Removal of motion compromised ultrasound images for optimal multi-beat cardiac quantization

Abstract

An ultrasound imaging system includes a processor for communicating with a display, a transducer array of a handheld ultrasound probe, and a memory. A processor receives a plurality of ultrasound images of a patient's anatomy and identifies one or more ultrasound images of motion impairment. The processor then extracts one or more motion-corrupted ultrasound images to form temporal data blocks of remaining ultrasound images. The processor then determines whether the blocks of temporal data each correspond to at least one periodic period, and after having determined that the blocks of temporal data include sufficient data, calculates a patient metric based on each block of temporal data. The ultrasound image, the patient metric, a status indicator corresponding to one of the temporal data blocks, and a status indicator corresponding to the extracted motion impairment of the ultrasound image are then displayed.

Description

Technical Field

[0001] This disclosure generally relates to the field of ultrasound imaging. Specifically, this disclosure relates to systems and methods for identifying and extracting ultrasound images of motion-induced damage and calculating quantitative measures based on the remaining ultrasound images. Background Technology

[0002] Physicians use many different medical diagnostic systems and tools to monitor a subject's health and diagnose and manage medical conditions. Ultrasound imaging systems are widely used in medical imaging and measurement. An ultrasound transducer probe may include an array of ultrasound transducer elements that emit sound waves into the subject's body and record sound waves reflected and backscattered from the subject's internal anatomical structures, which may include tissues, blood vessels, and internal organs. The emission and reception of sound waves, along with various beamforming and processing techniques, create images of the subject's internal anatomy.

[0003] Ultrasound imaging is a safe, useful, and non-invasive tool for diagnostic examinations, interventions, and / or treatments in several applications. Ultrasound imaging can be used to diagnose a wide range of medical conditions. It can be used to image and quantify the motion of a patient's heart. However, obtaining accurate measurements can be challenging because non-periodic or non-cardiac motion can cause interference, which can lead to errors in the data. Non-periodic motion can be caused by several sources, including probe movement during acquisition or patient movement during the acquisition process, such as due to breathing or other movements. This non-periodic or non-cardiac motion can cause measurement drift, resulting in inaccurate measurements. Inaccuracy in the measurement of physiological signals can have significant consequences for patient care, as incorrect diagnostic or treatment plans may be developed based on inaccurate data.

[0004] US 2017 / 273669 A1 relates to a quality metric for multi-beat echocardiographic acquisition for real-time user feedback and discloses an imaging system comprising: an imaging device configured to acquire images in a multi-beat acquisition mode; a quality scoring module configured to evaluate changes in the image between portions of the multi-beat cycle to calculate a quality score indicating the fit of the image; and a display for viewing the image and displaying the quality score as real-time feedback of the image.

[0005] US 2005 / 033123 A1 discloses a method for performing motion correction on ultrasound images automatically selected from multiple ultrasound images associated with the same phase of the cardiac cycle. Summary of the Invention

[0006] This disclosure relates to systems, apparatus, and methods for optimal quantification of multi-beating hearts. Advantageously, these aspects identify and extract images of motion-damped hearts from a collection of ultrasound images received during an imaging procedure. The system then calculates quantization metrics only for the unextracted images, improving the accuracy of the results. These aspects can assist novice users or users in non-ideal procedure settings to calculate accurate results based on received data, even if that data includes ultrasound images of motion-damped hearts.

[0007] In some aspects, the system's processor receives multiple ultrasound images during or after the imaging process. The processor then identifies motion-damaged images and removes them from the set. The processor then analyzes the remaining ultrasound images and forms a temporal data block of ultrasound images. The temporal data block can be a subset of ultrasound images that are not motion-damaged and correspond to at least one heartbeat cycle. Ultrasound images that are not motion-damaged but occur within the same heartbeat cycle as motion-damaged ultrasound images can also be extracted. The processor system then calculates a metric based on the temporal data block including the remaining ultrasound images. Therefore, the calculated metric is based only on non-motion-damaged ultrasound images, thus improving the accuracy of the metric.

[0008] In an exemplary aspect, an ultrasound imaging system is provided. The ultrasound imaging system includes a processor configured to communicate with a display, a transducer array of a handheld ultrasound probe, and a memory, wherein the processor is configured to: receive a plurality of ultrasound images corresponding to views of a patient's anatomy; identify one or more motion-damaged ultrasound images from the plurality of ultrasound images; extract the one or more motion-damaged ultrasound images from the plurality of ultrasound images; form a first time data block, the first time data block including at least some (or even all) of the remaining ultrasound images from the plurality of ultrasound images; determine whether the first time data block corresponds to at least one periodic cycle; calculate a metric based on the first time data block; and generate output for the display, the output including: the ultrasound image from the plurality of ultrasound images; the metric; a first status indicator corresponding to the first time data block; and a second status indicator corresponding to the extracted motion-damaged ultrasound image.

[0009] This metric can advantageously be a patient metric. Patient metrics can indicate the performance of patient anatomy structures included in ultrasound images. In some respects, patient metrics indicate cardiac performance.

[0010] In the context of this disclosure, a time data block may advantageously comprise a time series of ultrasound images spanning at least one periodic period. In some aspects, at least some of the ultrasound images in the time series have been acquired within the same periodic period. In some aspects, each ultrasound image in a subset of the ultrasound images in the time series has been acquired at a time point with a different delay (or phase) relative to the start of the periodic period.

[0011] In some aspects, the processor is configured to compute a metric, particularly a patient metric, after it has been determined that a first time data block corresponds to at least one periodic period. That is, the processor is configured to first determine whether a first time data block corresponds to at least one periodic period, and then compute the patient metric based on the first time data block.

[0012] In some aspects, the processor is also configured to determine the image quality of multiple ultrasound images.

[0013] In some aspects, the processor is also configured to identify one or more motion-damaged images by recognizing and tracking features within multiple ultrasound images.

[0014] In some aspects, in order to track features, the processor is configured to: determine the positional changes of the feature within each of multiple ultrasound images; and identify ultrasound images in which the positional changes of the feature exceed a threshold.

[0015] In some respects, the processor is also configured to identify the one or more motion-damaged images based on one or more of the following: conventional image processing, RF data peak jumps, AI image processing, AI processing of RF data, or AI processing of ultrasound B-mode data.

[0016] In some respects, the measurement includes cardiac-related parameters. In some respects, the measurement includes at least one of the following: end-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), ejection fraction (EF), global longitudinal strain (GLS), or cardiac output (CO).

[0017] In some respects, periodic cycles include heartbeat cycles. Periodic cycles may advantageously include one or more heartbeat cycles.

[0018] In some respects, the metric includes an average, such as the average of data from a first-time data block. For example, when a periodic period comprises multiple heartbeat cycles, the metric may advantageously include an average over some or even all of the multiple heartbeat cycles.

[0019] In some aspects, the first time-series data block comprises a first subset of remaining ultrasound images from multiple ultrasound images; and the processor is further configured to form a second time-series data block comprising a second subset of remaining ultrasound images from multiple ultrasound images, wherein the first and second time-series data blocks are temporally spaced by motion-damaged ultrasound images. In some aspects, the metric comprises the average of data from the first and second time-series data blocks. In some aspects, the processor is further configured to calculate a patient metric based on the average of data from the first and second time-series data blocks.

[0020] In some aspects, the processor is also configured to receive an acceptance metric from the user. In other aspects, the processor is also configured to receive a rejection metric from the user.

[0021] In some aspects, the processor is also configured to receive a first user input identifying a first periodic period of the first time data block. In some of these aspects, the processor is also configured to discard a subset of ultrasound images corresponding to the first periodic period of the first time data block based on a second user input.

