Ultrasound imaging techniques for shear wave elastography
Automatically positioning the liver area of interest and performing shear wave elastic imaging through the ultrasound imaging system, solving the problem of liver hardness evaluation in NAFLD diagnosis, achieving non-invasive and accurate liver hardness measurement, reducing diagnostic costs and errors.
Patent Information
- Application Number
- CN202410639304.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-06-05
- Filing Date
- 2024-05-22
- Publication Date
- 2024-12-06
AI Technical Summary
The prior art is difficult to effectively diagnose and evaluate non-alcoholic fatty liver disease (NAFLD), especially due to biomarking problems caused by increased liver hardness, and traditional examination methods are invasive and expensive, and are affected by sampling errors and interpretation volatility.
Automatically identify and locate areas of interest in the liver through ultrasound imaging system, perform shear wave elastic imaging, measure the hardness of liver tissue, and display the angle and spatial relationship between the probe and the liver in real time to ensure accuracy and non-invasiveness. .
A non-invasive and accurate liver hardness assessment is achieved, which reduces diagnostic costs, reduces sampling error and interpretation volatility, and improves diagnostic efficiency.
Smart Images

Figure CN119074043A_ABST
Abstract
Description
Background Art
[0001] In general, the present application relates to ultrasound imaging and shear wave elastography. Non-alcoholic fatty liver disease (NAFLD) is a cause of chronic liver disease, which can be characterized by the accumulation of excess fat in the liver or caused by the accumulation of excess fat in the liver, leading to damage and inflammation. Currently, the incidence of NAFLD in the United States is on the rise, resulting in considerable medical costs. Liver biopsy can be used to diagnose NAFLD, but it is an invasive and relatively expensive test and may be affected by sampling errors and interpretation fluctuations. Due to these limitations, non-invasive alternatives have been developed, including ultrasound. As NAFLD progresses, liver stiffness increases, making it a biomarker. Shear wave elastography (SWE) is an ultrasound method that can measure or estimate the stiffness of liver tissue. Summary of the invention
[0002] According to an embodiment, a method includes: receiving ultrasound image data of a patient, including a segmented region corresponding to a liver; automatically identifying an interval of a region of interest within the segmented region, wherein the region of interest corresponds to a region in the liver for performing shear wave elastography; and presenting the ultrasound image data and the interval of the region of interest on a display. The method may also include segmenting the ultrasound image data to form a segmented region. The interval of the region of interest may be a region of interest. The method may also include receiving an input to locate the region of interest within the interval of the region of interest. The step of automatically identifying the interval of the region of interest within the segmented region may also include: determining a first mask by filtering pixels that do not correspond to liver tissue; determining a second mask for identifying an axial position in the segmented region; determining a third mask for identifying a lateral position in the segmented region; and combining the first mask, the second mask, and the third mask to limit the interval of the region of interest within the segmented region. The first mask may filter out pixels corresponding to at least one blood vessel in the liver. The first mask may filter out pixels corresponding to at least one highly echogenic region in the liver. The step of automatically identifying the interval of the region of interest may also include: determining a fourth mask corresponding to the image data in the area caused by poor contact between the probe and the patient; and combining the first mask, the second mask, the third mask and the fourth mask to limit the interval of the region of interest in the segmented region. The method may also include performing shear wave elastic imaging to receive elastic information of the region of interest in the liver. The method may also include: determining the angle and spatial relationship between the segmented region and the ultrasound probe in real time; and presenting a dynamic real-time indicator corresponding to the angle and spatial relationship between the segmented region and the ultrasound probe on a display.
[0003] According to an embodiment, an ultrasound imaging system includes: a probe including at least one transducer configured to transmit ultrasound and receive reflected ultrasound; a display configured to present an illustration to an operator; and a processor configured to process data corresponding to the reflected ultrasound to determine a segmented region corresponding to the patient's liver, and the processor is further configured to cause the display to present an illustration, wherein the illustration includes image data of the segmented region and at least one dynamic region of interest indicator, the at least one dynamic region of interest indicator indicating a corresponding region of interest in the liver, from which the reflected ultrasound shear wave is processed to determine the elasticity of the liver. The system may also include a user interface, wherein the processor is configured to receive data indicating the final position of the region of interest from the user interface. The processor may be further configured to determine the region of interest by: determining a first mask by filtering pixels that do not correspond to liver tissue; determining a second mask for identifying an axial position in the segmented region; determining a third mask for identifying a lateral position in the segmented region; and combining the first mask, the second mask, and the third mask to limit the interval of the region of interest within the segmented region. The first mask may filter out pixels corresponding to at least one blood vessel in the liver. The first mask may filter out pixels corresponding to at least one hyperechoic region in the liver. The processor may be further configured to determine the region of interest by: determining a fourth mask corresponding to image data in a region caused by poor contact between the probe and the patient; and combining the first mask, the second mask, the third mask, and the fourth mask to limit the interval of the region of interest within the segmented region. The illustration may also include an indicator of poor probe contact. The system may also include a shear wave generator located outside the probe, which is used to generate ultrasonic shear waves in the region of interest. The processor may be further configured to: determine the angle and spatial relationship between the segmented region and the ultrasound probe in real time; and include a dynamic indicator in the illustration, which indicates the angle and spatial relationship between the segmented region and the ultrasound probe in real time. The processor may be further configured to determine the distance between the epidermis contacting the probe and the segmented region. BRIEF DESCRIPTION OF THE DRAWINGS
[0004] Figure 1 An ultrasound system according to an embodiment is shown.
[0005] Figure 2 An ultrasound system for performing shear wave elastography is shown in accordance with an embodiment.
[0006] Figure 3 An ultrasound imaging system according to an embodiment is shown.
[0007] Figure 4 Ultrasound image data is shown.
[0008] Figure 5 A segmented liver is shown according to an embodiment.
[0009] Figure 6 A segmented liver mask is shown according to an embodiment.
[0010] Figure 7 A bad probe contact mask is shown according to an embodiment.
[0011] Figure 8 A bad probe contact artifact mask is shown in accordance with an embodiment.
[0012] Fig. 9 A liver tissue mask is shown according to an embodiment.
[0013] Fig.10 An axial distance mask according to an embodiment is shown.
[0014] Fig.11 A lateral distance mask according to an embodiment is shown.
[0015] Fig.12 A mask combination according to an embodiment is shown.
[0016] Fig.13 A mask combination with identified intervals for placing regions of interest is shown, according to an embodiment.
[0017] Fig.14 A graphical representation of ultrasound image data with indicators is shown according to an embodiment.
[0018] Fig.15A , Fig. 15B and Fig. 15C Steps for generating a liver tissue mask are shown according to an embodiment.
[0019] Fig.16 A technique for generating a bad probe contact indicator according to an embodiment is shown.
[0020] Fig.17 A technique for determining the extent of bad probe contact image data according to an embodiment is shown.
[0021] The foregoing summary of the invention and the following detailed description of certain technologies of the present application will be better understood when read in conjunction with the accompanying drawings. For illustrative purposes, certain technologies are shown in the accompanying drawings. However, it should be understood that the claims are not limited to the arrangements and tools shown in the accompanying drawings. DETAILED DESCRIPTION
[0022] Disclosed herein are embodiments of ultrasound methods and systems for identifying one or more regions of interest (referred to herein as "regions of interest" or "ROIs," unless otherwise specified) in a patient's liver and obtaining shear wave elastography measurements of the regions of interest. The regions of interest may indicate locations in the liver from which propagation of shear waves is tracked as part of a shear wave elastography process. The propagation of these shear waves in liver tissue in the regions of interest may be analyzed to determine or estimate the stiffness of the liver tissue. The regions of interest may be located automatically, or the location may be facilitated by an automated process. The regions of interest may be located based on analysis of B-mode ultrasound image data (or other image data), wherein the liver capsule or liver (referred to herein as "liver," unless otherwise specified). Various aspects of the segmented liver image data may be evaluated to locate the regions of interest. The location of the regions of interest may be fully automatic, or one or more options may be provided to the operator for manually locating the regions of interest. Embodiments herein also disclose determining and illustrating intervals in the image data corresponding to poor contact of the probe with the patient's epidermis when locating the regions of interest.
[0023] When reading in conjunction with the accompanying drawings, the following specific embodiments of the aforementioned invention content and certain embodiments will be better understood. In terms of the scope of the figures of the functional blocks of each embodiment shown in the accompanying drawings, these functional blocks do not necessarily represent the division between the hardware circuits. Therefore, for example, one or more functional blocks (e.g., processors or memory) can be implemented in a single piece of hardware (e.g., a general signal processor or random access memory block, a hard disk, etc.) or multiple hardware components. Similarly, a program can be an independent program, can be incorporated into an operating system as a subroutine, can be a function in an installed software package, etc. It should be understood that each embodiment is not necessarily limited to the arrangement and tools shown in the accompanying drawings. It should also be understood that the embodiments can be combined as should be understood, or other embodiments can be utilized, and structural, logical and electrical changes can be made without departing from the scope of each embodiment. Therefore, the following detailed description should not be considered as a restrictive meaning, and the scope of the present invention is limited by the attached claims and their equivalents.
