System for strain imaging in contrast echocardiography

Abstract

The system (110) can receive (510) contrast-enhanced ultrasound data of an anatomical structure of a heart of a subject during a first cardiac cycle of the heart of the subject, and receive (520) non-enhanced ultrasound data of the anatomical structure of the heart of the subject during a second cardiac cycle of the heart of the subject. The system (110) can determine (530) a first region of interest (ROI) of the anatomical structure in the contrast-enhanced ultrasound data, and determine (540) a second ROI of the anatomical structure in the non-enhanced ultrasound data based on the first ROI of the anatomical structure in the contrast-enhanced ultrasound data. The system (110) can perform (550) joint strain imaging using the first ROI in the contrast-enhanced ultrasound data and the second ROI in the non-enhanced ultrasound data. The system (110) can determine (560) and display (570) information related to cardiac deformation of the anatomical structure of the heart of the subject.

Description

Technical Field

[0001] This disclosure relates throughout to a system for performing combined strain imaging using contrast-enhanced ultrasound data and non-contrast ultrasound data. More specifically, this disclosure relates to a system that receives contrast-enhanced ultrasound data of the anatomy of a subject's heart corresponding to a first cardiac cycle, receives non-contrast ultrasound data of the anatomy of a subject's heart corresponding to a second cardiac cycle, uses the contrast-enhanced ultrasound data to determine a region of interest (ROI) of the anatomy of the subject's heart, and uses the ROI to perform combined strain imaging relative to the contrast-enhanced ultrasound data and the non-contrast ultrasound data. Background Technology

[0002] Strain imaging refers to imaging techniques used to assess myocardial deformation. Strain refers to the change in the length of the myocardium from end-diastole to end-systole. Strain imaging can be used to assess myocardial mechanics. For example, strain imaging can be used to detect cardiomyopathy, heart disease, and myocardial dysfunction. For strain imaging using ultrasound data, the region of interest (ROI) of the heart can be segmented into a set of myocardial segments in the ultrasound data. Myocardial segments can be tracked during the cardiac cycle using strain imaging techniques (e.g., template matching, image registration, artificial intelligence (AI) techniques, etc.) and ultrasound data. Strain values ​​for the set of myocardial segments can be determined based on the tracking of myocardial segments. For example, a strain curve or "strain trace" that includes the strain values ​​of myocardial segments during the cardiac cycle can be determined. Various relevant strain values ​​(e.g., end-systolic strain, peak systolic strain, peak strain, etc.) can be determined from the strain curve.

[0003] Contrast-enhanced echocardiography, also known as contrast-enhanced ultrasound, is an ultrasound imaging technique that utilizes an acoustically active contrast agent (e.g., microbubbles) that circulates through the cardiovascular system during ultrasound imaging. The contrast agent produces a highly reflective ultrasound image. In this way, contrast-enhanced ultrasound is particularly useful for enhancing the visualization of endocardial boundaries. Contrast-enhanced ultrasound may involve pulse inversion techniques, which enhance contrast resolution by sending pairs of ultrasound signals with opposite phases and combining the received echo signals to cancel out tissue signals while enhancing the signal from the contrast agent. This technique improves the depiction of endocardial boundaries. In this way, contrast-enhanced ultrasound can be beneficial for strain imaging because it estimates myocardial length more accurately than non-contrast-enhanced echocardiography (e.g., B-mode echocardiography), especially in patients with hypertrophic cardiomyopathy.

[0004] However, contrast-enhanced ultrasound can provide very weak tissue signals, leading to a decrease in the acquisition frame rate and reduced visibility of the mitral hinge point. All of these factors can inhibit the accuracy and power of strain imaging using contrast-enhanced ultrasound. For example, due to the specific imaging settings used for contrast-enhanced ultrasound, the frame rate often drops below the minimum required for strain imaging. Furthermore, contrast-enhanced ultrasound in strain imaging may not form recognizable features that persist throughout the cardiac cycle in the basal region. This can make it difficult to distinguish tissue from chambers, especially when the myocardium is thin. This adversely affects the accuracy of strain imaging. Basal points can be critical landmarks in strain imaging and act as a major driver of longitudinal strain. If tracking of these basal points fails, global longitudinal strain may be inaccurate. In non-contrast ultrasound, these regions are robust features to be tracked during strain imaging. Additionally, the contrast echo signal can suppress tissue signals. Therefore, it may not be possible to define and track segmental longitudinal boundaries using contrast-enhanced ultrasound.

[0005] Non-contrast ultrasound may underestimate left ventricular volume. In contrast, contrast-enhanced ultrasound can improve accuracy by making the endocardial boundaries clearer, which leads to better agreement between measurements and cardiac magnetic resonance imaging (CMR). Furthermore, contrast-enhanced ultrasound improves the accuracy and reproducibility of global strain measurements, resulting in better agreement with CMR, even in patients with suboptimal acoustic windows.

[0006] Strain imaging algorithms may struggle to track various structures in contrast-enhanced ultrasound data because these structures may lack identifiable features. When a region of interest (ROI) is placed in this region, the ROI typically descends into the left atrium (LA) or left ventricle (LV) chamber during strain imaging, which can lead to incorrect global longitudinal strain.

[0007] To accurately report segmented strain on contrast-enhanced ultrasound images, it may be important to effectively track the longitudinal segmental boundaries over time. However, due to the very low signal intensity of tissue, tracking these boundaries using contrast-enhanced ultrasound becomes challenging and makes it difficult to report accurate segmented strain.

[0008] Given the foregoing, non-contrast ultrasound may not provide a clear depiction of the myocardium, but it offers a high frame rate. Furthermore, non-contrast ultrasound provides robust acoustic markers suitable for strain imaging. Contrast-enhanced ultrasound suffers from a low frame rate and does not provide strong markers for tissue tracking. However, contrast-enhanced ultrasound can provide very accurate myocardial boundary delineation with the correct myocardial layer length. Summary of the Invention

[0009] This invention provides a more detailed description of the concepts described in the specific embodiments. It should not be used to identify the essential features of the claimed subject matter, nor should it be used to limit the scope of the claimed subject matter.

[0010] In one aspect, a system may include: a lens, an acoustic matching layer, an acoustic dematching layer, and a plurality of transducer elements; a memory configured to store instructions; and one or more processors configured to execute instructions to: receive contrast-enhanced ultrasound data of the anatomical structure of the subject's heart during a first cardiac cycle of the subject's heart; receive non-enhanced ultrasound data of the anatomical structure of the subject's heart during a second cardiac cycle of the subject's heart; determine a first region of interest (ROI) of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data; determine a second ROI of the anatomical structure of the subject's heart in the non-enhanced ultrasound data based on the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data; perform combined strain imaging using the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data and the second ROI of the anatomical structure of the subject's heart in the non-enhanced ultrasound data; determine information related to cardiac deformation of the anatomical structure of the subject's heart based on the performance of combined strain imaging; and display information related to cardiac deformation of the anatomical structure of the subject's heart.