[0022] In some aspects, ultrasound images also include structures representing the patient's anatomy and corresponding contours of measurement. Specifically, in some aspects, in order to generate output, the processor is also configured to generate said contours on the ultrasound image.

[0023] In some aspects, an ultrasound imaging system also includes: a display, a handheld ultrasound probe including a transducer array, and a memory.

[0024] In an exemplary aspect, an ultrasound system for measuring the performance of a patient's cardiac system is provided. The ultrasound system includes a handheld ultrasound probe comprising a transducer array; a display; a memory; and a processor configured to communicate with the transducer array, the display, and the memory, wherein the processor is configured to: control the transducer array to acquire multiple ultrasound images corresponding to a view of the left ventricle of a patient's heart; identify one or more motion-damaged ultrasound images from the multiple ultrasound images; extract the one or more motion-damaged ultrasound images from the multiple ultrasound images; form a first time data block comprising at least a subset of remaining ultrasound images from the multiple ultrasound images; determine whether the first time data block corresponds to at least one cardiac cycle; calculate a metric based on the first time data block; and generate output for the display, the output comprising: an ultrasound image from the multiple ultrasound images; the metric; a first status indicator corresponding to the first time data block; and a second status indicator corresponding to the extracted motion-damaged ultrasound image.

[0025] In an exemplary aspect, a processor circuit is provided for extracting motion-damaged ultrasound images from a set of acquired ultrasound images and performing quantization based on the acquired set. The processor circuit includes a processor configured to: receive a plurality of ultrasound images corresponding to views of a patient's anatomy; identify one or more motion-damaged ultrasound images from the plurality of ultrasound images; extract the one or more motion-damaged ultrasound images from the plurality of ultrasound images; form a first time data block including at least some (or even all) of the remaining ultrasound images from the plurality of ultrasound images; determine whether the first time data block corresponds to at least one periodic cycle; calculate a metric based on the first time data block; and generate an output including: the ultrasound image from the plurality of ultrasound images; the metric; a first state indicator corresponding to the first time data block; and a second state indicator corresponding to the extracted motion-damaged ultrasound image.

[0026] In some aspects, the processor circuitry also includes a memory and a communication module, wherein the processor, memory, and communication module are configured to communicate with each other, and wherein the communication module is also configured to communicate with the display and the transducer array of the handheld ultrasound probe.

[0027] In one exemplary aspect, the ultrasound imaging system includes: a handheld ultrasound probe including a transducer array; a display; and processor circuitry as defined above.

[0028] In an exemplary aspect, a method is provided for extracting motion-damaged ultrasound images from a set of acquired ultrasound images and performing quantization based on the acquired set. The method includes: receiving a plurality of ultrasound images from an ultrasound imaging system, the plurality of ultrasound images corresponding to views of a patient's anatomy; identifying one or more motion-damaged ultrasound images from the plurality of ultrasound images; extracting the one or more motion-damaged ultrasound images from the plurality of ultrasound images; forming a first time data block, the first time data block including at least a subset of remaining ultrasound images from the plurality of ultrasound images; determining whether the first time data block corresponds to at least one periodic period; calculating a metric (such as a patient metric) based on the first time data block; and generating an output including: the ultrasound image from the plurality of ultrasound images; the metric; a first state indicator corresponding to the first time data block; and a second state indicator corresponding to the extracted motion-damaged ultrasound image.

[0029] In some aspects, the step of calculating patient metrics is performed after the step of determining that the first time data block corresponds to at least one periodic period.

[0030] In one exemplary aspect, a computer program product is provided. The computer program product includes computer-readable instructions that, when executed by a processor, cause the processor to perform the methods as defined above.

[0031] Additional aspects, features, and advantages of this disclosure will become apparent from the following detailed description. Attached Figure Description

[0032] The illustrative aspects of this disclosure will be described with reference to the accompanying drawings, in which: Figure 1 This is a schematic diagram of an ultrasound imaging system according to various aspects of this disclosure.

[0033] Figure 2 This is a schematic diagram of the processor circuit according to various aspects of this disclosure.

[0034] Figure 3 It is a graphical representation of patient measurements based on the acquired ultrasound image data according to various aspects of this disclosure.

[0035] Figure 4 It is a graphical representation of patient measurements based on the acquired ultrasound image data according to various aspects of this disclosure.

[0036] Figure 5 This is a flowchart of a method for extracting motion-damaged ultrasound images from a set of acquired ultrasound images and performing quantization based on the acquired set, according to various aspects of this disclosure.

[0037] Figure 6 It is a graphical representation of a method for extracting motion-damaged ultrasound images from a set of acquired ultrasound images and performing quantization based on the acquired set, according to various aspects of this disclosure.

[0038] Figure 7 It is a graphical representation of the graphical user interface according to various aspects of this disclosure.

[0039] Figure 8 It is a graphical representation of the graphical user interface according to various aspects of this disclosure.

[0040] Figure 9 It is a graphical representation of the graphical user interface according to various aspects of this disclosure.

[0041] Figure 10 It is a graphical representation of a method for extracting ultrasound images of motion-induced damage according to various aspects of this disclosure.

[0042] Figure 11 It is a graphical representation of a method for identifying motion-damaged ultrasound images according to various aspects of this disclosure. Detailed Implementation

[0043] To facilitate an understanding of the principles of this disclosure, reference will now be made to the aspects illustrated in the accompanying drawings, and these aspects will be described using specific language. However, it should be understood that this is not intended to limit the scope of this disclosure. Any changes and further modifications to the described apparatus, systems, and methods, as well as any further application of the principles of this disclosure, are fully contemplated and included within this disclosure, as would normally occur to those skilled in the art to which this disclosure pertains. In particular, it is fully contemplated that features, components, and / or steps described with respect to one aspect can be combined with features, components, and / or steps described with respect to other aspects of this disclosure. However, for the sake of brevity, multiple iterations of these combinations will not be described separately.

[0044] Figure 1 This is a schematic diagram of an ultrasound imaging system 100 according to various aspects of this disclosure. System 100 is used to scan a region or volume of a subject's body. The subject may include a patient in the ultrasound imaging process, or any other person, or any suitable living or non-living organism or structure. System 100 includes an ultrasound imaging probe 110 that communicates with a host 130 via a communication interface or link 120. Probe 110 may include a transducer array 112, a beamformer 114, a processor 116, and a communication interface 118. Host 130 may include a display 132, a processor 134, a communication interface 136, and a memory 138 for storing subject information.

[0045] In some aspects, probe 110 is an external ultrasound imaging device including a housing 111 configured for hand-held operation by a user. Transducer array 112 can be configured to acquire ultrasound data when the user grips the housing 111 of probe 110 such that the transducer array 112 is positioned adjacent to or in contact with the subject's skin. Probe 110 is configured to acquire ultrasound data of anatomical structures within the subject's body when probe 110 is positioned outside the subject's body for general imaging, such as for abdominal imaging, liver imaging, etc. In some aspects, probe 110 can be an external ultrasound probe, a transthoracic probe, and / or a curved array probe.

[0046] In other aspects, probe 110 can be an internal ultrasound imaging device and may include a housing 111 configured to be positioned within a lumen of a body object for general imaging, such as for abdominal imaging, liver imaging, etc. In some aspects, probe 110 may be a curved array probe. Probe 110 can have any suitable form for any suitable ultrasound imaging application, including both external and internal ultrasound imaging.

