User-specific adaptive segmentation in medical imaging

Abstract

Systems and methods are provided for providing an adaptive and intelligent segmentation process that supports personalization during an ultrasound scan. An ultrasound imaging system includes processing circuitry having a processor coupled to a memory device having instructions stored thereon that, when executed, cause the processing circuitry to perform operations including generating an ultrasound image based on image data obtained by a transducer, segmenting an anatomical structure in the ultrasound image using a segmentation algorithm, presenting the ultrasound image on a display of the ultrasound imaging system, the ultrasound image including the segmentation of the anatomical structure, receiving input from a user via the display, the input including an adjustment to the segmentation of the anatomical structure, adjusting the segmentation of the anatomical structure based on the input, presenting the ultrasound image with the adjusted segmentation of the anatomical structure via the display, and updating the segmentation algorithm based on the input.

Description

Technical Field

[0001] The embodiments of the subject matter disclosed herein relate to ultrasound imaging, and more specifically, to providing adaptive and intelligent segmentation of anatomical regions during an ultrasound imaging workflow based on the personalized preferences of the user performing the ultrasound imaging workflow. Background Technology

[0002] Medical images acquired during medical imaging procedures depict a variety of anatomical features and structures. In some cases, these anatomical features and structures are automatically segmented in the medical images to assist observers (e.g., technicians, physicians, etc.) in analyzing the images. Summary of the Invention

[0003] The implementation 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 thereon, which, when executed, cause the processing circuitry to perform operations including: generating an ultrasound image based on image data acquired by the transducer; segmenting anatomical structures in the ultrasound image using a segmentation algorithm; presenting the ultrasound image, including the segmentation of the anatomical structures, on a display of the ultrasound imaging system; receiving input from a user via the display, wherein the input includes adjustments to the segmentation of the anatomical structures; adjusting the segmentation of the anatomical structures based on the input; presenting the ultrasound image with the adjusted segmentation of the anatomical structures via the display; and updating the segmentation algorithm based on the input.

[0004] Another embodiment relates to a medical imaging system including processing circuitry with a processor coupled to a memory device storing instructions that, when executed, cause the processing circuitry to perform operations. These operations include: generating a medical image; segmenting anatomical structures in the medical image using a segmentation algorithm; presenting the medical image, including the segmentation of the anatomical structures, on a display of the medical imaging system; receiving input from a user via the display, wherein the input includes adjustments to the segmentation of the anatomical structures; adjusting the segmentation of the anatomical structures based on the input; presenting the medical image with the adjusted segmentation of the anatomical structures via the display; and updating the segmentation algorithm based on the input from the user.

[0005] Another implementation relates to a method. The method includes: generating a medical image by processing circuitry of a medical imaging system. The method includes: segmenting anatomical structures in the medical image by the processing circuitry using a segmentation algorithm. The method includes: presenting the medical image by the processing circuitry, the medical image including the segmentation of the anatomical structures. The method includes: receiving input from a user by the processing circuitry, wherein the input includes adjustments to the segmentation of the anatomical structures. The method includes: adjusting the segmentation of the anatomical structures by the processing circuitry based on the input. The method includes: presenting the medical image with the adjusted segmentation of the anatomical structures by the processing circuitry. The method includes: updating the segmentation algorithm based on the input from the user.

[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 2 It is based on the example implementation plan. Figure 1 A block diagram of the processing circuitry used in an ultrasound imaging system.

[0009] Figure 3 This is an example of the use of the example implementation scheme. Figure 1 The flowchart provides an adaptive segmentation method for ultrasound imaging systems.

[0010] Figure 4 This is an example implementation of updating based on user preferences. Figure 3 The flowchart of the segmentation method provided during the method period.

[0011] Figure 5 This is for use according to the example implementation plan. Figure 1 A block diagram illustrating the workflow of an ultrasound imaging system performing user-specific adaptive segmentation.

[0012] Figure 6A This is an example of an ultrasound image based on an example implementation, which includes user-defined adjustments to the default segmentation of anatomical features.

[0013] Figure 6B It is based on the example implementation plan. Figure 6A An example of an ultrasound image, which includes adjusted segmentation based on user-defined adjustments.

[0014] Figure 7A This is an example of an ultrasound image based on an example implementation, which includes default segmentation of multiple anatomical features and user-defined adjustments to one of the default segments.

[0015] Figure 7B It is based on the example implementation plan. Figure 7A An example of an ultrasound image, which includes an adjusted segmentation of multiple anatomical features based on a user-defined adjustment of one of the default segments.

[0016] Figure 8 This is an example of a user interface configured to facilitate user-specific adaptive segmentation based on an example implementation. Detailed Implementation

[0017] Referring generally to the accompanying drawings, a system and method for providing user-specific adaptive segmentation of anatomical structures in medical images are disclosed. The system and method disclosed herein adjust the segmentation based on user input and store the received user input, thereby ensuring closer consistency between automatically generated segmentations and user preferences and behaviors during continuous medical imaging procedures.

[0018] During ultrasound, the delineation and / or measurement of anatomical structures in ultrasound images often exhibit considerable inter-observer variability. This variability is primarily due to variations in image quality caused by patient characteristics and acquisition settings. Furthermore, the expected segmentation output can vary depending on the specific clinical protocol, user, institution, patient, and / or demographic characteristics. However, conventional segmentation algorithms used for automated anatomical structure detection are affected by the quality and distribution of the underlying data and therefore cannot fully adapt to user- and / or institution-specific preferences or examination protocols. Consequently, automated segmentation of anatomical structures often requires subsequent user editing to accommodate user- and / or institution-specific preferences or examination protocols. Such editing may include manually editing the ultrasound image or restarting the entire process to generate a user-preferred result (e.g., by applying new image acquisition settings). Therefore, existing systems for automatically generating segmentations of anatomical structures in ultrasound images ultimately reduce workflow efficiency and increase examination time.

[0019] To bridge the gap between providing a generic solution for generating anatomical segmentation and providing intra-observer variability (e.g., personalization), the systems and methods disclosed herein provide adaptive algorithms / workflows for contour delineation (e.g., segmentation) and / or measurement of any 2D or 3D structures in medical images. Furthermore, the adaptive workflow described herein improves efficiency in adjusting for user-provided anatomical segmentation. Additionally, this workflow adapts to user preferences by learning user behavior and cues to deliver improved automated segmentation results over time.

