Method and system for automatically estimating hepato-renal index from ultrasound images

Abstract

The present invention is entitled "Method and system for automatically estimating the hepatorenal index from ultrasound images". The present invention provides a system and method for automatically estimating the hepatorenal index (HRI) from ultrasound images. The method includes acquiring a sequence of ultrasound image data until a desired ultrasound image view is obtained. The method includes segmenting the liver and the renal cortex in the obtained ultrasound image view. The method includes identifying valid samples in the liver and the renal cortex in the obtained ultrasound image view by excluding invalid samples. The method includes automatically locating a liver region of interest and a renal cortex region of interest in the obtained ultrasound image view based on the valid samples and at least one criterion. The method includes determining the HRI and causing a display system to present the HRI.

Description

Technical Field

[0001] Certain embodiments relate to ultrasound imaging. More particularly, certain embodiments relate to a method and system for automatically estimating the hepatorenal index (HRI) from ultrasound images. Background Art

[0002] Ultrasound imaging is a medical imaging technique used to image organs and soft tissues in the human body. Ultrasound imaging uses real-time, non-invasive, high-frequency sound waves to produce two-dimensional (2D), three-dimensional (3D), and / or four-dimensional (4D) images (i.e., real-time / continuous 3D images).

[0003] Ultrasound imaging is a valuable, non-invasive tool for diagnosing a variety of medical conditions, such as non-alcoholic fatty liver disease (NAFLD). NAFLD is one of the most common causes of liver disease in the United States, with 30% to 40% of adults in the United States suffering from NAFLD. A fatty liver (i.e., one with a fat content greater than 5%) can appear brighter on ultrasound than the adjacent kidneys. The hepatorenal index (HRI), defined as the ratio of the mean sample value of the liver to the mean sample value of the renal cortex, is a biomarker used in clinical practice to grade NAFLD steatosis and is a simple and effective method for identifying hepatic steatosis. However, due to the lack of guidelines and social consensus, clinicians are highly subjective when estimating HRI. In addition, identifying liver and kidney regions for calculating HRI depends on the clinician's skill level, region size, anatomical view, depth, ultrasound machine, type of input data, and the selection / avoidance of certain anatomical sites. For example, the small region of interest (ROI) size often used by clinicians makes HRI very susceptible to variations in renal anatomy.

[0004] Further limitations and disadvantages of conventional and traditional approaches will become apparent to those skilled in the art by comparing such systems with certain aspects of the present disclosure as set forth in the remainder of this application with reference to the accompanying figures. Summary of the Invention

[0005] There is provided a system and / or method for automatically estimating a hepatorenal index (HRI) from ultrasound images, substantially as shown and / or described in connection with at least one of the accompanying drawings, and as more fully set forth in the claims.

[0006] These and other advantages, aspects and novel features of the present disclosure, as well as details of illustrated embodiments thereof, will be more fully understood from the following description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a block diagram of an exemplary ultrasound system operable to automatically estimate a hepatorenal index (HRI) from ultrasound images, in accordance with various embodiments.

[0008] Figure 2 is an exemplary display of an ultrasound image view of Morrison's pouch with anatomical segmentation of the liver and renal cortex, according to various embodiments.

[0009] Figure 3 is a valid sample with an identification according to various embodiments Figure 2 An exemplary display of a segmented Morrison's notch ultrasound image view.

[0010] Figure 4 According to various embodiments, Figure 3 An exemplary display of a segmented Morrison's pouch ultrasound image view of an identified valid sample with automatically located liver region of interest and renal cortex region of interest for HRI calculation.

[0011] Figure 5 is a flow chart illustrating exemplary steps that may be used to automatically estimate HRI from ultrasound images according to an exemplary embodiment. DETAILED DESCRIPTION

[0012] Certain embodiments may be found in methods and systems for automatically estimating the hepatorenal index (HRI) from ultrasound images. Various embodiments have the technical effect of automatically calculating HRI from ultrasound images of Morrison's notch views. Certain embodiments have the technical effect of automatically identifying liver and kidney anatomical structures in ultrasound image views. Various aspects of the present disclosure provide the technical effect of identifying valid samples in the liver and kidney regions that can be used for HRI calculation. Various embodiments have the technical effect of identifying appropriate anatomical views for HRI calculation, calculating HRI scores, and providing confidence scores for each HRI calculation. Certain embodiments have the technical effect of automatically locating the liver region of interest and the renal cortex region of interest based on the identified valid samples. Various aspects of the present disclosure have the technical effect of automatic HRI calculation that is objective, user-independent, accurate, and optimizes clinical protocols.

[0013] When reading in conjunction with the accompanying drawings, the following specific embodiments of the foregoing invention summary and certain embodiments will be better understood. With regard to the scope of the figures of the functional blocks of various embodiments 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 memories) can be implemented in a single piece of hardware (e.g., a general-purpose signal processor or random access memory block, a hard disk, etc.) or multiple pieces of hardware. Similarly, a program can be an independent program, can be included in an operating system as a subroutine, can be a function in an installed software package, etc. It should be understood that the various embodiments are not limited to the arrangements and tools shown in the accompanying drawings. It should also be understood that embodiments can be combined, or other embodiments can be utilized, and structural, logical and electrical changes can be made without departing from the scope of the various embodiments. Therefore, the following detailed description should not be considered as restrictive, and the scope of this disclosure is limited by the appended claims and their equivalents.

[0014] As used herein, an element or step listed in the singular and beginning with the word "a" or "an" should be understood as not excluding a plurality of said elements or steps, unless such exclusion is explicitly stated. Furthermore, references to "exemplary embodiments," "various embodiments," "certain embodiments," "representative embodiments," etc. are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features. Furthermore, unless explicitly stated to the contrary, embodiments that "comprise," "include," or "have" an element or elements having a particular property may include additional elements that do not have that property.

[0015] In addition, as used herein, the term "image" refers broadly to both a visual image and data representing a visual image. However, many embodiments generate (or are configured to generate) at least one visual image. In addition, as used herein, the phrase "image" is used to refer to ultrasound modes, such as B-mode (2D mode), M-mode, three-dimensional (3D) mode, CF mode, PW Doppler, CW Doppler, MGD, and / or sub-modes of B-mode and / or CF, such as shear wave elastography (SWEI), TVI, Angio, B-flow, BMI, BMI_Angio, and in some cases also MM, CM, TVD, where "image" and / or "plane" includes a single beam or multiple beams.

[0016] 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 implementations.