[0047] In some aspects, the aspects of this disclosure can be realized using medical images of the object obtained using any suitable medical imaging device and / or modality. Examples of medical images and medical imaging devices include X-ray images (angiographic images, fluoroscopic images, images with or without contrast agents) obtained by X-ray imaging devices, computed tomography (CT) images obtained by CT imaging devices, positron emission tomography-computed tomography (PET-CT) images obtained by PET-CT imaging devices, magnetic resonance imaging (MRI) images obtained by MRI devices, single-photon emission computed tomography (SPECT) images obtained by SPECT imaging devices, optical coherence tomography (OCT) images obtained by OCT imaging devices, and intravascular photoacoustic (IVPA) images obtained by IVPA imaging devices. Medical imaging devices are capable of acquiring medical images when positioned outside the object's body, spaced apart from the object's body, adjacent to the object's body, in contact with the object's body, and / or inside the object's body.

[0048] For an ultrasound imaging device, transducer array 112 emits ultrasound signals toward the anatomical target 105 of the object and receives echo signals reflected back to transducer array 112 from the target 105. Ultrasonic transducer array 112 can include any suitable number of acoustic elements, including one or more acoustic elements and / or multiple acoustic elements. In some cases, transducer array 112 includes a single acoustic element. In some cases, transducer array 112 can include an array of acoustic elements with any number of acoustic elements having any suitable configuration. For example, transducer array 112 can include between 1 and 10,000 acoustic elements, including values ​​such as 2, 4, 36, 64, 128, 500, 812, 1,000, 3,000, 8,000 acoustic elements, and / or other values ​​larger and smaller. In some cases, transducer array 112 may comprise an array of acoustic elements having any number of acoustic elements in any suitable configuration, such as linear arrays, planar arrays, curved arrays, wavy arrays, circumferential arrays, ring arrays, phased arrays, matrix arrays, one-dimensional (1D) arrays, 1.x-dimensional arrays (e.g., 1.5D arrays), or two-dimensional (2D) arrays. The acoustic element array (e.g., one or more rows, one or more columns, and / or one or more orientations) can be uniformly or independently controlled and activated. Transducer array 112 can be configured to obtain one-dimensional, two-dimensional, and / or three-dimensional images of an object's anatomy. In some aspects, transducer array 112 may comprise a piezoelectric micromechanical ultrasonic transducer (PMUT), a capacitive micromechanical ultrasonic transducer (CMUT), a single crystal, lead zirconate titanate (PZT), PZT composites, other suitable transducer types, and / or combinations thereof.

[0049] Target 105 may include any anatomical structure or feature, such as the kidneys, liver, and / or any other anatomical structure of the object. This disclosure can be implemented in the context of any number of anatomical locations and tissue types, including, but not limited to: organs, including the liver, kidneys, gallbladder, pancreas, and lungs; ducts; intestines; nervous system structures, including the brain, dural sac, spinal cord, and peripheral nerves; the urinary tract; and valves within blood vessels, blood, abdominal organs, and / or other systems of the body. In some aspects, target 105 may include malignant diseases, such as tumors, cysts, lesions, hemorrhages, or blood pools within any part of a human anatomical structure. Anatomical structures may be blood vessels, arteries or veins of the vascular system of the object, including the cardiac vascular system, peripheral vascular system, neurovascular system, renal vascular system, and / or any other suitable lumen within the body. In addition to natural structures, this disclosure can be implemented in the context of artificial structures, such as, but not limited to, heart valves, stents, shunts, filters, implants, and other devices.

[0050] Beamformer 114 is coupled to transducer array 112. Beamformer 114 controls transducer array 112, for example, for transmitting ultrasonic signals and receiving ultrasonic echo signals. In some aspects, beamformer 114 may apply a time delay to signals transmitted to individual acoustic transducers within the array in transducer 112, such that the acoustic signals are manipulated in any suitable direction of propagation away from probe 110. Beamformer 114 may also provide image signals to processor 116 based on the response of the received ultrasonic echo signals. Beamformer 114 may include multi-stage beamforming. Beamforming can reduce the number of signal lines used to couple to processor 116. In some aspects, transducer array 112 combined with beamformer 114 may be referred to as an ultrasonic imaging component.

[0051] Processor 116 is coupled to beamformer 114. Processor 116 can also be described as processor circuitry capable of including other components communicating with processor 116, such as memory, beamformer 114, communication interface 118, and / or other suitable components. Processor 116 may include a central processing unit (CPU), graphics processing unit (GPU), digital signal processor (DSP), application-specific integrated circuit (ASIC), controller, field-programmable gate array (FPGA) device, another hardware device, firmware device, or any combination thereof configured to perform the operations described herein. Processor 116 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 combined with a DSP core, or any other such configuration. Processor 116 is configured to process the beamformed image signal. For example, processor 116 may perform filtering and / or quadrature demodulation to modulate the image signal. Processor 116 and / or 134 can be configured to control array 112 to obtain ultrasound data associated with target 105.

[0052] Communication interface 118 is coupled to processor 116. Communication interface 118 may include one or more transmitters, one or more receivers, one or more transceivers, and / or circuitry for transmitting and / or receiving communication signals. Communication interface 118 may include hardware and / or software components implementing a specific communication protocol suitable for transmitting signals to host 130 via communication link 120. Communication interface 118 may be referred to as a communication device or communication interface module.

[0053] Communication link 120 can be any suitable communication link. For example, communication link 120 can be a wired link, such as a Universal Serial Bus (USB) link or an Ethernet link. Alternatively, communication link 120 can be a wireless link, such as an Ultra Wideband (UWB) link, an IEEE 802.11 WiFi link, or a Bluetooth link.

[0054] At host 130, communication interface 136 can receive image signals. Communication interface 136 can be substantially similar to communication interface 118. Host 130 can be any suitable computing and display device, such as a workstation, personal computer (PC), laptop computer, tablet computer, or mobile phone.

[0055] Processor 134 is coupled to communication interface 136. Processor 134 can also be described as processor circuitry capable of including other components communicating with processor 134, such as memory 138, communication interface 136, and / or other suitable components. Processor 134 can be implemented as a combination of software and hardware components. Processor 134 may include a central processing unit (CPU), graphics processing unit (GPU), digital signal processor (DSP), application-specific integrated circuit (ASIC), controller, FPGA device, another hardware device, firmware device, or any combination thereof configured to perform the operations described herein. Processor 134 can 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 combined with a DSP core, or any other such configuration. Processor 134 can be configured to generate image data based on image signals received from probe 110. Processor 134 can apply advanced signal processing and / or image processing techniques to the image signals. In some aspects, processor 134 is capable of forming a three-dimensional (3D) volumetric image from the image data. In some aspects, processor 134 is capable of performing real-time processing on image data to provide streaming video of ultrasound images of target 105. In some aspects, host 130 includes a beamformer. For example, processor 134 may be part of such beamformer and / or otherwise communicate with such beamformer. The beamformer in host 130 may be a system beamformer or a master beamformer (providing one or more subsequent beamforming stages), while beamformer 114 may be a probe beamformer or a microwave beamformer (providing one or more initial beamforming stages).

[0056] Memory 138 is coupled to processor 134. Memory 138 can be any suitable storage device, such as cache memory (e.g., cache memory of processor 134), random access memory (RAM), magnetoresistive RAM (MRAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, solid-state memory device, hard disk drive, solid-state drive, other forms of volatile and non-volatile memory, or a combination of different types of memory.

[0057] Memory 138 can be configured to store object information, measurement results, the object's medical history, the history of procedures performed, data or files related to the object's associated anatomical or biological features, characteristics, or medical condition, computer-readable instructions (such as code, software, or other applications), and any other suitable information or data. Memory 138 may be located within host 130. Object information may include measurement results, data, files, other forms of medical history, such as, but not limited to, ultrasound images, ultrasound videos, and / or any imaging information related to the object's anatomy. Object information may include parameters related to the imaging process, such as the anatomical scan window, probe orientation, and / or the object's position during the imaging process. Memory 138 can also be configured to store information related to the training and implementation of machine learning algorithms (e.g., neural networks) and / or information related to the implementation of image recognition algorithms, image quantization algorithms, and / or image acquisition guidance algorithms (including those described herein) for detecting / segmenting anatomical structures.