[0024] As used herein, elements or steps listed in the singular and beginning with the word "a" or "an" should be understood not to exclude a plurality of said elements or steps, unless such exclusion is explicitly stated. Furthermore, reference to "one embodiment" or "an embodiment" is not intended to be interpreted as excluding the existence of other embodiments that also include the described features. Furthermore, unless explicitly stated otherwise, an embodiment that "comprises" or "has" an element or elements having a particular property may include additional elements that do not have that property.
[0025] In addition, as used herein, the term "image" or "image data" refers in a broad sense to both a visible image and data representing a visible image. Some embodiments generate (or are configured to generate) at least one visible image. In addition, as used herein, the term "image" or "image data" is used to refer to an ultrasound mode, such as B-mode, CF mode and / or a sub-mode of B-mode and / or CF, such as shear wave elastic imaging (SWEI), TVI, Angio, B-flow, BMI, BMI_Angio, and in some cases also includes MM, CM, PW, TVD, CW, where "image" and / or "plane" includes a single beam or multiple beams.
[0026] Furthermore, as used herein, the term processor or processing unit refers to any type of processing unit that can perform the computations of the various embodiments, such as single-core or multi-core: CPU, graphics board, DSP, FPGA, ASIC, or combinations thereof.
[0027] Various embodiments of generating or forming an image described herein may include a process for forming an image that includes beamforming in some embodiments and does not include beamforming in other embodiments. For example, an image may be formed without beamforming, such as by multiplying a matrix of demodulated data by a matrix of coefficients such that the product is an image and wherein the process does not form any "beams." Additionally, the formation of an image may be performed using a combination of channels that may originate from more than one transmit event (e.g., synthetic aperture techniques).
[0028] In various embodiments, ultrasound processing to form images, including ultrasound beamforming, such as receive beamforming, is performed, for example, in software, firmware, hardware, or a combination thereof. One specific implementation of an ultrasound system having a software beamformer architecture formed according to various embodiments disclosed herein.
[0029] Furthermore, as used herein, the term processor or processing unit refers to any type of processing unit, whether single-core or multi-core: CPU, accelerated processing unit (APU), graphics board, DSP, FPGA, ASIC, or a combination thereof, that can perform the required computations required by various embodiments.
[0030] Other embodiments may provide a computer-readable device and / or a non-transitory computer-readable medium, and / or a machine-readable device and / or a non-transitory machine-readable medium, on which a machine code and / or a computer program having at least one code segment executable by a machine and / or a computer is stored, so that the machine and / or the computer performs the steps for automatically estimating the hepatorenal index (HRI) from ultrasound images as described herein.
[0031] Therefore, the present disclosure may be implemented in hardware, software, or a combination of hardware and software. The present disclosure may be implemented in a centralized manner in at least one computer system, or in a distributed manner, where different elements are distributed across several interconnected computer systems. Any type of computer system or other device suitable for executing the methods described herein is suitable.
[0032] The various embodiments may also be embedded in a computer program product, which comprises all the features enabling the implementation of the methods described herein and which, when loaded into a computer system, is capable of carrying out these methods. A computer program herein refers to any expression of a set of instructions in any language, code or notation, which is intended to cause a system with information processing capabilities to perform specific functions directly or after either or both of the following: a) conversion into another language, code or notation; b) reproduction in a different material form.
[0033] Although the present disclosure has been described with reference to certain embodiments, it will be appreciated by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the scope of the present disclosure. In addition, many modifications may be made to adapt specific circumstances or materials to the teachings of the present disclosure without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the specific embodiments disclosed, but the present disclosure will include all embodiments falling within the scope of the appended claims.
[0034] Figure 1 is a block diagram of an exemplary ultrasound system 100 operable to segment the liver and automatically determine regions of interest therein, according to various embodiments. Figure 1 , an ultrasound system 100 and a training system 190 are shown. The ultrasound system 100 includes a transmitter 102, an ultrasound probe 104, a transmit beamformer 110, a receiver 118, a receive beamformer 120, an A / D converter 122, an RF processor 124, an RF / IQ buffer 126, a user input device 130, a signal processor 132, an image buffer 136, a display system 134, and an archive 138.
[0035] The transmitter 102 may include suitable logic, circuitry, interfaces, and / or code operable to drive the ultrasound probe 104. The ultrasound probe 104 may include a two-dimensional (2D) array of piezoelectric elements. The ultrasound probe 104 may include a set of transmit transducer elements 106 and a set of receive transducer elements 108 that are generally constructed of the same elements. In certain embodiments, the ultrasound probe 104 is operable to acquire ultrasound image data covering at least a majority of an anatomical structure, such as the liver or any suitable anatomical structure.
[0036] The transmit beamformer 110 may include suitable logic, circuitry, interfaces, and / or code operable to control the transmitter 102 to drive the set of transmit transducer elements 106 via the transmit sub-aperture beamformer 114 to transmit ultrasound transmit signals into a region of interest (e.g., a person, an animal, an underground cavity, a physical structure, etc.). The transmitted ultrasound signals may be backscattered from structures in the object of interest (such as blood cells or tissue) to generate echoes. The echoes are received by the receive transducer elements 108.
[0037] The set of receive transducer elements 108 in the ultrasound probe 104 may be operable to convert received echoes into analog signals, sub-aperture beamformed by the receive sub-aperture beamformer 116, and then transmitted to the receiver 118. The receiver 118 may include suitable logic, circuitry, interfaces, and / or code that may be operable to receive the signals from the receive sub-aperture beamformer 116. The analog signals may be transmitted to one or more of the plurality of A / D converters 122.
[0038] The plurality of A / D converters 122 may include suitable logic components, circuits, interfaces, and / or codes that are operable to convert analog signals from the receiver 118 into corresponding digital signals. The plurality of A / D converters 122 are disposed between the receiver 118 and the RF processor 124. Nevertheless, the present disclosure is not limited in this regard. Therefore, in some embodiments, the plurality of A / D converters 122 may be integrated within the receiver 118.
[0039] The RF processor 124 may include suitable logic components, circuits, interfaces, and / or codes that are operable to demodulate the digital signals output by the plurality of A / D converters 122. According to an embodiment, the RF processor 124 may include a complex demodulator (not shown) that is operable to demodulate the digital signals to form I / Q data pairs representing corresponding echo signals. The RF or I / Q signal data may then be transferred to the RF / IQ buffer 126. The RF / IQ buffer 126 may include suitable logic components, circuits, interfaces, and / or codes that are operable to provide temporary storage of the RF or I / Q signal data generated by the RF processor 124.
[0040] The receive beamformer 120 may comprise suitable logic, circuitry, interfaces, and / or code operable to perform digital beamforming processing, e.g., to sum delayed channel signals received from the RF processor 124 via the RF / IQ buffer 126 and output a beam summed signal. The resulting processed information may be a beam summed signal output from the receive beamformer 120 and communicated to the signal processor 132. According to some embodiments, the receiver 118, the plurality of A / D converters 122, the RF processor 124, and the beamformer 120 may be integrated into a single beamformer, which may be a digital beamformer. In various embodiments, the ultrasound system 100 includes a plurality of receive beamformers 120.
[0041] The user input device 130 may be used to enter patient data, scan parameters, settings, select a protocol and / or template, select an exam type, select a desired ultrasound image view, select an active sample identification algorithm, reposition an automatically placed region of interest, etc. In an exemplary embodiment, the user input device 130 is operable to configure, manage, and / or control the operation of one or more components and / or modules in the ultrasound system 100. In this regard, the user input device 130 is operable to configure, manage, and / or control the operation of the transmitter 102, ultrasound probe 104, transmit beamformer 110, receiver 118, receive beamformer 120, RF processor 124, RF / IQ buffer 126, user input device 130, signal processor 132, image buffer 136, display system 134, and / or archive 138. The user input device 130 may include a button, a rotary encoder, a touch screen, a touch pad, a trackball, motion tracking, voice recognition, a mouse device, a keyboard, a camera, and / or any other device capable of receiving user instructions. In some embodiments, for example, one or more of the user input devices 130 may be integrated into other components such as the display system 134. For example, the user input device 130 may include a touch screen display.