[0017] It should be noted that the various embodiments described herein for generating or forming an image may include a process for forming the image that, in some embodiments, includes beamforming and in other embodiments does not include beamforming. For example, an image may be formed without beamforming, such as by multiplying a matrix of demodulated data by a coefficient matrix such that the product is an image, and wherein the process does not form any "beams." Additionally, image formation may be performed using a combination of channels that may originate from more than one transmit event (e.g., synthetic aperture techniques).

[0018] 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 is described in Figure 1 Shown in.

[0019] Figure 1 is a block diagram of an exemplary ultrasound system 100 operable to automatically estimate the hepatorenal index (HRI) from ultrasound images, according to various embodiments. Figure 1 , shows an ultrasound system 100 and a training system 200. 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.

[0020] The transmitter 102 may comprise suitable logic, circuitry, interfaces, and / or code operable to drive the ultrasound probe 104. The ultrasound probe 104 may comprise a two-dimensional (2D) array of piezoelectric elements. The ultrasound probe 104 may comprise a set of transmit transducer elements 106 and a set of receive transducer elements 108, which are generally constructed as identical elements. In certain embodiments, the ultrasound probe 104 may be operable to acquire ultrasound image data covering at least a majority of an anatomical structure, such as the liver and kidneys, or any suitable anatomical structure.

[0021] The transmit beamformer 110 may comprise 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 subaperture 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 (e.g., blood cells or tissue) to generate echoes, which are received by the receive transducer elements 108.

[0022] The set of receive transducer elements 108 in the ultrasound probe 104 may be operable to convert received echoes into analog signals, which may be sub-aperture beamformed by the receive sub-aperture beamformer 116 and then transmitted to the receiver 118. The receiver 118 may comprise 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.

[0023] The plurality of A / D converters 122 may comprise suitable logic, circuitry, interfaces, and / or code 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. However, the present disclosure is not limited in this respect. Thus, in some embodiments, the plurality of A / D converters 122 may be integrated within the receiver 118.

[0024] The RF processor 124 may comprise suitable logic, circuitry, interfaces, and / or code that may be operable to demodulate the digital signals output by the plurality of A / D converters 122. According to one embodiment, the RF processor 124 may comprise a complex demodulator (not shown) that may be 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 comprise suitable logic, circuitry, interfaces, and / or code that may be operable to provide temporary storage of the RF or I / Q signal data generated by the RF processor 124.

[0025] The receive beamformer 120 may comprise suitable logic, circuitry, interfaces, and / or code operable to perform digital beamforming processing, for example, 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 the 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 digital. In various embodiments, the ultrasound system 100 includes a plurality of receive beamformers 120.

[0026] The user input device 130 may be used to input patient data, scan parameters, settings, select a protocol and / or template, select an exam type, select a desired ultrasound image view, select a valid sample identification algorithm, reposition an automatically placed region of interest, and the like. In an exemplary embodiment, the user input device 130 may be operable to configure, manage, and / or control the operation of one or more components and / or modules of the ultrasound system 100. In this regard, the user input device 130 may be used 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 buttons, rotary encoders, touch screens, touch pads, trackballs, motion tracking, voice recognition, mouse devices, keyboards, cameras, and / or any other device capable of receiving user commands. In certain embodiments, for example, one or more of the user input devices 130 can be integrated into other components, such as the display system 134. For example, the user input device 130 can include a touch screen display.

[0027] The signal processor 132 may comprise suitable logic, circuitry, interfaces, and / or code operable to process ultrasound scan data (i.e., the summed IQ signal) to generate an ultrasound image for presentation on the display system 134. The signal processor 132 may be 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 configured to perform display processing and / or control processing, among other things. 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-than-real-time manner in either online or offline operations. In various embodiments, the processed image data may be presented at the display system 134 and / or may be stored in 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 other suitable device for storing images and related information.

[0028] The signal processor 132 may be one or more central processing units, microprocessors, microcontrollers, and the like. For example, the signal processor 132 may be an integrated component or may be distributed across 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, a region of interest (ROI) location processor 170, and a hepato-renal index (HRI) processor 180. 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 may be displayed by the display system 134, and manipulating the output in response to input information from the user input device 130. The signal processor 132 (which includes the image analysis processor 140, the segmentation processor 150, the sample identification processor 160, the region of interest (ROI) location processor 170, and the hepato-renal index (HRI) processor 180) may be capable of, for example, executing any of the methods and / or instruction sets discussed herein according to various embodiments.

[0029] 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 range from 20 to 120, but can be lower or higher. The acquired ultrasound scan data can be displayed on the display system 134 at a display rate that is the same as the frame rate, or 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 at least several minutes of frames of ultrasound scan data. The frames of ultrasound scan data are stored in a manner that allows for easy retrieval based on their acquisition order or time. The image buffer 136 can be embodied as any known data storage medium.

[0030] The signal processor 132 may include an image analysis processor 140 comprising suitable logic, circuitry, interfaces, and / or code 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 has been obtained, such as an ultrasound image view of the Morrison's pouch or any suitable ultrasound image view of the liver and kidneys. Once the desired image view has been 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 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., convolutional neural networks, such as a u-net), and / or may utilize any suitable image analysis technique 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 remote processors 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 may be operable to provide quality metrics associated with the acquired views. For example, the image analysis processor 140 may analyze the acquired ultrasound image view (as a whole), a region of the acquired ultrasound image view, an acquired ultrasound image view segmented by the segmentation processor 150, and the like to provide quality metrics associated with the acquired views. The image analysis processor 140 may be configured to cause the display system 134 to correlate the quality metrics with the acquired ultrasound image view. Figure 1 The quality metric may be presented together. For 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 code (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 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.

[0031] The signal processor 132 may include a segmentation processor 150 comprising suitable logic, circuitry, interfaces, and / or code operable to segment the streaming image frames and the B-mode frames. The segmentation processor 150 may be configured to identify the liver and the renal cortex of the kidneys in an acquired ultrasound image view (such as a Morrison's fossa 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 U-Net), and / or may utilize any suitable form of artificial intelligence image analysis technology or machine learning processing functionality configured to provide automated segmentation functionality. Additionally and / or alternatively, the artificial intelligence image analysis technology or machine learning processing functionality configured to provide automated segmentation may be provided by a different processor or distributed across multiple processors at the ultrasound system 100 and / or distributed across a remote processor communicatively coupled to the ultrasound system 100. For example, the image segmentation functionality may be provided as a deep neural network, which may be comprised of, for example, an input layer, an output layer, and one or more hidden layers between the input and output layers. Each layer may be comprised of a plurality of processing nodes, which may be referred to as neurons. For example, an image segmentation function may include an input layer having a neuron for each sample or set of samples from an acquired ultrasound image view of the liver and kidneys. The output layer may have neurons corresponding to a plurality 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 a plurality of neurons in a downstream layer for further processing. For example, neurons in a first layer may learn to identify edges of structures in an acquired ultrasound image. Neurons in a second layer may learn to recognize shapes based on detected edges from the first layer. Neurons in a 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 may identify anatomical structures and the location of the structures in the acquired ultrasound image with a high probability.