[0058] Display 132 is coupled to processor 134. Display 132 may be a monitor or any suitable display. Display 132 is configured to display ultrasound images, video images, and / or any imaging information of target 105.

[0059] System 100 can be used to assist sonographers in performing ultrasound scans. Scans can be performed in a point-of-care setting. In some cases, the host unit 130 is a console or a mobile cart. In other cases, the host unit 130 can be a mobile device, such as a tablet, mobile phone, or laptop. During the imaging process, the ultrasound system is able to acquire ultrasound images of specific regions of interest within the subject's anatomy. The ultrasound system 100 can then analyze the ultrasound images to identify various parameters associated with the image acquisition, such as scan window, probe orientation, subject position, and / or other parameters. The system 100 can then store the images and these associated parameters in memory 138. At subsequent imaging stages, the system 100 can retrieve previously acquired ultrasound images and associated parameters for display to the user, which can be used to guide the user of the system 100 in using the same or similar parameters in subsequent imaging stages, as will be described in more detail below.

[0060] In some aspects, processor 134 may utilize a deep learning-based predictive network to identify parameters of the ultrasound image, including the anatomical scan window, probe orientation, object position, and / or other parameters. In some aspects, processor 134 may receive or perform various calculations related to the physiological state of the region of interest or object imaged during the imaging process. These measurements and / or calculations may also be displayed to the sonographer or other user via display 132.

[0061] Figure 2This is a schematic diagram of a processor circuit according to various aspects of this disclosure. One or more processor circuits can be configured to perform the operations described herein. Processor circuit 210 can be located at probe 110, Figure 1 The processor 116 of probe 110 can be implemented in host system 130 or any other suitable location. For example, processor 116 of probe 110 can be part of processor circuitry 210. For example, processor 134 and / or memory 138 can be part of processor circuitry 210. In one example, processor circuitry 210 can communicate with transducer array 112, beamformer 114, communication interface 122, communication interface 136 and / or display 132, and any other suitable components or circuitry within ultrasound system 100. As shown, processor circuitry 210 can include processor 260, memory 264, and communication module 268. These components can communicate directly or indirectly with each other, for example, via one or more buses.

[0062] Processor 260 may include a CPU, GPU, DSP, application-specific integrated circuit (ASIC), controller, FPGA, another hardware device, firmware device, or any combination thereof configured to perform the operations described herein. Processor 260 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 combined with a DSP core, or any other such configuration. Processor 260 may also include an analysis module, as will be discussed in more detail below. The analysis module may implement various machine learning algorithms and may be implemented in hardware or software. Processor 260 may additionally include a preprocessor in either hardware or software implementations. Processor 260 may execute various instructions, including instructions stored on a non-transitory computer-readable medium such as memory 264.

[0063] Memory 264 may include cache memory (e.g., the cache memory of processor 260), random access memory (RAM), magnetoresistive RAM (MRAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, solid-state memory devices, hard disk drives, other forms of volatile and non-volatile memory, or combinations of different types of memory. In some cases, memory 264 includes non-transitory computer-readable media. Memory 264 may store instructions 266. Instructions 266 may include instructions that, when executed by processor 260, cause processor 260 to perform actions on reference probe 110 and / or host 130 (…). Figure 1Instructions 266 describe the operations described. Instructions 266 may also be referred to as code. The terms "instructions" and "code" should be interpreted broadly to include any type of computer-readable statement(s). For example, the terms "instructions" and "code" can refer to one or more programs, routines, subroutines, functions, flows, etc. "Instructions" and "code" can include a single computer-readable statement or many computer-readable statements. Instructions 266 can include aspects of a preprocessor, machine learning algorithms, convolutional neural networks (CNNs), or various other instructions or codes. In some aspects, memory 264 may be or include non-transitory computer-readable media.

[0064] Communication module 268 can include any electronic and / or logic circuitry to facilitate direct or indirect data communication between processor circuitry 210, probe 110, and / or host 130. In this regard, communication module 268 can be an input / output (I / O) device. In some cases, communication module 268 facilitates direct or indirect data communication between processor circuitry 210 and / or probe 110. Figure 1 ) and / or host 130 ( Figure 1 Direct or indirect communication between various components.

[0065] Figure 3 It is a graphical representation of patient metrics based on acquired ultrasound image data measured over time, according to various aspects of this disclosure. Figure 3 Includes graph 300, which shows a dataset 330 representing ultrasound data acquired over time. Graph 300 includes an x-axis 310 corresponding to time, which can have any suitable unit, such as frames or seconds, and a y-axis 320 corresponding to volume, which can have any suitable unit, such as milliliters, cubic centimeters, or any other suitable unit of volume.

[0066] Dataset 330 illustrates multiple periodic cycles, identifiable by several regions 340, 341, 342, 343, 344, and 345. Graph 300 may include any suitable number of cycles, and these cycles may correspond to a specific structure or organ being imaged. For example, a cycle may correspond to the cardiac cycle, where the heart contracts and expands to pump blood through the body. In other respects, the region of interest being imaged may be any other organ or structure in the patient's anatomy that also exhibits periodic movement, such as structures of the lungs, gastrointestinal tract, or any other feature of the patient's anatomy. Graph 300 may include any suitable number of cycles. Regions 340, 341, and 342 may correspond to data acquired by the ultrasound transducer when the transducer and patient are stationary. In contrast, regions 343, 344, and 345 may correspond to data acquired by the ultrasound transducer when the transducer or patient is moving. Therefore, regions 343, 344, and 345 may correspond to ultrasound images that may contain artifacts or motion distortions.

[0067] Graphical element 350 can be used to identify regions corresponding to the curve 300 of an image with motion damage. Graphical element 350 can be any suitable visual marker, such as color or shading pattern, that distinguishes regions 343, 344, and 345 from regions 340, 341, and 342. Depending on the specific application, graphic element 350 can be applied automatically by a computer program or manually by a user.

[0068] Figure 4 It is a graphical representation of patient measurements based on the acquired ultrasound image data according to various aspects of this disclosure. Figure 4 This includes a graph 400 that displays a dataset 430 of ultrasound data acquired over time. The graph 400 includes an x-axis 410 representing time, which can have any suitable unit, such as a frame or a second, and a y-axis 420 representing the phase of non-periodic motion.

[0069] Dataset 430 shows multiple peaks 441, 442, and 443. Each peak corresponds to a time point where the movement of the ultrasound transducer or patient exceeds a threshold, causing the phase to shift from one extreme to another. These peaks are caused by extreme non-periodic movements (such as sudden twitches or movements), and the severity and duration of the movement can correspond to the number of peaks present in graph 400. In some respects, the presence of motion peaks in ultrasound data can indicate that the resulting image is motion-damped and may contain artifacts or distortions.

[0070] Figure 5This is a flowchart of a method for extracting motion-damaged ultrasound images from a set of acquired ultrasound images and performing quantization based on the acquired set, according to various aspects of this disclosure. As shown, method 500 includes a plurality of enumerated steps, but aspects of method 500 may include additional steps before, after, or between the enumerated steps. In some aspects, one or more of the enumerated steps may be omitted, performed in a different order, or performed simultaneously. The steps of method 500 can be performed by any suitable component within system 100, and all steps do not need to be performed by the same component. In some aspects, one or more steps of method 500 can be performed by or under the guidance of a processor, which includes, for example, processor 116 (… Figure 1 ), processor 134 ( Figure 1 ), processor 260 ( Figure 2 (or any other suitable component.)

