Ultrasound imaging system and method

Abstract

According to one aspect, there is provided a computer-implemented method performed as part of an ultrasonic US examination of a target of a subject. The method comprises: i) causing a three-dimensional (3D) ultrasound probe to obtain a first 2D US image, the first 2D US image being obtained in a first scanning plane of the probe; ii) causing the US probe to obtain one or more other 2D US images in a sub-volume around the first scanning plane in a 3D field of view of a 3D mode of the US probe, where the sub-volume has a spanning angle smaller than a spanning angle of the 3D mode of the probe; and iii) determining whether the target is closer to the first 2D US image or closer to one of the one or more other 2D US images.

Description

Technical Field

[0001] The present disclosure relates to ultrasound imaging. More particularly, but not exclusively, the present disclosure relates to providing directional guidance to image a target through a subject during an ultrasound examination. Background Art

[0002] Ultrasound (US) is the modality of choice for many examinations, such as fetal screening, because it is able to depict anatomical structures in sufficient detail while being timely and cost-effective, with no known adverse effects.

[0003] The screening process is standardized to some extent by the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG), but there are specific variations in different geographic regions. Typically, fetal screening is performed in specific standardized fetal anatomical views in order to obtain appropriate and standardized growth metrics. Some of these standardized views are described in the following paper: ATPapageorghiou et al.: Title: "International standards for fetal growth based on serialultrasound measurements:The Fetal Growth Longitudinal Study of theINTERGROWTH-21st Project" (The Lancet 384, 869-879, 2014).

[0004] Other US examinations are similarly standardized and require measurement and / or assessment of anatomical features in specific view planes. Examples include, but are not limited to, brain scans, liver scans, and heart scans.

[0005] In order to find and evaluate the appropriate standard planes during US examination, rapid navigation and evaluation of many anatomical views is required.

[0006] The obstetric expertise of those performing fetal and other types of screening varies greatly around the world. In the US, for example, a general practitioner may perform screening rather than a practitioner with specialized ultrasound or obstetric expertise. This can be inefficient (especially if the practitioner takes a long time to find the appropriate standardized plane), and / or can be inaccurate if the incorrect plane is inadvertently imaged.

[0007] US2022 / 0211348 A1 relates to ultrasound systems and methods for identifying anatomical features via ultrasound imaging and guiding a user to capture a desired view of a target feature. Specific embodiments may utilize at least one neural network and an associated display configured to generate customized user instructions based on anatomical features identified in a current ultrasound image. Embodiments also include an ultrasound image acquisition component configured to automatically switch between 2D and volumetric (also known as 3D) imaging modes. US2016 / 081663 A1 relates to systems and methods for imaging an object. A subset of image frames including a target structure is identified from a 3D frame, and a selected image frame including a desired scan plane is used to measure a diagnostic parameter corresponding to the target structure. Summary of the invention

[0008] Due to the large number of anatomical views that need to be studied during US examinations (such as fetal scans), the quality of screening in terms of completeness and accuracy can be low. Due to the inherent difficulties of ultrasound and the challenges of examining a patient within a patient, it can be difficult for a less skilled practitioner to navigate the ultrasound probe in order to acquire the correct view for a given biometric measurement or organ assessment. The purpose of the embodiments herein is to improve this situation.

[0009] According to a first aspect, a computer-implemented method is provided as part of an ultrasound US examination of a target of an object. The method comprises: i) causing a three-dimensional 3D ultrasound probe to obtain a first 2D US image, wherein the first 2D US image is obtained in a first scanning plane of the probe; ii) causing the probe to obtain one or more other 2D US images in a sub-volume around the first scanning plane in a 3D field of view of a 3D mode of the US probe, wherein the span angle of the sub-volume is less than the span angle of the 3D field of view of the 3D mode of the probe; and iii) determining whether the target is closer to the first 2D US image or to one of the one or more other 2D US images. Here, when the probe is operated in a 3D imaging mode (also referred to as a volume imaging mode), the span angle of the 3D field of view (FOV) of the 3D mode of the probe is referred to as the span angle of the 3D FOV of the probe, and for simplicity, it is sometimes referred to as the span angle of the 3D mode of the probe. The span angle of the sub-volume may be a predetermined value (such as a default value or a fixed value), or may be a pre-selected value (such as a value selected by a user).

[0010] According to a second aspect, a device for performing ultrasound US inspection on a target of an object is provided. The device includes: a memory including instruction data representing an instruction set; and a processor configured to communicate with the memory and execute the instruction set, wherein the instruction set, when executed by the processor, causes the processor to: i) obtain a first 2D US image using a three-dimensional 3D ultrasound imaging probe, wherein the first 2D US image is obtained in a first scanning plane of the probe; ii) obtain one or more other 2D US images in a sub-volume around the first scanning plane in a 3D field of view of a 3D mode of the US probe, wherein the span angle of the sub-volume is smaller than the span angle of the 3D mode of the probe; iii) determine whether the target is closer to the first 2D US image or to one of the one or more other 2D US images.

