Automatic establishment of measurement position control for Doppler ultrasound

Abstract

An equipment for automatically establishing measurement location control for a Doppler ultrasound examination is described. The equipment receives a first ultrasound image and a user input selecting an anatomical structure appearing therein. The equipment performs localization to determine a location of the selected anatomical structure in the first image and determines a first measurement location control arrangement for the structure. On the ultrasound machine, the equipment invokes one or more first Doppler ultrasound modes using the first arrangement. The equipment receives a second ultrasound image generated by the ultrasound machine using the one or more first modes, determines a flow location and flow direction based on the second ultrasound image, and determines a second arrangement for the flow location. The equipment invokes one or more second Doppler ultrasound modes using the second arrangement, and receives results from the invocation of the one or more second Doppler ultrasound modes.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. patent application Ser. No. 17 / 693,848, filed Mar. 14, 2022, and entitled “AUTOMATICALLY ESTABLISHING MEASUREMENT LOCATION CONTROLS FOR DOPPLER ULTRASOUND,” which is incorporated by reference in its entirety.

[0002] In the event that this application conflicts with a document incorporated by reference, this application will control. [Background technology]

[0003] Ultrasound imaging is a useful medical imaging modality. For example, the internal structures of a patient's body can be imaged before, during, or after a therapeutic intervention. Qualitative and quantitative observations in ultrasound images can also be the basis for diagnosis. For example, ventricular volumes determined via ultrasound are the basis for diagnosing, for example, ventricular systolic dysfunction and diastolic heart failure.

[0004] A medical professional typically holds a handheld ultrasound probe, sometimes called a "transducer," in close proximity to the patient and moves the transducer as needed to visualize one or more target structures within the patient's region of interest. The transducer may be placed on the surface of the body, or in some procedures, the transducer is inserted inside the patient's body. The medical professional coordinates the movement of the transducer to obtain a desired representation on a screen, such as a two-dimensional cross-section of a three-dimensional volume.

[0005] Certain views of organs or other tissues or body features (such as fluids, bones, joints, etc.) may be clinically important and may be prescribed by clinical standards as views that the ultrasound operator should capture depending on the target organ, diagnostic objective, etc.

[0006] Spectral analysis is often performed to assess blood flow direction and measure the velocity of heart valves, blood vessels, and other pathological lesions (areas in organs or tissues that have been damaged through injury or disease). Spectral analysis can be performed using either continuous wave (CW) or pulsed wave (PW) Doppler. CW uses two crystals to continuously transmit and receive signals. It is generally used to measure high blood flow velocities, such as those above 2 m / sec. PW, on the other hand, transmits using a single crystal and waits to receive and analyze the return signal. PW is typically limited to measuring low blood flow velocities, such as less than 2 m / sec, as it suffers from signal aliasing at higher blood flow velocities. The type of spectral analysis to be deployed (CW or PW) and the structures to be examined are generally determined by the suspected pathology. Sometimes color Doppler is used with either PW or CW for more precise gate / focus placement.

[0007] As a basis for measuring blood flow velocity using spectral analysis, the ultrasound operator defines the region of the ultrasound cone where measurements are to be made using measurement location controls that vary between Doppler modes. For CW, the operator specifies a Doppler line that includes an origin at the apex of the ultrasound cone and a point at the curved base of the cone, and the maximum velocity at any point on the line is determined. For PW, the operator specifies both a Doppler line and a segment of that line defined by placing a gate that bounds the line, and the velocity along that segment of the line is determined. For color Doppler, the operator specifies a color box that bounds a sample volume that lies within a range of depths over a continuous sequence of scan lines, and uses color to display flow velocity and direction within that sample volume. The best location for placing these Doppler measurement location controls may vary depending on the structure under scrutiny, the suspected pathology, and the cardiac view. [Brief description of the drawings]

[0008] The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee. [Figure 1] FIG. 1 is a block diagram illustrating some of the components typically incorporated in at least some of the computer systems and other devices in which the facility operates. [Diagram 2] FIG. 1 is a block diagram illustrating some of the components typically incorporated in at least some of the computer systems and other devices in which the facility operates. [Diagram 3] FIG. 1 is a flow diagram illustrating a process performed by the equipment in some embodiments to automatically establish measurement position control for Doppler ultrasound. [Figure 4] 1 is an ultrasound diagram showing a cardiac ultrasound image captured of a person. [Diagram 5] FIG. 2 is an ultrasound view showing a first time point at the beginning of diastole. [Figure 6] FIG. 13 is an ultrasound view showing a second time point during diastole. [Figure 7] FIG. 13 is an ultrasound view showing a third time point during diastole. [Figure 8] FIG. 11 is an ultrasound view showing a fourth time point during diastole. [Figure 9] FIG. 11 is an ultrasound view showing a fifth time point during diastole. [Figure 10] 1A-1C are ultrasound diagrams showing examples of determining the angle between a Doppler line and a determined flow direction. [Figure 11] 11A-11C are sample ultrasound diagrams illustrating repositioning of an ultrasound probe to better align the scan axis with the directional position determined by the fixture for flow. [Figure 12] FIG. 2 is a sample ultrasound view showing a pathological heart at a first time point. [Figure 13] FIG. 2 is a sample ultrasound view showing a diseased heart at a second time point. [Figure 14]FIG. 11 is a sample ultrasound view showing a diseased heart at a third time point. [Figure 15] FIG. 11 is a sample ultrasound view showing a pathological heart at a fourth time point. [Figure 16] FIG. 11 is a sample ultrasound view showing a diseased heart at a fifth time point. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The present inventors have recognized that conventional approaches using spectral and color Doppler ultrasound have significant drawbacks.