[0020] This disclosure relates to a novel, intelligent, and universally applicable system for adjusting default / automatic segmentation based on received user cues for any 2D or 3D homogeneous structure or anatomical feature in a medical image. The systems and methods described herein improve workflow efficiency and reduce examination time without compromising accuracy across a wide range of medical imaging applications. The adaptive workflow described herein is also configured to update the underlying algorithm over time to adapt to user preferences and ensure more appropriate segmentation results in successive medical imaging procedures.

[0021] 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 how to synthesize and utilize user input from various ultrasound scans to provide user-specific adaptive segmentation of anatomical structures in ultrasound images. By integrating user-specific data, these systems provide real-time intelligent segmentation of anatomical features and structures during ultrasound scans. Therefore, this approach offers specific technical improvements to various technical problems, including those described herein.

[0022] Before turning to the accompanying drawings, which illustrate certain exemplary embodiments in detail, 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 considered limiting.

[0023] 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 a patient. Although the system and methods are described herein in the context of the ultrasound imaging system 100, it should be understood that the user-specific adaptive segmentation can be performed using any of a variety of medical imaging systems (e.g., medical resonance imaging, X-ray, computed tomography, positron emission tomography, etc.).

[0024] Examples of procedures performed using the ultrasound imaging system 100 may include mid-pregnancy fetal examination, pelvic examination, uterine fibroid and follicle monitoring, etc. In each of these examples, two-dimensional (2D) and / or three-dimensional (3D) contouring of relevant anatomical structures and / or measurements (e.g., caliper placement) is an integral part of the procedure. Taking mid-pregnancy fetal examination as a specific example, contouring is essential for measuring biparietal diameter, head circumference, abdominal circumference, etc. Similarly, contouring affects area and diameter measurements performed during uterine fibroid and follicle monitoring. Therefore, the operator of the ultrasound imaging system 100 relies on contours from the ultrasound images it generates to assess fetal health, monitor the growth of anatomical structures, and perform other medical assessments.

[0025] 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.

[0026] 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.

[0027] 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 and 2D color flow data. Alternatively or additionally, 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, probe 106 may include a positioning sensor configured to detect the positioning of 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 probe 106 relative to its position. For example, the anatomical structure being imaged may be identified as the left atrial appendage (LAA) at a first location of probe 106. The position sensor may then track the movement of probe 106 relative to the LAA to identify successive positions of probe 106. In some embodiments, the positioning sensor may transmit position data to be stored within the ultrasound imaging system 100 (e.g., in memory 118).

[0028] 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.

[0029] 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 backtracking transmit beamforming (RTB). Alternatively, in embodiments where receiver beamformer 112 is a software beamformer, a processor (e.g., processor 116 described below) may be configured to perform some or all of the functions associated with receiver beamformer 112.

[0030] 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.

[0031] Still referencing Figure 1 An 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 segmentation 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 segmentation 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).

[0032] 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 interconnected via a bus to enable independent, parallel, pipelined, or multi-threaded instruction execution. All such variations are intended to fall within the scope of this disclosure.

[0033] Processor 116 can be configured to control transmit beamformer 102, transmitter 104, receiver 110, and receive beamformer 112. Processor 116 can also communicate electronically with probe 106. For the purposes of this disclosure, the term "electronic communication" can be defined to include both wired and wireless communication.

[0034] 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.

[0035] 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.).

[0036] 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 executed 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.

[0037] 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 an embodiment, a first processor of the multiple processors may be configured to demodulate and decimate RF signals, while a second processor of 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.

[0038] Processor 116 can also communicate electronically with display device 132, enabling processor 116 to process ultrasound data obtained by probe 106 and generate images for display on display device 132 (e.g., ultrasound image 600 and ultrasound image 700, referred to below respectively). Figures 6A to 6B and Figures 7A to 7B (As described).

[0039] 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.

[0040] 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.

[0041] The processing circuit 114 also includes an image processing circuit 120 and a segmentation circuit 122. Both the image processing circuit 120 and the segmentation circuit 122 are configured to facilitate user-specific adaptive segmentation of anatomical features in ultrasound images, as described herein.

[0042] 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.

[0043] Based on image analysis performed by image processing circuit 120, segmentation circuit 122 is configured to segment anatomical structures identified in the image data. In some implementations, such as Figure 1 As shown, the segmentation circuit 122 may include an artificial intelligence (AI) model 124, which is configured to perform segmentation of anatomical structures, as referenced below. Figure 2 As described.

[0044] 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 circuit 114 (e.g., segmentation circuit 122) can retrieve information for segmenting anatomical structures depicted in ultrasound image data. 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 processing circuit 114 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 uterine fibroid and follicle monitoring, the processing circuit 114 may retrieve clinical guidelines and standard practices relevant to the hospital setting and the uterine fibroid and follicle monitoring. Continuing this example, the processing circuit 114 may also retrieve information from medical literature, medical textbooks, published studies, and previous case studies related to the anatomy of the uterus and ovaries.

[0045] 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 a medical setting.

[0046] 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).

[0047] 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, and soft keys configurable to control different functions. 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 8 An example of GUI 800 is given, in which at least some physical controls of user interface 130 are represented by various user interface icons.

[0048] 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 located on the display device 132 or as part of a touchscreen separate from the display device 132.

[0049] Now for reference Figure 2 The processing circuitry 114 of the ultrasound imaging system 100 is shown in more detail. More specifically, Figure 2 A memory 118 and a segmentation circuit 122 are depicted, which is configured to facilitate user-specific adaptive segmentation of anatomical structures in ultrasound images, as described herein.

[0050] Memory 118 is shown as including user profile 205. User profile 205 refers to the profile of the operator of the ultrasound imaging system 100 (e.g., an ultrasound physician, technician, clinician, etc.). For example, as described below with reference to step 301 of method 300, the ultrasound imaging system 100 may identify the operator before initiating the collection of ultrasound data. In such a case, memory 118 may then be configured to retrieve the user profile 205 associated with the identified operator. Figure 2 As shown, user profile 205 may include segmentation preference 210. Segmentation preference 210 refers to the user's preference for segmenting anatomical structures in medical images associated with user profile 205. For example, a first user may prefer oversegmentation of anatomical structures, while a second user may prefer undersegmentation. See below for reference. Figure 3 and Figure 4As described, segmentation preferences 210 can be collected and stored in memory 118 during a medical imaging procedure based on adjustments (e.g., adjustments to the default segmentation) and / or selections received from the user. In this way, segmentation preferences 210 can be retrieved during continuous ultrasound scans when identifying the user profile 205 associated with the operator of the ultrasound imaging system 100.