[0042] The signal processor 132 may include suitable logic components, circuits, interfaces and / or codes that are operable to process ultrasound scan data (i.e., summed IQ signals) to generate an ultrasound image for presentation on a display system 134. The signal processor 132 is operable to perform one or more processing operations based on a plurality of selectable ultrasound modalities on the acquired ultrasound scan data. In an exemplary embodiment, the signal processor 132 may be used to perform display processing and / or control processing, etc. The acquired ultrasound scan data may be processed in real time during a scanning session as echo signals are received. Additionally or alternatively, the ultrasound scan data may be temporarily stored in the RF / IQ buffer 126 during a scanning session and processed in a less real-time manner in an online operation or an offline operation. In various embodiments, the processed image data may be presented at the display system 134 and / or may be stored at an archive 138. The archive 138 may be a local archive, a picture archiving and communication system (PACS), an enterprise archive (EA), a vendor-independent archive (VNA), or any suitable device for storing images and related information.
[0043] The signal processor 132 may be one or more central processing units, microprocessors, microcontrollers, etc. For example, the signal processor 132 may be an integrated component, or may be distributed in various locations. In an exemplary embodiment, the signal processor 132 may include an image analysis processor 140, a segmentation processor 150, a sample identification processor 160, and a region of interest (ROI) positioning processor 170. The signal processor 132 may be capable of receiving input information from the user input device 130 and / or the archive 138, receiving image data, generating output that can be displayed by the display system 134, and manipulating the output in response to the input information from the user input device 130, etc. The signal processor 132 including the image analysis processor 140, the segmentation processor 150, the sample identification processor 160, and the region of interest (ROI) positioning processor 170 can, for example, execute any of the methods and / or instruction sets discussed herein according to various embodiments.
[0044] The ultrasound system 100 is operable to continuously acquire ultrasound scan data at a frame rate suitable for the imaging situation under consideration. Typical frame rates are in the range of 20 to 120, but may be lower or higher. The acquired ultrasound scan data may be displayed on a display system 134 at a display rate that is the same as the frame rate, or at a display rate that is slower or faster than the frame rate. An image buffer 136 is included to store processed frames of acquired ultrasound scan data that are not scheduled for immediate display. Preferably, the image buffer 136 has sufficient capacity to store ultrasound scan data frames equivalent to at least several minutes. The frames of ultrasound scan data are stored in a manner that is easy to retrieve from them according to their acquisition order or time. The image buffer 136 may be embodied as any known data storage medium.
[0045] The signal processor 132 may include an image analysis processor 140 that includes suitable logic, circuitry, interfaces, and / or code that is operable to analyze acquired ultrasound image data to determine whether a desired ultrasound image view has been obtained. For example, the image analysis processor 140 may analyze ultrasound image data acquired by the ultrasound probe 104 to determine whether a desired view, such as any suitable ultrasound image view of the liver, has been obtained. Once the desired image view is obtained, the image analysis processor 140 may instruct the signal processor 132 to freeze the view presented at the display system 134. The view may be stored in the archive 138 and / or at any suitable data storage medium. The image analysis processor 140 may include, for example, an artificial intelligence image analysis algorithm, one or more deep neural networks (e.g., a convolutional neural network, such as ENet), and / or may utilize any suitable image analysis technology or machine learning processing functionality configured to determine whether a desired view has been obtained. Additionally and / or alternatively, artificial intelligence image analysis techniques or machine learning processing functionality configured to provide image analysis techniques may be provided by different processors or distributed across multiple processors at the ultrasound system 100 and / or distributed across a remote processor communicatively coupled to the ultrasound system 100. In various embodiments, the image analysis processor 140 may include suitable logic, circuitry, interfaces, and / or code that is operable to provide quality metrics associated with an acquired view. For example, the image analysis processor 140 may analyze an acquired ultrasound image view (as a whole), a region of an acquired ultrasound image view, an acquired ultrasound image view segmented by a segmentation processor 150, and the like to provide quality metrics associated with the acquired view. The image analysis processor 140 may be configured to cause the display system 134 to compare the quality metrics with an acquired ultrasound image view. Figure 1For example, the quality metric may be a score (e.g., 1, 2, 3, 4, 5), a grade (e.g., A, B, C, D, F), a rating (e.g., excellent, good, fair, poor), a color coding (e.g., green, yellow, red), etc. for the acquired ultrasound image view (as a whole) and / or each region of the acquired ultrasound image view. The quality metric may help the user determine whether to continue acquiring the view or to obtain additional ultrasound image data. The image analysis processor 140 may store the quality metric in an archive and / or any suitable data storage medium.
[0046] The signal processor 132 may include a segmentation processor 150, which includes suitable logic, circuits, interfaces and / or codes that are operable to segment the flow image frames and the B-mode frames. The segmentation processor 150 can be used to identify the liver in the obtained ultrasound image view. In this regard, the segmentation processor 150 may include, for example, an artificial intelligence image analysis algorithm, one or more deep neural networks (e.g., convolutional neural networks, such as ENet), and / or may utilize any suitable form of artificial intelligence image analysis technology or machine learning processing functions configured to provide automated segmentation functions. Additionally and / or alternatively, the artificial intelligence image analysis technology or machine learning processing functions configured to provide automated segmentation may be provided by different processors or distributed on multiple processors at the ultrasound system 100 and / or distributed on remote processors communicatively coupled to the ultrasound system 100. For example, the image segmentation function may be provided as a deep neural network, which may be composed of, for example, an input layer, an output layer, and one or more hidden layers between the input layer and the output layer. Each layer may be composed of multiple processing nodes that may be referred to as neurons. For example, an image segmentation function may include an input layer having neurons for each sample or a group of samples from an acquired ultrasound image view of the liver and kidneys. The output layer may have neurons corresponding to a variety of predefined anatomical structures, such as the liver, the renal cortex, or any suitable anatomical structure. Each neuron in each layer may perform a processing function and pass the processed ultrasound image information to one of the multiple neurons in the downstream layer for further processing. For example, neurons in the first layer may learn to identify structural edges in an acquired ultrasound image. Neurons in the second layer may learn to recognize shapes based on detected edges from the first layer. Neurons in the third layer may learn the location of the recognized shapes relative to landmarks in the acquired ultrasound image. The processing performed by the deep neural network can identify anatomical structures and the locations of the structures in the acquired ultrasound image with a high probability.
[0047] In an exemplary embodiment, the segmentation processor 150 can be configured to store the image segmentation information in the archive 138 and / or any suitable storage medium. The segmentation processor 150 can be configured to cause the display system 134 to present the image segmentation information together with the acquired ultrasound image. The image segmentation information can be provided to the image analysis processor 140 for providing a quality metric associated with the acquired ultrasound image view, as discussed above. The image segmentation information can be provided to the sample identification processor 160 for identifying valid samples in the liver of the acquired ultrasound image, as described below.
[0048] Still reference Figure 1 , the training system 190 may include a training engine 192 and a training database 194. The training engine 192 may include suitable logic components, circuits, interfaces and / or codes that are operable to train neurons of a deep neural network (e.g., an artificial intelligence model) inferred (i.e., deployed) by the image analysis processor 140, the segmentation processor 150, the sample identification processor 160 and / or the ROI positioning processor 170. For example, the artificial intelligence model inferred by the image analysis processor 140 may be trained to automatically identify ultrasound image views (e.g., liver capsule). The artificial intelligence model inferred by the segmentation processor 150 may be trained to automatically segment the obtained ultrasound image views to identify anatomical structures (e.g., liver). For example, the training engine 192 may use the database to train the deep neural network deployed by the image analysis processor 140 and / or the segmentation processor 150. The ultrasound image may include an ultrasound image of a particular anatomical feature such as a liver, or any suitable ultrasound image and feature.
[0049] In certain embodiments, the training engine 192 and / or the training database 194 may be a remote system communicatively coupled to the ultrasound system 100 via a wired or wireless connection, such as Figure 1 As shown. Additionally and / or alternatively, components or all of the training system 190 can be integrated with the ultrasound system 100 in various forms. In some embodiments, the training system 190 can be separate from the ultrasound system 100, and a model can be trained, which can then be included in the ultrasound system 100. For example, a model can be trained to segment the liver capsule or the liver, and the trained model can then be included in the ultrasound system 100, for example as part of the signal processor 132 or associated memory. Certain types of training are disclosed in U.S. Serial No. 18 / 205,804, filed on June 5, 2023, which is incorporated herein by reference in its entirety.