[0010] In particular, the inventors have recognized that conventional Doppler ultrasound techniques rely on manual placement of measurement location controls such as the Doppler line, gate, focus, and color Doppler color box. This requires significant skill and experience on the part of the operator, and thus precludes operators lacking such skill and experience from performing such examinations. Moreover, even for a skilled and experienced operator, it can consume significant amounts of time, both from the patient and the ultrasound machine, and can result in suboptimal results.

[0011] In response to recognizing these shortcomings, the present inventors have devised and implemented a software and / or hardware facility ("Facility") that automatically establishes measurement position control for Doppler ultrasound examinations.

[0012] In some embodiments, the equipment receives user input identifying a structure, such as a valve, where a measurement location control is to be located. In various embodiments, the equipment receives such user input via voice, by touching a display showing the ultrasound visual output at a point where the identified structure is shown, or the like.

[0013] In some embodiments, the equipment performs localization to determine the location of one or more structures of interest in the ultrasound image, such as heart valves, including the mitral valve, tricuspid valve, and aortic valve. In various embodiments, the equipment performs localization via (1) object detection to identify regions of the image that include the structure, or (2) object segmentation to identify each pixel of the image that exhibits the structure.

[0014] In some embodiments, the equipment determines an ultrasonic measurement position control arrangement relative to a determined location for a structure identified by the user, such as the center of a valve identified by the user, or the center of the top end, inner end, front end, rear end, outer end, inner end, upstream end, or downstream end of the valve.

[0015] In some embodiments, the equipment detects flow location and / or flow direction, such as laminar blood flow in healthy patients and aliasing in diseased patients. At various moments, the equipment performs segmentation, object detection, or linear regression to detect flow location.

[0016] In some embodiments, the facility uses the detected flow location to adjust the ultrasound measurement location control arrangement to more accurately capture the detected flow for Doppler measurement, which in some embodiments includes lowering the Doppler line to pass through the center of the detected flow location and positioning a gate or focal point to encompass the detected flow location.

[0017] In some embodiments, the equipment compares the determined flow direction to the directions of the Doppler lines to determine whether the lines are close to parallel. If the angle between the lines is greater than a threshold, the equipment takes action, such as instructing the operator to reposition the probe to better align the Doppler lines with laminar flow or aliasing. In some embodiments, the equipment applies trigonometric techniques to adjust the determined velocities along the Doppler lines to reflect velocities along the flow direction.

[0018] By implementing some or all of these methods, the facility reduces the level of operator skill and experience, time, and imprecision incurred by Doppler ultrasound examinations.

[0019] Additionally, the facility increases the capabilities of computers or other hardware by reducing the dynamic display area, processing, storage, and / or data transmission resources required to perform a particular task, thereby allowing the task to be performed by less powerful, less powerful, and / or less expensive hardware devices, and / or allowing the task to be performed with less latency, and / or preserving more of the conserved resources for use in performing other tasks, etc. For example, by reducing the amount of time an ultrasound machine is used for a particular test, the ultrasound machine can be used for multiple tests during its life, or versions that can be manufactured that can be used for the same number of tests, at a lower cost. Also, by reducing the number of unsuccessful tests that must be repeated, the facility increases the availability of the ultrasound machine for additional original tests.

[0020] 1 is a schematic diagram of a physiological sensing device in accordance with one or more embodiments of the present disclosure. The device 10, in the illustrated embodiment, includes a probe 12 electrically coupled to a handheld computing device 14 by a cable 17. The cable 17 includes a connector 18 that removably connects the probe 12 to the computing device 14. The handheld computing device 14 may be any portable computing device having a display, such as a tablet computer, a smartphone, etc. In some embodiments, the probe 12 need not be electrically coupled to the handheld computing device 14, but may operate independently of the handheld computing device 14, and the probe 12 may communicate with the handheld computing device 14 via a wireless communication channel.

[0021] The probe 12 is configured to transmit ultrasonic signals toward a target structure and to receive echo signals returning from the target structure in response to the transmission of the ultrasonic signals. The probe 12 includes an ultrasonic sensor 20, which in various embodiments may include an array of transducer elements (e.g., a transducer array) capable of transmitting ultrasonic signals and receiving subsequent echo signals.

[0022] The device 10 further includes a processing circuit and a driver circuit. In part, the processing circuit controls the transmission of ultrasonic signals from the ultrasonic sensor 20. The driver circuit is operatively coupled to the ultrasonic sensor 20 for driving the transmission of the ultrasonic signals, for example, in response to control signals received from the processing circuit. The driver circuit and processor circuit may be included in one or both of the probe 12 and the handheld computing device 14. The device 10 also includes a power supply that provides power to the driver circuit for transmitting ultrasonic signals, for example, in a pulsed wave or continuous wave mode of operation.

[0023] The ultrasonic sensor 20 of the probe 12 may include one or more transmit transducer elements that transmit ultrasonic signals and one or more receive transducer elements that receive echo signals returning from the target structure in response to the transmission of the ultrasonic signals. In some embodiments, some or all of the transducer elements of the ultrasonic sensor 20 may function as transmit transducer elements during a first period of time and as receive transducer elements during a second period of time that is different from the first period of time (i.e., the same transducer element may be usable to transmit ultrasonic signals and receive echo signals at different times).