[0032] 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 along 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 and kidney cortex portions of the acquired ultrasound image, as described below.

[0033] Figure 2is an exemplary display 200 of an ultrasound image view 202 of Morrison's pouch with anatomical segmentations 210, 220 of the liver 204 and renal cortex 208 according to various embodiments. Figure 2 , the display 200 includes an acquired ultrasound image view 202, such as an ultrasound image view 202 of Morrison's pouch having a liver 204 and a kidney 206. The segmentation processor 150 may perform image segmentation 210, 220 on the acquired ultrasound image view 202 to identify the liver 204 and the renal cortex 208 of the kidney 206. The acquired ultrasound image view 202, having the liver 204 segmented 210 and the renal cortex 208 of the kidney 206 segmented 220, may be displayed 200 at the display system 134, provided to the image analysis processor 140, provided to the sample identification processor 160, and / or stored at the archive 138 and / or any suitable data storage medium.

[0034] The signal processor 132 may include a sample identification processor 160 comprising suitable logic, circuitry, interfaces, and / or code operable to identify valid samples in the liver 204 and the renal cortex 208 in the acquired ultrasound image view 202 by excluding invalid samples. For example, the sample identification processor 160 may identify valid samples based on excluding invalid samples from the liver 204 and the renal cortex 208 in the acquired ultrasound image view 202. The sample identification processor 160 may exclude samples from the segmentation 210 of the liver 204 in the acquired ultrasound image view 202 by applying an artificial intelligence algorithm and / or any suitable image analysis technique to exclude samples that are within large ducts, blood vessels, masses, and cysts in the liver 204. The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to exclude samples that have artifacts and / or are in artifact-prone areas in the segmentation 210 of the liver 204. The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to exclude samples within a threshold distance from the boundary of the liver 204 in the segmentation 210. The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to identify valid samples within the segmentation 210 of the liver 204 that are only within a homogeneous region of the segmentation 210 of the liver 204. The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to exclude samples within the segmentation 210 of the liver 204 that have sample values ​​above an upper threshold or below a lower threshold. The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to exclude samples within the segmentation 210 of the liver 204 that have a distance from the kidney 206 greater than a threshold distance.

[0035] The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to exclude samples within masses, cysts, collecting systems, and external renal tissue from the renal cortex 208 of the segmentation 210. The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to exclude samples with artifacts and / or in artifact-prone areas from the renal cortex 208 of the segmentation 210. The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to exclude samples within a threshold distance from the boundary of the kidney 206 from the renal cortex 208 of the segmentation 210. The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to identify valid samples within the renal cortex 208 of the segmentation 210 that are only within a homogeneous region of the renal cortex 208 of the segmentation 210. The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to exclude samples within the renal cortex 208 of the segmentation 210 that have sample values ​​above an upper threshold or below a lower threshold. The sample identification processor 160 may apply an artificial intelligence algorithm and / or any suitable image analysis technique to exclude samples from the renal cortex 208 of the segmentation 210 that are located at a distance from the liver 204 greater than a threshold distance.

[0036] In various embodiments, the sample identification processor 160 can be configured to identify valid samples using highlighting, shading, marking, and / or any suitable visual indication. The obtained ultrasound image view 202 with the visual indication of the identified sample can be displayed at the display system 134. Additionally and / or alternatively, the sample identification processor 160 can provide the obtained ultrasound image view 202 with the identified valid sample (with or without the visual indication) to the ROI positioning processor 170. Additionally and / or alternatively, the sample identification processor 160 can store the obtained ultrasound image view 202 with the identified valid sample (with or without the visual indication) to the archive 138 and / or any suitable data storage medium.

[0037] Figure 3 is a valid sample 230, 240 with identification according to various embodiments Figure 2 An exemplary display 300 of a segmented Morrison's notch ultrasound image view 202 is shown. Figure 3 , showing 300 including Figure 22 . The segmented ultrasound image view 202 depicts the Morrison's pouch ultrasound image view 202 with the liver 204 and the kidney 206. The sample identification processor 160 may apply a sample identification algorithm to the segmented ultrasound image view 202 to identify valid samples of the liver 204 and the renal cortex 208 of the kidney 206. The sample identification processor 160 may be configured to identify the valid samples using highlighting, shading, marking, and / or any suitable visual indication 230, 240. The segmented ultrasound image view 202 with the visual indication 230 of the identified valid sample of the liver 204 and the visual indication 240 of the identified valid sample of the renal cortex 208 may be displayed 300 at the display system 134. The samples 232, 242 of the segmented liver 204 and renal cortex 208 that were excluded by the sample identification processor 160 may not include a visual indication or may be provided with a different visual indication than the valid samples 230, 240. The segmented ultrasound image view 202 with the identified active sample 230 of the liver 204 and the identified active sample 240 of the renal cortex 208 of the kidney 206 may be displayed 300 at the display system 134 , provided to the ROI localization processor 170 , and / or stored at the archive 138 and / or any suitable data storage medium.

[0038] The signal processor 132 may include a region of interest (ROI) localization processor 170 comprising suitable logic, circuitry, interfaces, and / or code operable to automatically localize a liver region of interest and a renal cortex region of interest in the acquired ultrasound image view 202 based on the identified valid samples 230, 240 and at least one criterion. For example, the ROI localization processor 170 may be configured to apply an algorithm defined by the at least one criterion to the valid samples 230, 240 of the acquired ultrasound image view 202 to identify the densest valid sample region in the renal cortex 208 of the kidney 206 and the densest valid sample region in the liver 204. The ROI location processor 170 may determine the densest effective sample region of the liver 204 based, at least in part, on one or more of the following: the shortest distance to the centerline of the transducer data; the shortest distance to the densest effective sample region of the renal cortex 208; the densest effective sample region of the liver 204 and the densest effective sample region of the renal cortex 208 being at the same image depth; and / or the densest effective sample region of the liver 204 and the densest effective sample region of the renal cortex 208 being at the same geometric depth (e.g., if a curved array transducer is used). The ROI location processor 170 may be configured to provide a visual indication of the liver region of interest and the renal cortex region of interest in the acquired ultrasound image view 202. The visual indication of the region of interest may include highlighting, shading, markings, overlaid shapes, and / or any suitable visual indication. The acquired ultrasound image view 202 with the visual indication of the liver region of interest and the renal cortex region of interest may be displayed at the display system 134. Additionally and / or alternatively, the ROI localization processor 170 may provide the obtained ultrasound image view 202 with the located liver region of interest and the renal cortex region of interest (with or without a visual indication) to the HRI processor 180. Additionally and / or alternatively, the ROI localization processor 170 may store the obtained ultrasound image view 202 with the located liver region of interest and the renal cortex region of interest (with or without a visual indication) to the archive 138 and / or any suitable data storage medium.