[0071] Step 502 of method 500 includes receiving an ultrasound image. The ultrasound image can be obtained from any suitable ultrasound imaging system, such as a two-dimensional (2D) or three-dimensional (3D) ultrasound imaging system. In some aspects, an ultrasound image can be obtained using a probe placed on the surface of the patient's body. The ultrasound image can include any suitable number of frames and can be obtained at any suitable frame rate.

[0072] Step 504 of method 500 includes extracting ultrasound images of the motion-induced damage. Any suitable technique can be used to identify the motion-induced damage in ultrasound images, such as those referenced below. Figure 10 and Figure 11 Any techniques shown and described. Once motion-damaged ultrasound images have been identified, they can be removed from the dataset to prevent them from interfering with subsequent analysis, as described in step 506.

[0073] Step 506 of method 500 includes forming a time data block from the received ultrasound images. The time data block may be formed from consecutive, non-motion-damaged ultrasound image frames of at least one complete periodic cycle. In this regard, the time data block can be formed by removing motion-damaged or ultrasound image frames belonging to a periodic cycle of ultrasound images including motion-damaged ones. In some aspects, the frames of the time data block can be selected such that they correspond to at least a complete heartbeat cycle.

[0074] Step 508 of method 500 includes determining whether the time block includes at least one periodic cycle. Any suitable technique can be used to identify periodic cycles, such as by identifying peaks in a graph corresponding to a complete heartbeat cycle. If the time block does not include at least one periodic cycle, method 500 may proceed to step 510.

[0075] Step 510 of method 500 includes determining that insufficient data was not received in step 502. This may include outputting an indication to a graphical user interface indicating that insufficient data was not received in step 502. Method 500 may then return to step 502 and may receive additional ultrasound images.

[0076] Step 512 of method 500 includes performing quantization (or measurement) of the ultrasound images of the time block. The system's processor can be configured to perform any suitable quantization. For example, at step 512, the processor can determine any of the following for any ultrasound image frame: end-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), ejection fraction (EF), global longitudinal strain (GLS), or cardiac output (CO). In some aspects, multiple time blocks can be created at step 506. Steps 512-522 can be performed for each time block formed at step 506 or for all time blocks as a whole. For example, steps 512-522 can be performed simultaneously for all ultrasound images of all time blocks formed at step 506. In some aspects, quantization or measurement can be calculated for each ultrasound image of time block 506.

[0077] In some aspects, quantifying the ultrasound image at step 512 may additionally include determining the image quality of the ultrasound image. For example, determining the image quality may include calculating image quality factors such as whether the endocardial boundary can be visualized, the clarity of the left ventricle, septal alignment, left ventricular depth coverage and shortening, temporal image quality, or any other feature.

[0078] Step 514 of method 500 includes outputting a graphical user interface. The graphical user interface may include an ultrasound image. The ultrasound image may be one of the ultrasound images received at step 502. In some aspects, the ultrasound image may be one of the ultrasound images in a time block formed at step 506. In some aspects, the ultrasound image may be an ultrasound image that was not extracted at step 504.

[0079] The graphical user interface may also include one or more quantizations or measures, such as any quantization calculated at step 512. The graphical user interface may also include a graph of the measure for each ultrasound image of the time block. The graph may include indicators identifying regions of the graph corresponding to ultrasound images acquired as part of a complete cardiac cycle that are not motion-damaged. In some aspects, the graph may include indicators identifying regions of the graph corresponding to acquired ultrasound images that are not motion-damaged but are not part of a complete cardiac cycle. In some aspects, the graph may include indicators identifying regions of the graph corresponding to motion-damaged ultrasound images.

[0080] Step 516 of method 500 includes receiving user input to accept data, reject data, or modify data. User input can be received through any suitable input device, such as a keyboard, mouse, or touchscreen.

[0081] Step 518 of method 500 includes determining if the user input corresponds to user-accepted data, in which case method 500 may proceed to step 520, where method 500 terminates. In some aspects, if the user input corresponds to user-rejected data, method 500 may return to step 502 and may receive additional ultrasound images. If the user input corresponds to user-modified data, method 500 may proceed to step 522.

[0082] Step 522 of method 500 includes receiving user input for modified data. The user input can be received through any suitable input device and may include modifications to the quantization or metric calculated in step 512.

[0083] Figure 6 This is a graphical representation of a method 600 for extracting motion-damaged ultrasound images from a set of acquired ultrasound images and performing quantization based on the acquired set, according to various aspects of this disclosure. For example... Figure 6 As shown, the system can receive multiple ultrasound images 610. These ultrasound images can be transmitted to a motion-damaged image extraction module 615. The motion-damaged image extraction module 615 can be configured according to the following reference. Figure 10 and 11 Any method or technique described to extract motion-damped images. Figure 6As shown, the motion-damaged image extraction module 615 can output several time data blocks. For example, a subset of ultrasound images 620 can form a first time data block. An additional subset of ultrasound images 625 can form a second time data block. In some aspects, the ultrasound images 620 of the first time data block can be acquired by an ultrasound imaging probe within a first time range prior to the time at which the second subset 625 of the ultrasound images is acquired. In some aspects, the time period can separate the time at which the first subset 620 of the ultrasound images is acquired from the time at which the second subset 625 of the ultrasound images is acquired.

[0084] In some aspects, after each time block is created, the ultrasound images of each time block can be analyzed to determine whether it corresponds to at least one cardiac cycle. If, for any time data block, the system determines that the time data block does not contain enough ultrasound images to correspond to at least one cardiac cycle, the system can output an indication that there are not enough ultrasound images within the time data block to correspond to at least one cardiac cycle. In some aspects, time data blocks that do not contain enough ultrasound images can be discarded. The same process occurs for each time data block, such as... Figure 6 As shown.

[0085] After each time data block has been analyzed to ensure it contains sufficient data, all time data blocks can be forwarded to quantization module 640. Quantization module 640 can perform any suitable quantization, such as any of the quantizations described in step 512 of reference method 500. After quantization is complete, the system can generate a graphical user interface. The graphical user interface can be output to the display of device 700.

[0086] Figure 7 This is a graphical representation of a graphical user interface according to various aspects of this disclosure. The graphical user interface can be displayed on device 700. The device can be any kind of device, including smartphones, tablets, computers, laptops, portable medical devices, or any other suitable device. The graphical user interface includes a set of metrics 725.

[0087] The set of measures 725 displayed on the graphical user interface may include any quantifications calculated at step 512. The set of measures 725 may also include any other relevant information associated with the ultrasound image, such as the time and date of the ultrasound, the patient's name and medical identification number, the ultrasound machine settings, and any other relevant information. These measures may be any measures determined at step 512 of method 500.

[0088] In some aspects, the graphical user interface may include a 2D or 3D ultrasound image 720, which may be one of the ultrasound images received at step 502, one of the ultrasound images in a time block formed at step 506, or an ultrasound image not extracted at step 504. The ultrasound image 720 may be displayed together with a set of measurements 725 to provide a visual representation of the ultrasound data. The ultrasound image 720 may also be annotated with graphical elements such as arrows or text boxes to highlight specific features or structures of interest.

[0089] The graphical user interface can indicate the number of beats used in the analysis reported under N beat measures. Measure 725 may also include summary statistics. In some aspects, the user can select the "Change Data Mode" button 730 to change measure 725 to any other suitable measure. For example, the Change Data Mode button 730 can switch measure 725 between the default summary statistics mode and other types of modes. The default summary statistics mode can correspond to the average measure of all beats analyzed. Some available options for other types of modes include median, mode, rank, or standard deviation. In some aspects, the user can optionally select one of the N beats, and the graphical user interface can display only the measure corresponding to the selected beat. Measure 725 can include any suitable type of measure, such as ejection fraction (EF), stroke volume (SV), global longitudinal strain (GLS), cardiac output (CO), or any other suitable measure.

