ultrasound imaging system 100 is described, and the method 600 can be implemented by the ultrasound imaging system 100. In some embodiments, the method 600 can be implemented as a memory of the ultrasound imaging system 100 (such as...). Figure 1 Executable instructions in memory 118.

[0081] like Figure 6 As shown, method 600 can begin when a user logs into a user profile and initiates an ultrasound scan at step 605. Furthermore, step 605 may include loading context information 205, such as information related to the ultrasound physician's preferences, patient information, and procedure information.

[0082] At step 610, the ultrasound probe (e.g., probe 106) may be held in place for a duration. In some embodiments, the user may hold probe 106 in a stationary position above the anatomical region being imaged during an ultrasound scan. For example, during a fetal examination, the user may hold probe 106 in a stationary position above the patient's uterus for three to six seconds. In some embodiments, the image data collected while holding the ultrasound probe in place at step 610 may be image data received at step 315 of method 300 using the imaging parameters determined at step 310. That is, as described above, the ultrasound imaging system 100 automatically changes a set of AI-recommended imaging parameters and acquires images / images based on each of the constituent imaging parameters. For example, the constituent imaging parameters used to acquire ultrasound data may be changed twice at intervals of 1 to 2 seconds to generate three dynamic cyclic images, each 1 to 2 seconds long and acquired using different constituent imaging parameters.

[0083] After holding the probe in the appropriate position for a certain period of time in step 610, a split-screen display of the image is presented to the user in step 615. For example, the split-screen display could be as follows: Figure 8 The GUI 800 shown above displays ultrasound images 805a to 805c. In this way, the split-screen display presented at step 615 allows the user to perform a side-by-side comparison of each ultrasound image / image obtained using a corresponding set of imaging parameters.

[0084] At step 620, a selection of one image from the images presented via split-screen display at step 615 is received. In some embodiments, the selection received at step 620 of method 600 refers to the selection received at step 325 of method 300, as referenced above. Figure 3 As described. For example, the selection could be to select ultrasound image 805b from ultrasound images 805a through 805c, as... Figure 10 As shown.

[0085] Based on the selection received at step 620, the ultrasound scan continues at step 625 based on the imaging parameters of the selected image. For example, to continue selecting image 805b, the ultrasound scan can be continued at step 625 using imaging parameters 905, as follows... Figure 9 and Figure 10 As shown.

[0086] At step 630, a selection is received regarding an option to change imaging parameters (e.g., imaging parameters used during the continuation of the ultrasound scan at step 625). In some embodiments, the option selected at step 630 refers to optional element 1005, such as... Figure 10 As shown below. (See reference below) Figure 10As described, optional element 1005 can be configured to present a split screen (e.g., GUI 800) once selected. In this way, after receiving the selection of an option to change imaging parameters at step 630, method 600 can return to step 615, in which a split-screen display of the image is presented to the user.

[0087] Therefore, method 600 can represent an iterative process in which steps 615 through 625 are repeated when a selection for changing imaging parameters is received at step 630. For example, in the first iteration of method 600, the selection received at step 620 could be a selection for image 805b, and step 625 could include continuing the ultrasound scan using the imaging parameters associated with ultrasound image 805b. However, during the second iteration of method 600 (e.g., after selecting the option to change imaging parameters, when a split-screen display of ultrasound images 805a through 805c is received at step 615), the selection received at step 620 could be a selection for image 805a, and step 625 could include continuing the ultrasound scan using the imaging parameters associated with ultrasound image 805a.

[0088] refer to Figure 7 Examples are shown in Figure 4 The diagram illustrates the method for training an AI model during the 400-period training phase. More specifically, Figure 7 A dataset 705 depicts customer information for the ultrasound imaging system (e.g., information about users of the ultrasound imaging system 100). In some embodiments, dataset 705 may include information collected at step 405 of method 400. Dataset 705 can be used to train a default AI model 710a, as described above with reference to step 410 of method 400. Therefore, Figure 7 The dataset 705 and the default AI model 710a can represent the offline training of the AI ​​model, as referenced above. Figure 5 As described.

[0089] At box 715, a default AI model 710a is presented to the user, and feedback is received from the user. In other words, box 715 may represent installing the default AI model 710a on the scanner for general use (as described in step 415 of method 400). Receiving feedback from the user at box 715 may include storing image selections recommended by the default AI model 710a (e.g., image selections received at step 325 of method 300), as described above with reference to step 420 of method 400. The received feedback can then be used to configure the default AI model 710a such that it is retrained at step 710b to take user preferences into account, as described above with reference to step 425 of method 400. In this way, boxes 715 and 710b may represent online training of the AI ​​model, as described above with reference to Figure 5 As described.