[0024] The computing device 14 shown in FIG. 1 includes a display screen 22 and a user interface 24. The display screen 22 may be a display incorporating any type of display technology, including but not limited to LCD or LED display technology. The display screen 22 is used to display one or more images generated from echo data obtained from echo signals received in response to transmission of ultrasound signals, and in some embodiments, the display screen 22 may be used to display color flow image information, such as may be provided in a Color Doppler imaging (CDI) mode. Additionally, in some embodiments, the display screen 22 may be used to display audio waveforms, such as waveforms representing acquired or conditioned auscultation signals.

[0025] In some embodiments, the display screen 22 may be a touch screen capable of receiving input from an operator touching the screen. In such embodiments, the user interface 24 may include a portion or all of the display screen 22 capable of receiving operator input via touch. In some embodiments, the user interface 24 may include one or more buttons, knobs, switches, etc. capable of receiving input from an operator of the ultrasound device 10. In some embodiments, the user interface 24 may include a microphone 30 capable of receiving audible input, such as voice commands.

[0026] Computing device 14 may further include one or more audio speakers 28 that may be used to output an audible representation of acquired or conditioned auscultation signals, or echo signals, blood flow during Doppler ultrasound imaging, or other features derived from the operation of device 10.

[0027] The probe 12 includes a housing that forms an exterior portion of the probe 12. The housing includes a sensor portion located near a distal end of the housing and a handle portion between the proximal and distal ends of the housing. The handle portion is located proximal to the sensor portion.

[0028] The handle portion is the portion of the housing that is gripped by an operator during use to hold, control, and manipulate the probe 12. The handle portion may include a gripping mechanism, such as one or more cleats, and in some embodiments, the handle portion may have the same general shape as the portion of the housing distal or proximal to the handle portion.

[0029] The housing encloses the internal electronic components and / or circuits of the probe 12, including, for example, electronics such as drive circuits, processing circuits, oscillators, beam forming circuits, filtering circuits, etc. The housing may be formed to enclose or at least partially enclose an externally disposed portion of the probe 12, such as the sensing surface. The housing may be a sealed housing such that moisture, liquids, or other fluids are prevented from entering the housing. The housing may be formed of any suitable material, and in some embodiments, the housing is formed of a plastic material. The housing may be formed of a single piece (e.g., a single material molded to enclose the internal components). Alternatively, the housing may be formed of two or more pieces (e.g., an upper half and a lower half) that are joined or otherwise attached to each other.

[0030] In some embodiments, the probe 12 includes a motion sensor. The motion sensor is operable to sense motion of the probe 12. The motion sensor may be included in or on the probe 12 and may include, for example, one or more accelerometers, magnetometers, or gyroscopes for sensing motion of the probe 12. For example, the motion sensor may be or include any of a piezoelectric, piezoresistive, or capacitive accelerometer capable of sensing motion of the probe 12. In some embodiments, the motion sensor is a three-axis motion sensor capable of sensing motion about any of three axes. In some embodiments, two or more motion sensors 16 are included in or on the probe 12. In some embodiments, the motion sensor includes at least one accelerometer and at least one gyroscope.

[0031] The motion sensor may be at least partially contained within the housing of the probe 12. In some embodiments, the motion sensor is located on or near the sensing surface of the probe 12. In some embodiments, the sensing surface is the surface that is in operative contact with the patient during an examination, such as ultrasound imaging or auscultation sensing. The ultrasound sensor 20 and one or more auscultation sensors are positioned on, part of, or near the sensing surface.

[0032] In some embodiments, the transducer array of the ultrasonic sensor 20 is a one-dimensional (1D) array or a two-dimensional (2D) array of transducer elements. The transducer array may include a piezoelectric ceramic, such as lead zirconate titanate (PZT), or may be based on a microelectromechanical system (MEMS). For example, in various embodiments, the ultrasonic sensor 20 may include a piezoelectric micromachined ultrasonic transducer (PMUT), which is a microelectromechanical system (MEMS)-based piezoelectric ultrasonic transducer, or the ultrasonic sensor 20 may include a capacitive micromachined ultrasound transducer (CMUT), in which energy conversion is provided due to changes in capacitance.

[0033] The ultrasonic sensor 20 may further include an ultrasonic focusing lens that may be positioned on the transducer array and may form a part of the sensing surface. The focusing lens may be any lens operable to focus an ultrasonic beam transmitted from the transducer array towards the patient and / or to focus an ultrasonic beam reflected from the patient back to the transducer array. In some embodiments, the ultrasonic focusing lens may have a curved surface shape. The ultrasonic focusing lens may have different shapes depending on the desired application, such as the desired operating frequency. The ultrasonic focusing lens may be formed of any suitable material, and in some embodiments, the ultrasonic focusing lens is formed of a room-temperature-vulcanizing (RTV) rubber material.

[0034] In some embodiments, a first membrane and a second membrane may be positioned adjacent to opposite sides of the ultrasonic sensor 20 and form a portion of the sensing surface. The membranes may be formed of any suitable material, and in some embodiments, the membranes are formed of a room temperature vulcanizing (RTV) rubber material. In some embodiments, the membranes are formed of the same material as the ultrasound focusing lens.