[0090] The graphical user interface also includes a graph 750. Graph 750 can display any metric calculated over time (e.g., frame-by-frame). In some aspects, if the user selects a specific pulsation, for example by changing the data mode button 730 or by selecting and / or moving various indicators within graph 750, then in some aspects, when a specific pulsation is selected, an ultrasound image corresponding to the selected pulsation can be displayed. In some aspects, all ultrasound images corresponding to that pulsation will be displayed in graph 750 by indicators (see, for example...) Figure 9 The indicator 960 is highlighted. See below for reference. Figure 8 A more detailed description of graph 750.

[0091] In some aspects, the graphical user interface includes an ultrasound image 720. The ultrasound image 720 can be any ultrasound image obtained at step 502 of method 500 or any ultrasound image of a time data block formed at step 506. The ultrasound image 720 can be one of a series of ultrasound images corresponding to a selected periodic period (such as a heartbeat cycle).

[0092] The graphical user interface also includes an annotation button 732, a save image button 734, and a measurement button 736. In some aspects, in response to a user selecting the measurement button 736, measurement indicators and scales can be presented to the user within the graphical user interface. In response to a user selecting the save image button 734, the ultrasound image 720 and / or measurement 725 can be stored in the memory of the device 700 or in another memory associated with the device 700. For example, the device 700 can communicate wirelessly with a storage device, such as an external memory or cloud storage server that can store the ultrasound image 720 and / or measurement 725. In some aspects, the graphical user interface can be modified to include various displays, buttons, or indicators that allow the user to provide annotations associated with or overlaid on the ultrasound image 720. In some aspects, the graphical user interface can also be modified to allow the user to highlight, outline, or otherwise annotate the ultrasound image 720 and / or its corresponding features, measurements, or indicators.

[0093] Figure 8 This is a graphical representation of a graphical user interface according to various aspects of this disclosure. In some cases, the graphical user interface may be... Figure 7 The portion or area of ​​the graphical user interface shown.

[0094] The graph 750 may include an x-axis 751 corresponding to time. The time axis 751 may have units of frames (e.g., ultrasound image frames). The y-axis 753 may correspond to volumes in milliliters. However, the y-axis 753 may correspond to any metric described in step 512 of the reference method 500.

[0095] Graph 750 includes dataset 710. Dataset 710 shows measures over time, such as volume, and illustrates the periodicity of the measured parameters. Graph 750 includes multiple indicators located on dataset 710. In some aspects, the system can classify each ultrasound image frame based on one of three categories shown in key 770. For example, each ultrasound image frame received at step 502 of method 500 can be classified as an acquired ultrasound image without motion damage (e.g., no motion damage indicator 771), an acquired ultrasound image with motion damage (e.g., motion damage indicator 773), or an ultrasound image without motion damage but acquired within a periodic period in which all ultrasound images of the periodic period are not motion-damaged (e.g., some ultrasound images within the period are motion-damaged, indicated by insufficient data indicator 772). Indicators corresponding to each of these categories can be positioned within graph 750 to reflect the data in graph 750. For example, the first two periodic cycles of dataset 710 may correspond to ultrasound images obtained without motion damage, as shown in indicator 760. Figure 7The last periodic cycle shown in graph 750 can be obtained without motion damage, as indicated by indicator 764. Ultrasound images obtained between the shown periodic cycles may not be available. In some examples, the ultrasound images obtained between the shown periodic cycles may correspond to one, two, or more periodic cycles. However, some of these ultrasound images may have been motion-damaged. This is indicated by indicator 762. Additionally, while all ultrasound images between the periodic cycles shown in graph 750 may not yet be motion-damaged, the remaining undamaged ultrasound images are part of the same (one or more) periodic cycles corresponding to the images at indicator 762. These ultrasound images can be identified by indicators 761 and 762, and although not motion-damaged, are not part of a complete undamaged periodic cycle and can therefore be discarded.

[0096] In some aspects, indicators 771, 772, and 773 can be visually distinguished in any suitable manner. For example, indicator 771 can be green, indicator 772 can be yellow, and indicator 773 can be red. Indicators 771, 772, and 773 can also be visually distinguished in any other way, including by using different colors, line patterns, widths, or by varying any other visual characteristics. In some aspects, any other type of indicator can be positioned in or near different areas of the graph 750 to indicate the status of the ultrasound image acquired at the corresponding location / time.

[0097] The graph 750 also includes two indicators 712 and 714. Indicators 712 and 714 can identify a single periodic cycle. Figure 8 In the graph 750, the first periodic period can be identified by indicators 712 and 714. In some examples, the periodic period can be identified by any other indicator. For example, the indicator may include a box positioned around the periodic period or any other suitable method or indicator to highlight the periodic period. Additionally, indicators 712 and 714 and / or any other suitable similar indicator can identify any suitable area of ​​the data in the graph 750. For example, multiple periodic periods, as well as portions of the period or any other suitable area or multiple areas, can be identified and highlighted.

[0098] Figure 9 This is a graphical representation of a graphical user interface 900 according to aspects of this disclosure. The graphical user interface 900 includes an ultrasound image 920. The ultrasound image 920 may be similar to an ultrasound image 720. For example... Figure 9As shown, a graphical user interface 900 can be displayed to the user to view specific periodic cycles, such as a heartbeat. For example, an ultrasound image 920 can be displayed along with a title 922. The title 922 can indicate which beat is currently displayed for viewing. In the example shown, beat 2 can be displayed for viewing. As explained in more detail below, beat 2 can correspond to area 910b.

[0099] In some aspects, the graphical user interface 900 may also include a set of measures 924. Measures 924 may include the type of analysis performed, such as whether the analysis is performed on a single beat or multiple beats. In some aspects, measures 924 may correspond to or resemble... Figure 7 The measurement is 725.

[0100] The graphical user interface 900 may also include keys 970. Keys 970 may be similar to the previously described key 770. Keys 970 include three categories: indicators 971 corresponding to no motion damage, indicators 973 corresponding to motion damage, and indicators 972 corresponding to insufficient data.

[0101] In some aspects, the graphical user interface 900 may include a graph 950. The graph 950 includes an x-axis 951 corresponding to time. This x-axis 951 may correspond to units of frames (such as ultrasound image frames) or any other unit of time. In some aspects, the graph 950 includes a y-axis 952 corresponding to a measure such as volume. In some aspects, the y-axis 952 may correspond to any other suitable measure, such as any measure quantified, for example, at step 512 of method 500. The graph 950 includes a dataset 910 corresponding to periodic measurements. Several periodic cycles, such as heartbeats, are shown in the graph 950. For example, regions 910a, 910b, 910c, 910d, and 910e may each correspond to a heartbeat.

[0102] The graph 950 may include several indicators corresponding to any of the three categories of key 970. For example, indicator 953 may be positioned above a portion of graph 950. This indicates to the user that the ultrasound image corresponding to that region of graph 950 is motion-damped. Therefore, no data is present in that region because it has been discarded. Indicator 954 is shown positioned above curve 910 along regions 910a and 910b. This indicates to the user that the ultrasound images corresponding to regions 910a and 910b are not motion-damped. Indicator 956 is shown on a portion of region 910c. This indicates to the user that the ultrasound image corresponding to the portion of region 910c corresponding to indicator 956 is motion-damped. As a result, no data is shown in that portion of region 910c. Indicators 955 and 957 are positioned on either side of indicator 956. These indicators may indicate insufficient data. In this respect, the ultrasound images obtained in the regions corresponding to indicators 955 and 957 may not be motion-damped. However, because they are in the same region 910c corresponding to a single heartbeat, ultrasound image frames obtained without motion damage within region 910c cannot be used, since not all ultrasound images of region 910c were obtained without motion damage (e.g., the ultrasound image corresponding to indicator 956 is motion-damped and comes from the same heartbeat corresponding to region 910c). Indicator 958 is shown positioned above regions 910d and 910e. Similar to indicator 954, this indicator can indicate that the ultrasound images of regions 910d and 910e are not motion-damped and display data.