[0051] As in Figure 2 As illustrated, segmentation preference 210 from user profile 205 can be retrieved from memory 118 and received by segmentation circuit 122. In this way, when segmentation of anatomical structures is performed during a medical imaging procedure, segmentation circuit 122 can segment the anatomical structures according to the received segmentation preference 210 associated with the user / operator.

[0052] The segmentation circuit 122 is shown as including an AI model 124 and a training database 212. In some embodiments, the AI ​​model 124 refers to a segmentation algorithm configured to perform segmentation of one or more anatomical structures depicted in an image received from the image processing circuit 120. The AI ​​model 124 may be trained based on information stored in the training database 212, including adjustments to segmentation 215 and / or segmentation selection 220, such as... Figure 2 As shown. Segmentation adjustment 215 refers to adjustments made by the user to the segmentation generated by segmentation circuit 122 (e.g., input received at step 315 of method 300, additional adjustments received at step 405 of method 400, etc.) and may be reflected in segmentation preference 210 of user profile 205. For example, segmentation adjustment may include negative prompts (e.g., negative points 610(1), 710(1)) in response to oversegmentation of anatomical structures generated by segmentation circuit 122. Alternatively or additionally, segmentation adjustment may include positive prompts (e.g., positive points 610(2), 710(2)) in response to undersegmentation of anatomical structures generated by segmentation circuit 122. Segmentation selection 220 refers to a selection made by the user between medical images with different segments having the same anatomical structure (e.g., a selection between a medical image presented at step 325a of method 300 and a medical image presented at step 325b of method 300). The segmentation selection 220 can be reflected in the segmentation preference 210 of the user profile 205.

[0053] See below for reference Figure 3 and Figure 4As described, adjustments to segmentation 215 and / or segmentation selections 220 can be received from the user during a live medical imaging procedure (e.g., ultrasound scan) and therefore can be received by segmentation circuitry 122 and then stored in memory 118 as segmentation preference 210. In this way, adjustments to segmentation 215 and / or segmentation selections 220 received during a first ultrasound scan can be stored in memory 118 and applied to segmentation circuitry 122 during subsequent ultrasound scans. That is, AI model 124 can be trained using additional training data from training database 212 (e.g., adjustments to segmentation 215 and / or segmentation selections 220 received during the first ultrasound scan), which enables segmentation circuitry 122 to perform segmentation of anatomical features during subsequent ultrasound scans that differs from the segmentation of anatomical features performed by segmentation circuitry 122 during the first ultrasound scan.

[0054] refer to Figure 3 A flowchart illustrating a method 300 for providing adaptive segmentation of anatomical features in a medical image using a medical imaging system is shown. In at least one embodiment, the medical imaging system referred to by 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.

[0055] Before initiating the collection of ultrasound data, method 300 may begin at step 301 when an operator (e.g., an ultrasound physician, technician, or other clinician) is identified as a user of ultrasound imaging system 100. In some embodiments, the operator may authenticate themselves as an authorized user of ultrasound imaging system 100 by logging into a portal (e.g., an online application accessible via user interface 130) associated with the environment in which ultrasound imaging system 100 is implemented (e.g., a hospital or other healthcare provider). For example, the operator may log in using a unique identifier (e.g., username, password, biometric scan, PIN, etc.). Once the operator is identified and successfully authenticated, ultrasound imaging system 100 may be configured to retrieve a user profile (e.g., user profile 205) associated with the identified operator. In some embodiments, the user profile may include various preferences of the operator regarding the collection and processing of ultrasound data by ultrasound imaging system 100.

[0056] like Figure 3As shown, method 300 may include receiving a medical image at step 305, the medical image depicting a segmentation of an anatomical structure. In some embodiments, receiving the medical image at step 305 may include generating the medical image. For example, the medical image may be an ultrasound image (e.g., ultrasound image 600, ultrasound image 700) generated by image processing circuitry 120 based on ultrasound data obtained using probe 106.

[0057] The medical image received at step 305 may further include segmentation of anatomical structures in the medical image. In some embodiments, the anatomical structures may be segmented at step 305 by segmentation circuit 122 using a segmentation algorithm (e.g., AI model 124). The segmentation performed by segmentation circuit 122 at step 305 may be referred to as default segmentation (e.g., default segmentation 605a, 705a). That is, default segmentation refers to the segmentation of the anatomical structures before any operator input adjusts the segmentation (e.g., as described in step 315 of method 300). In some embodiments, the medical image received at step 305 may depict multiple anatomical structures (e.g., such as...). Figure 7A and Figure 7B (As shown in ultrasound image 700). In this case, at step 305, each of the multiple anatomical structures can be segmented by segmentation circuit 122.

[0058] At step 310, the medical image received at step 305 is presented to the user (e.g., the user of the medical imaging system identified at step 301). That is, the medical image presented to the user includes segmentation of anatomical structures. As described below, the medical image may be presented as ultrasound image 600 and / or ultrasound image 700. In some embodiments, such as Figures 6A to 8 The embodiments shown may exemplify the segmentation using the outline of anatomical features superimposed on the medical image (e.g., default segmentation 605a, 705a). In some cases, the medical image is presented via display device 132.

[0059] After presenting the medical image to the user at step 310, method 300 includes receiving input from the user at step 315 to adjust the segmentation of the anatomical structures as shown in the medical image. That is, at step 315, the user adjusts the default segmentation generated by segmentation circuit 122, and the medical image is presented at step 310. The user can use display device 132 to adjust the segmentation (e.g., by tapping a point on a touchscreen with a finger, using a stylus or other probe to select a point on the touchscreen, etc.).

[0060] The input received at step 315 may include at least one of a negative prompt (e.g., negative points 610(1), 710(1)) or a positive prompt (e.g., positive points 610(2), 710(2)). A negative prompt is a user-provided prompt that specifies points on the medical image to be excluded from the segmentation of anatomical structures (e.g., points previously included in the default segmentation presented at step 310). A positive prompt is a user-provided prompt that specifies points on the medical image to be included in the segmentation of anatomical structures (e.g., points not previously included in the default segmentation presented at step 310). In other words, a negative prompt is configured to adjust the segmentation in the case of oversegmentation, while a positive prompt is configured to adjust the segmentation in the case of undersegmentation.