[0035] 2 is a block diagram illustrating some of the components typically incorporated in at least some of the computer systems and other devices on which the facilities operate. In various embodiments, these computer systems and other devices 200 may include server computer systems, virtual machines on a cloud computing platform or other configuration, desktop computer systems, laptop computer systems, netbooks, mobile phones, personal digital assistants, televisions, cameras, automobile computers, electronic media players, physiological sensing devices and / or their associated display devices, and the like. In various embodiments, the computer system and device includes zero or more of each of the following: a processor 201, such as a CPU, GPU, TPU, NNP, FPGA, or ASIC, for executing computer programs and / or training or applying machine learning models; computer memory 202, including equipment and associated data, an operating system including a kernel, and device drivers, for storing the programs and data while the programs and data are in use; persistent storage 203, such as a hard drive or flash drive, for persistently storing the programs and data; a computer readable media drive 204, such as a floppy, CD-ROM, or DVD drive, for reading the programs and data stored on the computer readable media; and a network connection 205, for connecting the computer system to other computer systems to send and receive data via the Internet or another network and its networking hardware, such as switches, routers, repeaters, electrical cables and optical fibers, light emitters and receivers, wireless transmitters and receivers. Although a computer system configured as described above is typically used to support the operation of the equipment, one skilled in the art will understand that the equipment may be implemented using various types and configurations of devices and have various components.

[0036] 3 is a flow diagram illustrating a process performed by the equipment in some embodiments to automatically establish measurement location control for Doppler ultrasound. In operation 301, the equipment receives user input to select an anatomical structure, which may include an anatomical structure to be shown in a captured and displayed ultrasound image of a person. In various embodiments, the user input received by the equipment in operation 301 represents an operator speaking the name of a structure or touching a particular point in the displayed ultrasound image.

[0037] 4 is an ultrasound diagram showing cardiac ultrasound images captured of a person. Image 400 shows an apical five-chamber view of the person's heart 420. While many ultrasound images show the outline of an ultrasound cone surrounding the ultrasound image, ultrasound image 400 shown in FIG. 4, and some of the other ultrasound images shown in the figures, do not. Some of the illustrated ultrasound images have been subject to black and white inversion from their typical appearance to make them more visually understandable.

[0038] In the heart, the ultrasound image shows the aortic valve 430 through which blood normally flows from the left ventricle 433, through the left ventricular outflow tract 434, and into the aorta 432. Using color Doppler, the blue region 431 shows blood flow in that direction throughout the region 431 during the ventricular systole phase of the cardiac cycle. In these figures, blue indicates flow away from the ultrasound source (i.e., generally downward in the drawing), and red indicates flow toward the ultrasound source (i.e., generally upward in the drawing). Also shown is the tricuspid valve 440, through which blood normally flows from the right atrium 443 to the right ventricle 442. The red region 441 shows blood in the right atrium flowing upward toward the tricuspid valve. Additionally, the mitral valve 450 is shown through which blood normally flows from the left atrium 453 to the left ventricle 433. The red region 451 shows blood in the left atrium flowing upward toward the mitral valve. As an example, to select an anatomical structure in this ultrasound image, the operator may say the name of the mitral valve, tricuspid valve, or aortic valve, or may touch the screen where one of these valves is displayed.

[0039] Returning to Figure 3, in operation 302, the equipment analyzes the user input received in operation 301 to determine the anatomical structure selected by the user input. In operation 303, the equipment performs localization to determine the location of the selected structure within the ultrasound image captured of the person. In various embodiments, the equipment performs localization using object detection to identify a region of the image that includes the structure, or object segmentation to identify each of the pixels of the image that show the structure.In various embodiments, the equipment performs object detection and / or segmentation as described in one or more of the following, each of which is incorporated herein by reference: U.S. Patent Application No. 17 / 088,390, entitled “GATING MACHINE LEARNING PREDICTIONS ON MEDICAL ULTRASOUND IMAGES VIA RISK AND UNCERTAINTY QUANTIFICATION,” filed November 3, 2020; U.S. Patent Application No. 16 / 913,322, entitled “AUTOMATICALLY IDENTIFYING ANATOMICAL STRUCTURES IN MEDICAL IMAGES IN A MANNER THAT IS SENSITIVE TO THE PARTICULAR VIEW IN WHICH EACH IMAGE IS CAPTURED,” filed June 16, 2020; U.S. Patent Application No. 16 / 103,322, entitled “AUTOMATIC EVALUATION OF ULTRASOUND PROTOCOLS AND METHOD FOR ... U.S. Patent Application No. 17 / 068,143 entitled "ROBUST SEGMENTATION THROUGH HIGH-LEVEL IMAGE UNDERSTANDING" filed on November 6, 2020; U.S. Patent Application No. 17 / 091,263 entitled "AUTOMATIC DEPTH SELECTION FOR ULTRASOUND IMAGING" filed on October 25, 2021; U.S. Patent Application No. 17 / 509,987 entitled "AUTOMATIC DEPTH SELECTION FOR ULTRASOUND IMAGING" filed on November 18, 2021; U.S. Patent Application No. 17 / 529,565 entitled "AUTOMATICALLY DETECTING AND QUANTIFYING ANATOMICAL STRUCTURES IN AN ULTRASOUND IMAGE USING A CUSTOMIZED SHAPE PRIOR" filed on February 23, 2022; No. 17 / 678,813, entitled "SEQUENCE OF ULTRASOUND IMAGES." In the event that a document incorporated by reference herein conflicts with this disclosure, this disclosure controls.

[0040] In operation 304, the equipment determines an ultrasound measurement position control location relative to the structure location determined in operation 301. By way of example, for color Doppler, the equipment determines the location of the color box, for CW, the equipment determines the location of the Doppler line, and for PW, the equipment determines the location of the Doppler line and the location of a segment of that line bounded by a gate. In various embodiments, the location determined by the equipment is the center of the valve selected by the user or the center of an end of the valve, such as the top, bottom, front, back, outer, inner, normally upstream, or normally downstream end of the valve.