[0011] In another aspect, a method may include: receiving contrast-enhanced ultrasound data of the anatomical structure of the subject's heart during a first cardiac cycle; receiving non-enhanced ultrasound data of the anatomical structure of the subject's heart during a second cardiac cycle; determining a first region of interest (ROI) of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data; determining a second ROI of the anatomical structure of the subject's heart in the non-enhanced ultrasound data based on the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data; performing combined strain imaging using the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data and the second ROI of the anatomical structure of the subject's heart in the non-enhanced ultrasound data; determining information related to cardiac deformation of the anatomical structure of the subject's heart based on the combined strain imaging; and displaying information related to cardiac deformation of the anatomical structure of the subject's heart.

[0012] In another aspect, a non-transitory computer-readable medium may store instructions that, when executed by one or more processors, cause the one or more processors to: receive contrast-enhanced ultrasound data of the anatomical structure of the subject's heart during a first cardiac cycle of the subject's heart; receive non-enhanced ultrasound data of the anatomical structure of the subject's heart during a second cardiac cycle of the subject's heart; determine a first region of interest (ROI) of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data; determine a second ROI of the anatomical structure of the subject's heart in the non-enhanced ultrasound data based on the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data; perform combined strain imaging using the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data and the second ROI of the anatomical structure of the subject's heart in the non-enhanced ultrasound data; determine information related to cardiac deformation of the anatomical structure of the subject's heart based on the performance of combined strain imaging; and display information related to cardiac deformation of the anatomical structure of the subject's heart. Attached Figure Description

[0013] Figure 1 This is an illustration of an exemplary system for performing combined strain imaging using contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data.

[0014] Figure 2 This is a diagram of an exemplary strain imaging system for performing combined strain imaging using contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data.

[0015] Figure 3 This is a diagram of an exemplary ultrasound system used to acquire and compare contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data.

[0016] Figure 4 This is a diagram of an exemplary preoperative imaging system for receiving preoperative imaging data of regions of interest representing the anatomical features of a subject's heart.

[0017] Figure 5 This is a flowchart of an exemplary procedure for performing combined strain imaging using contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data.

[0018] Figure 6 This is a graph comparing contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data.

[0019] Figure 7 This is a diagram comparing the first ROI in contrast-enhanced ultrasound data with the second ROI in non-contrast-enhanced ultrasound data.

[0020] Figure 8 This is a diagram comparing the tracking points in contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data.

[0021] Figure 9This is an illustration of an exemplary user interface for displaying information related to cardiac deformities in relation to the anatomical structure of the subject's heart.

[0022] Figure 10 This is an illustration of an exemplary user interface for displaying information related to cardiac deformities in relation to the anatomical structure of the subject's heart. Detailed Implementation

[0023] As mentioned above, strain imaging can be performed using either non-contrast-enhanced ultrasound data or contrast-enhanced ultrasound data. Each type of ultrasound data has its own advantages and disadvantages for performing strain imaging. For example, non-contrast-enhanced ultrasound data offers a high frame rate and provides robust acoustic markers suitable for strain imaging, but may not provide a clear depiction of the myocardium. Contrast-enhanced ultrasound data can provide very accurate myocardial boundary delineation with correct myocardial layer length, but may not offer a high frame rate and may not provide strong markers for tissue tracking.

[0024] This disclosure provides an image acquisition mode that operates over multiple complete cardiac cycles following contrast agent injection. The cardiac cycles utilize contrast-enhanced ultrasound (e.g., a contrast agent-specific imaging setting), and subsequent cardiac cycles utilize non-enhanced ultrasound (e.g., a mode B imaging setting). Contrast-enhanced ultrasound produces a clear depiction of myocardial boundaries and length. Non-enhanced ultrasound provides high frame rate scans with robust acoustic markers for strain imaging, as well as well-defined longitudinal segmental boundaries. Regions of interest (ROIs) can be automatically extracted from the cardiac cycles associated with contrast-enhanced ultrasound. The ROIs can be used to perform joint strain imaging.

[0025] By utilizing both contrast-enhanced and non-contrast-enhanced ultrasound data and performing combined strain imaging, the embodiments described herein achieve improvements in the field of strain imaging by more accurately determining information related to cardiac deformation in relation to the anatomical structure of the subject's heart. Furthermore, in this way, some embodiments described herein provide improvements to strain imaging systems by allowing strain imaging systems to more accurately determine information related to cardiac deformation in relation to the anatomical structure of the subject's heart.

[0026] More specifically, according to one embodiment, the system can receive contrast-enhanced ultrasound data of the anatomical structure of the subject's heart during a first cardiac cycle; receive ultrasound data of the anatomical structure of the subject's heart during a second cardiac cycle; determine a first region of interest (ROI) of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data; determine a second ROI of the anatomical structure of the subject's heart in the ultrasound data based on the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data; perform combined strain imaging using the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data and the second ROI of the anatomical structure of the subject's heart in the ultrasound data; determine information related to cardiac deformation of the anatomical structure of the subject's heart based on the combined strain imaging; and display information related to cardiac deformation of the anatomical structure of the subject's heart.

[0027] Figure 1 This is an illustration of an exemplary system for performing combined strain imaging using contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data. Figure 1 As shown, system 100 may include strain imaging system 110, ultrasound system 120, preoperative imaging system 130 and network 140.

[0028] The strain imaging system 110 can be configured to receive contrast-enhanced ultrasound data of the anatomical structure of the subject's heart during a first cardiac cycle; receive ultrasound data of the anatomical structure of the subject's heart during a second cardiac cycle; determine a first region of interest (ROI) of the subject's heart anatomical structure in the contrast-enhanced ultrasound data; determine a second region of interest (ROI) of the subject's heart anatomical structure in the ultrasound data based on the first ROI of the subject's heart anatomical structure in the contrast-enhanced ultrasound data; perform combined strain imaging using the first ROI of the subject's heart anatomical structure in the contrast-enhanced ultrasound data and the second ROI of the subject's heart anatomical structure in the ultrasound data; determine information related to cardiac deformation of the subject's heart anatomical structure based on the performed combined strain imaging; and display information related to cardiac deformation of the subject's heart anatomical structure. For example, the strain imaging system 110 can be a computer, server, medical device, etc.

[0029] The ultrasound system 120 can be configured to acquire contrast-enhanced ultrasound data of the anatomical features of a subject's heart, and can also be configured to acquire non-contrast ultrasound data of the anatomical features of a subject's heart. For example, the ultrasound system 120 can be a two-dimensional (2D) ultrasound system, a three-dimensional (3D) ultrasound system, a four-dimensional (4D) ultrasound system, a Doppler ultrasound system, etc. The subject can be a human, animal, or phantom, etc.

[0030] The preoperative imaging system 130 can be configured to receive preoperative imaging data of the region of interest of the patient's heart. For example, the preoperative imaging system 130 can be a computed tomography (CT) system, a magnetic resonance imaging (MRI) system, an ultrasound system, an X-ray system, or a positron emission tomography (PET) device.

[0031] Network 140 may permit communication between strain imaging system 110, ultrasound system 120, and preoperative imaging system 130. For example, network 140 may be a local area network (LAN), wide area network (WAN), metropolitan area network (MAN), cellular network, private network, ad hoc network, intranet, Internet, fiber-optic network, wired network, wireless network, and / or a combination of these or other types of networks.