[0011] According to a third aspect, there is an ultrasound (US) imaging system for imaging a target of an object, comprising a three-dimensional (3D) ultrasound probe. The US imaging system is configured to operate the probe in a scanning mode, whereby the probe is configured to: i) obtain a first 2D US image in a first scanning plane of the probe; ii) obtain one or more other 2D US images in a sub-volume around the first scanning plane in a 3D field of view of the 3D mode of the US probe, wherein the span angle of the sub-volume is smaller than the span angle of the 3D mode of the probe; and repeat steps i) and ii) in a continuous manner, and the ultrasound imaging system is further configured to iii) determine whether the target is closer to the first 2D US image or to one of the one or more other 2D US images.

[0012] Therefore, in an embodiment of the present invention, a 3D probe is used to obtain a first 2D US image and one or more other 2D US images in a surrounding subvolume. The first image and the one or more other images are then processed to determine whether a target (such as a target structure or a target imaging plane) is closer to the first 2D US image or to one of the other 2D US images in the one or more other 2D US images. This can be used to provide directional guidance to a user or operator of the US probe so as to guide the user to obtain an image of the target. In addition, obtaining one or more other 2D images in a subvolume of the complete 3D volume allows a higher frame rate than scanning the entire 3D volume. This allows US images to be obtained along the first scanning plane and displayed to the user of the probe in real time, while also obtaining one or more other images for (internal) analysis and guidance purposes without the user being aware of the delay.

[0013] These and other aspects will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Example embodiments will now be described, by way of example only, with reference to the following drawings, in which:

[0015] Figure 1 is an example apparatus according to some embodiments herein;

[0016] Figure 2 An example ultrasound imaging system according to some embodiments herein is shown;

[0017] Figure 3 An example method according to some embodiments herein is shown;

[0018] Figure 4 An US probe and example imaging planes of an example probe are shown.

[0019] Figure 5 shows an example output of a YOLO network according to some embodiments herein;

[0020] Figure 6 shows example directional guidance according to some embodiments herein; and

[0021] Figure 7 An example GUI workflow visualizer is shown. DETAILED DESCRIPTION

[0022] Now turn to Figure 1 In some embodiments, there is an apparatus 100 for performing an ultrasound US examination on an object according to some embodiments herein. Typically, the apparatus may form part of a computer apparatus or system (e.g., such as a laptop, desktop computer, or other computing device). In some embodiments, the apparatus 100 may form part of a distributed computing apparatus or cloud.

[0023] The apparatus includes a memory 104 and a processor 102 (e.g., processing circuitry or logic), the memory 104 including instruction data representing an instruction set, and the processor 102 being configured to communicate with the memory and execute the instruction set. Generally, the instruction set, when executed by the processor, can cause the processor to perform any of the embodiments of the method 300 described below.

[0024] The processor 102 may include one or more processors, processing units, multi-core processors, or modules configured or programmed to control the device 100 in the manner described herein. In a particular embodiment, the processor 102 may include a plurality of software and / or hardware modules, each of which is configured to perform or be used to perform individual or multiple steps of the method described herein. The processor 102 may include one or more processors, processing units, multi-core processors, and / or modules configured or programmed to control the device 100 in the manner described herein. In some embodiments, for example, the processor 102 may include multiple (e.g., interoperable) processors, processing units, multi-core processors, and / or modules configured for distributed processing. Those skilled in the art will appreciate that such processors, processing units, multi-core processors, and / or modules may be located in different locations and may perform different steps of the method described herein and / or different parts of a single step.

[0025] The memory 104 is configured to store program codes that can be executed by the processor 102 to perform the methods described herein. Alternatively or additionally, one or more memories 104 may be external to the device 100 (i.e., separate from or away from the device 100). For example, one or more memories 104 may be part of another device. The memory 104 may be used to store a first 2D US image, one or more other 2D US images, and / or any other information or data received, calculated, or determined by the processor 102 of the device 100 or from any interface, memory, or device external to the device 100. The processor 102 may be configured to control the memory 104 to the first 2D US image, one or more other 2D US images, and / or any other information or data.

[0026] In some embodiments, the memory 104 may include multiple sub-memories, each of which can store one instruction data. For example, at least one sub-memory can store instruction data representing at least one instruction in the instruction set, and at least one other sub-memory can store instruction data representing at least one other instruction in the instruction set.

[0027] It should be understood that Figure 1Only the components required to illustrate this aspect of the disclosure are shown, and in actual implementations, the device 100 may include additional components to the components shown. For example, the device 100 may also include a display. The display may include, for example, a computer screen and / or a screen on a mobile phone or tablet computer. The device may also include a user input device, such as a keyboard, a mouse, or other input device that enables a user to interact with the device, for example, to provide initial input parameters to be used in the methods described herein. The device 100 may include a battery or other power source for powering the device 100 or a module for connecting the device 100 to a mains power supply.