[0050] Figure 2A block diagram of an exemplary ultrasound system 200 is shown that is operable to perform a shear wave elastography procedure, for example, to obtain information about liver tissue in a region of interest. The ultrasound system 200 may be similar to and / or share components with the ultrasound system 100. For example, the ultrasound system 200 and the ultrasound system 100 may be integrated with each other. For example, there may be only one system that performs conventional ultrasound imaging and shear wave elastography. Figure 2 An ultrasound system 200 and a vibrating device or transducer 20 are shown. The transducer 20 may be located external to the ultrasound system 200. The transducer 20 may be configured to provide an external "push" force 22 to generate shear waves 5 in tissue 1 of a patient. As will be discussed further, the tissue 1 may be liver tissue or tissue or structure proximate to liver tissue. Additionally and / or alternatively, the ultrasound system 200 itself may provide a push force, such as a relatively high intensity ultrasound push pulse 205, for generating shear waves 5 in the tissue 1. The ultrasound system 200 includes a transmitter 202 (e.g., similar or identical to the transmitter 102 ), an ultrasound probe (or “probe”) 204 (e.g., similar or identical to the probe 104 ), a transmit beamformer 210 (e.g., similar or identical to the transmit beamformer 110 ), a receiver 218 (e.g., similar or identical to the receiver 118 ), a receive beamformer 220 (e.g., similar or identical to the receive beamformer 120 ), an RF processor 224 (e.g., similar or identical to the RF processor 124 ), an RF / IQ buffer 226 (e.g., similar or identical to the RF / IQ buffer 126 ), a user input module 230 (e.g., similar or identical to the user input module 130 ), a signal processor 132 (e.g., similar or identical to the signal processor 132 ), an image buffer 236 (e.g., similar or identical to the image buffer 136 ), and a display system 234 (e.g., similar or identical to the display system 134 ).
[0051] The transmitter 202 may include suitable logic, circuitry, interfaces and / or code operable to drive a transducer ultrasound probe 204. The ultrasound probe 204 may include a one-dimensional (1D, 1,25D, 1,5D or 1,75D) array or a two-dimensional (2D) array of transducers such as piezoelectric elements. The ultrasound probe 204 may include a transmitting transducer element 106 and a receiving transducer element 208 that may be fully coextensive, partially coextensive or separated.
[0052] The transmit beamformer 210 may comprise suitable logic, circuitry, interfaces and / or code operable to control the transmitter 202 to drive the transmit transducer elements 206 via the transmit sub-aperture beamformer 214 to transmit relatively high intensity ultrasound push pulses 205 into the interference points of the tissue 1 and to transmit ultrasound transmit signals 207 into the region of interest of the tissue 1. As used herein, the term “high intensity ultrasound push pulse” refers to an ultrasound transmit signal 207 having a relatively high intensity and a relatively high intensity. 2 Up to 700mW / cm 2 The derated spatial peak time average intensity (ISPTA.3) between the interference points. The transmitted high-intensity ultrasonic push pulse 205 can displace the tissue 1 to produce a shear wave 5 that propagates laterally from the interference point. The transmitted ultrasonic signal 207 can be reflected from structures such as the tissue 1 deformed by the shear wave 5 to produce an echo 209. The echo 209 is received by the receiving transducer element 208. The group of receiving transducer elements 208 in the ultrasonic probe 204 is operable to convert the received echo 209 into an analog signal, perform sub-aperture beamforming through the receiving sub-aperture beamformer 216, and then transmit it to the receiver 218.
[0053] The receiver 218 may include suitable logic, circuitry, interfaces, and / or code operable to receive and demodulate signals from the receive subaperture beamformer 216. The demodulated analog signals may be communicated to one or more A / D converters of the plurality of A / D converters 222 (e.g., similar to the A / D converter 122). The plurality of A / D converters 222 may include suitable logic, circuitry, interfaces, and / or code operable to convert the demodulated analog signals from the receiver 218 into corresponding digital signals. The plurality of A / D converters 222 are disposed between the receiver 218 and the receive beamformer 220. However, the invention is not limited in this respect. Thus, in some embodiments, the plurality of A / D converters 222 may be integrated within the receiver 218.
[0054] The receive beamformer 220 may comprise suitable logic, circuitry, interfaces, and / or code operable to perform digital beamforming processing on signals received from the plurality of A / D converters 222. The resulting processed information may be converted back into corresponding RF signals. The corresponding output RF signals output from the receive beamformer 220 may be communicated to the RF processor 224. According to some embodiments, the receiver 218, the plurality of A / D converters 222, and the beamformer 220 may be integrated into a single beamformer, which may be a digital beamformer.
[0055] The RF processor 224 may include suitable logic components, circuits, interfaces and / or codes that can operate to demodulate the RF signal. According to an embodiment, the RF processor 224 may include a complex demodulator (not shown) that can operate to demodulate the RF signal to form an I / Q data pair representing the corresponding echo signal. The RF or I / Q signal data can then be transmitted to the RF / IQ buffer 226.
[0056] The RF / IQ buffer 226 may comprise suitable logic, circuitry, interfaces and / or code that may be operable to provide temporary storage of RF or I / Q signal data generated by the RF processor 224 .
[0057] The user input module 230 may be used to initiate shear wave elastography, change scan modes, enter patient data, surgical instrument data, scan parameters, set up, configure parameters, etc. In an exemplary embodiment, the user input module 230 is operable to configure, manage, and / or control the operation of one or more components and / or modules in the ultrasound system 200. In this regard, the user input module 230 is operable to configure, manage, and / or control the operation of the transmitter 202, the ultrasound probe 204, the transmit beamformer 210, the receiver 218, the receive beamformer 220, the RF processor 224, the RF / IQ buffer 226, the user input module 230, the signal processor 232, the image buffer 236, and / or the display system 234. The user input module 230 may be located at various locations on and / or around the ultrasound system 200, such as on the probe 204, at a control panel, and / or at any suitable location.
[0058] The signal processor 232 may include suitable logic components, circuits, interfaces and / or codes that are operable to process ultrasound information (i.e., RF signal data or IQ data pairs) for presentation on a display system 234. The signal processor 232 is operable to perform one or more processing operations based on a plurality of selectable ultrasound modalities on the acquired ultrasound information. The acquired ultrasound information may be processed in real time during a scanning session as echo signals are received. Additionally or alternatively, the ultrasound information may be temporarily stored in an RF / IQ buffer 226 during a scanning session and processed in a less real-time manner when operating online or offline. In an exemplary embodiment, the signal processor 232 may include a shear wave elastography processing module 240.
[0059] The ultrasound system 200 is operable to continuously acquire ultrasound information at a frame rate suitable for the imaging situation under consideration. Typical frame rates are in the range of 20fps to 70fps, but can be lower or higher. For example, the frame rate associated with the high pulse repetition frequency used to image the shear waves 5 in the tissue 1 for shear wave elastography can be higher. In various embodiments, the pulse repetition frequency in the shear wave elastography mode is at least 300 pulses / second, and preferably greater than or equal to 1000 pulses / second. The acquired ultrasound information can be displayed on the display system 234 at a display rate that is the same as the frame rate or at a slower or faster display rate than the frame rate. An image buffer 236 is included for storing processed frames of acquired ultrasound information that are not scheduled for immediate display. Preferably, the image buffer 236 has sufficient capacity to store ultrasound information frames equivalent to at least a few seconds. The ultrasound information frames are stored in a manner that facilitates retrieval according to their acquisition order or time. The image buffer 236 can be embodied as any known data storage medium.
[0060] The shear wave elastography processing module 240 may include suitable logic components, circuits, interfaces and / or codes that are operable to handle processing of shear wave ultrasound data to provide information about a region of interest, such as a region of interest in the liver. As used herein, the term "shear wave ultrasound data" refers to ultrasound information received at the signal processor 232 corresponding to a received echo 209 generated by backscattering the transmitted ultrasound signal 207 from structures (e.g., tissue 1) and surgical instruments in the object of interest that are deformed by the shear wave 5. In this regard, the shear wave elastography processing module 240 may include suitable logic components, circuits, interfaces and / or codes that are operable to handle processing of shear wave ultrasound data to determine the local distribution of shear wave velocity in the tissue 1. The shear wave velocity may be calculated by direct inversion of the Helmholtz equation, time of flight measurement, or any suitable calculation method. For example, shear wave ultrasound data can be acquired after a push disturbance is induced in the tissue 1 by the force of the focused ultrasound beam 205 or by an external driving force 22. The push disturbances 205, 22 generate shear waves 5 that propagate laterally from the disturbance point. The ultrasound system 200 acquires shear wave ultrasound data using a high pulse repetition frequency. As used herein, the term "high pulse repetition frequency" refers to a pulse repetition frequency of at least 300 pulses / second. In a preferred embodiment, the pulse repetition frequency used to acquire shear wave ultrasound data is greater than or equal to 1000 pulses / second.
[0061] The shear wave elastic imaging processing module 240 may include suitable logic components, circuits, interfaces and / or codes that are operable to convert the local distribution of shear wave velocity in the tissue 1 into a map, such as a velocity distribution map, an elasticity map, a spatial gradient map, or any suitable map representing the contrast between the needle 10 and the surrounding tissue 1. For example, the local distribution can be plotted based on the shear wave velocity to generate a velocity distribution map. For another example, the local distribution can be converted into an elasticity map by calculating the hardness based on Young's modulus, a similar shear modulus, or any suitable conversion calculation method. In addition, in various embodiments, a spatial gradient filter can be applied to the velocity distribution map and / or the elasticity map to generate a spatial gradient map that provides enhanced visualization of the tissue of interest.