[0041] 5-9 are a series of sample ultrasound diagrams illustrating an example of measurement location control placement of the equipment over the course of ventricular diastole of the cardiac cycle in a healthy heart. FIG. 5 is an ultrasound diagram showing a first time point at the beginning of diastole. Diagram 500 shows a heart 520 in which the equipment has placed measurement location control by (1) descending a Doppler line 560 from an origin 569 at the top of the diagram through the center of the mitral valve 550, and (2) establishing Doppler gate walls 563 and 564 at points along the length of the Doppler line that encompass the space just above and normally downstream of the mitral valve. So positioned, one or more Doppler mode ultrasound waves measure blood flow velocity along the Doppler line between these two walls. In a properly functioning heart, the flow direction is from the left atrium 553 to the left ventricle 533 over the course of the subsequent portion of ventricular diastole. However, at this point, with the mitral valve closed, the equipment measures a blood flow velocity in the gate near 0, but the red area 551 indicates that blood is flowing toward the closed mitral valve in the left atrium. Velocity versus time graph 590 shows this measured 0 velocity at the point in time 591 to which graph 500 corresponds.

[0042] 6 is an ultrasound diagram showing a second time point during diastole. At the second time point, shown as time point 692 on the velocity graph, diastole is progressing and the velocity along the Doppler line within the gate is increasing. This can be seen reflected in the expansion of the red region 651 into the left ventricle 633 as compared to the red region 551 shown in FIG. 5.

[0043] 7 is an ultrasound diagram showing a third time point in diastole. At the third time point, shown as time point 793 on the velocity graph, diastole has progressed further and the velocity along the gated Doppler line is at a maximum. This corresponds to a further shift of the red region 751 from the left atrium 753 to the left ventricle 733 as compared to the red region 651 shown in FIG. 6.

[0044] 8 is an ultrasound diagram showing a fourth time point during diastole. The fourth time point, shown as time point 894 on the velocity graph, is at or near the diastolic phase of diastole, where the velocity through the mitral valve and deployed gate is at its minimum during diastole. This is reflected by the red region 851 shifting further from the left atrium 853 to the left ventricle 833.

[0045] 9 is an ultrasound diagram showing a fifth time point during diastole. The fifth time point, shown as time point 995 on the velocity graph, corresponds to a second, lower peak in velocity reflected by the majority of the red region 951 within the left ventricle 933.

[0046] Returning to FIG. 3 , in operation 305, the equipment uses the position control arrangement determined in operation 304 to determine flow location and flow direction using one or more Doppler ultrasound modes. In various embodiments, the equipment determines flow location and flow direction using object detection or object segmentation on the Doppler ultrasound images generated using the position control arrangement. In some cases, the flow of interest is normal laminar blood flow through the heart. In some cases, the flow of interest is a backflow to the proper flow of blood through the heart, and / or a backflow that may constitute turbulent flow. In such cases, in some embodiments, the equipment performs localization on aliasing patterns in the ultrasound images that represent this abnormal blood flow.

[0047] In various embodiments, the facility uses segmentation, object detection, or linear regression to determine flow location and flow direction. For segmentation techniques, in some embodiments, the facility trains and applies a convolutional neural network whose independent variables are color Doppler and B-mode images, and whose dependent variables are probability maps indicating the spatial location and flow direction of aliasing in the images. For object detection techniques, in some embodiments, the facility parameterizes the output bounding box by height, width, and rotation angle. For linear regression techniques, in some embodiments, the facility parameterizes by two points passing through the center of laminar flow or aliasing.

[0048] In operation 306, the equipment adjusts the position control arrangement using the flow location determined in operation 305. In some embodiments, the equipment performs this adjustment by lowering a Doppler line to pass through the center of the detected flow location and placing a gate or focal point along that Doppler line to encompass the detected flow location.

[0049] In operation 307, the equipment determines the angle between the Doppler line and the flow direction determined in operation 305. Figure 10 is an ultrasound diagram showing an example of determining the angle between the Doppler line and the determined flow direction. In diagram 1000, it can be seen that the Doppler line 1060 starts at the origin 1069 at the top of the diagram, intersects the outer wall of the heart 1020 at point 1061, and passes through the center of the aortic valve 1030. The determined flow direction is shown as dashed line 1034. The equipment determines the angle 1062 between the Doppler line and the flow direction.

[0050] Returning to FIG. 3, in operation 308, if the size of the angle determined in operation 307 is less than a threshold angle size, such as 10 degrees, the equipment proceeds to operation 309, otherwise the equipment proceeds to operation 311. In operation 309, the equipment uses the position control adjusted in operation 306 to determine the flow velocity. In operation 310, the equipment reports the determined flow velocity. In various embodiments (not shown), the equipment uses the determined flow velocity in various ways, such as displaying it, storing it on behalf of a person, using it as a basis for making other ultrasound observations, making automatic diagnoses, etc. As an example, a stenosis can be automatically diagnosed based on a high blood flow velocity in a normal direction. After operation 310, the process ends. In operation 311, because the size of the angle exceeds the threshold size, the equipment declines to use the current position control configuration to determine the flow velocity, and instead instructs the operator of the ultrasound machine to reposition the probe to better align the probe's scanning axis with the direction and position determined relative to the flow in operation 305. This may include, for example, pivoting, unfolding, and / or repositioning the probe relative to the exterior of the person's body. In various embodiments, the equipment provides this instruction via synthesized or recorded voice output, overlaying text on the ultrasound display, overlaying image animation on the ultrasound display, displaying text and / or image animation on a separate visual display, etc. After operation 311, the equipment continues to operation 303 and uses localization to determine the location of the selected structure in the new ultrasound view resulting from the repositioning of the probe.