[0039] Figure 4 According to various embodiments, Figure 3 An exemplary display 400 of a segmented Morrison's pouch ultrasound image view 202 of an identified valid sample 230, 240 with an automatically positioned liver region of interest 250 and renal cortex region of interest 260 for HRI calculation. Figure 4 , showing 400 including Figure 3400 , the segmented ultrasound image view 202 depicts the Morrison's pouch ultrasound image view 202 with the liver 204 and the kidney 206 having the identified valid specimens 230, 240. The ROI location processor 170 can automatically locate a liver region of interest 250 and a renal cortex region of interest 260 in the acquired ultrasound image view 202 based on the identified valid specimens 230, 240 and at least one criterion. The ROI location processor 170 can be configured to identify the liver region of interest 250 and the renal cortex region of interest 260 using highlighting, shading, markings, overlapping shapes, and / or any suitable visual indication. The segmented ultrasound image view 202 with the automatically located liver region of interest 250 and renal cortex region of interest 260 can be displayed 400 on the display system 134, provided to the HRI processor 180, and / or stored in the archive 138 and / or any suitable data storage medium. In various embodiments, the clinician may reposition the automatically located liver region of interest 250 and renal cortex region of interest 260 via the user input device 130 .

[0040] The signal processor 132 may include a hepatorenal index (HRI) processor 180 comprising suitable logic, circuitry, interfaces, and / or code operable to determine an HRI based on a liver region of interest 250 and a renal cortex region of interest 260 in the segmented ultrasound image view 202. For example, the HRI processor 180 may determine the HRI by calculating a ratio of liver data in the liver region of interest 250 to renal cortex data in the renal cortex region of interest 260. The liver data and renal cortex data may include beamformed data, in-phase and quadrature (I / Q) data, post-processed data, or grayscale values. The HRI processor 180 may be configured to cause the display system 134 to present the HRI value. In certain embodiments, the HRI processor 180 may be configured to determine a quality score corresponding to the determined HRI value. For example, the HRI processor 180 may apply a quality score algorithm based on a standard deviation of a plurality of regions of interest in the liver 204 and renal cortex 208 of the segmented ultrasound image view 202. The HRI processor 180 may be configured to cause the display system 134 to present the quality score along with the HRI value.

[0041] The display system 134 can be any device capable of conveying visual information to a user. For example, the display system 134 can include a liquid crystal display, a light emitting diode display, and / or any other suitable display or displays. The display system 134 can be operable to display information from the signal processor 132 and / or the archive 138, such as the ultrasound image 202 with and / or without image quality metrics, segmentation information 210, 220, valid sample information 230, 240 and / or invalid sample information 232, 242, regions of interest 250, 260, HRI values, HRI quality scores, and / or any other suitable information.

[0042] The archive 138 may be one or more computer-readable memories, such as a picture archiving and communication system (PACS), an enterprise archive (EA), a vendor-independent archive (VNA), a server, a hard disk, a floppy disk, a CD, a CD-ROM, a DVD, a compact storage device, a flash memory, a random access memory, a read-only memory, an electrically erasable and programmable read-only memory, and / or any other suitable memory, that is integrated with and / or communicatively coupled (e.g., via a network) to the ultrasound system 100. The archive 138 may include, for example, a database, a library, a collection of information, or other memory that is accessed by and / or in conjunction with the signal processor 132. For example, the archive 138 may be capable of storing data temporarily or permanently. The archive 138 may be capable of storing medical image data, data generated by the signal processor 132, and / or instructions readable by the signal processor 132, among other things. In various embodiments, the archive 138 stores the ultrasound image 202, image quality metrics generated by the image analysis processor 140, instructions for analyzing the ultrasound image 202 and generating the image quality metrics, segmentation information generated by the segmentation processor 150, instructions for performing image segmentation, valid sample information 230, 240 and / or invalid sample information 232, 242 generated by the sample identification processor 160, instructions for identifying valid samples 230, 240, region of interest information 250, 260 generated by the ROI positioning processor 170, instructions for automatically positioning the regions of interest 250, 260, HRI values ​​generated by the HRI processor 180, instructions for determining HRI values, HRI quality scores generated by the HRI processor 180 and / or instructions for generating HRI quality scores, etc.

[0043] The components of the ultrasound system 100 may be implemented in software, hardware, firmware, etc. The various components of the ultrasound system 100 may be communicatively connected. The components of the ultrasound system 100 may be implemented separately and / or integrated in various forms. For example, the display system 134 and the user input device 130 may be integrated into a touch screen display.

[0044] Still refer to Figure 1, the training system 200 may include a training engine 210 and a training database 220. The training engine 160 may include suitable logic, circuitry, interfaces, and / or code 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, the ROI localization processor 170, and / or the HRI processor 180. For example, the artificial intelligence model inferred by the image analysis processor 140 may be trained to automatically identify ultrasound image views (e.g., Morrison's pouch ultrasound image view 202). The artificial intelligence model inferred by the segmentation processor 150 may be trained to automatically segment acquired ultrasound image views to identify anatomical structures (e.g., the liver 204 and the renal cortex 208 of the kidney 206). For example, the training engine 210 can use the database 220 of classified Morrison's pouch ultrasound image views of the liver 204 and the renal cortex 208 of the kidney 206 to train a deep neural network deployed by the image analysis processor 140 and / or the segmentation processor 150. The ultrasound image can include an ultrasound image of a particular anatomical feature, such as the Morrison's pouch ultrasound image view 202 with the liver 204 and the renal cortex 208 of the kidney 206, or any suitable ultrasound image and features.

[0045] In various embodiments, the database of training images 220 may be a picture archiving and communication system (PACS) or any suitable data storage medium. In certain embodiments, the training engine 210 and / or the training image database 220 may be a remote system communicatively coupled to the ultrasound system 100 via a wired or wireless connection, such as Figure 1 Additionally and / or alternatively, components or all of the training system 200 may be integrated with the ultrasound system 100 in various forms.