[0062] The graph represents the velocity of the shear wave passing through the tissue at the lateral position from the interference point in the shear wave ultrasound data. The shear wave propagation velocity corresponds to the hardness of the tissue at the lateral position. Specifically, a higher shear wave velocity corresponds to a higher hardness, while a lower shear wave velocity corresponds to a lower hardness. Based on differences in velocity and / or elasticity of tissue (e.g., a region of interest in the liver), the hardness of the liver can be assessed. For example, these graphs can be color-coded graphs or grayscale graphs with a color or grayscale range corresponding to the shear wave velocity and / or elasticity. Specifically, the elasticity graph can have a dark blue or dark gray / black corresponding to soft elasticity to a red or light gray / white corresponding to hard elasticity, and so on. The graph with elasticity information can be superimposed on an ultrasound image such as a B-mode image or any suitable ultrasound image.
[0063] Additionally and / or alternatively, the shear wave elastography processing module 240 may include suitable logic, circuitry, interfaces and / or code operable to perform image segmentation. In various embodiments, the shear wave elastography processing module 240 may automatically or semi-automatically perform image segmentation.
[0064] Figure 3 An ultrasound imaging system 300 is shown, which may be similar or identical to the ultrasound system 100 and / or the ultrasound system 200. The ultrasound imaging system 300 may be a system that performs both conventional ultrasound imaging and obtaining shear wave elastography measurements (e.g., measurements that may be converted to image data or used to determine other properties of human anatomy, such as liver stiffness associated with non-alcoholic fatty liver disease). Thus, the ultrasound imaging system 300 may be a combination of the ultrasound system 100 and the ultrasound system 200 (or components thereof), and may be only one system.
[0065] The ultrasound receiver 310 may include various components for receiving conventional ultrasound data and / or shear wave elastic imaging data. The ultrasound receiver 310 may receive signals from a probe (e.g., probe 104, 204) and may convert those signals into signals that may be processed by a processor 320. Components of the ultrasound receiver 310 may include a receiver (e.g., receiver 118, 218), an A / D converter (e.g., A / D converter 122, 222), an RF processor (e.g., RF processor 124, 224), an RF / IQ buffer (e.g., RF / IQ buffer 126, 226), or a receive beamformer (e.g., receive beamformer 120, 220). The ultrasound receiver 310 may provide ultrasound image data or shear wave elastic imaging measurements to the processor 320.
[0066] The processor 320 may execute the following Figures 4 to 16 The processing operations discussed. The processor 320 can be one processor or multiple processors, or can be grouped together (for example, in one ASIC) and / or remotely distributed in different packages. The processor 320 can receive information from the ultrasound receiver 310, which is ultrasound image data or can be converted into ultrasound image data by the processor 320. The processor may include functions such as those disclosed in connection with the signal processors 132, 232. The processor 320 may include a segmentation processor 322, a trained model 324, and a ROI position processor 326, as discussed below. The segmentation processor 322 may include functions similar to the segmentation processor 150, or include some of its functions. The segmentation processor 322 is operable to segment the liver capsule or the liver in the ultrasound image data. The segmentation processor 322 can work with the trained model 324 stored in the processor or stored in an associated memory to segment the anatomical structure in the ultrasound image data. The segmentation processor 322 can also segment non-anatomical features such as areas where data is obtained through poor probe contact. The ROI position processor 326 may be similar to the ROI location processor 170 or include some of the functionality of the ROI location processor.
[0067] The processor 320 may receive signals from the user input 340 to control the ultrasound imaging system 300. The processor 320 may cause information, such as a graphical representation, to be presented or displayed on the display 330. The processor 320 may cause operation of the shear wave transducer 350, such as as a process to collect shear wave elastography measurements of a region of interest of a patient's liver to measure the stiffness of the liver.
[0068] The display 330 may be similar to the display systems 134, 234. The display 330 may be used to present ultrasound image data and associated illustrations as discussed herein. The user input 340 may be similar to the user input devices 130, 230. The shear wave transducer 350 may be similar to the transducer 20 and / or the transducer element 206.
[0069] Figure 4 to Figure 1 5 shows image data and masks for performing image processing and for identifying a region of interest in a patient's liver from which shear wave elastography measurements are evaluated. These figures are described in relation to system 300, but this is for exemplary purposes only. Similar or identical components in system 100 and system 200 (or other ultrasound systems) may also be used to generate image data and perform processing, as will be understood.
[0070] Figure 4 Ultrasound image data 1000 that can be obtained using an ultrasound receiver 310 is shown. As shown, the ultrasound image data 1000 includes B-mode data, which is 1055×616 pixels with a grayscale depth of 8 bits. The ultrasound image data 1000 can be scaled before or during data processing. For example, before performing some image processing techniques described herein, the ultrasound image data 1000 can be scaled to 224×224 pixels. The ultrasound image data 1000 can be scaled multiple times. For example, the ultrasound image data 1000 can be scaled back to the original size (e.g., 1055×616 pixels) after certain image processing operations. As explained herein, other types of ultrasound image data 1000 can be used with the techniques described herein, but for exemplary purposes, ultrasound image data 1000 is provided. The ultrasound image data 1000 includes image data of the patient's liver (and structures or features in the liver) and skin. An ultrasound probe (e.g., probe 104, 204) is used to generate the ultrasound image data 1000. During image acquisition, the ultrasound probe is located at a curved region at the top of the ultrasound image data 1000. The ultrasound image data 1000 may be stored in a memory.
[0071] Figure 5A segmented liver 1010 extracted from the ultrasound image data 1000 is shown. The segmented liver 1010 corresponds to the patient's liver, as shown in the ultrasound image data 1000. The segmented liver 1010 may be determined by the processor 320, which may process the ultrasound image data 1000. The processor 320 may determine the segmented liver 1010 using a segmentation processor 322 in conjunction with a trained model 324. The trained model 324 may have been previously trained, for example, as described in U.S. Serial No. 18 / 205,804 filed on June 5, 2023, which is incorporated herein by reference in its entirety. The segmentation processor 320 may execute inference instructions to process the ultrasound image data 1000 using the trained model 324. When the ultrasound image data 1000 is generated, the segmentation processor 322 may determine the segmented liver 1010 substantially in real time. For example, the segmented liver 1010 may be determined between 0.5 seconds and 2 seconds (not limited thereto) after obtaining the ultrasound image data 1000. The segmented liver 1010 may be determined by the segmentation processor 322 using other techniques not based on machine learning, such as clustering, region growing, level set, or watershed transform.
[0072] Reference Figures 6 to 16 The processes discussed may be performed, at least in part, by the ROI location processor 326 .
[0073] Figure 6 A segmented liver mask 1020 corresponding to the segmented liver 1010 is shown. As shown, the segmented liver mask 1020 has the same outer contour as the segmented liver 1010. The area of the segmented liver mask 1020 within the outer contour is white, while the area outside the outer contour is black. As will be discussed further, the black area of the segmented liver mask 1020 is used to filter out the corresponding pixels in the ultrasound image data 1000. The segmented liver mask 1020 can be determined or generated by the ROI position processor 326 or the segmentation processor 322. The segmented liver mask 1020 can be used as part of the process of locating a region of interest in the liver, wherein the shear wave elastography data is analyzed according to the region of interest. Other masks described herein can also be used as part of the process.
[0074] Figure 7A bad probe contact mask 1030 determined from the ultrasound image data 1000 is shown. The bad probe contact mask 1030 can be designed to filter out areas where data has been collected even if there is a bad contact between the probe (e.g., the probe 104 or the probe 204) and the patient. Bad probe contact refers to insufficient or inappropriate contact between the ultrasound probe and the patient's skin, which may result in a suboptimal ultrasound image, thereby affecting the quality of diagnosis or treatment. Poor probe contact may result in less reliable data, and the bad probe contact mask 1030 can reduce errors generated when processing such less reliable data by removing this data (e.g., not processing this data). When processing the ultrasound image data 1000, the bad probe contact mask 1030 can be determined or generated by the processor 320. The processor 320 can use the segmentation processor 322, for example, in conjunction with the trained model 324 to determine the bad probe contact mask 1030. The processor 320 can execute inference instructions to process the ultrasound image data 1000 using the segmentation processor 322 and the trained model 324. Examples of training and using the segmentation processor 322 and the trained model 324 to obtain the bad probe contact mask 1030 are discussed in U.S. Serial No. 18 / 205,804 filed on June 5, 2023, which is incorporated herein by reference in its entirety. The segmentation processor 322 can determine the segmented liver 1010 (or the segmented liver mask 1020) and the bad probe contact mask 1030 substantially simultaneously. According to an embodiment, the bad probe contact mask 1030 is adapted from the segmented liver mask 1020. According to an embodiment, the top contour and the bottom contour of the bad probe contact mask correspond to the top contour and the bottom contour of the segmented liver mask 1020. According to an embodiment, according to Fig.16 , Fig.17 and the angles θ1 and θ2 disclosed in the corresponding text to determine the side of the bad probe contact mask 1030. For example, by Fig.16 , Fig.17 The line defined by θ1 shown may correspond to the left side of the bad probe contact mask. Fig.16 , Fig.17 The line defined by θ2 shown may correspond to the right side of the bad probe contact mask. Figure 7 As shown, the black areas outside the outline of the poor probe contact mask 1030 correspond to pixels in the ultrasound image data 1000 that will be filtered out due to problems with poor probe contact with the patient (eg, the patient's skin).