[0051] Those skilled in the art will appreciate that the acts depicted in Figure 3 may be modified in various ways, such as by reordering the acts, by performing some acts in parallel, by omitting acts depicted or including other acts, by dividing acts depicted into sub-acts, or by combining multiple depicted acts into a single act, etc.

[0052] FIG. 11 is a sample ultrasound diagram showing repositioning of the ultrasound probe to better align the scan axis with the directional position determined by the equipment for flow. After repositioning, the equipment establishes a Doppler line 1160 that starts at the origin 1169 at the top of the diagram 1100, intersects the outer wall of the heart 1120 at point 1161, and passes through the center of the aortic valve 1130. Line 1134 shows the direction determined for flow by the equipment. The angle 1162 between these two lines is significantly smaller than the angle 1062 shown in FIG. 10. Thus, the Doppler line 1160 is better aligned with the flow direction, and the components of the flow velocity measured along the Doppler line are much closer to the flow velocity in the flow direction. Thus, in this repositioned orientation, in some cases, the velocities measured along the Doppler line can be used as a reasonable proxy for the velocity in the flow direction. In some embodiments, the facility adapts the velocity measured along the Doppler line by dividing it by the cosine of the angle to estimate the velocity along the flow direction.

[0053] 12-16 are a series of sample sonograms captured during the systole phase of the cardiac cycle showing an example of the operation of the equipment with respect to a heart experiencing aortic regurgitation. FIG. 12 is a sample sonogram showing a diseased heart at a first time point. FIG. 1200 shows a color box 1270 positioned by the equipment for a color Doppler mode to identify the region and direction of blood flow in the region of the aortic valve 1230. The blue region 1231 shows blood beginning to flow from the left ventricle 1233 through the aortic valve into the aorta 1232.

[0054] 13 is a sample ultrasound diagram showing a diseased heart at a second time point. Diagram 1300 shows that the blue region 1331 shifts further into the aorta 1332.

[0055] 14 is a sample ultrasound view showing a diseased heart at a third time point, where the aortic valve 1430 begins to close, slowing blood flow into the aorta 1432, represented by blue region 1431.

[0056] 15 is a sample ultrasound view of a diseased heart at time point 4. At time point 4, the aortic valve 1530 is in a fully closed position. Despite this, blood begins to flow from the aorta 1532 into the left ventricular outflow tract 1534 as a result of the aortic valve's inability to completely seal when closed. This is indicated by a red regurgitant jet composed of a flow convergence region 1538 and a jet body 1539.

[0057] FIG. 16 is a sample ultrasound view of a diseased heart at a fifth time point. At the fifth time point, the regurgitant flow is larger and the jet body 1639 is larger in area compared to the jet body 1539 shown in FIG. 15. In some embodiments, to measure the severity of the regurgitant flow, the equipment places a measurement location control relative to the regurgitant jet. In some embodiments, the equipment determines whether the Doppler plane passes through the entire jet such that it is approximately parallel to the flow direction. In some embodiments, the equipment does this by determining whether both the jet convergence region and the jet body are clearly visualized in the ultrasound image. If so, there is little deviation between the flow direction and the velocity measurement direction in the Z dimension (i.e., the dimension in which the probe fanning is performed), and the flow velocity in the flow measurement direction more closely resembles the flow velocity in the flow direction and can be used directly as a proxy for it with reasonable accuracy, or can be adjusted using trigonometric calculations as described above.

[0058] The equipment can be applied to a wide variety of ultrasound imaging scenarios, using a wide variety of views of each of a wide variety of organs or other anatomical regions or features. A few non-exclusive examples include:

[0059] Organ: Heart View: PSAX (parasternal short axis) base of the heart Doppler type: CW Conditions to rule out: Reflux Structure: Tricuspid valve Use Case: Using Color Doppler to detect tricuspid regurgitation (TR) and better align the CW line to the TR flow Process: Align the CW line parallel to the counterflow jet.

[0060] Organ: Heart View: PSAX (parasternal short axis) base of the heart Doppler type: PW Use Case: RVOT VTI (Velocity Time Integral) to measure acceleration time, QP:QS (P-pulmonary, S-systemic, Q-flow) Structure: Pulmonary valve (PV) Process: Automatically places the PW line across the PV and the gate just below the PV leaflet (RVOT right ventricular outflow tract).

[0061] Organ: Heart View: PSAX (parasternal short axis) base of the heart Doppler type: CW Conditions to rule out: Reflux / Stenosis Structure: Pulmonary valve (PV) Process: To measure the PV velocity, automatically place a CW line across the PV and a CW focus directly under the PV.

[0062] Organ: Heart View: A4C (apex 4 chambers) Doppler type: PW / CW What is evaluated: Regurgitation / Stenosis (CW) Diastolic Function (PW) Structure: Mitral valve (MV) Process: PW: Automatically place PW line across MV and PW gate at tip of MV leaflet to assess MV inflow. CW: (regurgitation: atrial side, stenosis: ventricular side) + collar to better position focus.

[0063] Organ: Heart View: A4C (apex 4 chambers) Doppler type: CW Conditions to rule out: CW: Reflux Structure: Tricuspid valve (TV) Process: Detect tricuspid regurgitation (TR) using color Doppler and better align CW line to TR flow. Automatically place CW line across TV and CW focus just on TV leaflet to measure PV velocities. + Color to better position focus.