[0032] The number and arrangement of systems 100 are provided as examples. In implementation, systems 100 may include additional systems, fewer systems, different systems, or systems related to... Figure 1 The systems shown are arranged differently. Additionally or alternatively, the collection of systems of system 100 (e.g., one or more systems) may be integrated into a single system and / or perform one or more functions described as being performed by another system or another collection of systems of system 100.

[0033] Figure 2 This is an illustration of an exemplary strain imaging system for performing combined strain imaging using contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data. Figure 2 As shown, the strain imaging system 110 may include a bus 202, a processor 204, a memory 206, a storage component 208, an input component 210, an output component 212, and a communication interface 214.

[0034] Bus 202 includes components that allow communication between components of strain imaging system 110. Processor 204 can be implemented in hardware, firmware, or a combination of hardware and software. Processor 204 can be a central processing unit (CPU), graphics processing unit (GPU), accelerated processing unit (APU), microprocessor, microcontroller, digital signal processor (DSP), field-programmable gate array (FPGA), application-specific integrated circuit (ASIC), or another type of processing component.

[0035] Processor 204 may include one or more processors capable of being programmed to perform functions. Processor 204 may include one or more processors 204 configured to perform the operations described herein. For example, a single processor 204 may be configured to perform all the operations described herein. Alternatively, multiple processors 204 may be collectively configured to perform all the operations described herein, and each of the multiple processors 204 may be configured to perform a subset of the operations described herein. For example, a first processor 204 may perform a first subset of the operations described herein, a second processor 204 may be configured to perform a second subset of the operations described herein, and so on.

[0036] Memory 206 may include random access memory (RAM), read-only memory (ROM), and / or another type of dynamic or static storage device (e.g., flash memory, magnetic memory, and / or optical memory) that stores information and / or instructions for use by processor 204.

[0037] Storage component 208 may store information and / or software related to the operation and use of strain imaging system 110. For example, storage component 208 may include hard disk (e.g., magnetic disk, optical disk, magneto-optical disk and / or solid-state disk), compact disc (CD), digital multifunction disc (DVD), floppy disk, cassette, magnetic tape and / or another type of non-transitory computer-readable medium and corresponding drives.

[0038] Input component 210 may include components that allow strain imaging system 110 to receive information, such as via user input (e.g., touchscreen display, keyboard, keypad, mouse, buttons, switches, camera, and / or microphone). Additionally or alternatively, input component 210 may include sensors for sensing information (e.g., a Global Positioning System (GPS) component, accelerometer, gyroscope, and / or actuator). Output component 212 may include components that provide output information from strain imaging system 110 (e.g., a display, a speaker for outputting sound at an output sound level, and / or one or more light-emitting diodes (LEDs)).

[0039] Communication interface 214 may include transceiver-like components (e.g., a transceiver and / or separate receiver and transmitter) that enable strain imaging system 110 to communicate with other systems, such as via wired, wireless, or a combination of wired and wireless connections. Communication interface 214 may allow strain imaging system 110 to receive information from and / or provide information to another system. For example, communication interface 214 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi interface, or a cellular network interface, etc.

[0040] The strain imaging system 110 can perform one or more of the processes described herein. The strain imaging system 110 can perform these processes based on software instructions stored in non-transitory computer-readable media such as memory 206 and / or storage components 208, executed by processor 204. Computer-readable media can be defined herein as non-transitory memory devices. Memory devices can include memory space within a single physical storage device or memory space distributed across multiple physical storage devices.

[0041] Software instructions can be read from another computer-readable medium or from another system into memory 206 and / or storage component 208 via communication interface 214. When executed, the software instructions stored in memory 206 and / or storage component 208 can cause processor 204 to perform one or more processes described herein. Additionally or alternatively, hardwired circuitry may be used in place of or in combination with software instructions to perform one or more processes described herein. Therefore, the specific implementations described herein are not limited to any particular combination of hardware circuitry and software.

[0042] Figure 2 The number and arrangement of components shown are provided as an example. In practice, the strain imaging system 110 may include additional components, fewer components, different components, or components similar to those in the original system. Figure 2 The components shown are arranged differently. Additionally or alternatively, the set of components of strain imaging system 110 (e.g., one or more components) can perform one or more functions described as being performed by another set of components of strain imaging system 110.

[0043] Figure 3 This is an illustration of an exemplary ultrasound system used to acquire contrast-enhanced ultrasound data and non-contrast ultrasound data of a region of interest in a subject's heart. Figure 3 As shown, the ultrasound system 120 may include an ultrasound probe 302, a transmit beamformer 304, a transmitter 306, an element 308, a receiver 310, a receive beamformer 312, a user input device 314, a processor 316, a display 318, a memory 320, and a communication interface 322. The aforementioned components may be connected via wired or wireless connections.

[0044] The ultrasound probe 302 can be configured to receive ultrasound data. For example, the ultrasound probe 302 can be a linear probe, a phased array probe, a curved linear probe coupled to a positioning and tracking system, a mechanically manipulated linear array transducer, a phased array transducer, a curved linear array transducer, an electronically manipulated 2D transducer array, an electronic 3D (e3D) probe, an electronic 4D (e4D) probe, or a low-profile wearable patch version of any of the aforementioned probes. According to one embodiment, the ultrasound probe 302 can be configured to generate ultrasound signals, emit ultrasound signals toward the region of interest of a subject, receive echo ultrasound signals backscattered from the region of interest of the subject, generate ultrasound data based on the echo ultrasound signals, and output ultrasound data. The ultrasound probe 302 may include a lens, an acoustic matching layer, a transducer element 308, an acoustic dematching layer, and a backing layer.

[0045] According to one embodiment, the lens can be configured to direct the ultrasonic signal toward the region of interest of the subject. For example, the lens can be made of silicone, epoxy resin, rubber, etc. According to one embodiment, an acoustic matching layer can be configured to facilitate impedance matching, which can exist between a relatively high-impedance transducer element and a relatively low-impedance subject. For example, the acoustic matching layer can be made of graphite, plastic, resin, etc. According to one embodiment, transducer elements 308 can be configured to receive element-specific transmitted signals, convert element-specific transmitted signals into ultrasonic signals, and transmit ultrasonic signals toward the region of interest. Additionally or alternatively, transducer element 308 can be configured to receive echo signals reflected or backscattered from the region of interest, convert the echo signals into electrical signals, and transmit electrical signals. For example, transducer element 308 can be a piezoelectric material, such as Pb(Mg) 1 / 3 Nb 2 / 3 )O3-PbTiO3 ("PMN-PT"), Pb(In 1 / 2Nb 1 / 2 O3-Pb(Mg) 1 / 3 Nb 2 / 3 Examples of suitable acoustic dematching layers include tungsten carbide, silicon carbide, etc. According to one embodiment, the acoustic dematching layer can be configured to reduce insertion loss and enhance the frequency bandwidth of the transducer element 308. For example, the acoustic dematching layer can be tungsten carbide, silicon carbide, etc. According to one embodiment, the backing layer can be configured to attenuate the ultrasonic signal guided from the transducer element 308 in the opposite direction to the subject, and to attenuate the ultrasonic signal deflected by the housing of the ultrasonic probe 302. For example, the backing layer can be epoxy resin, metal, etc.