[0061] Then, the input received from the user at step 315 can be stored in the memory of the medical imaging system used to perform method 300 at step 316. For example, as referenced above. Figure 2 As described, this input can be stored in the memory 118 of the ultrasound imaging system 100. More specifically, the input can be stored in relation to the user's profile (e.g., user profile 205) identified at step 301. Figure 2 As shown, this input can be stored in the segmentation preference 210 in the user profile 205.

[0062] At step 320 of method 300, the segmentation of the anatomical structure is adjusted based on the input received at step 315 (e.g., default segmentation 605a, 705a). For example, if the input received at step 315 includes a negative cue, adjusting the segmentation at step 320 may include excluding multiple points along the contour of the anatomical structure based on the negative cue (e.g., multiple points previously included in the segmentation presented at step 310). That is, in such cases, the segmentation is adjusted to compensate for oversegmentation previously generated by segmentation circuit 122 (e.g., depicted by adjustments 615(1), 715(1)). Alternatively or additionally, if the input received at step 315 includes a positive cue, adjusting the segmentation at step 320 may include adding / including multiple points along the contour of the anatomical structure based on the positive cue (e.g., multiple points previously excluded from the segmentation presented at step 310). That is, in such cases, the segmentation is adjusted to compensate for undersegmentation previously generated by segmentation circuit 122 (e.g., depicted by adjustments 615(2), 715(2)).

[0063] In some cases, where the medical image presented at step 305 depicts multiple anatomical structures, step 320 may include adjusting the segmentation of the multiple anatomical structures based on the input. That is, as described below... Figure 7A and Figure 7BIn more detail, the input received at step 315 for adjusting the segmentation of the first anatomical structure can be applied to multiple anatomical structures depicted in a medical image. For example, if the input received at step 315 includes a negative cue (e.g., negative point 710(1)), adjusting the segmentation at step 320 may include excluding multiple points along the contour of each of the multiple anatomical structures based on the negative cue. Similarly, as another example, if the input received at step 315 includes a positive cue (e.g., positive point 710(2)), adjusting the segmentation at step 320 may include adding / including multiple points along the contour of each of the multiple anatomical structures based on the positive cue.

[0064] Method 300 continues by presenting a medical image with adjusted segmentation of the anatomical structure at step 325a. The medical image may be presented at step 325a via display device 132. In some cases, where the anatomical structure is the first anatomical structure among a plurality of anatomical structures depicted in the medical image, the medical image is presented with adjusted segmentation of the plurality of anatomical structures (e.g., as shown in the image). Figure 7B (The ultrasound image 700 depicts this).

[0065] In some cases, adjusted segmented medical images without anatomical structures may be presented at step 325b. Depending on the situation, steps 325a and 325b may be performed simultaneously, such that adjusted segmented medical images with anatomical structures can be presented side-by-side with adjusted segmented medical images without anatomical structures (e.g., unadjusted segmentation) (e.g., via split screen, etc.). The adjusted and unadjusted segments may be presented to a user of the ultrasound imaging system via display device 132. For example, in the case where display device 132 includes a touchscreen, the user can participate in the presentation of adjusted and / or unadjusted segments.

[0066] refer to Figure 4 A flowchart illustrating method 400 is shown, through which a user can participate in the presentation of adjusted segments (e.g., step 325a from method 300) and / or the presentation of unadjusted segments (e.g., step 325b from method 300). In at least one embodiment, the medical imaging system referred to by method 400 is the one described above. Figure 1 and Figure 2 The ultrasound imaging system 100 is described, and the method 400 can be implemented by the ultrasound imaging system 100. In some embodiments, the method 400 can be implemented as a memory of the ultrasound imaging system 100 (such as...). Figure 1 Executable instructions in memory 118.

[0067] For example, when presenting an adjusted segmented medical image with anatomical structures at step 325a, the ultrasound imaging system 100 may receive additional adjustments to the segmentation of the anatomical structures from the user at step 405 of method 400. That is, the user may apply one or more additional negative cues (e.g., negative points 610(1), 710(1)) to indicate additional points along the contour of the anatomical structure to exclude them from the segmentation presented with the medical image at step 325a. Alternatively or additionally, at step 405, the user may apply one or more additional positive cues (e.g., positive points 610(2), 710(2)) to indicate additional points along the contour of the anatomical structure to include them in the segmentation presented with the medical image at step 325a.

[0068] Therefore, when additional adjustments to the segmentation of the anatomical structure are received at step 405, method 400 may continue to update the adjustments to the segmentation of the anatomical structure at step 410. Step 410 may be performed as described above with reference to step 320 of method 300. That is, if the additional adjustments received at step 405 include a negative cue, updating the adjustments to the segmentation at step 410 may include excluding multiple points along the contour of the anatomical structure (e.g., multiple points previously included in the segmentation presented at step 325a) based on the negative cue. Alternatively or additionally, if the additional adjustments received at step 405 include a positive cue, updating the adjustments to the segmentation at step 410 may include adding / including multiple points along the contour of the anatomical structure (e.g., multiple points previously excluded from the segmentation presented at step 325a) based on the positive cue.

[0069] like Figure 4 As shown, after receiving an update on the segmentation adjustment at step 410, the ultrasound imaging system 100 is configured to present a medical image with adjusted segmentation (e.g., step 325a of method 300) and a medical image without adjusted segmentation (e.g., step 325b). However, in such cases, adjusted segmentation refers to an update to the segmentation performed at step 410 based on additional adjustments received at step 405, rather than an adjustment to the segmentation performed at step 320 of method 300 based on input received from the user at step 315. In other words, Figure 4 This represents an iterative process through which the ultrasound imaging system 100 receives additional adjustments to the segmentation of anatomical structures from the user (e.g., received at step 405) and presents an updated version of the medical image to reflect such adjustments to the segmentation (e.g., updated at step 410).

[0070] In some cases, such as when the user has not made additional adjustments to the segmentation presented at step 325a, method 400 may continue by receiving a selection of a medical image from the user at step 415. More specifically, this selection refers to the choice between a medical image with adjusted segmentation presented at step 325a and a medical image without adjusted segmentation presented at step 325b. For example, if the user approves the adjusted segmentation of the anatomical structure presented at step 325a, the user may select the medical image with adjusted segmentation. On the other hand, if the user does not approve the adjusted segmentation and prefers the version of the medical image without adjusted segmentation, the user may select the medical image without adjusted segmentation. For example, if the user has already applied one or more additional adjustments (e.g., at step 405) to the segmentation, the user may prefer the segmentation before it was updated according to the additional adjustments (e.g., at step 410), and therefore may select the medical image without adjusted segmentation.