[0075] Figure 8A poor probe contact artifact mask 1040 determined from ultrasound image data 1000 is shown. The poor probe contact artifact mask 1040 may be black and white and may represent one or more locations where the contact between the ultrasound probe and the skin is insufficient. For example, due to the curved nature of the probe, these locations may appear at various locations in the ultrasound image data 1000. They may appear on the upper left interval, the upper right interval, or both intervals of the ultrasound image data 1000. The height of the features in the poor probe contact artifact mask 1040 may be greater than the thickness of the patient's skin. The ultrasound image data 1000 is constructed from acoustic wave data acquired by a transducer. The acoustic wave data includes amplitude, frequency, and the time it takes for an ultrasound signal to return to the transducer. The image is then constructed in a manner that represents the depth of the tissue, thereby forming a "height" in the image data, even if poor probe contact occurs at the skin surface. Therefore, when the contact between the probe and the skin is poor, the echo may be affected, thereby forming an artifact that may affect the image in terms of depth, thereby generating an artifact "height" within the image. The bad probe contact artifact mask 1040 may be combined with the bad probe contact mask 1030. As described herein, the bad probe contact mask 1030 and the bad probe contact artifact mask 1040 may be considered as part of the same mask and may be referred to simply as the bad probe contact mask 1030. The bad probe contact artifact mask 1040 may be determined using the segmentation processor 322 in conjunction with the trained model 324. The processor 320 may execute inference instructions to process the ultrasound image data 1000 using the segmentation processor 322 and the trained model 324. Examples of training and using the segmentation processor 322 and the trained model 324 to obtain the bad probe contact artifact mask 1040 are discussed in U.S. Serial No. 18 / 205,804 filed on June 5, 2023, which is incorporated herein by reference in its entirety. The segmentation processor 322 may determine the segmented liver 1010 (or the segmented liver mask 1020 ) and the poor probe contact artifact mask 1040 substantially simultaneously. Fig.16 , Fig.17 Additional disclosure regarding determining bad probe contact based on the bad probe contact artifact mask 1040 is provided in and corresponding text. Figure 7 , Fig.16 , Fig.17 Additional disclosure regarding determining the bad probe contact mask 1030 based on the bad probe contact artifact mask 1040 is provided in the context of .
[0076] One or more undesirable probe contact artifacts (segment types) may be present in the mask 1040. For example, one undesirable probe contact artifact may appear to the left of the centerline of the ultrasound image data 1000, while one undesirable probe contact artifact may appear to the right of the centerline of the ultrasound image data 1000. If an undesirable probe contact artifact is present, a corresponding indicator 1104 may be determined and displayed. Fig.14 , Fig.16 , Fig.17 Implementations of such processes are further disclosed in and corresponding text.
[0077] Fig. 9 A liver tissue mask 1050 is shown, which is determined based on the ultrasound image data 1000 and can be optionally limited to the segmented liver 1010. In the illustrated embodiment, the liver tissue mask 1050 is determined with reference to the ultrasound image data 1000, rather than only with reference to the segmented liver 1010. In an embodiment, and as shown, the liver tissue mask 1050 corresponds to areas that are not excluded by the bad probe contact mask 1030, but a liver tissue mask 1050 for the entire segmented liver 1010 can be generated. The liver tissue mask 1050 can be determined or generated by the processor 320, for example, using the ROI location module 326. The liver tissue mask 1050 is used to filter out pixels in the ultrasound image data 1000 that are located within the segmented liver 1010 but do not correspond to liver tissue. Examples of such structures or features include blood vessels and hyperechoic areas. Examples of hyperechoic areas include fat, calcification (deposition of calcium in tissue), or fibrosis (scar tissue formed when the liver attempts to heal itself after injury). For example, hyperechoic areas may occur where air pockets or gas pockets are present. For example, where there is an interface between fluid or tissue and air, a relatively large amount of ultrasound energy will be reflected. Such areas may correspond to features that are not liver tissue, even though they may be located within the liver. The liver tissue mask 1050 excludes such structures or features so that the clinical consultation can focus on the liver tissue itself (e.g., by determining the stiffness of the liver using shear wave elastography measurements). Such structures or features may be determined by various techniques, including FIG. 15A to FIG. 15C Those techniques described in the context of .
[0078] Fig.15A , Fig. 15B and Fig. 15CThe steps for generating a liver tissue mask 1050 are shown, and can be generated or performed by the processor 320, for example, using the ROI position processor 326. Step 1052 is a mask, and it involves filtering out at least blood vessels located in the liver. In an embodiment, and as shown, the mask 1052 excludes areas where the image data corresponds to poor probe contact (e.g., the poor probe contact mask 1030 has been applied to the ultrasound image data 1000, or optionally only applied to the segmented liver 1010 before determining the mask 1052). However, the mask 1052 can be determined for the entire segmented liver 1010 or the ultrasound image data 1000. In order to determine the pixels in the ultrasound image data 1000 that may correspond to liver tissue, one or more thresholds can be applied to the pixel brightness. For example, there may be a low threshold for pixel brightness, wherein any pixel below the low threshold is excluded. Similarly, there may also be a high threshold for pixel brightness, wherein any pixel above the high threshold is excluded. The thresholds can be absolute numbers, or they can be percentages or some other metric. As an example, there is only a low threshold and it is 10% (percentage). In this case, the darkest 10% of pixels will be filtered out.
[0079] After filtering out pixels by the brightness threshold, as part of step 1052, a local difference threshold is evaluated. This comparison can be used to determine the edge of a blood vessel. For each pixel (or a subset thereof) in the ultrasound image data 1000, the brightness of a given pixel can be compared with nearby pixels. For example, the brightness of a pixel can be compared with nearby pixels within a square interval of size 45×45 pixels, where the given pixel is at the center of the square interval. Relatively large differences may indicate the edge of a blood vessel. If the difference is outside an acceptable range (e.g., greater than a high threshold and / or less than a low threshold), those pixels can be filtered out. The threshold can be an absolute number or some other metric, such as a percentage. For example, when the difference is in the lowest 10% percentage, the pixel can be filtered out.
[0080] In addition to step 1052, additional steps for determining the liver tissue mask 1050 may be performed, including step 1054 ( Fig. 15B ) and step 1056( Fig. 15C). Steps 1054, 1056 involve filtering out highly echogenic pixels in the ultrasound image data 1000. In an embodiment, and as shown, steps 1054, 1056 include areas of the image data corresponding to poor probe contact (e.g., the poor probe contact mask 1030 has not been applied to the ultrasound image data 1000 or has not been applied to the segmented liver 1010 before performing steps 1054, 1056). However, steps 1054, 1056 may be performed only on the segmented liver 1010 that has been filtered by the poor probe contact mask 1030. Step 1054 is a saliency map determined from the ultrasound image data 1000. The pixel intensities in the saliency map 1054 represent the saliency (i.e., uniqueness) of the corresponding area in the original image, rather than their intensity or brightness. This can be viewed as converting the original pixel intensities into new quantities (i.e., saliency) rather than scaling those intensities. The significance can be determined by a variety of techniques, including spectral residual methods, Itti Koch significance models, graph-based visual significance (GBVS), Boolean map-based significance (BMS) models, or Gaussian division (DIVoG / DoG) significance detection techniques. In this example, step 1054 is determined using the DIVoG / DoG significance detection technique. After generating the significance map 1054, a threshold can be applied to filter out intervals with high significance, thereby forming step 1056, which is a mask. Such thresholds can be determined to effectively detect and avoid hyperechoic regions, which may have relatively high uniqueness in ultrasound images. In this way, regions with lower significance can be highlighted, and such regions may represent liver tissue rather than hyperechoic regions.
[0081] Masks 1052 and 1056 may be combined (eg, multiplied by each other) to obtain Fig. 9 Liver tissue mask 1050 is shown. Thus, liver tissue mask 1050 can filter out structures such as blood vessels and highly echogenic regions in the liver. However, liver tissue mask 1050 can be generated or designed to identify non-liver tissue (or liver tissue) in other ways.