[0046] Figure 5 FIG. 5 is a flow chart 500 illustrating exemplary steps 502 through 516 that may be used to automatically estimate HRI from ultrasound images according to an exemplary embodiment. Figure 5 , a flowchart 500 including exemplary steps 502 through 516 is shown. Certain embodiments may omit one or more steps, and / or perform steps in an order different from the order listed, and / or combine certain steps discussed below. For example, some steps may not be performed in certain embodiments. For another example, certain steps may be performed in a different chronological order than listed below, including simultaneously.

[0047] At step 502, the ultrasound system 100 may acquire a sequence of ultrasound data. For example, the ultrasound probe 104 of the ultrasound system 100 may continuously acquire ultrasound image data until a desired ultrasound image view is obtained. The acquired ultrasound data sequence may be processed and presented on the display system 134.

[0048] At step 504, the signal processor 132 of the ultrasound system 100 may determine whether the desired ultrasound image view 202 has been obtained. For example, the image analysis processor 140 of the signal processor 132 of the ultrasound system 100 may analyze the ultrasound image data acquired at step 502 to determine whether the desired ultrasound image view 202 has been obtained. The desired ultrasound image view 202 may be an ultrasound image view of the Morrison's pouch or any suitable ultrasound image view of the liver 204 and kidneys 206. Once the desired image view has been obtained, the image analysis processor 140 may instruct the signal processor 132 to freeze the view presented at the display system 134. The image analysis processor 140 may include, for example, an artificial intelligence image analysis algorithm, one or more deep neural networks (e.g., convolutional neural networks, such as u-nets), and / or may utilize any suitable image analysis technology or machine learning processing functionality configured to determine whether the desired view has been obtained.

[0049] At step 506, the signal processor 132 of the ultrasound system 100 may assign a quality metric to the acquired ultrasound image view 202. For example, the image analysis processor 140 may analyze the acquired ultrasound image view 202 (as a whole), a region of the acquired ultrasound image view 202, the acquired ultrasound image view segmented by the segmentation processor 150 at step 508, etc., to provide a quality metric associated with the acquired ultrasound image view 202. The image analysis processor 140 may be configured to cause the display system 134 to present the quality metric along with the acquired ultrasound image view 202.

[0050] At step 508, the signal processor 132 of the ultrasound system 100 may segment 210, 220 the liver 204 and the renal cortex 208 in the acquired ultrasound image view 202. For example, the segmentation processor 140 of the signal processor 132 may be configured to identify 210, 220 the liver 204 and the renal cortex 208 of the kidney 206 in the acquired ultrasound image view 202 (such as a Morrison's pouch view). 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 u-nets), and / or may utilize any suitable form of artificial intelligence image analysis technology or machine learning processing functionality configured to provide automated segmentation functionality. The segmentation processor 150 may be configured to cause the display system 134 to present the image segmentation information 210, 220 along with the acquired ultrasound image 202.

[0051] At step 510 , the signal processor 132 of the ultrasound system 100 may identify valid samples 230 , 240 in the liver 204 , 210 and the renal cortex 208 , 220 in the acquired ultrasound image view 202 by excluding invalid samples 232 , 242 . For example, the sample identification processor 160 of the signal processor 132 of the ultrasound system 100 can be configured to exclude samples 232 from the liver 204 in the segmentation 210 of the obtained ultrasound image view 202 by applying an artificial intelligence algorithm and / or any suitable image analysis technique to exclude the following: samples 232 in the liver 204 that are inside large ducts, blood vessels, masses, and cysts; samples 232 in the liver 204 in the segmentation 210 that have artifacts and / or are in artifact-prone areas; samples 232 in the liver 204 in the segmentation 210 that are within a threshold distance from the boundary of the liver 204; samples 232 in the liver 204 in the segmentation 210 that are in inhomogeneous areas; samples in the liver 204 in the segmentation 210 whose sample values ​​are above an upper threshold or below a lower threshold; and / or samples in the liver 204 in the segmentation 210 that are greater than a threshold distance from the kidney 206. For another example, the sample identification processor 160 can apply an artificial intelligence algorithm and / or any suitable image analysis technique to exclude the following: samples 242 within masses, cysts, collecting systems, and external renal tissue in the renal cortex 208 of the segmentation 210; samples 242 with artifacts and / or in artifact-prone areas in the renal cortex 208 of the segmentation 210; samples 242 within a threshold distance from the border of the kidney 206 in the renal cortex 208 of the segmentation 210; samples 242 in a heterogeneous area in the renal cortex 208 of the segmentation 210; samples 242 with sample values ​​above an upper threshold or below a lower threshold in the renal cortex 208 of the segmentation 210; and / or samples 242 with a distance from the liver 204 greater than a threshold distance in the renal cortex 208 of the segmentation 210. The sample identification processor 160 can be configured to identify valid samples using highlighting, shading, marking, and / or any suitable visual indication. The obtained ultrasound image view 202 with the visual indication of the identified sample may be displayed at the display system 134 .

[0052] At step 512, the signal processor 132 of the ultrasound system 100 may automatically locate the liver region of interest 250 and the renal cortex region of interest 260 in the acquired ultrasound image view 202 based on the valid samples 230, 240 and the at least one criterion. For example, the region of interest (ROI) localization processor 170 of the signal processor 132 of the ultrasound system 100 may be configured to apply an algorithm defined by the at least one criterion to the valid samples 230, 240 of the acquired ultrasound image view 202 to identify the densest valid sample region in the renal cortex 208 of the kidney 206 and the densest valid sample region in the liver 204. The ROI location processor 170 may determine the densest effective sample region of the liver 204 based, at least in part, on one or more of the following: the shortest distance to the centerline of the transducer data; the shortest distance to the densest effective sample region of the renal cortex 208; the densest effective sample region of the liver 204 being at the same image depth as the densest effective sample region of the renal cortex 208; and / or the densest effective sample region of the liver 204 being at the same geometric depth as the densest effective sample region of the renal cortex 208 (e.g., if a curved array transducer is used). The ROI location processor 170 may be configured to provide a visual indication of the liver region of interest 250 and the renal cortex region of interest 260 in the acquired ultrasound image view 202. The visual indication of the region of interest may include highlighting, shading, markings, overlay shapes, and / or any suitable visual indication. The acquired ultrasound image view 202 with the visual indication of the liver region of interest and the renal cortex region of interest may be displayed on the display system 134. In various embodiments, the clinician may reposition the automatically located liver region of interest 250 and renal cortex region of interest 260 via the user input device 130.