[0071] At step 420 of method 400, the selection received at step 415 is stored in system memory. More specifically, the selection may be stored in memory 118 as user preferences (e.g., in segmentation preferences 210) associated with the user profile (e.g., user profile 205) identified at step 301 of method 300.

[0072] Therefore, the ultrasound imaging system 100 stores the segmentation adjustments (e.g., at step 315, at step 405) and selections of medical images received from the user, such that during the segmentation of anatomical structures in the continuous medical images, the segmentation circuit 122 (e.g., AI model 124) applies user preferences (e.g., segmentation preference 210) associated with the segmentation adjustments and / or selections. In this way, method 400 is shown as including: performing segmentation of anatomical structures in the continuous medical images based on the stored selections (e.g., received at step 415) and user input (e.g., received at step 315 of method 300 and at step 405 of method 400).

[0073] For example, if a user selects a medical image with adjusted segmentation of anatomical structures (e.g., presented at step 325a) at step 415, and this selection is stored in memory 118 at step 420, step 425 can begin by identifying anatomical structures in a series of ultrasound images using ultrasound imaging system 100 (e.g., image processing circuitry 120). Then, based on the identification of the anatomical structures, step 425 may include using segmentation circuitry 122 to segment the anatomical structures in the series of ultrasound images based on the input and selection, such that after segmenting the anatomical structures in the series of ultrasound images, the series of ultrasound images resembles an ultrasound image with adjusted segmentation of anatomical structures. That is, segmentation circuitry 122 is configured to identify segmentation preference 210 from user profile 205 and apply such segmentation preference 210 to the ultrasound images because segmentation preference 210 is associated with the anatomical structures identified by image processing circuitry 120.

[0074] refer to Figure 5 The illustration shows a workflow 500 for performing adaptive and intelligent segmentation of anatomical structures. In at least one embodiment, workflow 500 may be implemented by ultrasound imaging system 100. In some embodiments, workflow 500 may be implemented as a memory of ultrasound imaging system 100 (such as...). Figure 1 Executable instructions in memory 118.

[0075] Workflow 500 represents a continuous adaptive system that begins with the user initiating automatic segmentation of the desired anatomical structure at step 505 of box 1 (e.g., a pre-existing automated algorithm, such as AI model 124 of segmentation circuit 122), as... Figure 5 As shown.

[0076] After initiating automatic segmentation at step 505, workflow 500 includes determining whether the solution (e.g., automatic segmentation generated at step 505 in response to an initiation from the user) is suitable for the user's preferences (e.g., segmentation preference 210).

[0077] If the solution does not match user preferences, workflow 500 continues to adjust the split output at box 2, such as... Figure 5 As illustrated in step 515 of workflow 500, the user can determine whether the segmentation output depicts undersegmentation (e.g., excluding segments of points / regions along the contours of anatomical structures that the user prefers to include in the segmentation) and / or oversegmentation (e.g., including segments of points / regions along the contours of anatomical structures that the user prefers not to include in the segmentation). In some embodiments, the segmentation output may include only undersegmented regions, only oversegmented regions, or both undersegmented and oversegmented regions.

[0078] The segmentation output can be adjusted as described above with reference to methods 300 and / or 400. That is, the user can adjust the segmentation output with simple and minimal interaction by marking points to be excluded from oversegmentation (e.g., negative hints) or marking points to be included due to undersegmentation (e.g., positive hints). For example, if it is determined at step 515 that the segmentation depicts an oversegmentation, workflow 500 may include: at step 520(1), the user clicks on oversegmented pixels / voxels (e.g., negative points 610(1), 710(1)) to adjust the structure of the segmentation. Alternatively or additionally, if it is determined at step 515 that the segmentation depicts an undersegmentation, workflow 500 may include: at step 520(2), the user clicks on missing (e.g., excluded, omitted, etc.) pixels / voxels (e.g., positive points 610(2), 710(2)) to adjust the structure of the segmentation.

[0079] In response to a negative point received at step 520(1) and / or a positive point received at step 520(2), a segmentation algorithm (e.g., segmentation circuit 122) may be configured to adjust the segmentation accordingly at step 525. The prompts received at steps 520(1) and / or 520(2) may be used to adjust or change the entire segmentation using characteristics of user-marked points (e.g., pixels, voxels, etc.). For example, when adjusting the segmentation at step 525, the segmentation algorithm (e.g., segmentation circuit 122) may use pixel / voxel characteristics such as neighborhood histogram distribution, contrast variation, homogeneity of neighboring pixels, and shape smoothness. Furthermore, in cases where a medical image includes multiple (e.g., more than one) anatomical structures, pixel / voxel characteristics may be used to propagate the adjustment to multiple instances of the same structure. For example, ultrasound images obtained during ovarian ultrasound can depict multiple follicles, and the remaining follicles among the multiple follicles can be adjusted by the segmentation circuit 122 based on inputs from the user applied to the first follicle among the multiple follicles (e.g., positive and / or negative points).

[0080] After adjusting the segmentation, at step 530, the input can be stored in system memory (e.g., adaptive workflow memory). Figure 5 As shown, the adaptive workflow memory allows workflow 500 to execute feedback loops (e.g., depicted by box 3) that include learning user behavior and preferences over time (e.g., based on segmentation and adjustments saved to the adaptive workflow memory), such that the segmentation algorithm is updated according to the learned user behavior and preferences. In this way, subsequent segmentation suggestions provided to the user by segmentation circuit 122 (e.g., in response to initiating automatic segmentation at step 505) require little or no adjustments / edits from the user, because the automatically generated segmentation matches the user's preferences and previous behavior.