[0064] Organ: Heart Views: A5C (apical 5 chambers) and A3C (apical 3 chambers) Doppler type: PW Purpose: To evaluate LVOT flow / VTI, obstruction, stroke volume, and aortic valve area Structure: Aortic valve (AV) Process: Automatically place the PW wire at the hinge point of the aortic valve and the PW gate just below the AV leaflets (LVOT - left ventricular outflow tract), approximately 5 mm below the AV.

[0065] Organ: Heart Views: A5C (apical 5 chambers) and A3C (apical 3 chambers) Doppler type: CW Purpose: Evaluation of AV flow Structure: Aortic valve (AV) Process: Automatically place CW line across the aortic valve and CW focus just at the AV leaflets. Use color aliasing to predict highest velocity flow. Use color direction to determine regurgitation vs. stenosis.

[0066] Organ: Heart View: Subcostal short axis view Doppler type: PW Structure: Hepatic vein Objective: To evaluate hepatic venous blood flow velocity and flow pattern Automatic detection of hepatic veins Use color Doppler at low velocity scales to identify HVs Process: Automatically align the PW line through the hepatic vein and automatically place the PW gate at the center of the hepatic vein 1-2 cm proximal to its junction to the IVC.

[0067] Organ: Heart View: Inferior vena cava (IVC) Doppler type: PW Structure: IVC Objective: To evaluate IVC blood flow velocity and flow patterns Automatically detect IVCs Color Doppler at low velocity scales is used to identify the IVC. Process: Automatically align the PW line through the IVC and automatically place the PW gate at the center of the IVC.

[0068] Organ: Heart View: Subcostal short axis view Doppler type: PW Structure: Hepatic vein / abdominal aorta Objective: To assess hepatic venous flow velocity and flow patterns, and to evaluate the abdominal aorta for pan-diastolic reversal of flow associated with significant aortic regurgitation Automatic detection of hepatic veins / proximal descending aorta and abdominal aorta Color Doppler on normal velocity scale Process: Automatically align the PW line through the abdominal aorta; The PW gate is automatically placed at the center of the abdominal aorta.

[0069] Organ: Heart View: Suprasternal fossa Doppler type: PW / CW Structure: Aortic arch (PW) / descending aorta (CW) Purpose: AV reflux or AO obstruction Automatic detection of the aortic arch Process: Color Doppler on standard velocity scale to detect aliasing (presence of faster velocities). >2m / sec. Automatically aligns PW line through descending aorta and places sample gate 1cm distal to origin of left subclavian artery. PW at proximal descending aorta can be used to assess total diastolic flow reversal associated with severe aortic regurgitation. Automatically aligns CW line through descending aorta with focus in color aliasing. Indicates occlusion (common with stenosis-bicuspid AV valve).

[0070] The various embodiments described above can be combined to provide further embodiments. All U.S. patents, U.S. patent application publications, U.S. patent applications, foreign patents, foreign patent applications, and non-patent publications mentioned herein and / or listed in the Application Data Sheets are incorporated herein by reference in their entirety. Aspects of the embodiments can be modified, if necessary, to use concepts from various patents, specifications, and publications to provide further embodiments.

[0071] These and other changes can be made to the embodiments in light of the above Detailed Description. Generally, in the following claims, the terms used should not be construed to limit the claims to the specific embodiments disclosed in the specification and claims, but should be construed to include all possible embodiments along with the full scope of equivalents to which such claims are entitled. Accordingly, the claims are not limited by the disclosure herein.

Claims

1. 1. A system comprising: An ultrasonic transducer; a computing device, the computing device comprising: a communications interface configured to receive ultrasound data sensed by the ultrasound transducer directly from a human, the received ultrasound echo data comprising a sequence of ultrasound images; and and a processor configured to execute a method, the method comprising: Receiving a first ultrasound image generated by an ultrasound machine; receiving a user input selecting an anatomical structure appearing in the first ultrasound image; performing localization to determine a location of the selected anatomical structure in the first ultrasound image; determining a first measurement position control configuration for the determined location of the selected anatomical structure; invoking one or more first Doppler ultrasound modes on the ultrasound machine using the determined first measurement position control arrangement; receiving one or more second ultrasound images produced by the ultrasound machine using the one or more first Doppler ultrasound modes; determining flow location and flow direction based on the one or more second ultrasound images; determining a second measurement position control arrangement for the determined flow position; invoking one or more second Doppler ultrasound modes on the ultrasound machine using the second measurement position control arrangement; and receiving results from the calling of the one or more second Doppler ultrasound modes.

2. the one or more first Doppler ultrasound modes include a color Doppler mode; The system of claim 1 , wherein the one or more second Doppler ultrasound modes include a pulsed wave Doppler mode.

3. The first measurement position control arrangement arranges a color box; The system of claim 1 , wherein the second measurement position control arrangement positions a Doppler line and a gate.

4. the one or more first Doppler ultrasound modes include a color Doppler mode; The system of claim 1 , wherein the one or more second Doppler ultrasound modes include a continuous wave Doppler mode.

5. The first measurement position control arrangement arranges a color box; The system of claim 1 , wherein the second measurement position control arrangement arranges a Doppler line.

6. 2. The system of claim 1, wherein the received results include one or more third ultrasound images generated by the ultrasound machine in one or more third Doppler ultrasound mode invocations, the one or more third ultrasound images indicating flow location and flow direction relative to anatomical structures appearing in the one or more third ultrasound images.