[0082] Fig.10An axial distance mask 1060 is shown. As used herein, "axial" refers to the dimension between the probe and the pixels in the ultrasound image data 1000. The axial distance mask 1060 can be determined by the processor 320, for example, using the ROI position processor 326. As shown, the axial distance mask 1060 corresponds to the segmented liver 1010. As the distance from the probe becomes greater, the intensity of the pixels in the axial distance mask 1060 decreases in intensity, although not necessarily proportionally. The axial distance mask 1060 can adjust the pixel value (depth value) based on the distance of the pixel value (depth value) from a reference point (e.g., the liver capsule or the skin surface). The axial distance mask 1060 can be used to highlight or de-highlight a specific area of the image based on the proximity of the specific area of the image to the reference point. The axial distance mask 1060 can be formed in the following exemplary manner. First, for pixels located in the first area (e.g., 0 to 1 cm from the liver capsule), the value is set to 0 (i.e., black). Thus, these pixels are filtered out, so that the interval next to the liver capsule is not suitable for placing ROI. Second, for the pixels in the second area (for example, between 1cm and 1.5cm from the liver capsule), their values are gradually increased from 0 to 1. This forms a smooth transition from the masked interval around the liver capsule to the subsequent area. Third, for the pixels in the third area (for example, between 1.5cm and 7cm from the liver capsule), their values are set to 1 (that is, white). This emphasizes and highlights the interval within this distance range, making it the main interval of interest for further analysis or processing. Fourth, for the pixels located in the fourth area (for example, greater than 7cm or from the skin), their values gradually decay from 1 to 0. This decay effect can help to cancel the area that is more prominent away from the skin surface, thereby guiding the focus to the interval closer to the liver capsule. The axial distance mask 1060 can be combined with other masks described herein to determine the position of the region of interest. The axial distance mask 1060 tends to give greater weight to the position close to the probe in the liver. In other words, the axial distance mask 1060 increases the chance that the region of interest is located near the probe, as shown in the figure. For shear wave elastography measurements, shallower depths may be preferred because such measurements may be affected by the depth of the target tissue and the distance to the target tissue. By highlighting or de-highlighting specific areas of the image based on their proximity to a reference point (e.g., the liver capsule or the skin surface), the axial distance mask 1060 can help improve the accuracy and reliability of shear wave elastography measurements by directing the focus to intervals closer to the liver capsule (where measurements may be more reliable). The axial distance mask 1060 can be generated based on the entire segmented liver 1010 or a portion that is not filtered out by the poor probe contact mask 1030.
[0083] Fig.11A lateral distance mask 1070 is shown. The lateral distance mask 1070 may be similar to the axial distance mask 1060. As used herein, "lateral" refers to a horizontal dimension in the ultrasound image data 1000. The lateral distance mask 1070 may be determined by the processor 320, for example, using the ROI position processor 326. As shown, the lateral distance mask 1070 corresponds to the segmented liver 1010. As the distance from the centerline of the segmented liver 1010 or the centerline of the ultrasound image data 1000 increases, the intensity of the pixels in the lateral distance mask 1070 decreases in intensity, although not necessarily proportionally. The lateral distance mask 1070 may be generated in the following exemplary manner. First, the centerline of the ultrasound image data 1000 is identified. From this, the distance between the centerline and each other point in the ultrasound image data 1000 is calculated. These distances are then used to form a mask in which the intensity of each pixel corresponds to its distance from the centerline. The closer to the center line in the lateral distance mask 1070, the higher the intensity of the pixel, and the farther away from the center line, the lower the intensity of the pixel. This reduction in intensity follows linear decay, thereby producing a gradient effect, wherein the intensity at the center line is the largest and uniform linear decay occurs toward the edge. The lateral distance mask 1070 will be combined with other masks described herein to determine the position of the region of interest. The lateral distance mask 1070 tends to give greater weight to the position close to the center line of the segmented liver 1010 or the center line of the ultrasound image data 1000. In other words, the lateral distance mask 1070 increases the chance that the region of interest is located near the center line, as shown in the figure. The center line area of the ultrasound image data 1000 can be generated by more consistent and reliable acoustic characteristics. This is because the center line of the ultrasound image data 1000 is usually the place where the ultrasound beam is most focused and the place where the sound wave attenuation is less. In addition, placing the region of interest toward the center of the image can help minimize the impact of artifacts or other interference sources that may be more common toward the edge of the image (e.g., ribs). The lateral distance mask 1070 may be generated based on the entire segmented liver 1010 or the portion that is not filtered out by the bad probe contact mask 1030 .
[0084] Fig.12A mask combination 1080 of a liver tissue mask 1050, an axial distance mask 1060, and a lateral distance mask 1070 is shown. The mask combination 1080 may be determined by the processor 320, for example, using the ROI position processor 326. According to an embodiment, the liver tissue mask 1050 is multiplied by the axial distance mask 1060 and the lateral distance mask 1070 is added. In addition, the bad probe contact mask 1030 has been incorporated as part of the generation of the liver tissue mask 1050. The bad probe contact mask 1030 may be multiplied with the other masks as part of the combination process. According to an embodiment, the liver tissue mask 1050 is multiplied by both the axial distance mask 1060 and the bad probe contact mask 1030 and the lateral distance mask 1070 is added.
[0085] like Fig.13 As shown, the brighter intervals in the mask combination 1080 represent the preferred or identified intervals in the liver for placing the region of interest 1090, such as Fig.13As shown. Automatic identification for placing a region of interest 1090 can be determined by the processor 320, for example, using the ROI position processor 326. The region of interest 1090 may include one or more regions of interest. The region of interest 1090 may identify an interval in the liver from which the propagation of shear waves is tracked as part of the shear wave elastography process, for example, to assess the stiffness of the liver at this location. As shown, the region of interest 1090 includes a trapezoidal region of interest and a circular region of interest. The trapezoidal region of interest can be used to measure liver stiffness over a wider area of the liver to provide a more comprehensive assessment of potential liver fibrosis, although it may be more susceptible to artifact (e.g., blood vessel) inclusions due to its larger coverage. The circular region of interest can be used to more accurately measure the liver stiffness of a specific interval, thereby potentially reducing artifact inclusions to aid in the diagnosis of liver fibrosis. The region of interest 1090 can be automatically placed in the mask combination 180 by the processor 320, for example, based on the size of the region of interest 1090 and the available intervals in the mask combination 1080. In addition or as an alternative, the operator may select a suitable location for the region of interest 1090. For example, the processor 320 may automatically select an interval for the region of interest 1090 in the ultrasound image data 1000 and present it on the display 330. The operator may then interact via a user input 340 (e.g., a mouse or touch screen) to indicate to the processor 320 the desired location of the region of interest 1090. For example, the operator may agree to automatically place the region of interest 1090 and instruct to do so via the user input 340. As an alternative, the operator selects a different location for the region of interest 1090. For example, the operator may use the user interface 340 to drag and drop the region of interest 1090. Such drag and drop operations may be viewed in real time on the display 330. As another alternative, the processor 320 may automatically determine possible intervals for placing the region of interest 1090 and present it on the display 330. The operator may then select the location of the region of interest 1090 from the possible intervals by interacting with the user input 340. Although Fig.13 The region of interest 1090 is shown on the mask combination 1080, but as described above, the region of interest 1090 (or possible intervals of the region of interest 1090) may be presented on the ultrasound image data 1000 (ie, not just the masked portions of the ultrasound image data 1000).
[0086] Fig.14A diagram 1100 of ultrasound image data 1000 is shown with various indicators 1102, 1104, 1106, 1108. The processor 320 may cause the diagram 1100 to be presented on the display 330, including the indicators 1102, 1104, 1106, 1108 and any updates (e.g., real-time updates). The indicator 1102 is for a region of interest and may be similar to the region of interest 1090. The operator may be able to move the region of interest indicator 1102 around on the diagram 1100 via the user interface 340.
[0087] Indicator 1104 may indicate where the probe is not in contact with the patient. Indicator 1104 may change in real time in response to movement of the probe or the patient. Indicator 1104 may change size based on the interval where poor probe contact exists. If contact improves, indicator 1104 may disappear completely (on one or both sides). Fig.16 104. An embodiment is shown regarding how a bad probe contact indicator 1104 may be generated. Figure 8 As shown, for example, a bad probe contact artifact may be identified in a bad probe contact artifact mask 1040. If an artifact is present, a corresponding indicator 1104 is determined. If an artifact is identified on the right side, an indicator 1104 for the right side is determined. If an artifact is identified on the left side, an indicator 1104 for the left side is determined. When no artifact is identified, the indicator 1104 may not be determined.