[0090] Reference Figure 8 A GUI 800 displaying multiple ultrasound images 805a, 805b, and 805c is shown. In some embodiments, GUI 1000 may be a GUI generated for display on a display device 132. Furthermore, GUI 1000 may be configured as a touchscreen display, allowing a user to interact with information contained on the touchscreen display by touching corresponding locations on the information. For example, each of ultrasound images 805a, 805b, and 805c may be configured as an optional element, allowing a user to select one of ultrasound images 805a, 805b, and 805c by touching corresponding locations on the touchscreen display.

[0091] As described above, GUI 800 may be a split-screen display presented at step 615 of method 600. Furthermore, each of the multiple ultrasound images 805a, 805b, and 805c can be obtained using a set of recommended ultrasound imaging parameters determined at step 310 of method 300, and thus may be image data presented to the user at step 320 of method 300. GUI 800 is also shown to include the display of contextual information 810 (e.g., patient X, 10-week ultrasound, age 28, BMI: 24.2). The display of contextual information 810 may include contextual information 205 (e.g., contextual information identified at step 305 of method 300) received as input by AI algorithm 124.

[0092] refer to Figure 9 It shows that in Figure 8 An example of one ultrasound image and a corresponding set of recommended ultrasound imaging parameters (e.g., imaging parameter 210) displayed on the user interface. More specifically, Figure 9An ultrasound image 805b and a display of imaging parameters 905 used to obtain ultrasound image 805b (e.g., FPS: 48, frequency: 5.0 MHz, power: -1 dB, gain: 0 dB, compression: 60 dB, persistence: 0.7, depth: 12.0 cm) are depicted. The display of imaging parameters 905 may refer to a set of imaging parameters determined at step 310. In some embodiments, as described above, ultrasound image 805b may be selected from a plurality of ultrasound images 805a, 805b, and 805c presented via GUI 800 at step 320 of method 300.

[0093] refer to Figure 10 This illustrates a GUI 1000 generated in response to receiving a selection of one of a plurality of ultrasound images 805a, 805b, and 805c displayed on the GUI 800. (See diagram 1000 for details.) Figure 10 As shown, the image selected from GUI 800 is ultrasound image 805b. GUI 1000 is also shown as including a display of context information 810 and imaging parameters 905 associated with the selected image (e.g., imaging parameters associated with ultrasound image 805b, such as...). Figure 9 The display (shown). Therefore, based on the selection of image 805b, the ultrasound imaging system 100 is configured to use parameters included in the display of parameters 905 to collect more image data of the anatomical region depicted in ultrasound image 805b.

[0094] The GUI 1000 also includes an optional element 1005 representing the option to pause the current ultrasound scan (e.g., examination) and return to the imaging options. That is, upon receiving a selection of the optional element 1005 (e.g., as described above in step 630 of reference method 600), the ultrasound imaging system 100 is configured to present... Figure 8 The split screen shown allows the user to select another ultrasound image from ultrasound images 805a, 805b, and 805c. (See above reference.) Figure 6 As described, the iterative process can continue to use different compositional image parameters associated with new selections from ultrasound images 805a, 805b, and 805c to obtain new image data.

[0095] The embodiments described herein have been illustrated with reference to the accompanying drawings. The drawings illustrate certain details of specific embodiments providing the systems, methods, and procedures described herein. However, the use of the drawings to describe the embodiments should not be construed as imposing any limitations that may exist in the drawings on the content of this disclosure.

[0096] It should be understood that no element of any claim herein may be applied under 35 USC. The provisions of 112(f) shall be interpreted unless the element is explicitly described using the phrase “parts for…”.

[0097] As used herein, terms of degree such as “about,” “approximately,” “substantially,” and similar terms are intended to have a broad meaning consistent with common and accepted usage by one of ordinary skill in the art to which the subject matter of this disclosure pertains. Those skilled in the art who read this disclosure will understand that these terms are intended to allow for the description of certain features described and claimed, without limiting the scope of these features to any precise numerical range provided. Therefore, these terms should be interpreted as indicating that non-substantial or irrelevant modifications or alterations to the described and claimed subject matter are considered to be within the scope of the disclosure set forth in the appended claims.