[0046] Transmit beamformer 304 can be configured to apply a delay time to the electrical signal provided to element 308 to focus the corresponding ultrasonic signal at the region of interest. Transmitter 306 can be configured to send an electrical signal to element 308 to drive element 308 to transmit an ultrasonic signal toward the region of interest. Element 308 can be configured to receive the electrical signal from transmitter 306, convert the electrical signal into an ultrasonic signal, and transmit the ultrasonic signal toward the region of interest. Element 308 can be configured to receive the echo ultrasonic signal backscattered from the region of interest, convert the echo ultrasonic signal into an electrical signal, and provide the electrical signal to receiver 310. Receiver 310 can be configured to receive the electrical signal from element 308 and provide the electrical signal to receiver beamformer 312. Receiver beamformer 312 can apply a delay time to the electrical signal received from element 308.

[0047] User input device 314 can be configured to receive user input and provide the user input to processor 316. For example, user input device 314 may be a touch screen display, keyboard, keypad, mouse, button, switch, or microphone, etc. Additionally or alternatively, user input device 314 can be configured to sense information. For example, user input device 314 may sense information from an electromagnetic positioning system, inertial measurement system, accelerometer, gyroscope, or actuator, etc.

[0048] Processor 316 may be configured to perform the operations described herein. For example, processor 316 may be a CPU, GPU, APU, microprocessor, microcontroller, DSP, FPGA, ASIC, or another type of processing component. Processor 316 may be implemented in hardware, firmware, or a combination of hardware and software. Processor 316 may include one or more processors 316 configured to perform the operations described herein. For example, a single processor 316 may be configured to perform all the operations described herein. Alternatively, multiple processors 316 may be collectively configured to perform all the operations described herein, and each of the multiple processors 316 may be configured to perform a subset of the operations described herein. For example, a first processor 316 may perform a first subset of the operations described herein, a second processor 316 may be configured to perform a second subset of the operations described herein, and so on.

[0049] Processor 316 can be configured to control ultrasound probe 302 to receive ultrasound data. Processor 316 can be configured to control which elements in element 308 are active and to control the shape of the beam emitted from ultrasound probe 302. Processor 316 can generate ultrasound images for display. For example, processor 316 can generate B-mode images, color Doppler images, anatomical M-mode images, or color M-mode images, etc. Ultrasound images can be 3D images, 2D images, single-plane images, dual-plane images, tri-plane images, or multi-plane images, etc. Ultrasound images can correspond to various anatomical planes (e.g., sagittal, coronal, and transverse) of the region of interest.

[0050] Display 318 can be configured to display information. For example, display 318 can be a monitor, LED display, cathode ray tube, projection display, touch screen, tablet computer, mobile phone, etc. Display 318 can display ultrasound images based on ultrasound data in real time. For example, display 318 can display ultrasound images within one second, two seconds, five seconds, etc., of ultrasound data received by ultrasound probe 302.

[0051] Memory 320 may be configured to store information and / or instructions for use by processor 316. Memory 320 may be a non-transitory computer-readable medium. For example, memory 320 may be random access memory (RAM), read-only memory (ROM), and / or another type of dynamic or static storage device (e.g., flash memory, magnetic memory, and / or optical memory) for storing information and / or instructions for use by processor 316. Memory 320 may be configured to store instructions that, when executed by processor 316, cause processor 316 to perform the operations described herein.

[0052] The communication interface 322 can be configured to enable the processor 316 to communicate with other systems, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. For example, the communication interface 322 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, an RF interface, a USB interface, a Wi-Fi interface, a cellular network interface, etc.

[0053] Figure 3 The number and arrangement of components in the ultrasound system 120 shown are provided as an example. In practice, the ultrasound system 120 may include additional components, fewer components, different components, or components related to... Figure 3 The components shown are arranged differently. Additionally or alternatively, the assembly of components of the ultrasound system 120 (e.g., one or more components) can perform one or more functions described as being performed by another assembly of components of the ultrasound system 120.

[0054] Figure 4This is an illustration of an exemplary preoperative imaging system for receiving preoperative imaging data of regions of interest representing the anatomical features of a subject's heart. Figure 4 As shown, the preoperative imaging system 130 may include a gantry 402, a rotating frame 404, an X-ray source 406, an X-ray detector 408, an examination table 410, a processor 412, a memory 414, a display 416, a user input device 418, a communication interface 420, a picture archiving and communication system (PACS) 422, and a server 424.

[0055] Processor 412 can be configured to control the operation of preoperative imaging system 130. For example, processor 412 can be a CPU, GPU, APU, microprocessor, microcontroller, DSP, FPGA, or ASIC. Processor 412 can be implemented in hardware, firmware, or a combination of hardware and software. Processor 412 can include one or more processors 412 configured to perform the operations described herein. For example, a single processor 412 can be configured to perform all the operations described herein. Alternatively, multiple processors 412 can be collectively configured to perform all the operations described herein, and each of the multiple processors 412 can be configured to perform a subset of the operations described herein. For example, a first processor 412 can perform a first subset of the operations described herein, a second processor 412 can be configured to perform a second subset of the operations described herein, and so on.

[0056] The processor 412 can be configured to control the movement of the rack 402, the rotating frame 404, the X-ray source 406, the X-ray detector 408, and the inspection table 410.

[0057] Memory 414 may be configured to store information and / or instructions for use by processor 412. Memory 414 may be a non-transitory computer-readable medium. For example, memory 414 may be RAM, ROM, flash memory, magnetic memory, or optical memory, etc. Memory 414 may be configured to store instructions that, when executed by processor 412, cause processor 412 to perform the operations described herein.

[0058] Display 416 can be configured to display information. For example, display 416 can be a monitor, LED display, cathode ray tube, projection display, touch screen, tablet computer, or mobile phone, etc.

[0059] User input device 418 can be configured to receive user input and provide the user input to processor 412. For example, user input device 418 may be a touch screen display, keyboard, keypad, mouse, button, switch, or microphone, etc. Additionally or alternatively, user input device 418 can be configured to sense information. For example, user input device 418 may sense information from an electromagnetic positioning system, inertial measurement system, accelerometer, gyroscope, or actuator, etc.

[0060] Communication interface 420 can be configured to enable processor 412 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. For example, communication interface 420 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, an RF interface, a USB interface, a Wi-Fi interface, or a cellular network interface. PACS 422 can be configured to communicate with external systems and / or networks to allow users at various locations to access medical images. Server 424 can be configured to store one or more models as described herein. For example, server 424 may be a local server, a cloud server, or a virtual machine.

[0061] Figure 4 The number and arrangement of components of the preoperative imaging system 130 shown are provided as an example. In practice, the preoperative imaging system 130 may include additional components, fewer components, different components, or components related to... Figure 4 The components shown are arranged differently. Additionally or alternatively, the set of components of the preoperative imaging system 130 (e.g., one or more components) can perform one or more functions described as being performed by another set of components of the preoperative imaging system 130.

[0062] Figure 5 This is a flowchart of an exemplary procedure 500 for performing combined strain imaging using contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data.

[0063] like Figure 5 As shown, process 500 may include receiving contrast-enhanced ultrasound data of the anatomical structures of the subject's heart during the first cardiac cycle of the subject's heart (operation 510). For example, strain imaging system 110 may receive contrast-enhanced ultrasound data of the anatomical structures of the subject's heart during the first cardiac cycle of the subject's heart.