7. The system of claim 1 , wherein the received results include flow velocities determined in the calls of the one or more second Doppler ultrasound modes.

8. 1. A method in a computing system, comprising: Receiving a first ultrasound image generated by an ultrasound machine; determining a first measurement position control configuration for a location where a selected anatomical structure is visualized in the first ultrasound image; invoking one or more first Doppler ultrasound modes on the ultrasound machine using the determined first measurement position control arrangement; receiving one or more second ultrasound images produced by the ultrasound machine using the one or more first Doppler ultrasound modes; determining a flow location based on the one or more second ultrasound images; and determining a second measurement position control arrangement for the determined flow position; invoking one or more second Doppler ultrasound modes on the ultrasound machine using the second measurement position control arrangement; and receiving results from the calling of the one or more second Doppler ultrasound modes.

9. 9. The method of claim 8, wherein the received results include one or more third ultrasound images generated by the ultrasound machine in invocation of the one or more third Doppler ultrasound modes, the one or more third ultrasound images indicating flow location and flow direction relative to anatomical structures appearing in the one or more third ultrasound images.

10. The method of claim 8 , wherein the received results include flow velocities determined in the invocations of the one or more second Doppler ultrasound modes.

11. the received results include one or more third ultrasound images generated by the ultrasound machine in the invocation of the one or more third Doppler ultrasound modes; The method of claim 10 , further comprising causing at least a portion of the received third ultrasound image to be displayed along with a visual representation of the received flow velocity.

12. The method of claim 10 further comprising storing the received flow rate.

13. The method of claim 10 , further comprising performing predictive diagnostics based on the received flow rates.

14. the second measurement position control arrangement positions a Doppler line having a direction; The method further comprising: determining an angle between a direction of the Doppler line and the determined flow direction, the determined angle exceeds a threshold angle; and applying a trigonometric transformation to determine a component of the received flow velocity that is parallel to the determined flow direction using the determined angle; The method of claim 10 , further comprising: outputting an indication to the user that the determined component is the flow velocity.

15. the selected anatomical structure is a heart valve; the second measurement position control arrangement positions a Doppler line having a direction; the received results further include one or more third ultrasound images produced by the ultrasound machine in the invocation of the one or more third Doppler ultrasound modes; The method further comprising: determining an angle between a direction of the Doppler line and the determined flow direction, the determined angle exceeds a threshold angle; and assessing a visualization quality in at least one of the one or more third ultrasound images of (1) a substantially circular flow converging portion of the flow through the selected heart valve that is generally downstream of the valve and flows in a generally upstream direction, and (2) an elliptical jet portion of the flow through the selected heart valve that is generally upstream of the valve and flows in a generally upstream direction; If the evaluation determines that the visualization quality of both of the two portions is high, applying a trigonometric transformation to determine a component of the received flow velocity that is parallel to the determined flow direction using the determined angle; The method of claim 10 , further comprising: outputting an indication to the user that the determined component is the flow velocity.

16. The second measurement position control arrangement arranges a Doppler line having a direction, and the method further comprises: determining an angle between the direction of the Doppler line and the determined flow direction; 10. The method of claim 8, further comprising: if the determined angle exceeds a threshold angle, repositioning a probe of the ultrasound machine in a direction output to a user to better align the Doppler line with a scanning axis of the probe before invoking the one or more second Doppler ultrasound modes.

17. One or more computer memories having contents collectively configured to cause a computing system to perform a method, the method comprising: Receiving a first ultrasound image generated by an ultrasound machine; determining a first measurement position control configuration for a location in the first ultrasound image where a selected anatomical structure is visualized in the first ultrasound image; invoking one or more first Doppler ultrasound modes on the ultrasound machine using the determined first measurement position control arrangement; and receiving one or more second ultrasound images produced by the ultrasound machine using the one or more first Doppler ultrasound modes.

18. The method further comprising: receiving a user input selecting the selected anatomical structure; The one or more computer memories of claim 17 , further comprising: performing localization to determine a location of the selected anatomical structure.

19. 20. The one or more computer memories of claim 18, wherein the received user input is a voice input. The method further comprising: determining, for each of at least a portion of the anatomical structures appearing in the first ultrasound image, text identifying the anatomical structure; performing a speech-to-text process on the user input to obtain an input text; and selecting an anatomical structure appearing in the first ultrasound image for which identifying text matching the acquired input text has been determined.

20. and displaying the first ultrasound image. the received user input is a touch user input selecting a location within the displayed first ultrasound image; The method further comprising: The one or more computer memories of claim 18, further comprising selecting an anatomical structure appearing in the initial ultrasound image at the selected location.

21. The one or more computer memories of claim 18 , wherein performing localization includes applying an object detection model to the initial ultrasound image.

22. The one or more computer memories of claim 18 , wherein performing localization comprises applying a segmentation model to the initial ultrasound image.

23. The method further comprising: determining flow location and flow direction based on the one or more second ultrasound images; determining a second measurement position control arrangement for the determined flow position; invoking one or more second Doppler ultrasound modes on the ultrasound machine using the second measurement position control arrangement; and receiving results from the invocation of the one or more second Doppler ultrasound modes.

24. The one or more computer memories of claim 23 , wherein determining flow location and direction comprises applying a segmentation model to the initial ultrasound image.

25. The one or more computer memories of claim 23 , wherein determining flow location and direction comprises applying an object detection model to the initial ultrasound image.

26. The one or more computer memories of claim 23 , wherein determining flow location and direction comprises applying a regression model to the initial ultrasound image.

Images