[0088] like Fig.16 As shown, indicators 1104 for the left side and the right side can be determined for presentation with the ultrasound image data 1000. The indicators 1104 are shown as trapezoids, although other shapes may be suitable. The height of the trapezoids can be any suitable height. For example, the height can correspond to the thickness between the epidermis and the liver capsule, such as Fig.14 As shown. The width or orientation of the side of the indicator 1104 can be determined as follows. For each indicator 1104, the angle α and the angle θ can be determined relative to the center line of the ultrasound image data 1000 or relative to some other reference. As shown, α1 and θ1 correspond to the left indicator 1104, while α2 and θ2 correspond to the right indicator 1104. Angles α1 and α2 can be the same or different, as can θ1 and θ2. The discussion herein will only focus on one angle α and one angle θ, although two or even more angles may also be used. The side of the indicator 1104 may just match the line determined by the angle, or may have some relationship or correspondence with the line determined by the angle or just the angle.
[0089] The most lateral point that the probe can reach on the ultrasound image data 1000 can be identified (e.g., Fig.16The angle α can then be determined by drawing the line to the inferred position of the ultrasound transducer ( Fig.16 An angle α may be determined based on the line compared to a centerline of the ultrasound image data 1000 or some other reference such as a vertical line extending through the inferred position of the ultrasound transducer.
[0090] Angle θ may be identified within the range of angle α (angle θ may be smaller than angle α). Fig.17 is an illustration of an embodiment. Figure 8 The bad probe contact artifact mask 1040 has two segments. A line can be drawn from the inferred position of the ultrasound transducer to the innermost position of a given segment (or a position corresponding to the innermost position of a given segment). This line can determine the angle θ. Fig.17 In the example shown, a first angle θ1 is determined by drawing a line from the inferred position of the ultrasound transducer to the innermost position of the left segment of the bad probe contact artifact mask 1040. A second angle θ2 is determined by drawing a line from the inferred position of the ultrasound transducer to the innermost position of the right segment of the bad probe contact artifact mask 1040. The angles θ1 and θ2 may be used to determine the indicator 1104 and / or the bad probe contact mask 1030, as discussed above.
[0091] Back to Fig.14 , indicator 1106 indicates the distance between the patient's epidermis and the liver capsule or liver. The upper extent of the liver or liver capsule can be determined by segmentation, as discussed above. Indicator 1106 can be a length measurement in millimeters, for example. The length of the distance can be an indicator of the patient's condition or measurement such as body mass index. The actual distance expressed in units can also be displayed on the diagram 1100 (not shown).
[0092] Indicator 1108 indicates the angular, spatial relationship between the orientation of the probe and the patient's liver. This relationship can be relative and cannot determine the angle of the probe and / or liver relative to some other reference (e.g., a table). For example, the angular, spatial relationship can be determined in part by the shape and orientation of the segmented liver 1010. If the probe is substantially parallel to the patient's liver, better data (e.g., clearer and more accurate data) can be obtained. The angular, spatial relationship between the orientation of the probe and the liver can be performed in the following manner. The slope of the liver capsule is determined by selecting multiple points (e.g., three points) along the capsule: one point is at the center, and the other two points are fixed distances to the left and right of the center. The line connecting these points forms two angles, one angle between the center and the right point, and the other angle between the center and the left point. The slope of the liver capsule is then obtained by averaging these two angles. The slope is compared to a predefined threshold (e.g., 5 degrees). If the slope is greater than the threshold, it is recommended to adjust the angle of the probe clockwise. If the slope is less than the negative value of the threshold, it is recommended to adjust the counterclockwise. If the slope falls within (-5, +5), no adjustment is recommended. Indicator 1108 may indicate to the operator whether the probe should be angled to better match the orientation of the probe to the orientation of the patient's liver. Indicator 1108 may change in real time as the probe and / or patient moves.
[0093] Those skilled in the art will appreciate that various changes may be made and equivalents may be substituted without departing from the scope of the new technology disclosed in this application. In addition, many modifications may be made to adapt specific situations or materials to the teachings of the new technology without departing from the scope of the invention. Therefore, the new technology is not intended to be limited to the specific technology disclosed, but the new technology will include all technologies that fall within the scope of the appended claims.
Claims
1. A method, comprising: Receiving ultrasound image data (1000) of a patient, including a segmented region corresponding to a liver (1020); automatically identifying an interval of a region of interest (1090) within the segmented region (1020), wherein the region of interest (1090) corresponds to a region of the liver for performing shear wave elastography; and The ultrasound image data (1000) and the interval of the region of interest (1090) are presented on a display (134, 234, 330).
2. The method according to claim 1, further comprising segmenting the ultrasound image data (1000) to form the segmented region (1020).
3. The method of claim 1, further comprising receiving an input (130, 230, 340) to locate the region of interest (1090) within the interval of the region of interest (1090).
4. The method according to claim 1, wherein the automatically identifying the interval of the region of interest (1090) within the segmented region (1020) further comprises: determining a first mask (1050) by filtering pixels that do not correspond to liver tissue; determining a second mask (1060) for identifying axial positions in the segmented region (1020); determining a third mask (1070) for identifying lateral positions in the segmented region (1020); and The first mask (1050), the second mask (1060), and the third mask (1070) are combined to limit the interval of the region of interest (1090) within the segmented region (1020).
5. The method of claim 1, wherein the first mask (1050) filters out pixels corresponding to at least one blood vessel in the liver.
6. The method of claim 5, wherein the first mask (1050) filters out pixels corresponding to at least one hyperechoic region in the liver.
7. The method according to claim 4, wherein the automatically identifying the interval of the region of interest (1090) further comprises: determining a fourth mask (1030) corresponding to image data in an area caused by poor contact between the probe and the patient; as well as The first mask (1050), the second mask (1060), the third mask (1070), and the fourth mask (1030) are combined to limit the interval of the region of interest within the segmented region.
8. The method according to claim 1, further comprising performing shear wave elastography (200) to receive elasticity information of the region of interest (1090) in the liver.
9. The method according to claim 1, further comprising: Determining in real time the angle and spatial relationship between the segmented area (1020) and the ultrasound probe (104, 204); as well as A dynamic real-time indicator (1108) corresponding to the angular, spatial relationship between the segmented region (1020) and the ultrasound probe (104, 204) is presented on the display (134, 234, 330).
10. An ultrasound imaging system (100, 200, 300), the ultrasound imaging system comprising: A probe (104, 204), the probe comprising at least one transducer (106, 108, 206, 208), the at least one transducer being configured to transmit ultrasonic waves and receive reflected ultrasonic waves; a display (134, 234, 330) configured to present the graphical representation (1100) to an operator; and a processor (132, 232, 320) configured to process data corresponding to the reflected ultrasound waves to determine a segmented region (1020) corresponding to a liver of the patient, and further configured to cause the display (134, 234, 330) to present the graphical representation (1100), The diagram (1100) includes image data of the segmented region (1020) and at least one dynamic region of interest indicator (1102), wherein the at least one dynamic region of interest indicator indicates a corresponding region of interest (1090) in the liver, from which reflected ultrasonic shear waves are processed to determine the elasticity of the liver.
11. The ultrasound imaging system (100, 200, 300) of claim 10, wherein the processor (132, 232, 320) is further configured to determine the region of interest (1090) by: determining a first mask (1050) by filtering pixels that do not correspond to liver tissue; determining a second mask (1060) for identifying axial positions in the segmented region; determining a third mask (1070) for identifying lateral positions in the segmented region; and The first mask (1050), the second mask (1060), and the third mask (1070) are combined to limit the interval of the region of interest (1090) within the segmented region (1020).
12. The ultrasound imaging system (100, 200, 300) of claim 11, wherein the processor (132, 232, 320) is further configured to determine the region of interest (1090) by: determining a fourth mask (1030) corresponding to image data in an area caused by poor contact between the probe and the patient; and The first mask (1050), the second mask (1060), the third mask (1070), and the fourth mask (1030) are combined to limit the interval of the region of interest (1090) within the segmented region (1020).
13. The ultrasound imaging system (100, 200, 300) of claim 12, wherein the graphical representation (1100) further comprises an indicator (1104) of poor probe contact.
14. The ultrasound imaging system (100, 200, 300) according to claim 10, further comprising a shear wave generator (20) located outside the probe (104, 204), the shear wave generator being used to generate ultrasonic shear waves in the region of interest (1090).
15. The ultrasound imaging system (100, 200, 300) of claim 10, wherein the processor (132, 232, 320) is further configured to: Determining in real time the angle and spatial relationship between the segmented area (1020) and the ultrasound probe (104, 204); and The diagram (1100) includes a dynamic indicator (1108) that indicates the angular, spatial relationship between the segmented region (1020) and the ultrasound probe (104, 204) in real time.