[0064] According to one implementation plan, the anatomical structures of the heart can include the left atrium, left ventricle, right atrium, right ventricle, mitral valve, aortic valve, pulmonary valve, tricuspid valve, etc. The subject of the examination can be a patient, animal, or phantom. Although the implementation plan described in this article is in conjunction with cardiac structures, it should be understood that the implementation plan described in this article applies to non-cardiac structures.

[0065] According to one implementation, contrast-enhanced ultrasound data can be acquired during the first cardiac cycle of the subject's heart. For example, the first cardiac cycle can be a specific cardiac cycle of the subject's heart. According to one implementation, contrast-enhanced ultrasound data can be acquired at a first frame rate. For example, the first frame rate can be any frame rate used for acquiring contrast-enhanced ultrasound data. As an example, the first frame rate could be fifty frames per second, fifty-five frames per second, sixty frames per second, etc.

[0066] According to one embodiment, contrast-enhanced echocardiography can be used to acquire contrast-enhanced ultrasound data. For example, ultrasound system 120 can use contrast-enhanced echocardiography to acquire contrast-enhanced ultrasound data and provide such data to strain imaging system 110. It should be understood that in some embodiments, strain imaging system 110 and ultrasound system 120 may be the same underlying system.

[0067] like Figure 5 As further shown, process 500 may include receiving non-contrast ultrasound data of the anatomy of the subject's heart during the second cardiac cycle of the subject's heart (operation 520). For example, strain imaging system 110 may receive non-contrast ultrasound data of the anatomy of the subject's heart during the second cardiac cycle of the subject's heart.

[0068] According to one embodiment, non-contrast ultrasound data can be acquired during a second cardiac cycle of the subject's heart. For example, the second cardiac cycle can be a specific cardiac cycle of the subject's heart. The second cardiac cycle can be a subsequent cardiac cycle relative to the first cardiac cycle. For example, the second cardiac cycle can be a cardiac cycle immediately following the first cardiac cycle. Alternatively, one or more intermediate cardiac cycles may exist between the first and second cardiac cycles. Due to the higher mechanical index in the non-contrast imaging mode, switching from contrast acquisition to non-contrast acquisition may destroy the contrast agent. Therefore, the strain imaging system 110 can set the second cycle to be suitable for strain imaging. To avoid any potential residual effects, the strain imaging system 110 can avoid acquiring non-contrast ultrasound data until multiple cardiac cycles have occurred before acquiring the non-contrast ultrasound data. Alternatively, the second cardiac cycle can be the same cardiac cycle as the first cardiac cycle. To reiterate, the strain imaging system 110 can acquire contrast-enhanced ultrasound data of the subject's cardiac anatomy during a specific cardiac cycle using contrast-enhanced echocardiography, and can also acquire non-enhanced ultrasound data of the subject's cardiac anatomy during the same specific cardiac cycle using echocardiography. This technique eliminates the time shift between contrast-enhanced and non-enhanced ultrasound data. Furthermore, this technique eliminates the need for interpolation.

[0069] According to one implementation, non-contrast ultrasound data can be acquired at a second frame rate. For example, the second frame rate can be any frame rate used for acquiring non-contrast ultrasound data and can be greater than the first frame rate. As an example, the second frame rate could be 150 frames per second, 155 frames per second, 160 frames per second, etc. Furthermore, as another example, if the first frame rate is 50 frames per second, the second frame rate could be 150 frames per second.

[0070] According to one embodiment, non-contrast echocardiography can be used to acquire non-contrast ultrasound data. For example, ultrasound system 120 can use non-contrast echocardiography (e.g., B-mode imaging) to acquire non-contrast ultrasound data and provide the non-contrast ultrasound data to strain imaging system 110.

[0071] like Figure 5 As further shown, process 500 may include determining a first region of interest (ROI) of the anatomical structure of the subject's heart in contrast-enhanced ultrasound data (operation 530). For example, strain imaging system 110 may determine the first ROI of the anatomical structure of the subject's heart in contrast-enhanced ultrasound data.

[0072] According to one embodiment, the strain imaging system 110 can use image processing techniques to determine a first ROI of the anatomical structure of the subject's heart in contrast-enhanced ultrasound data. For example, the image processing techniques may include segmentation techniques, pattern matching techniques, feature extraction techniques, image analysis techniques, edge detection techniques, image registration techniques, etc. In this case, the strain imaging system 110 can use image processing techniques to analyze the contrast-enhanced ultrasound data and determine the first ROI of the subject's heart based on this analysis.

[0073] According to one implementation, the strain imaging system 110 can use an AI model to determine a first Region of Interest (ROI) of the anatomical structure of the subject's heart in contrast-enhanced ultrasound data. The AI ​​model can be a convolutional neural network (CNN) model, a residual neural network, a random forest model, a decision tree model, an artificial neural network (ANN), a naive Bayes model, a decision tree, a recurrent neural network (RNN), a logistic regression model, a support vector machine, etc. Additionally or alternatively, the AI ​​model can be a segmentation model, such as an edge-based segmentation model, a clustering-based segmentation model, a neural network-based segmentation model, a region-based segmentation model, etc. In this case, the strain imaging system 110 can input the contrast-enhanced ultrasound data into the AI ​​model and determine the first ROI based on the output of the AI ​​model.

[0074] According to one embodiment, strain imaging system 110 can use preoperative imaging data of the subject's cardiac anatomy acquired by preoperative imaging system 130 to determine a first ROI of the subject's cardiac anatomy in contrast-enhanced ultrasound data. For example, strain imaging system 110 can register contrast-enhanced ultrasound data with preoperative images from a preoperative imaging dataset acquired by preoperative imaging system 130 that identifies the first ROI of the cardiac anatomy, and determine the first ROI of the cardiac anatomy based on the registration of contrast-enhanced ultrasound data with preoperative images. In this case, the preoperative imaging data may identify one or more flow regions. In one embodiment, preoperative imaging data can be automatically analyzed to determine the first ROI of the cardiac anatomy. Alternatively, the first ROI of the cardiac anatomy can be manually labeled using the first ROI of the cardiac anatomy.

[0075] According to one embodiment, strain imaging system 110 can determine a first ROI (Region of Interest) of the anatomical structure of a subject's heart in contrast-enhanced ultrasound data based on user input. For example, a user of strain imaging system 110 can interact with a user input device to select the first ROI of the anatomical structure of the subject's heart. Strain imaging system 110 can determine the first ROI of the anatomical structure of the subject's heart based on the selection.

[0076] According to one embodiment, strain imaging system 110 can segment a first region of interest (ROI) of an anatomical structure into a set of myocardial segments. For example, strain imaging system 110 can segment the first ROI into a set of n myocardial segments. Additionally or alternatively, strain imaging system 110 can depict a set of tracking points for strain imaging within the first ROI.

[0077] According to one embodiment, strain imaging system 110 can determine a first ROI in each frame of contrast-enhanced ultrasound data. For example, strain imaging system 110 can receive n frames of contrast-enhanced ultrasound data and determine a first ROI in each of the n frames of contrast-enhanced ultrasound data.