[0081] like Figure 5 As shown in block 3, the feedback loop of workflow 500 may include displaying an alternative segment at step 535 based on received user input (e.g., previous interaction between the user and a segment generated by segmentation circuit 122). For example, in the case where the user applies at least one of a negative point at step 520(1) or a positive point at step 520(2), the alternative segment may refer to the segment adjusted by segmentation circuit 122 at step 525. In other words, step 535 may refer to presenting a medical image at step 325a of method 300. In this way, the user may also receive a display of an unadjusted segment at step 535 (e.g., as described above with reference to step 325b of method 300). Thus, existing segments (e.g., from step 505) and updated segments (e.g., from step 525) may be presented to the user, allowing the user to select a segment from existing segments (e.g., presented at step 325b) and updated segments (e.g., presented at step 325a) at step 540. In other words, the user decides whether to keep or discard the proposed alternative split. The feedback loop further includes storing the selection in an adaptive workflow memory (e.g., step 530) so that the user's default split settings are updated based on the user's selection.

[0082] If the solution generated in response to the automatic segmentation initiated at step 505 does indeed fit the user preference, as determined at step 510, workflow 500 continues to store the segmentation output in the adaptive workflow memory at step 530 and initiate the feedback loop depicted in block 3.

[0083] refer to Figure 6A and Figure 6B An ultrasound image 600 is shown. The ultrasound image 600 can be acquired by the ultrasound imaging system 100 during a uterine examination and can depict anatomical structures (e.g., the uterus). In some embodiments, the ultrasound image 600 can be a medical image as referred to in method 300 and / or method 400 described above. Furthermore, the ultrasound image 600 can be provided to a user of the ultrasound imaging system 100 via a display device 132.

[0084] like Figure 6AAs shown, the anatomical structure is outlined / segmented according to the default segmentation 605a. That is, the default segmentation 605a can be generated by the segmentation circuit 122 using a pre-existing segmentation algorithm. Alternatively or additionally, the default segmentation 605a can be generated by the segmentation circuit 122 using segmentation preferences 210 stored in a user profile 205 associated with the user performing the uterine examination. In some embodiments, the ultrasound image 600 with the default segmentation 605a is a medical image received at step 305 and presented to the user at step 310 of method 300.

[0085] The ultrasound image 600 is also shown as including a negative point 610(1) and a positive point 610(2). As described above, the negative point 610(1) specifies a point on the ultrasound image 600 to be excluded from the default segmentation 605a. The positive point 610(2) specifies a point on the ultrasound image 600 to be included in the default segmentation 605a. In other words, the negative point 610(1) is configured to adjust the default segmentation 605a in the case of oversegmentation, while the positive point 610(2) is configured to adjust the default segmentation 605a in the case of undersegmentation. In some embodiments, the negative point 610(1) and the positive point 610(2) are inputs received at step 315 of method 300. That is, the user can specify the negative point 610(1) and the positive point 610(2) by clicking on the corresponding points of the ultrasound image 600 presented on the touch screen (e.g., display device 132) (e.g., using a mouse, finger, stylus, probe, etc.).

[0086] like Figure 6B As shown, the segmentation circuit 122 can be configured to adjust based on the negative point 610(1) and the positive point 610(2). Figure 6A The default segment 605a shown produces an adjusted segment 605b. More specifically, the adjusted segment 605b depicts a retracted region 615(1) based on a negative point 610(1) and an extended region 615(2) based on a positive point 610(2). The retracted region 615(1) refers to the portion of the default segment 605a removed from the adjusted segment 605b by the segmentation circuit 122 based on the negative point 610(1). In this way, the retracted region 615(1) shown along the adjusted segment 605b is configured to adjust the over-segmented region previously shown in the default segment 605a. Similarly, the extended region 615(2) refers to the portion of the default segment 605a added to the adjusted segment 605b by the segmentation circuit 122 based on the positive point 610(2). In this way, the extended region 615(2) shown along the adjusted segment 605b is configured to adjust the under-segmented region previously shown in the default segment 605a.

[0087] like Figure 6BAs shown, the retraction region 615(1) and the extension region 615(2) are not limited to the regions surrounding the negative point 610(1) and the positive point 610(2), respectively. Instead, the segmentation circuit 122 is configured to adjust the entire default segmentation 605a based on the negative point 610(1) and the positive point 610(2) using the pixels / voxels at each of the negative point 610(1) and the positive point 610(2) associated with the pixels / voxels of the entire default segmentation 605a.

[0088] refer to Figure 7A and Figure 7B An ultrasound image 700 is shown. The ultrasound image 700 can be acquired by the ultrasound imaging system 100 during a uterine examination and can depict multiple anatomical structures (e.g., multiple follicles). In some embodiments, the ultrasound image 700 can be a medical image as referred to in method 300 and / or method 400 described above. Furthermore, the ultrasound image 700 can be provided to a user of the ultrasound imaging system 100 via a display device 132.

[0089] like Figure 7A As shown, contour delineation / segmentation is performed on two anatomical structures out of multiple anatomical structures according to the default segmentation 705a. It should be understood that, although in Figure 7A and Figure 7B Only two anatomical structures are shown in the image, out of a plurality of anatomical structures delineated according to the default segmentation 705a, but any number of anatomical structures can be delineated according to the default segmentation 705a. The default segmentation 705a can be generated by the segmentation circuit 122 using a pre-existing segmentation algorithm. Alternatively or additionally, the default segmentation 705a can be generated by the segmentation circuit 122 using segmentation preferences 210 stored in a user profile 205 associated with the user performing the uterine examination. In some embodiments, the ultrasound image 700 with the default segmentation 705a is a medical image received at step 305 and presented to the user at step 310 of method 300.

[0090] The ultrasound image 700 is also shown as including a negative point 710(1) and a positive point 710(2). As described above, the negative point 710(1) specifies a point on the ultrasound image 700 to be excluded from the default segmentation 705a. The positive point 710(2) specifies a point on the ultrasound image 700 to be included in the default segmentation 705a. In other words, the negative point 710(1) is configured to adjust the default segmentation 705a in the case of oversegmentation, while the positive point 710(2) is configured to adjust the default segmentation 705a in the case of undersegmentation. In some embodiments, the negative point 710(1) and the positive point 710(2) are inputs received at step 315 of method 300. That is, the user can specify the negative point 710(1) and the positive point 710(2) by clicking on the corresponding points of the ultrasound image 700 presented on the touch screen (e.g., display device 132) using a mouse, finger, stylus, probe, etc. Figure 7A As shown, negative point 710(1) and positive point 710(2) can be specified on only one of the two anatomical structures delineated by the default segmentation 705a.