[0053] At step 514, the signal processor 132 of the ultrasound system 100 may determine a hepatorenal index (HRI) and a quality score for the HRI. For example, the HRI processor 180 of the signal processor 132 of the ultrasound system 100 may be configured to determine the HRI based on the liver region of interest 250 and the renal cortex region of interest 260 in the segmented ultrasound image view 202. The HRI processor 180 may determine the HRI by calculating a ratio of liver data in the liver region of interest 250 to renal cortex data in the renal cortex region of interest 260. The liver data and renal cortex data may include beamformed data, in-phase and quadrature (I / Q) data, post-processed data, or grayscale values. In certain embodiments, the HRI processor 180 may be configured to determine a quality score corresponding to the determined HRI value. For example, the HRI processor 180 may apply a quality score algorithm based on a standard deviation of a plurality of regions of interest in the liver 204 and renal cortex 208 of the segmented ultrasound image view 202.

[0054] At step 516, the signal processor 132 of the ultrasound system 100 may display the HRI and the quality score of the HRI. For example, the HRI processor 180 may be configured to cause the display system 134 to present the HRI value and the quality score of the HRI.

[0055] Aspects of the present disclosure provide for automatic estimation of a hepatorenal index (HRI) from an ultrasound image 202. According to various embodiments, a method 500 may include acquiring 502, by the ultrasound system 100, a sequence of ultrasound image data until a desired ultrasound image view 202 is obtained 504. The method 500 may include segmenting 508, by at least one processor 132, 150 of the ultrasound system 100, the liver 204, 210 and the renal cortex 208, 220 in the obtained ultrasound image view 202. The method 500 may include identifying 510, by the at least one processor 132, 160, valid samples 230, 240 in the liver 204, 210 and the renal cortex 208, 220 in the obtained ultrasound image view 202 by excluding invalid samples 232, 242. The method 500 may include automatically locating 512, by the at least one processor 132, 170, a liver region of interest 250 and a renal cortex region of interest 260 in the obtained ultrasound image view 202 based on the valid samples 230, 240 and at least one criterion. The method 500 may include determining 514, by the at least one processor 132, 180, a hepatorenal index (HRI). The method 500 may include causing 516, by the at least one processor 132, 180, the display system 134 to present the HRI.

[0056] In a representative embodiment, the method 500 may include determining 514, by the at least one processor 132, 180, a quality score for the HRI and causing the at least one processor 132, 180 to present the quality score for the HRI along with the HRI on the display system 134. In an exemplary embodiment, the method 500 may include assigning 506, by the at least one processor 132, 140, a quality metric to the acquired ultrasound image view 202 and causing the at least one processor 132, 140 to present the quality metric on the display system 134. In various embodiments, the invalid samples 232 in the liver 204, 210 include one or more of the following: samples within one or more of a duct, a blood vessel, a mass, and a cyst; one or both of samples depicting artifacts or samples in artifact-prone areas; samples within a threshold distance from a liver boundary line; samples in an inhomogeneous area within the liver 204, 210; samples having a value above an upper threshold or below a lower threshold; and samples having a distance greater than a defined distance from the kidney 206, 208. In some embodiments, the invalid samples 242 in the renal cortex 208, 220 include one or more of the following: samples within one or more of a mass, a cyst, a collecting system, and external renal tissue; one or both of samples depicting artifacts or samples in artifact-prone areas; samples within a threshold distance from the kidney boundary line; samples in a heterogeneous area within the renal cortex 208, 220; and samples with values ​​above an upper threshold or below a lower threshold. In representative embodiments, at least one criterion includes one or both of the following: the densest area of ​​valid samples in the renal cortex 208, 220; and the densest area of ​​valid samples in the liver 204, 210. The densest effective sample region in the liver 204, 210 can be identified based at least in part on one or more of the following: the shortest distance to the centerline of the transducer data; the shortest distance to the densest effective sample region in the renal cortex 208, 220; the densest effective sample region in the liver 204, 210 and the densest effective sample region in the renal cortex 208, 220 being at the same image depth; and the densest effective sample region in the liver 204, 210 and the densest effective sample region in the renal cortex 208, 220 being at the same geometric depth. In an exemplary embodiment, determining the HRI is based on a ratio of an average value of liver data in the liver region of interest 250 to an average value of renal cortex data in the renal cortex region of interest 260. The liver data and the renal cortex data can be one of the following: beamformed data, in-phase and quadrature (I / Q) data, post-processed data, or grayscale values.

[0057] Various embodiments provide an ultrasound system 100 for automatically estimating a hepatorenal index (HRI) from ultrasound images. The ultrasound system 100 may include an ultrasound probe 104, at least one processor 132, 140, 150, 160, 170, 180, and a display system 134. The ultrasound probe 104 may be operable to acquire a sequence of ultrasound image data until a desired ultrasound image view 202 is obtained. The at least one processor 132, 150 may be configured to segment the liver 204, 210 and the renal cortex 208, 220 in the obtained ultrasound image view 202. The at least one processor 132, 160 may be configured to identify valid samples 230, 240 in the liver 204, 210 and the renal cortex 208, 220 in the obtained ultrasound image view 202 by excluding invalid samples 232, 242. At least one processor 132, 170 can be configured to automatically locate a liver region of interest 250 and a renal cortex region of interest 260 in the acquired ultrasound image view 202 based on the valid samples 230, 240 and at least one criterion. At least one processor 132, 180 can be configured to determine a hepatorenal index (HRI). The display system 134 can be configured to present the HRI.

[0058] In an exemplary embodiment, at least one processor 132, 180 may be configured to determine a quality score for the HRI and cause the display system 134 to present the quality score for the HRI along with the HRI. In various embodiments, at least one processor 132, 140 may be configured to assign a quality metric to the acquired ultrasound image view 202 and cause the display system 134 to present the quality metric. In certain embodiments, the invalid samples 232 in the liver 204, 210 include one or more of the following: samples within one or more of a duct, a blood vessel, a mass, and a cyst; one or both of samples depicting artifacts or samples in artifact-prone areas; samples within a threshold distance from a liver boundary line; samples in an inhomogeneous area within the liver 204, 210; samples having a value above an upper threshold or below a lower threshold; and samples having a distance greater than a defined distance from the kidney 206, 208. In a representative embodiment, the invalid samples 242 in the renal cortex 208, 220 include one or more of the following: samples within one or more of a mass, a cyst, a collecting system, and external renal tissue; one or both of samples depicting artifacts or samples in artifact-prone areas; samples within a threshold distance from the kidney boundary line; samples in a heterogeneous area within the renal cortex; and samples with values ​​above an upper threshold or below a lower threshold. In an exemplary embodiment, at least one criterion may include one or both of the following: the densest valid sample area in the renal cortex 208, 220; and the densest valid sample area in the liver 204, 210. The densest effective sample region in the liver 204, 210 can be identified based at least in part on one or more of the following: the shortest distance to the centerline of the transducer data; the shortest distance to the densest effective sample region in the renal cortex 208, 220; the densest effective sample region in the liver 204, 210 and the densest effective sample region in the renal cortex 208, 220 being at the same image depth; and the densest effective sample region in the liver 204, 210 and the densest effective sample region in the renal cortex 208, 220 being at the same geometric depth. In various embodiments, at least one processor 132, 180 is configured to determine the HRI based on a ratio of an average value of the liver data in the liver region of interest 250 to an average value of the renal cortex data in the renal cortex region of interest 260. The liver data and the renal cortex data can be one of the following: beamformed data, in-phase and quadrature (I / Q) data, post-processed data, or grayscale values.