[0078] like Figure 5 As further shown, process 500 may include determining a second ROI of the subject's cardiac anatomy in non-contrast ultrasound data based on a first ROI of the subject's cardiac anatomy in contrast-enhanced ultrasound data (operation 540). For example, strain imaging system 110 may determine a second ROI of the subject's cardiac anatomy in non-contrast ultrasound data based on a first ROI of the subject's cardiac anatomy in contrast-enhanced ultrasound data.

[0079] According to one embodiment, the strain imaging system 110 can receive m frames of non-contrast ultrasound data. The number of m frames can be the same as the number of n frames of contrast-contrast ultrasound data. Alternatively, the number of m frames can be different from the number of frames of contrast-contrast ultrasound data. For example, the number of m frames can be more than the number of n frames, or it can be less than the number of n frames.

[0080] The strain imaging system 110 can determine frames of non-contrast ultrasound data corresponding to frames of contrast-enhanced ultrasound data. Figure 6 This is a graph comparing contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data (600). For example... Figure 6 As shown, the strain imaging system 110 can receive contrast-enhanced ultrasound data 610 and non-enhanced ultrasound data 620. Furthermore, the strain imaging system 110 can determine corresponding frame pairs. For example, as indicated by reference numeral 630, the strain imaging system 110 can determine a first frame of contrast-enhanced ultrasound data 610 corresponding to a first frame of non-enhanced ultrasound data 620. Furthermore, as indicated by reference numeral 640, the strain imaging system 110 can determine a second frame of contrast-enhanced ultrasound data 610 corresponding to a second frame of non-enhanced ultrasound data 620. Furthermore, as indicated by reference numeral 650, the strain imaging system 110 can determine an nth frame of contrast-enhanced ultrasound data 610 corresponding to an nth frame of non-enhanced ultrasound data 620.

[0081] According to one embodiment, the strain imaging system 110 can determine frames of non-contrast ultrasound data corresponding to frames of contrast-enhanced ultrasound data based on a timestamp that identifies the position of the frame within the cardiac cycle. Alternatively, the strain imaging system 110 can determine frames of non-contrast ultrasound data corresponding to frames of contrast-enhanced ultrasound data based on image processing techniques. For example, the strain imaging system 110 can determine frames of non-contrast ultrasound data corresponding to frames of contrast-enhanced ultrasound data based on frames that correspond to the same portion of the cardiac cycle, depict similar anatomical structures in similar anatomical locations, etc. Alternatively, the strain imaging system 110 can use interpolation techniques or the like to generate one or more additional frames to determine frames of non-contrast ultrasound data corresponding to frames of contrast-enhanced ultrasound data.

[0082] In some cases, a frame rate mismatch may exist between contrast-enhanced and non-enhanced acquisitions. That is, non-enhanced acquisitions may have a higher frame rate than contrast-enhanced acquisitions. Therefore, the exact corresponding frame selected from the contrast-enhanced ultrasound data may not appear in the non-enhanced ultrasound data. In this case, the strain imaging system 110 can determine the two nearest adjacent frames in the non-enhanced ultrasound data and perform frame interpolation for the exact corresponding time. Furthermore, if there is a slight frame time mismatch between the corresponding contrast-enhanced and non-enhanced ultrasound data, the accuracy of the strain imaging system 110 may not be affected because the motion can be assumed to be linear over short time intervals.

[0083] According to one embodiment, strain imaging system 110 can determine a second ROI of the subject's cardiac anatomy in non-contrast ultrasound data based on a first ROI of the subject's cardiac anatomy in contrast-enhanced ultrasound data. For example, strain imaging system 110 can determine the location of the second ROI of the subject's cardiac anatomy in non-contrast ultrasound data based on the location of the first ROI of the subject's cardiac anatomy in contrast-enhanced ultrasound data. As a particular example, strain imaging system 110 can superimpose the first ROI onto the non-contrast ultrasound data to determine the second ROI in the non-contrast ultrasound data.

[0084] Figure 7 This is illustration 700, comparing the first ROI in contrast-enhanced ultrasound data with the second ROI in non-contrast-enhanced ultrasound data. For example, as shown... Figure 7 As shown, the strain imaging system 110 can receive a first frame of contrast-enhanced ultrasound data 710 and a first frame of non-contrast ultrasound data 720. The strain imaging system 110 can determine a first ROI 730 in the contrast-enhanced ultrasound data 710 and can determine a second ROI 740 in the non-contrast ultrasound data 720 based on the first ROI 730.

[0085] like Figure 5 As further shown, process 500 may include performing combined strain imaging (operation 550) using a first ROI of the anatomical structure of the subject's heart in contrast-enhanced ultrasound data and a second ROI of the anatomical structure of the subject's heart in non-contrast-enhanced ultrasound data.

[0086] To perform combined strain imaging, and according to one embodiment, strain imaging system 110 can segment a first region of interest (ROI) of the subject's cardiac anatomy in contrast-enhanced ultrasound data into a set of myocardial segments, and can segment a second region of interest (ROI) of the subject's cardiac anatomy in non-contrast-enhanced ultrasound data into a set of myocardial segments. Furthermore, strain imaging system 110 can use strain imaging to track corresponding segments in contrast-enhanced and non-contrast-enhanced ultrasound data over time. Additionally, strain imaging system 110 can determine corresponding strain values ​​of the myocardial segment set over time based on tracking corresponding segments using strain imaging. For example, strain imaging system 110 can determine strain values ​​based on the initial length and final length of the segment. As an example, if the initial length of the segment is "10" and the final length of the segment is "8", then strain imaging system 110 can determine a strain value of "-20%". As another example, if the initial length of the segment is "8" and the final length of the segment is "10", then strain imaging system 110 can determine a strain value of "20%". The strain imaging system 110 can generate corresponding strain curves for a set of myocardial segments.

[0087] The strain imaging system 110 can perform joint strain imaging by determining a common motion vector that maximizes or improves image similarity in contrast-enhanced ultrasound data and non-contrast ultrasound data for each myocardial segment and / or tracking point. For example, the strain imaging system 110 can determine the common motion vector using the following cost function, which maximizes or improves image similarity in contrast-enhanced ultrasound data and non-contrast ultrasound data for each myocardial segment and / or tracking point:

[0088]

[0089] As shown above, “C” is the kernel from the current frame, and “R” is the kernel from the reference frame. Furthermore, “N” is the number of image samples in each kernel. Additionally, “α” and “β” are weighting parameters. The sum of the weighting parameters “α” and “β” can be equal to 1. The strain imaging system 110 can determine whether the motion vector indicated by both contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data is the correct motion vector for a given spot. This method enhances the reliability of strain imaging by introducing a majority vote. Since the underlying cardiac motion is independent of the acquisition mode, corresponding points from the contrast-enhanced ultrasound data and non-contrast-enhanced ultrasound data should exhibit the same or substantially similar motion. The weighting parameters can specify how much confidence should be given to each item (contrast-enhanced ultrasound data or non-contrast-enhanced ultrasound data). The strain imaging system 110 can be configured with predetermined information for setting the value of the weighting parameter for each tracking point. The strain imaging system 110 can assign higher weights to tracking points (kernels) that contain strong features suitable for feature tracking. In contrast, if the kernel includes a noise-like structure that reduces the confidence of feature tracking, the strain imaging system 110 can assign lower weights. Examples of such regions include the lateral wall near the apex in non-contrast ultrasound data and the mitral valve hinge point in contrast-contrast ultrasound data. If the feature intensities of both contrast-contrast and non-contrast ultrasound data are comparable, the strain imaging system 110 may assign substantially equal weights (e.g., 0.5).