[0098] It should be noted that terms such as “exemplary,” “example,” and similar terms used herein to describe various implementations are intended to indicate that such implementations are possible examples, representations, or illustrations of possible implementations, and such terms are not intended to imply that such implementations are necessarily special or excellent examples.

[0099] As used herein, the term "coupling" and its variations refer to the direct or indirect engagement of two components with each other. Such engagement can be static (e.g., permanent or fixed) or movable (e.g., removable or releasable). Such engagement can be achieved by directly coupling the two components together, by coupling the two components together using a separate intermediate component and any additional intermediate components coupled to each other, or by coupling the two components together using an intermediate component integrally formed with one of the two components. If "coupling" or its variations are modified by an additional term (e.g., direct coupling), the general definition of "coupling" provided above will be modified by the common linguistic meaning of the additional term (e.g., "direct coupling" refers to the engagement of two components without any separate intermediate component), resulting in a narrower definition of "coupling" than the general definition provided above. Such connections can be mechanical, electrical, or fluid.

[0100] As used herein, the term "or" is inclusive (not exclusive), and therefore, when used to connect lists of elements, the term "or" indicates one, some, or all of the elements in the list. Unless otherwise explicitly stated, conjunctions such as the phrase "at least one of X, Y, and Z" should be understood to mean that the elements can be X, Y, and Z; X and Y; X and Z; Y and Z; or X, Y, and Z (i.e., any element on its own or any combination of X, Y, and Z). Therefore, unless otherwise stated, such conjunctions generally do not imply that certain embodiments require at least one of X, at least one of Y, and at least one of Z to be present separately.

[0101] References to element positions in this document (e.g., "top", "bottom", "above", "below") are used only to describe the orientation of the individual elements in the figure. It should be noted that, according to other exemplary embodiments, the orientation of the various elements may differ, and such variations are intended to be covered by this disclosure.

[0102] As used herein, terms such as “engine” or “circuit” can include hardware and machine-readable media on which instructions for configuring hardware to perform the functions described herein are stored. An engine or circuit can be embodied as one or more circuit components, including but not limited to processing circuitry, network interfaces, peripheral devices, input devices, output devices, sensors, etc. In some embodiments, an engine or circuit can take the form of one or more analog circuits, electronic circuits (e.g., integrated circuits (ICs), discrete circuits, system-on-a-chip (SoC) circuits, etc.), telecommunications circuits, hybrid circuits, and any other type of circuit. In this respect, an engine or circuit can include any type of component for implementing or facilitating the implementation of the operations described herein. For example, an engine or circuit as described herein can include one or more transistors, logic gates (e.g., NAND, AND, NOR, OR, XOR, NOT, XNOR, etc.), resistors, multiplexers, registers, capacitors, inductors, diodes, wiring, etc.

[0103] An engine or circuit may be embodied as one or more processing circuits, which include one or more processors communicatively coupled to one or more memories or memory devices. In this respect, the one or more processors may execute instructions stored in memory or instructions otherwise accessible to the one or more processors. The one or more processors may be constructed in a manner sufficient to perform at least the operations described herein. In some embodiments, the one or more processors may be shared by multiple engines or circuits (e.g., engine A and engine B, or circuit A and circuit B may include or otherwise share the same processor, which in some example embodiments may execute instructions stored or otherwise accessed via different regions of memory).

[0104] Alternatively or additionally, one or more processors may be configured to perform or otherwise perform certain operations independently of one or more coprocessors. In other example embodiments, two or more processors may be bus-coupled to enable independent, parallel, pipelined, or multithreaded instruction execution. Each processor may be provided as one or more suitable processors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), or other suitable electronic data processing components configured to execute instructions provided by memory. One or more processors may take the form of a single-core processor, a multi-core processor (e.g., a dual-core processor, a triple-core processor, a quad-core processor, etc.), a microprocessor, etc. In some embodiments, one or more processors may be external to the device; for example, one or more processors may be remote processors (e.g., cloud-based processors). Alternatively or additionally, one or more processors may be internal to the device and / or local to the device. In this regard, a given engine or circuitry or its components may be deployed locally (e.g., as part of a local server, a local computing system, etc.) or remotely (e.g., as part of a remote server such as a cloud-based server). For this purpose, an engine or circuitry as described herein may include components distributed across one or more locations.