[0091] like Figure 7B As shown, the segmentation circuit 122 can be configured to adjust based on the negative point 710(1) and the positive point 710(2). Figure 7A The default segmentation 705a is shown, thereby producing an adjusted segmentation 705b. Although the negative point 710(1) and the positive point 710(2) are specified only on one of the two anatomical structures outlined by the default segmentation 705a, the adjusted segmentation 705b can be applied to both anatomical structures outlined by the default segmentation 705a. That is, the segmentation circuit 122 is configured to apply adjustments from the user (e.g., negative point 710(1) and positive point 710(2)) to any one of the multiple anatomical structures (e.g., applied to...). Figure 7A and Figure 7B (Any of the follicles shown).

[0092] More specifically, the adjusted segment 705b depicts a retracted region 715(1) based on a negative point 710(1) and an extended region 715(2) based on a positive point 710(2). The retracted region 715(1) refers to the portion of the default segment 705a removed from the adjusted segment 705b by the segmentation circuit 122 based on the negative point 710(1). In this way, the retracted region 715(1) shown along the adjusted segment 705b is configured to adjust the over-segmented region previously shown in the default segment 705a. Similarly, the extended region 715(2) refers to the portion of the default segment 705a added to the adjusted segment 705b by the segmentation circuit 122 based on the positive point 710(2). In this way, the extended region 715(2) shown along the adjusted segment 705b is configured to adjust the under-segmented region previously shown in the default segment 705a.

[0093] like Figure 7B As shown, the retraction region 715(1) and the extension region 715(2) are not limited to the regions surrounding the negative point 710(1) and the positive point 710(2), respectively. Instead, the segmentation circuit 122 is configured to adjust the entire default segmentation 705a based on the negative point 710(1) and the positive point 710(2) using the pixels / voxels at each of the negative point 710(1) and the positive point 710(2) associated with the pixels / voxels of the entire default segmentation 705a.

[0094] refer to Figure 8 The diagram illustrates a GUI 800 with selectable elements configured to allow a user (e.g., an operator of the ultrasound imaging system 100) to control the operation of the ultrasound imaging system 100 by selecting the selectable elements. In some embodiments, GUI 800 may be a GUI generated for display on a display device 132. Furthermore, GUI 800 may be configured as a touchscreen display, allowing a user to select one of the selectable elements by touching a corresponding location on the touchscreen display. Alternatively or additionally, each selectable element shown on GUI 800 may be configured as a hardware element (e.g., a physical button) included as part of the user interface 130.

[0095] As shown in the figure, GUI 800 includes an indication of user profile 805 and an option 810 to switch users. The indication of user profile 805 can be depicted as the name of the user of ultrasound imaging system 100 (e.g., the user identified at step 301 of method 300). Furthermore, the indication of user profile 805 can represent user profile 205 retrieved from memory 118, as described above. In this way, GUI 800 can be configured to reflect user preferences associated with user profile 205 (e.g., segmentation preference 210, etc.). The option 810 to switch users allows the user of ultrasound imaging system 100 to switch to a user profile other than the one currently indicated by the indication of user profile 805 (e.g., user profile 205).

[0096] The GUI is also shown as an ultrasound image 600 comprising a default segment 605a, a negative point 610(1), and a positive point 610(2), as referenced above. Figure 6A As described. Therefore, GUI 800 can be configured to allow the user of ultrasound imaging system 100 to adjust the default segmentation 605a by applying negative points 610(1) and positive points 610(2) via GUI 800. For example, GUI 800 includes instructions regarding ultrasound image 600 such as “Please indicate any negative points to exclude and / or positive points to include”.

[0097] like Figure 8As shown, selectable element 815 allows a user to adjust the default segmentation 605a by adding at least one of negative points (e.g., negative point 610(1)) or positive points (e.g., positive point 610(2)). For example, when “Add Positive Point” is selected from selectable element 815 displayed via GUI 800, any point on ultrasound image 600 subsequently selected by the user (e.g., click, tap, etc.) can be registered by segmentation circuit 122 as a point to be included in the adjusted segmentation (e.g., adjusted segmentation 605b) of the uterus depicted in ultrasound image 600. Alternatively or additionally, when “Add Negative Point” is selected from selectable element 815 displayed via GUI 800, any point on ultrasound image 600 subsequently selected by the user (e.g., click, tap, etc.) can be registered by segmentation circuit 122 to exclude points in the adjusted segmentation (e.g., adjusted segmentation 605b) of the uterus to be depicted in ultrasound image 600. After the user has specified the desired positive and negative points, the user can select “Done” from selectable element 815, which prompts segmentation circuit 122 to adjust the default segmentation 605a based on negative point 610(1) and positive point 610(2), and thus generate adjusted segmentation 605b. In this way, upon receiving an instruction from the user that "Complete" has been selected from selectable element 815, the GUI 800 can be updated such that the ultrasound image 600 is depicted on the GUI 800 as having an adjusted segmentation 605b including a retracted region 615(1) and an extended region 615(2), as shown. Figure 6B As shown.

[0098] 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.

[0099] 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 “device for…”.

[0100] 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.

[0101] 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.

[0102] As used herein, the term "connection" 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 linking the two components together, by using a separate intermediate component and any additional intermediate components connected to each other, or by utilizing an intermediate component integrally formed with one of the two components. If "connection" or its variations are modified by an additional term (e.g., direct connection), the general definition of "connection" provided above will be modified by the common linguistic meaning of the additional term (e.g., "direct connection" refers to the engagement of two components without any separate intermediate component), resulting in a narrower definition than the general definition of "connection" provided above. Such connections can be mechanical, electrical, or fluid.

[0103] 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 respectively.

[0104] 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.

[0105] 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.

[0106] 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 configured 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 executes instructions stored or otherwise accessed via different regions of memory).

[0107] 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 connected via a bus 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.

[0108] Example systems used to provide the overall system or part of the embodiments described herein may include one or more computers, including processing units, system memory, and a system bus that connects various system components, including the system memory, to the processing units. Each memory device may include non-transitory volatile storage media, non-volatile storage media, non-transitory storage media (e.g., one or more volatile and / or non-volatile memories), etc. In some embodiments, the non-volatile media 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 media 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.).

[0109] Although the accompanying drawings and description may illustrate 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.