[0090] Figure 8 This is an illustration 800 of tracking points in contrast-enhanced ultrasound data and non-contrast ultrasound data. For example, strain imaging system 110 may receive a first frame of contrast-enhanced ultrasound data 810 and a first frame of non-contrast ultrasound data 820. Furthermore, strain imaging system 110 may determine a first tracking point 830 in contrast-enhanced ultrasound data 810 and a first tracking point 840 in non-contrast ultrasound data 820. Additionally, strain imaging system 110 may determine a second tracking point 850 in contrast-enhanced ultrasound data 810 and a second tracking point 860 in non-contrast ultrasound data 820. Strain imaging system 110 may determine a common motion vector that maximizes or improves the image similarity between the first tracking point 840 in contrast-enhanced ultrasound data 810 and the first tracking point 830 in non-contrast ultrasound data 820. Furthermore, the strain imaging system 110 can determine a common motion vector that can maximize or improve the image similarity between the second tracking point 850 in the contrast-enhanced ultrasound data 810 and the second tracking point 860 in the non-contrast-enhanced ultrasound data 820.

[0091] Due to weak signal strength, the true delineation of the endocardial boundary in non-contrast ultrasound data, especially near the apex and lateral walls, can be ambiguous. This ambiguity can lead to an overestimation of strain in the apical segment, as the region of interest (ROI) is dragged downwards, and geometric effects play a significant role. Utilizing the first ROI determined from contrast-enhanced ultrasound data on subsequent non-contrast ultrasound data results in a more accurate delineation of segment length and thus more robust strain values.

[0092] The strain imaging system 110 can detect movement of the ultrasound probe 302 and / or movement of the subject from a first cardiac cycle to a second cardiac cycle, during which contrast-enhanced ultrasound data is acquired, and during the second cardiac cycle, non-enhanced ultrasound data is acquired. For example, the strain imaging system 100 can compare contrast-enhanced ultrasound data and non-enhanced ultrasound data that include the same timestamp and / or correspond to the same portion of the cardiac cycle. As a specific example, the strain imaging system 110 can compare contrast-enhanced ultrasound data and non-enhanced ultrasound data around the valve hinge point. If motion is present, the strain imaging system 110 can compensate for the motion and remove the motion from the estimated displacement.

[0093] like Figure 5 As further shown, process 500 may include information related to cardiac deformation in relation to the anatomical structure of the subject's heart based on the performance of combined strain imaging (operation 560). For example, strain imaging system 110 may determine information related to cardiac deformation in relation to the anatomical features of the subject's heart based on the performance of combined strain imaging.

[0094] According to one implementation scheme, information related to cardiac deformation in the region of interest of the subject's heart may include strain values ​​of myocardial segments, the time taken to reach the maximum strain value of the corresponding myocardial segment, specific myocardial segments associated with time taken greater than or less than a corresponding threshold, mechanical dispersion values, cardiac mechanical asynchrony parameters, etc. Additionally or alternatively, information related to cardiac deformation in the region of interest of the subject's heart may include end-systolic strain corresponding to the strain value at end-systole, peak systolic strain corresponding to the peak strain value during systole, positive peak systolic strain corresponding to local myocardial stretching, peak strain corresponding to the peak strain value throughout the cardiac cycle, etc. Additionally or alternatively, information related to cardiac deformation in the region of interest of the subject's heart may include the velocity, displacement, strain rate, etc., of myocardial segments.

[0095] like Figure 5As further shown, process 500 may include displaying information related to cardiac deformation in relation to the anatomical structure of the subject's heart (operation 570). For example, strain imaging system 110 may display information related to cardiac deformation in anatomical features of the heart, such as mechanical dispersion values, strain values ​​of segmental sets, the time amount to reach the maximum strain value of a corresponding segment, and specific segments associated with time amounts greater than or less than corresponding thresholds.

[0096] Figure 9 This is an illustration 900 of an exemplary user interface for displaying information related to cardiac deformation in relation to the anatomical structure of the subject's heart. For example, as shown, the strain imaging system 110 can display a non-enhanced ultrasound image 910 showing a depiction of the second ROI and the second ROI. Furthermore, the strain imaging system 110 can display a non-enhanced ultrasound image 920 showing the second ROI, its depiction, and depictions of individual segments of the second ROI. Additionally, as shown, the strain imaging system 110 can display strain curves 930 for this set of segments.

[0097] Figure 10 This is an illustration 1000 of an exemplary user interface for displaying information related to cardiac deformation in relation to the anatomical structure of a subject's heart. For example, as shown, the strain imaging system 110 can display a contrast-enhanced ultrasound image 1010 showing a first region of interest (ROI) and its depiction. Furthermore, the strain imaging system 110 can display a contrast-enhanced ultrasound image 1020 showing the first ROI, its depiction, and depictions of individual segments of the first ROI. Additionally, as shown, the strain imaging system 110 can display strain curves 1030 for this set of segments.

[0098] Because both non-contrast ultrasound data and contrast-enhanced ultrasound data are used to estimate underlying cardiac motion, the estimation of the Region of Interest (ROI) is identical for both. The strain imaging system 110 provides a toggle option on the user interface to select between non-contrast ultrasound data and contrast-enhanced ultrasound data. If contrast-enhanced ultrasound data is selected, the strain imaging system 110 can display the contrast-enhanced ultrasound data and overlay a depiction of a first ROI onto it. Similarly, if non-contrast ultrasound data is selected, the strain imaging system 110 can display the non-contrast ultrasound data and overlay a depiction of a second ROI onto it. This option allows the user to simultaneously examine both boundary tracking (e.g., contrast) and speckle tracking (e.g., B-mode).

[0099] According to one implementation, the strain imaging system 110 may use one or more AI models. These one or more AI models may be associated with training, deployment, and monitoring phases. During the training phase, the strain imaging system 110 may receive and process training data to generate a trained model. The training data may be generated, received, or otherwise obtained from internal and / or external resources.

[0100] Typically, a trained model may comprise a set of variables (e.g., nodes, neurons, or filters) tuned to different values ​​through the application of training data (e.g., weighting or biasing). According to one implementation, the training process may employ supervised, unsupervised, semi-supervised, and / or reinforcement learning processes to train the model. According to one implementation, a portion of the training data may be retained during training and / or used to validate the trained model.

[0101] For supervised learning processes, training data may include labels or scores that can facilitate the training process by providing ground truth values. For example, labels or scores may indicate the model's output. Training can continue by feeding a training dataset including the training data into the model. The model may have variables set to initial values ​​(e.g., randomly, based on Gaussian noise, or based on pre-trained values). The model may generate outputs based on the training dataset being fed into it. The outputs can be compared to corresponding labels or scores (e.g., ground truth values) indicating known outputs, and then backpropagated through the model to adjust the values ​​of the variables. This process can be repeated for multiple samples, at least until a determined loss or error falls below a predefined threshold. According to one implementation, some of the training data may be retained and used for further validation or testing of the trained model.