[0105] Example systems used to provide an overall system or part of the embodiments described herein may include one or more computers, including processing units, system memory, and a system bus coupling various system components, including the system memory, to the processing units. Each memory device may include a non-transitory volatile storage medium, a non-volatile storage medium (e.g., one or more volatile and / or non-volatile memories), etc. In some embodiments, the non-volatile medium may be in the form of ROM, flash memory (e.g., flash memory such as NAND, 3D NAND, NOR, 3D NOR, etc.), EEPROM, MRAM, magnetic storage devices, hard disks, optical disks, etc. In other embodiments, the volatile storage medium may be in the form of RAM, TRAM, ZRAM, etc. Combinations of the above are also included within the scope of machine-readable media. In this regard, machine-executable instructions include, for example, instructions and data that cause a general-purpose computer, a special-purpose computer, or a special-purpose processor to perform a function or a set of functions. According to the example implementation described herein, each respective memory device is operable to retain or otherwise store information relating to operations performed by one or more associated circuits, including processor instructions and related data (e.g., database components, object code components, script components, etc.).

[0106] Although the accompanying drawings may illustrate and the specification may describe a particular order and composition of method steps, the order of these steps may differ from the order depicted and described. For example, two or more steps may be performed simultaneously or partially simultaneously. Furthermore, some method steps performed as discrete steps may be combined, steps performed as combined steps may be divided into discrete steps, the order of certain processes may be reversed or otherwise altered, and the nature or number of discrete processes may be changed or varied. According to alternative embodiments, the order or sequence of any element or device may be changed or replaced. Therefore, all such modifications are intended to be included within the scope of this disclosure as defined in the appended claims. Such variations may depend, for example, on the chosen software and hardware system and the designer's choice. All such variations are within the scope of this disclosure. Similarly, software implementations of the described methods may be accomplished using standard programming techniques with rule-based logic and other logic to perform various connection steps, processing steps, comparison steps, and decision steps.

[0107] The foregoing description of embodiments has been given for purposes of illustration and description. It is not intended to be exhaustive or to limit the disclosure to the precise forms disclosed, and modifications and variations can be made, or may be derived from, the teachings described above. These embodiments were chosen and described to explain the principles of the disclosure and its practical application, thereby enabling those skilled in the art to utilize the various embodiments and make various modifications suitable for the intended particular purpose. Other substitutions, modifications, alterations, and omissions may be made to the design, operating conditions, and arrangement of the embodiments without departing from the scope of the disclosure as set forth in the appended claims.

Claims

1. An ultrasound imaging system (100), the ultrasound imaging system comprising: A transducer configured to transmit and receive ultrasonic signals; A matching layer, the matching layer being configured to have acoustic impedance between the tissue to be imaged and the material of the transducer; A damping block configured to absorb ultrasonic energy; and Processing circuitry (114) includes a processor (116) coupled to a memory device (118) storing instructions that, when executed, cause the processing circuitry (114) to perform operations, including: Identify contextual information about the patient regarding the ultrasound scan (205), (810); The multi-component imaging parameters (210) are determined using a machine learning model (124) and based on the context information (205), (810). The initial image data of the anatomical region is received and obtained by the transducer using the multi-component imaging parameters (210), wherein the initial image data is obtained using an ultrasound probe (106) in a fixed position above the anatomical region; Based on the initial image data, a plurality of initial images (805a), (805b), and (805c) are presented on the display device (132) of the ultrasound imaging system (100), wherein each of the initial images (805a), (805b), and (805c) corresponds to a set of imaging parameters from the plurality of imaging parameters (210); Receive user input selecting a preferred image (805b) from the plurality of initial images (805a), (805b), and (805c), wherein the preferred image (805b) has been obtained using a set of preferred imaging parameters (905) from the plurality of imaging parameters (210); and The ultrasound probe (106) is configured to receive additional image data of the anatomical region from the transducer using the preferred set of imaging parameters (905).

2. The ultrasound imaging system (100) according to claim 1, wherein the operation further comprises: The user input for selecting the preferred image (805b) is stored in a manner associated with the user's profile.

3. The ultrasound imaging system (100) of claim 2, wherein the user input is stored via at least one of: cloud storage, the memory device (118), or a server associated with the environment in which the ultrasound imaging system (100) is implemented.

4. The ultrasound imaging system (100) according to claim 2, wherein the operation further comprises: The machine learning model (124) is trained based on the user input that selects the preferred image (805b).

5. The ultrasound imaging system (100) according to claim 4, wherein the multi-group imaging parameters (210) are first multi-group imaging parameters (210), the initial image data are first initial image data, and the operation further includes: The user's profile is identified during continuous ultrasound scanning; The second multi-group imaging parameters are determined by a trained machine learning model (124); as well as Receive second initial image data obtained using the second multi-component imaging parameters during the continuous ultrasound scan.