[0103] In some aspects, such as Figure 8 As shown, metrics can be calculated and displayed for each available heartbeat in graph 950. For example, graph 950 includes metrics 981 corresponding to the ejection fraction and stroke volume of the first heartbeat corresponding to region 910a. These metrics can be calculated based solely on the ultrasound image of the first heartbeat in region 910a. Similarly, graph 950 also includes metrics 982 corresponding to the ejection fraction and stroke volume of the second heartbeat corresponding to region 910b. Graph 950 also includes metrics 983 corresponding to the ejection fraction and stroke volume of the third heartbeat corresponding to region 910d. Graph 950 also includes metrics 984 corresponding to the ejection fraction and stroke volume of the fourth heartbeat corresponding to region 910e. As shown, in some cases, metrics may not be displayed above the heartbeat corresponding to region 910c because these ultrasound image frames are discarded. In some aspects, any suitable metric, including any metric described herein, can be calculated and displayed for each heartbeat as shown.

[0104] In some respects, Figure 9One aspect of this disclosure may be illustrated, wherein the user has the ability to interact with a graphical user interface to accept, view, or reject measurements. In some aspects, the user is able to view and modify the quantification of multi-heartbeat results. For example... Figure 9 As shown, the graphical user interface may also include an indicator 960. The indicator 960 can identify a specific pulsation being analyzed. For example, as shown in header 922 in the example graphical user interface 900, a measure of pulsation 2 corresponding to the region 910b identified by the indicator 960 within the graph 950 can be displayed. Users can view data and results for a specific pulsation by adjusting the indicator 960, which may also be referred to as a pulsation selection slider. In some aspects, users can move the indicator 960 to view other pulsations. Similarly, users can adjust the size of the indicator 960 by moving its edges to view other areas of the data. In some aspects, users can also select different data statistics for display.

[0105] In some aspects, users can modify the contours within individual ultrasound image frames of a selected pulsation. The results are updated based on the updated contours, and the graphical user interface displays the updated results. In some aspects, users can delete pulsations from multi-pulse analysis. Users can use indicator 960 to select a specific pulsation to view, examine the pulsation in terms of contour tracking and quantitative results, and then delete the pulsation if it is not optimal. In some aspects, users can modify the results associated with a specific pulsation, multiple pulsations, or all pulsations in an analysis.

[0106] Figure 10 This is a graphical representation of a method for extracting ultrasound images of motion-induced damage according to various aspects of this disclosure. Figure 10 This can correspond to blocks extracted by non-periodic motion (such as...) Figure 6 The method executed by the motion-damaged image extraction module 615).

[0107] The purpose of the non-periodic motion extraction block can be to identify frames corrupted by non-periodic motion, such as probe movement or patient breathing. This block can be designed based on image and signal processing methods reported in either U.S. Patent US6589917 to Jago et al., published July 8, 2003, or in IEEE Publication 66, No. 1, entitled “Image-Based Methods for Phase Estimation, Gating, and Temporal Superresolution of Cardiac Ultrasound” by DR. Chittajallu et al. (published January 2019), the entire contents of which are incorporated herein by reference.

[0108] In some aspects, the system's processor can use cardiac and respiratory phase estimation methods to identify ultrasound image frames with motion impairment. In some aspects, multiple ultrasound images 610 can be received by the processor. The multiple ultrasound images 610 can form a movie loop. A first step of the process may include generating a frame similarity matrix 1020. In some aspects, normalized cross-correlation is calculated for all frame pairs present in the loop, resulting in a symmetric frame similarity matrix 1020 of dimension N×N, where N is the number of frames in the movie loop. This can be illustrated by axes 1022 and 1024, each corresponding to the number of image frames in the movie loop. Each row of this metric can be considered as a univariate time series containing cardiac and non-periodic motion. Next, a trend extraction method (such as a Hodrick Prescott (“HP”) filter) can be applied to each row to separate periodic signatures corresponding to cardiac motion and non-periodic motion. In some respects, the HP filter decomposes the time series into a sum of two components, including (1) a low-frequency trend component corresponding to the aperiodic motion used to form the aperiodic motion matrix 1030 and a high-frequency seasonal component corresponding to the heartbeats forming the heartbeat matrix 1040. For example... Figure 10 As shown, each of the aperiodic motion matrix 1030 and the heartbeat matrix 1040 may each include an axis with the same length as the axis of matrix 1020. In some aspects, matrix 1030 may include axis 1032, and axis 1034 may have a length corresponding to the number of ultrasound images 610. Similarly, matrix 1040 may include axis 1042, and axis 1044 may have a length corresponding to the number of ultrasound images 610.

[0109] like Figure 10 As shown, a periodogram can be calculated for each row of the heartbeat matrix 1040. In some aspects, the entropy of the spectral density can be estimated, and the row with the minimum entropy can be selected for aperiodic motion extraction, and the corresponding time series from the aperiodic motion matrix 1030 can be extracted from the determined frame number. Furthermore, the instantaneous phase can be extracted from the selected time series using a transformation, thereby obtaining... Figure 10 The non-periodic motion phase curve 1050 is shown. Curve 1050 may include an x-axis 1052, which corresponds to the frame number and includes the total number of frames in the ultrasound image 610. Curve 1050 may also include a y-axis corresponding to the phase. Highlighted areas 1058 and 1059 of the phase curve 1050 may correspond to the non-periodic motion. Figure 10In the example, the most aperiodic motion occurs in frames located around local minima of the phase curve, corresponding to a sharp change in phase value from maximum to minimum (1 to 0). To identify these frames, the phase values ​​around the local minima can be used as a filter. The following equation can be used to identify frames corrupted by aperiodic motion: in, w =0.2. In some respects, w You can choose based on experience.

[0110] Figure 11 This is a graphical representation of a method for identifying motion-damaged ultrasound images according to various aspects of this disclosure. Figure 11 Additional or alternative methods for identifying ultrasound images with non-periodic and / or non-cardiac motion can be described.

[0111] For example, another approach for non-periodic motion detection could include strain estimation using speckle tracking employed in speckle-tracking echocardiography. In some aspects, a sub-region of interest 1112 containing bright speckle content from the myocardium can be selected for speckle tracking. The selection process for the sub-region of interest 1112 can be automated using deep learning object detection methods such as Mask R-CNN, YOLO, or any other suitable deep learning method. In some aspects, a fixed search region 1114 surrounding the center of the sub-region of interest 1112 can be provided as input. This input can be provided by the user or as the output of a deep learning method. In some aspects, this input can be provided to a tracking algorithm. In this application, the search region 1114 can be set to a fixed number of pixels in both the axial and lateral dimensions. In some aspects, the inter-frame trajectory of the sub-region of interest 1112 can be tracked over the entire movie loop, and a median filter can be applied to estimate the trajectory. In some aspects, the trajectory is a vector containing both axial and lateral components. For example, the axial displacement component might be sufficient to identify frames with non-periodic motion damage. In other examples, the lateral displacement component may be sufficient to identify frames with non-periodic motion damage. The axial displacement component and the lateral displacement component can be shown in axial displacement diagram 1120 and lateral displacement diagram 1130, respectively.