[0102] For unsupervised learning processes, training data may not include pre-assigned labels or scores to aid the learning process. Instead, unsupervised learning processes can include clustering, classification, etc., to identify patterns naturally present in the training data. For example, training data can be clustered into groups based on identified similarities and / or patterns. K-means clustering or K-nearest neighbors can also be used, and these can be supervised or unsupervised. A combination of K-nearest neighbors and unsupervised clustering techniques can also be used. For semi-supervised learning, a combination of training data with pre-assigned labels or scores and training data without pre-assigned labels or scores can be used to train the model.

[0103] When reinforcement learning is employed, an agent (e.g., an algorithm) can be trained to make decisions based on training data through trial and error. For example, based on the decisions made, the agent can then receive feedback (e.g., a positive reward if the predicted value is above a predetermined threshold), adjust its next decision to maximize the reward, and repeat until the loss function is optimized.

[0104] After being trained, the trained model can be stored and subsequently applied by the strain imaging system 110 during the deployment phase. For example, during the deployment phase, the trained model executed by the strain imaging system 110 can receive input data. During the deployment phase, the trained model can perform actions such as combining... Figure 5 One or more operations as described.

[0105] The embodiments illustrated in the accompanying drawings and described above are merely illustrative embodiments and are not intended to limit the scope of the appended claims, including any equivalents included within the scope of the claims. Various modifications are possible and will be apparent to those skilled in the art. Any combination of non-mutually exclusive features described herein is intended to be within the scope of the invention. That is, features of the described embodiments may be combined with any suitable aspect described above, and optional features of any aspect may be combined with any other suitable aspect. Similarly, features listed in dependent claims may be combined with non-mutually exclusive features of other dependent claims, particularly where the dependent claims are subordinate to the same independent claim. In some jurisdictions that claim single-claim dependents, such single-claim dependents may have been used in practice, but this should not be construed as meaning that features in dependent claims are mutually exclusive.

Claims

1. A system (110), the system comprising: Lens, acoustic matching layer, acoustic dematching layer, and multiple transducer elements; Memory (206), the memory being configured to store instructions; and One or more processors (204), said one or more processors being configured to execute the instructions to: (510) Contrast-enhanced ultrasound data of the anatomical structure of the subject's heart are received during the first cardiac cycle of the subject's heart; During the second cardiac cycle of the subject's heart, (520) non-enhanced ultrasound data of the anatomical structure of the subject's heart are received; Identify (530) the first region of interest (ROI) of the anatomical structure of the heart of the subject in the contrast-enhanced ultrasound data. Based on the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data, (540) a second ROI of the anatomical structure of the subject's heart in the non-contrast-enhanced ultrasound data is determined; (550) Combined strain imaging is performed using the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data and the second ROI of the anatomical structure of the subject's heart in the non-contrast-enhanced ultrasound data; Based on the information determined (560) by performing the combined strain imaging related to cardiac deformation of the anatomical structure of the heart in the subject; as well as Display (570) the information relating to cardiac deformities of the anatomical structure of the heart of the subject.

2. The system (110) according to claim 1, wherein the one or more processors (204) are further configured to: The first ROI from the contrast-enhanced ultrasound data is superimposed on the non-contrast-enhanced ultrasound data to determine the second ROI of the anatomical structure of the subject's heart in the non-contrast-enhanced ultrasound data.

3. The system (110) according to claim 1, wherein the one or more processors (204) are further configured to: The common motion vector of each corresponding tracking point in the contrast-enhanced ultrasound data and the non-enhanced ultrasound data is determined to perform the joint strain imaging.

4. The system (110) according to claim 1, wherein the one or more processors (204) are further configured to: The contrast-enhanced ultrasound data is displayed based on the user's selection of which data to display.

5. The system (110) according to claim 1, wherein the one or more processors (204) are further configured to: The non-enhanced ultrasound data is displayed based on the user's selection of which data to display.

6. The system (110) according to claim 1, wherein the second cardiac cycle immediately follows the first cardiac cycle.

7. The system (110) according to claim 1, wherein there are one or more intermediate cardiac cycles between the first cardiac cycle and the second cardiac cycle.

8. A method (500), the method comprising: (510) Contrast-enhanced ultrasound data of the anatomical structure of the subject's heart are received during the first cardiac cycle of the subject's heart; During the second cardiac cycle of the subject's heart, (520) non-enhanced ultrasound data of the anatomical structure of the subject's heart are received; Identify (530) the first region of interest (ROI) of the anatomical structure of the heart of the subject in the contrast-enhanced ultrasound data. Based on the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data, (540) a second ROI of the anatomical structure of the subject's heart in the non-contrast-enhanced ultrasound data is determined; (550) Combined strain imaging is performed using the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data and the second ROI of the anatomical structure of the subject's heart in the non-contrast-enhanced ultrasound data; Based on the information determined (560) by performing the combined strain imaging related to cardiac deformation of the anatomical structure of the heart in the subject; as well as Display (570) the information relating to cardiac deformities of the anatomical structure of the heart of the subject.

9. The method (500) according to claim 8, further comprising: The first ROI from the contrast-enhanced ultrasound data is superimposed on the non-contrast-enhanced ultrasound data to determine the second ROI of the anatomical structure of the subject's heart in the non-contrast-enhanced ultrasound data.

10. The method (500) according to claim 8, further comprising: The common motion vector of each corresponding tracking point in the contrast-enhanced ultrasound data and the non-enhanced ultrasound data is determined to perform the joint strain imaging.

11. The method (500) according to claim 8, further comprising: The contrast-enhanced ultrasound data is displayed based on the user's selection of which data to display.

12. The method (500) according to claim 8, further comprising: The non-enhanced ultrasound data is displayed based on the user's selection of which data to display.

13. The method (500) of claim 8, wherein the second cardiac cycle immediately follows the first cardiac cycle.

14. The method (500) according to claim 8, wherein there is one or more intermediate cardiac cycles between the first cardiac cycle and the second cardiac cycle.

15. A non-transitory computer-readable medium (206) storing instructions that, when executed by one or more processors (204), cause the one or more processors (204) to: (510) Contrast-enhanced ultrasound data of the anatomical structure of the subject's heart are received during the first cardiac cycle of the subject's heart; During the second cardiac cycle of the subject's heart, (520) non-enhanced ultrasound data of the anatomical structure of the subject's heart are received; Identify (530) the first region of interest (ROI) of the anatomical structure of the heart of the subject in the contrast-enhanced ultrasound data. Based on the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data, (540) a second ROI of the anatomical structure of the subject's heart in the non-contrast-enhanced ultrasound data is determined; (550) Combined strain imaging is performed using the first ROI of the anatomical structure of the subject's heart in the contrast-enhanced ultrasound data and the second ROI of the anatomical structure of the subject's heart in the non-contrast-enhanced ultrasound data; Based on the information determined (560) by performing the combined strain imaging related to cardiac deformation of the anatomical structure of the heart in the subject; as well as Display (570) the information relating to cardiac deformities of the anatomical structure of the heart of the subject.

Images