[0110] The foregoing description of the embodiments has been provided 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; as well as Processing circuitry (114), including a processor (116) coupled to a memory device (118) storing instructions that, when executed, cause the processing circuitry (114) to perform operations, including: Ultrasonic images (600) and (700) are generated based on the image data obtained from the transducer. The segmentation algorithm (124) is used to segment the anatomical structures in the ultrasound images (600) and (700); The ultrasound images (600) and (700) are displayed on the display (132) of the ultrasound imaging system (100), the ultrasound images including the segmentation (605a) and (705a) of the anatomical structure; Input (215) from the user is received via the display (132), wherein the input (215) includes adjustments to the segmentation of the anatomical structure; The segmentation (605a) and (705a) of the anatomical structure are adjusted based on the input (215); The ultrasound images (600), (700) with adjusted segments (605b), (705b) having the anatomical structure are presented via the display (132); and The segmentation algorithm (124) is updated based on the input (215).

2. The ultrasound imaging system (100) of claim 1, wherein the input (215) includes at least one of a negative prompt (610(1)), (710(1)) or a positive prompt (610(2)), (710(2)), wherein the negative prompt (610(1)), (710(1)) specifies a point to be excluded from the segment (605a), (705a) of the anatomical structure, and wherein the positive prompt (610(2)), (710(2)) specifies a point to be included in the segment (605a), (705a) of the anatomical structure.

3. The ultrasound imaging system (100) of claim 2, wherein the input (215) includes the negative prompts (610(1)) and (710(1)), and wherein the segmentation (605a) and (705a) of adjusting the anatomical structure includes excluding a plurality of points along the contour of the anatomical structure based on the negative prompts (610(1)) and (710(1)).

4. The ultrasound imaging system (100) of claim 2, wherein the input (215) includes the positive cue (610(2)) and (710(2)), and wherein the segmentation (605a) and (705a) of adjusting the anatomical structure includes a plurality of points along the contour of the anatomical structure based on the positive cue (610(2)) and (710(2)).

5. The ultrasound imaging system (100) according to claim 1, wherein the anatomical structure is a first anatomical structure among a plurality of anatomical structures depicted by the ultrasound images (600), (700), and wherein the operation further comprises: The segmentation (605a), (705a) of the plurality of anatomical structures is adjusted according to the input (215); as well as The ultrasound images (600), (700) are presented to the user via the display (132), the ultrasound images having the adjusted segmentation (605b), (705b) of the plurality of anatomical structures.

6. The ultrasound imaging system (100) according to claim 1, wherein the operation further comprises: The ultrasound images (600), (700) of the adjusted segments (605b), (705b) without the anatomical structure are presented via the display (132).

7. The ultrasound imaging system (100) according to claim 6, wherein the operation further comprises: Receive from the user via the display (132) a selection (220) of either the ultrasound image (600), (700) of the adjusted segment (605b), (705b) without the anatomical structure or the ultrasound image (600), (700) of the adjusted segment (605b), (705b) with the anatomical structure; and The input (215) and the selection (220) from the user are stored so that the segmentation algorithm (124) applies the user preferences (210) associated with the input (215) and the selection (220) during the segmentation (605a), (705a) of the anatomical structures in the continuous ultrasound images.

8. The ultrasound imaging system (100) of claim 7, wherein the user selects the ultrasound image (600), (700) of the adjusted segmentation (605b), (705b) having the anatomical structure, and wherein the operation further comprises: Identify the anatomical structures in the continuous ultrasound images; as well as The segmentation algorithm (124) is used to segment the anatomical structure in the continuous ultrasound image based on the input (215) and the selection (220), such that after segmenting the anatomical structure in the continuous ultrasound image, the continuous ultrasound image is similar to the ultrasound image (600), (700) with the adjusted segmentation (605b), (705b) of the anatomical structure.

9. The ultrasound imaging system (100) of claim 1, wherein the segmentation algorithm (124) includes a machine learning model, and wherein the input (215) from the user is stored in a training database (212) for training the machine learning model.

10. A medical imaging system, the medical imaging system comprising: Processing circuit (114) having a processor (116) connected to a memory device (118) storing instructions that, when executed, cause the processing circuit (114) to perform operations, including: Generate medical images; The anatomical structures in the medical image are segmented using a segmentation algorithm (124); The medical image, including the segments (605a) and (705a) of the anatomical structure, is displayed on the display (132) of the medical imaging system; The display (132) receives input (215) from the user, wherein the input (215) includes adjustments to the divisions (605a), (705a) of the anatomical structure; The segmentation (605a) and (705a) of the anatomical structure are adjusted based on the input (215); The medical image, with adjusted segments (605b) and (705b) showing the anatomical structure, is presented via the display (132); and The segmentation algorithm (124) is updated based on the input (215) from the user.

11. The medical imaging system of claim 10, wherein the medical imaging system comprises an ultrasound imaging system (100), the ultrasound imaging system comprising: A transducer configured to transmit and receive ultrasonic signals; A matching layer, configured to have acoustic impedance between the tissue to be imaged and the material of the transducer; and A damping block configured to absorb ultrasonic energy.

12. The medical imaging system of claim 10, wherein the anatomical structure is depicted as a two-dimensional or three-dimensional structure in the medical image.

13. The medical imaging system of claim 10, wherein the input (215) includes at least one of a negative prompt (610(1)), (710(1)) or a positive prompt (610(2)), (710(2)), wherein the negative prompt (610(1)), (710(1)) specifies a point to be excluded from the segment (605a), (705a) of the anatomical structure, and wherein the positive prompt (610(2)), (710(2)) specifies a point to be included in the segment (605a), (705a) of the anatomical structure.

14. The medical imaging system of claim 13, wherein the anatomical structure is a first anatomical structure among a plurality of anatomical structures depicted by the medical image, and wherein the operation further comprises: The segmentation (605a), (705a) of the plurality of anatomical structures is adjusted according to the input (215); as well as The medical image, with its adjusted segments (605b) and (705b) having the plurality of anatomical structures, is presented to the user via the display (132).

15. The medical imaging system of claim 10, wherein the operation further comprises: The medical image of the adjusted segmentation (605b), (705b) without the anatomical structure is presented via the display (132); The user receives a selection (220) from the display (132) of either the medical image of the adjusted segment (605b), (705b) without the anatomical structure or the medical image of the adjusted segment (605b), (705b) with the anatomical structure. as well as The input (215) and the selection (220) from the user are stored so that the segmentation algorithm (124) applies the user preferences (210) associated with the input (215) and the selection (220) during the segmentation (605a), (705a) of the anatomical structures in the continuous medical images.

Images