6. The ultrasound imaging system (100) according to claim 1, wherein the context information (205), (810) includes at least one of the patient's body mass index (BMI), the patient's age, or gestational age.

7. The ultrasound imaging system (100) according to claim 1, wherein the machine learning model (124) comprises a Bayesian neural network.

8. The ultrasound imaging system (100) according to claim 7, wherein the operation further comprises: The probability associated with each of the plurality of initial images (805a), (805b), and (805c) is identified using the Bayesian neural network. as well as A subset of the plurality of initial images (805a), (805b), and (805c) is presented on the display device (132) based on the probability associated with each of the plurality of initial images (805a), (805b), and (805c).

9. The ultrasound imaging system (100) of claim 1, wherein the machine learning model (124) is pre-trained using interaction history associated with multiple users of the ultrasound imaging system (100), and wherein the operation further comprises: Identify historical image data from the interaction history associated with at least a portion of the context information (205), (810); as well as The multi-group imaging parameters (210) are used to obtain the historical image data, and the machine learning model (124) is used to determine the multi-group imaging parameters (210).

10. The ultrasound imaging system (100) according to claim 1, wherein the multiple imaging parameters (210) include at least one of frequency, acquisition angle, dynamic power, gain, or composite imaging settings.

11. The ultrasound imaging system (100) of claim 1, wherein the user input is a first user input, the preferred image (805b) is a first preferred image (805b), and the operation further comprises, when receiving the additional image data using the set of preferred imaging parameters (905): Receive a second user input requesting to view the plurality of initial images (805a), (805b), and (805c); The plurality of initial images (805a), (805b), and (805c) are displayed on the display device (132); Receive a third user input selecting a second preferred image from the plurality of initial images (805a), (805b), and (805c), wherein the second preferred image is different from the first preferred image (805b) and corresponds to a second composition imaging parameter among the plurality of imaging parameters (210); and The ultrasound probe (106) is configured to receive updated additional image data using the second set of imaging parameters.

12. A medical imaging system, the medical imaging system comprising: Processing circuit (114) having a processor (116) coupled to a memory device (118) storing instructions that, when executed, cause the processing circuit (114) to perform operations including: Identify contextual information about the patient regarding the medical imaging scan (205), (810); The multi-component imaging parameters (210) are determined using a machine learning model (124) and based on the context information (205), (810). Receive initial image data of the anatomical region using the multi-component imaging parameters (210), wherein the initial image data is obtained using an ultrasound probe (106) at a fixed position above the anatomical region; Based on the initial image data, a plurality of initial images (805a), (805b), and (805c) are presented on the display device (132) of the medical imaging system, wherein each of the initial images (805a), (805b), and (805c) corresponds to a set of imaging parameters from the plurality of imaging parameters (210). Receive user input selecting a preferred image (805b) from the plurality of initial images (805a), (805b), and (805c), wherein the preferred image (805b) has been obtained using a set of preferred imaging parameters (905) from the plurality of imaging parameters (210); and The medical imaging system is configured to receive additional image data of the anatomical region using the set of preferred imaging parameters (905).

13. The medical imaging system of claim 12, wherein the medical imaging system is an ultrasound imaging system (100), the ultrasound imaging system comprising: A transducer configured to transmit and receive ultrasonic signals; The initial image data and the additional image data are obtained by the transducer.

14. The medical imaging system of claim 12, wherein the multi-group imaging parameter (210) is a first multi-group imaging parameter (210), the initial image data is first initial image data, and the operation further comprises: The user input for selecting the preferred image (805b) is stored in a manner associated with the user's profile. The machine learning model (124) is trained based on the user input that selects the preferred image (805b). The user's profile is identified during continuous medical imaging scans; The second multi-group imaging parameters are determined by the trained machine learning model (124); as well as Receive second initial image data obtained using the second multi-component imaging parameters during the continuous medical imaging scan.

15. The medical imaging system of claim 12, wherein the machine learning model (124) comprises a Bayesian neural network, and wherein the operation further comprises: The probability associated with each of the plurality of initial images (805a), (805b), and (805c) is identified using the Bayesian neural network. as well as A subset of the plurality of initial images (805a), (805b), and (805c) is presented on the display device (132) based on the probability associated with each of the plurality of initial images (805a), (805b), and (805c).

Images