[0059] Certain embodiments provide a non-transitory computer-readable medium having a computer program stored thereon, the computer program having at least one code segment. The at least one code segment is executable by a machine to cause an ultrasound system to perform step 500. Step 500 may include receiving 502 a sequence of ultrasound image data until a desired ultrasound image view 202 is received 504. Step 500 may include segmenting 508 the liver 204, 210 and the renal cortex 208, 220 in the received ultrasound image view 202. Step 500 may include identifying 510 valid samples 230, 240 in the liver 204, 210 and the renal cortex 208, 220 in the received ultrasound image view 202 by excluding invalid samples 232, 242. Step 500 may include automatically locating 512 a liver region of interest 250 and a renal cortex region of interest 260 in the received ultrasound image view 202 based on the valid samples 230, 240 and at least one criterion. Step 500 may include determining 514 a hepatorenal index (HRI). Step 500 may include causing 516 display system 134 to present the HRI.

[0060] In various embodiments, step 500 may include assigning 506 a quality metric to the received ultrasound image view 202 and causing the display system 134 to present the quality metric. Step 500 may include determining 514 a quality score for the HRI and causing the display system 134 to present 516 the quality score for the HRI along with the HRI. In certain embodiments, the invalid samples 232 in the liver 204, 210 may include one or more of the following: samples within one or more of a duct, a blood vessel, a mass, and a cyst; one or both of samples depicting artifacts or samples in artifact-prone areas; samples within a threshold distance from a liver boundary line; samples in an inhomogeneous area within the liver 204, 210; samples having a value above an upper threshold or below a lower threshold; and samples having a distance from the kidney 206, 208 greater than a defined distance. In a representative embodiment, invalid samples 242 in the renal cortex 208, 220 may include one or more of the following: samples within one or more of a mass, cyst, collecting system, and external renal tissue; one or both of samples depicting artifacts or samples in artifact-prone areas; samples within a threshold distance from the kidney boundary line; samples in a heterogeneous area within the renal cortex 208, 220; and samples with values ​​above an upper threshold or below a lower threshold.

[0061] In an exemplary embodiment, the at least one criterion may include one or both of the following: the densest effective sample area in the renal cortex 208, 220; and the densest effective sample area in the liver 204, 210. The densest effective sample area in the liver 204, 210 may be identified based at least in part on one or more of the following: the shortest distance to the centerline of the transducer data; the shortest distance to the densest effective sample area in the renal cortex 208, 220; the densest effective sample area in the liver 204, 210 and the densest effective sample area in the renal cortex 208, 220 being at the same image depth; and the densest effective sample area in the liver 204, 210 and the densest effective sample area in the renal cortex 208, 220 being at the same geometric depth. In various embodiments, determining 514 the HRI may be based on a ratio of an average value of the liver data in the liver region of interest 250 to an average value of the renal cortex data in the renal cortex region of interest 260. The liver data and the renal cortex data may be one of: beamformed data, in-phase and quadrature (I / Q) data, post-processed data, or grayscale values.

[0062] As used herein, the term "circuit" refers to physical electronic components (i.e., hardware) and any software and / or firmware ("code") that can be configured, executed by the hardware, and / or otherwise associated with the hardware. For example, as used herein, when executing one or more first codes, a particular processor and memory may include a first "circuit," and when executing one or more second codes, a particular processor and memory may include a second "circuit." As used herein, "and / or" represents any one or more of the items in a list connected by "and / or." For example, "x and / or y" represents any element in a three-element set {(x), (y), (x, y)}. As another example, "x, y, and / or z" represents any element in a seven-element set {(x), (y), (z), (x, y), (x, z), (y, z), (x, y, z)}. As used herein, the term "exemplary" represents a non-limiting example, instance, or illustration. As used herein, the terms "e.g." and "for example" introduce a list of one or more non-limiting examples, instances, or illustrations. As used herein, a circuit is "configured to" or "configured to" perform a function whenever the circuit includes the necessary hardware and code (if necessary) to perform the function, regardless of whether performance of the function is disabled or not enabled by some user-configurable setting.

[0063] 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, thereby causing the machine and / or the computer to perform the steps for automatically estimating the hepatorenal index (HRI) from ultrasound images as described herein.

[0064] Thus, 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, with different elements distributed across several interconnected computer systems. Any type of computer system or other device suitable for executing the methods described herein is suitable.

[0065] 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 in this context is 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 certain functions either directly or after either or both of the following: a) conversion into another language, code or notation; or b) reproduction in a different material form.

[0066] Although the present disclosure has been described with reference to certain embodiments, it will be understood 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 a particular situation or material 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 rather the present disclosure is intended to include all embodiments falling within the scope of the appended claims.

Claims

1. A method for ultrasound imaging, comprising: acquiring, by the ultrasound system, a sequence of ultrasound image data until a desired ultrasound image view is obtained; segmenting, by at least one processor of the ultrasound system, the liver and the renal cortex in the acquired ultrasound image view; identifying, by the at least one processor, valid samples in the liver and the renal cortex in the acquired ultrasound image view by excluding invalid samples; automatically locating, by the at least one processor, a liver region of interest and a renal cortex region of interest in the acquired ultrasound image view based on the valid samples and at least one criterion; determining, by the at least one processor, a hepatorenal index (HRI); determining, by the at least one processor, a quality score for the HRI based on a standard deviation between a plurality of liver regions of interest and a plurality of renal cortex regions of interest; as well as The at least one processor causes a display system to present the quality score of the HRI together with the HRI.

2. The method according to claim 1, comprising: assigning, by the at least one processor, a quality metric to the obtained ultrasound image view; as well as The display system is caused, by the at least one processor, to present the quality metric.