[0112] In this regard, axial displacement diagram 1120 may include an x-axis 1124 corresponding to the frame number and a y-axis 1122 corresponding to the pixel. In this regard, the axial displacement of the sub-region of interest 1112 within the ultrasound image can be tracked by dataset 1126 and shown within diagram 1120. As shown, most of dataset 1126 corresponds to relatively uniform periodic motion. However, spikes 1128 in dataset 1126 illustrate how the non-periodic motion of the shown sub-region of interest 1112 is highlighted as shown by region 1129.

[0113] Similarly, the lateral displacement map 1120 may include an x-axis 1134 corresponding to the frame number and a y-axis 1132 corresponding to the pixel. In this regard, the lateral displacement of the sub-region of interest 1112 within the ultrasound image can be tracked by dataset 1136 and shown in Figure 1130. As shown, most of dataset 1136 corresponds to relatively uniform periodic motion. However, the spike 1138 in dataset 1136 illustrates how the non-periodic motion of the shown sub-region of interest 1112 is highlighted by region 1130.

[0114] In some aspects, the processor can implement reference Figure 10 The methods described and references Figure 11 Various combinations of the methods described. For example, one could use... Figure 10 The method is used to extract estimates of non-periodic motion. Then, it is possible to use... Figure 11 The method is used to track frames identified as having aperiodic motion. Frames identified as having aperiodic motion by both methods can then be discarded from the analysis.

[0115] In an additional aspect, ultrasound image frames with non-periodic motion can be identified based on accelerometer data from the ultrasound probe in an IMU data stream combined with movie loop storage. Frames corrupted by probe motion can be identified using the IMU data stream. The results from the IMU and image-based data analysis can then be combined to identify frames corrupted by non-periodic motion.

[0116] In an additional aspect, ultrasound image frames with non-periodic motion can be identified based on the motion-compensated normalized cross-correlation between the original movie loop and the motion-compensated movie loop. For example, speckle tracking can be used to estimate the accumulated Lagrange displacement field. Then, assuming a first reference as the time reference frame, all frames with movie loops can be warped to the first frame. Inter-frame NCC can then be estimated between the first frame and all warped frames. Frames corresponding to low motion-compensated NCC can be classified as frames corrupted by non-periodic motion. In this regard, non-periodic motion can cause peak jump errors in the estimated displacement field, resulting in inaccurate motion compensation and low NCC values.

[0117] In an additional aspect, a deep learning model can be used to identify ultrasound image frames with non-periodic motion. The input to the deep learning model can be a stored movie loop, and the output can be the frame number of the motion-damaged image. During training, expert annotation can be performed at the frame level to identify frames with and without motion damage. A deep learning classification model, such as ResNet, EfficientNet, Inceptionv3, or any other suitable deep learning model, can then be trained to provide frame-level predictions. Each frame can be classified into two categories, such as damaged or undamaged. Finally, using the frame-level classification from the deep learning model, the movie loop can be segmented into optimal temporal data blocks for quantitative analysis.

[0118] Those skilled in the art will recognize that the above-described apparatus, systems, and methods can be modified in various ways. Therefore, those skilled in the art will understand that the aspects covered by this disclosure are not limited to the specific exemplary aspects described above. In this regard, although illustrative aspects have been shown and described, extensive modifications, alterations, and substitutions are contemplated in the foregoing disclosure. It should be understood that such changes can be made to the foregoing without departing from the scope of this disclosure. Therefore, it is appropriate that the claims be interpreted broadly and in a manner consistent with this disclosure.

Claims

1. An ultrasound imaging system (100), comprising: A processor (134) configured to communicate with a display (132), a transducer array (112) of a handheld ultrasound probe (110), and a memory (138), wherein the processor is configured to: Receive multiple ultrasound images (610) corresponding to views of the patient's anatomy; Identify one or more motion-damaged ultrasound images from among the multiple ultrasound images; Extract one or more motion-damaged ultrasound images from the multiple ultrasound images; A first time data block is formed, the first time data block including at least a subset (620) of the remaining ultrasound images from the plurality of ultrasound images; Determine whether the first time data block corresponds to at least one periodic period; After determining that the first time data block corresponds to at least one periodic cycle, patient metrics (725, 924) are calculated based on the first time data block; and Generate output for the display, the output including: The ultrasound images (720, 920) in the multiple ultrasound images; The patient metrics; The first status indicator (771, 971) corresponding to the first time data block; and The second state indicator (773, 973) corresponds to the extracted ultrasound image of motion damage.

2. The ultrasound imaging system according to claim 1, wherein, The processor (134) is also configured to determine the image quality of the plurality of ultrasound images (610).

3. The ultrasound imaging system according to claim 1 or 2, wherein, The processor (134) is also configured to identify one or more motion-damaged images by recognizing and tracking features within the multiple ultrasound images.

4. The ultrasound imaging system according to claim 3, wherein, In order to track the features, the processor (134) is configured to: Determine the positional variation of the feature within each of the multiple ultrasound images (610); and Identify ultrasound images in which the positional change of the feature exceeds a threshold.

5. The ultrasound imaging system according to any one of claims 1 to 4, wherein, The processor (134) is also configured to identify the one or more motion-damaged images based on one or more of the following: conventional image processing, RF data peak jump, AI image processing, AI processing of RF data, or AI processing of ultrasound B-mode data.

6. The ultrasound imaging system according to any one of claims 1 to 5, wherein, The patient measures include at least one of the following: end-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), ejection fraction (EF), global longitudinal strain (GLS), or cardiac output (CO).

7. The ultrasound imaging system according to any one of claims 1 to 6, wherein, The periodic cycle includes the heartbeat cycle.

8. The ultrasound imaging system according to any one of claims 1 to 7, wherein, The patient metrics include average values.

9. The ultrasound imaging system according to any one of claims 1 to 7, in, The first time data block includes a first subset (620) of the remaining ultrasound images from the plurality of ultrasound images; and The processor (134) is further configured to form a second time data block, the second time data block comprising a second subset (625) of the remaining ultrasound images from the plurality of ultrasound images. The first time data block and the second time data block are time-separated by the motion-damaged ultrasound images.

10. The ultrasound imaging system according to claim 9, wherein, The patient metric includes the average of data from the first time block and the second time block.

11. The ultrasound imaging system according to any one of claims 1 to 10, wherein, The processor (134) is also configured to receive input from the user indicating whether to accept or reject the patient measurement.

12. The ultrasound imaging system according to any one of claims 1 to 11, wherein, The processor (134) is also configured to receive a first user input that identifies a first periodic period of the first time data block.

13. The ultrasound imaging system according to claim 12, wherein, The processor (134) is also configured to discard a subset of ultrasound images corresponding to the first periodic period of the first time data block based on a second user input.

14. A method (500) for extracting motion-damaged ultrasound images from a set of acquired ultrasound images and performing quantization based on said acquired set, comprising: Multiple ultrasound images (610) are received (502) from an ultrasound imaging system (100), the multiple ultrasound images corresponding to views of the patient's anatomy; Identify one or more motion-damaged ultrasound images from among the multiple ultrasound images; Extract (504) one or more motion-damaged ultrasound images from the multiple ultrasound images; Form (506) a first time data block, the first time data block comprising at least a subset (620) of the remaining ultrasound images from the plurality of ultrasound images; Determine (508) whether the first time data block corresponds to at least one periodic period; After determining that the first time data block corresponds to at least one periodic period, a patient metric is calculated based on the first time data block (512). as well as Generate (514) output, the output including: The ultrasound images (720, 920) in the multiple ultrasound images; The patient metrics (725, 924); The first status indicator (771, 971) corresponding to the first time data block; and The second state indicator (773, 973) corresponds to the extracted ultrasound image of motion damage.

15. A computer program product comprising computer-readable instructions that, when executed by a processor, cause the processor to perform the method according to claim 14.

Images