3. The method of claim 1 , wherein the invalid sample in the liver comprises one or more of: a sample from inside one or more of a duct, blood vessel, mass, or cyst; Delineating one or both of artifact-bearing samples or samples in artifact-prone areas; samples within a threshold distance from the liver boundary line; a sample in a heterogeneous region within the liver; Samples with values ​​above the upper threshold or below the lower threshold; and Samples whose distance from the kidney is greater than the defined distance.

4. The method of claim 1 , wherein the invalid sample in the renal cortex comprises one or more of: samples from within one or more of a mass, cyst, collecting system, and external renal tissue; Delineating one or both of artifact-bearing samples or samples in artifact-prone areas; samples within a threshold distance from the kidney boundary line; a sample in a heterogeneous region within the renal cortex; and Samples with values ​​above the upper threshold or below the lower threshold.

5. The method of claim 1 , wherein the at least one criterion comprises one or both of the following: The densest effective sample area in the renal cortex; and a densest effective sample region in the liver, wherein the densest effective sample region in the liver is identified based at least in part on one or more of: The shortest distance to the center line of the transducer data; the shortest distance to the densest effective sample area in the renal cortex; The densest effective sample area in the liver and the densest effective sample area in the renal cortex are at the same image depth; and The densest effective sample area in the liver and the densest effective sample area in the renal cortex are at the same geometric depth.

6. The method according to claim 1, wherein: determining the HRI based on a ratio of an average value of liver data in the liver region of interest to an average value of renal cortex data in the renal cortex region of interest, and The liver data and the renal cortex data are one of the following: Beamforming data, In-phase and quadrature (I / Q) data, Post-processing data, and Grayscale value.

7. An ultrasound system, comprising: an ultrasound probe operable to acquire a sequence of ultrasound image data until a desired ultrasound image view is obtained; at least one processor configured to: segmenting the liver and the renal cortex in the acquired ultrasound image view; identifying valid samples in the liver and the renal cortex in the acquired ultrasound image view by excluding invalid samples; automatically locating a liver region of interest and a renal cortex region of interest in the acquired ultrasound image view based on the valid sample and at least one criterion; and Determine the hepatorenal index (HRI); determining a quality score of the HRI based on a standard deviation between a plurality of liver regions of interest and a plurality of renal cortex regions of interest; as well as A display system is configured to present the quality score of the HRI together with the HRI.

8. The system of claim 7, wherein the at least one processor is configured to: assigning a quality metric to the obtained ultrasound image view; and The display system is caused to present the quality metric.

9. The system of claim 7, wherein the invalid sample in the liver comprises one or more of: a sample from inside one or more of a duct, blood vessel, mass, or cyst; Delineating one or both of artifact-bearing samples or samples in artifact-prone areas; samples within a threshold distance from the liver boundary line; a sample in a heterogeneous region within the liver; Samples with values ​​above the upper threshold or below the lower threshold; and Samples whose distance from the kidney is greater than the defined distance.

10. The system of claim 7, wherein the invalid samples in the renal cortex include one or more of: samples from within one or more of a mass, cyst, collecting system, and external renal tissue; Delineating one or both of artifact-bearing samples or samples in artifact-prone areas; samples within a threshold distance from the kidney boundary line; a sample in a heterogeneous region within the renal cortex; and Samples with values ​​above the upper threshold or below the lower threshold.

11. The system of claim 7, wherein the at least one criterion comprises one or both of the following: The densest effective sample area in the renal cortex; and a densest effective sample region in the liver, wherein the densest effective sample region in the liver is identified based at least in part on one or more of: The shortest distance to the center line of the transducer data; the shortest distance to the densest effective sample area in the renal cortex; The densest effective sample area in the liver and the densest effective sample area in the renal cortex are at the same image depth; and The densest effective sample area in the liver and the densest effective sample area in the renal cortex are at the same geometric depth.

12. The system of claim 7, wherein: The at least one processor is configured to determine the HRI based on a ratio of an average value of liver data in the liver region of interest to an average value of renal cortex data in the renal cortex region of interest, and The liver data and the renal cortex data are one of the following: Beamforming data, In-phase and quadrature (I / Q) data, Post-processing data, and Grayscale value.

13. A non-transitory computer-readable medium having a computer program stored thereon, the computer program having at least one code segment executable by a machine to cause an ultrasound system to perform steps comprising: receiving a sequence of ultrasound image data until a desired ultrasound image view is received; segmenting the liver and the renal cortex in the received ultrasound image view; identifying valid samples in the liver and the renal cortex in the received ultrasound image view by excluding invalid samples; automatically locating a liver region of interest and a renal cortex region of interest in the received ultrasound image view based on the valid samples and at least one criterion; Determine the hepatorenal index (HRI); determining a quality score of the HRI based on a standard deviation between a plurality of liver regions of interest and a plurality of renal cortex regions of interest; as well as The display system is caused to present the quality score of the HRI together with the HRI.

14. The non-transitory computer readable medium of claim 13, comprising the steps of: A quality metric is assigned to the received ultrasound image view and the display system is caused to present the quality metric.

15. The non-transitory computer-readable medium of claim 13, wherein the invalid sample in the liver comprises one or more of: a sample from inside one or more of a duct, blood vessel, mass, or cyst; Delineating one or both of artifact-bearing samples or samples in artifact-prone areas; samples within a threshold distance from the liver boundary line; a sample in a heterogeneous region within the liver; Samples with values ​​above the upper threshold or below the lower threshold; and Samples whose distance from the kidney is greater than the defined distance.

16. The non-transitory computer-readable medium of claim 13, wherein the invalid samples in the renal cortex include one or more of: samples from within one or more of a mass, cyst, collecting system, and external renal tissue; Delineating one or both of artifact-bearing samples or samples in artifact-prone areas; samples within a threshold distance from the kidney boundary line; a sample in a heterogeneous region within the renal cortex; and Samples with values ​​above the upper threshold or below the lower threshold.

17. The non-transitory computer-readable medium of claim 13, wherein the at least one criterion comprises one or both of the following: The densest effective sample area in the renal cortex; and a densest effective sample region in the liver, wherein the densest effective sample region in the liver is identified based at least in part on one or more of: The shortest distance to the center line of the transducer data; the shortest distance to the densest effective sample area in the renal cortex; The densest effective sample area in the liver and the densest effective sample area in the renal cortex are at the same image depth; and The densest effective sample area in the liver and the densest effective sample area in the renal cortex are at the same geometric depth.

18. The non-transitory computer-readable medium of claim 13, wherein: determining the HRI based on a ratio of an average value of liver data in the liver region of interest to an average value of renal cortex data in the renal cortex region of interest, and The liver data and the renal cortex data are one of the following: Beamforming data, In-phase and quadrature (I / Q) data, Post-processing data, and Grayscale value.

Images