[0028] In general, embodiments of the device 100 may be used to perform a US examination of an object. For example, some embodiments of the device 100 may be used to provide directional guidance to image a target through an object during an ultrasound US examination. More specifically, the instruction set, when executed by a processor, causes the processor to: i) obtain a first 2D US image using a three-dimensional 3D ultrasound imaging probe, wherein the first 2D US image is obtained in a first scanning plane of the probe; ii) obtain one or more other 2D US images in a subvolume surrounding the first scanning plane, wherein the span angle of the subvolume is less than the span angle of the 3D mode of the probe; and iii) determine whether the target is closer to the first 2D US image or to one of the one or more other 2D US images. Step i) and step ii) may be performed in any sequence order or simultaneously. In some embodiments, the probe is configured to obtain one or more other 2D US images after obtaining the first 2D US image. In some embodiments, the probe is configured to obtain a 2D image in a subvolume, which includes both a 2D US image and one or more other 2D US images.

[0029] In some embodiments, there is an ultrasound US imaging system including a three-dimensional 3D ultrasound probe. The US imaging system is configured to operate the probe in a scanning mode, whereby the probe: v) obtains a first 2D US image in a first scanning plane of the probe; vi) obtains one or more other 2D US images in a sub-volume around the first scanning plane, wherein the span angle of the sub-volume is smaller than the span angle of the 3D mode of the probe; and steps v) and vi) are repeated in a continuous manner.

[0030] For example, in the scanning mode herein, the 3D probe is configured to acquire a first 2D US image and one or more other 2D US images in a continuous cycle without acquiring a (full) 3D image. In other words, images in the full 3D volume available to the 3D probe are not acquired.

[0031] In some embodiments, the device 100 is part of a US imaging system. For example, the US imaging system may include the device 100, an imaging probe, and a display for displaying a first 2D US image. As described in more detail below, in some embodiments, the display may also display a directional guide. The directional guide includes the direction in which the US probe is to be moved to image the target, and is determined based on the result of step iii). The directional guide is determined in such a way that when the probe moves in the direction, the first scanning plane of the probe becomes closer to the target. In other words, the direction in which the US probe is to be moved is determined based on the result of step iii) so that the first scanning plane of the probe moves toward the target.

[0032] The device may be configured to instruct or cause the probe to perform steps v) and vi). For example, the device may be configured to cause the probe to operate in the above-mentioned scanning mode. In some embodiments, the device 100 may therefore obtain a first 2D US image by instructing or causing the probe to obtain a first 2D US image in a first scanning plane. The first scanning plane is a predetermined or pre-selected scanning plane of the probe, such as a central scanning plane or a primary scanning plane. The device 100 may also obtain one or more other 2D US images by instructing or causing the probe to obtain one or more other 2D US images.

[0033] In some embodiments, only the first 2D US image is displayed on the display, and one or more other 2D US images are used (only) to determine directional guidance. The ultrasound imaging system may be configured to repeat steps i), ii), and iii), displaying only the first image to the user in each iteration. In other words, one or more other 2D US images in the subvolume may be processed simultaneously with the first 2D US image (e.g., as a background process) to determine directional guidance.

[0034] In other words, the US image acquisition process can alternate between obtaining a first 2D US image in a first scanning plane and obtaining one or more other 2D US images in a subvolume surrounding the first scanning plane. Only the first 2D US image in each iteration can be displayed to the user. The US image system can use the other 2D US images in each iteration to determine, for example, directional guidance. In other words, other 2D US images can be obtained without the knowledge of the sonographer performing the US examination, for example, when the sonographer moves the US probe, the first 2D US image acquired in the first scanning plane is displayed as if the US probe is operating in 2D mode, and the probe is configured (or instructed) to obtain other 2D US images in an automatic manner in order to determine the user's directional guidance. In this way, a "2.5" D mode (named by the inventor) can be implemented, in which the user is working in a similar manner to the 2D imaging mode, and in the background, the US imager is obtaining other 2D US images in a plane different from the main imaging plane used by the user, which can be processed to provide directional guidance to the user. Since the sub-volume is smaller than the full volume, the acquisition of the center frame and the side frames can be performed faster than the acquisition of the full volume data in 3D mode, which allows for higher frame rates compared to 3D mode.

[0035] Example US imaging system 200 in Figure 2 . The US imaging system may also include other components, such as those associated with obtaining and processing US image data. The US system 200 includes an array transducer probe 4 having a transducer array 6 for transmitting ultrasound waves and receiving echo information. The transducer array 6 may include CMUT transducers; piezoelectric transducers formed of materials such as PZT or PVDF; or any other suitable transducer technology. In this example, the transducer array 6 is a two-dimensional array of transducers 8 capable of scanning a 2D plane or a three-dimensional volume of a region of interest. In another example, the transducer array may be a 1D array.

[0036] The transducer array 6 may be coupled to a microbeamformer 12 that controls the reception of signals by the transducer elements. The microbeamformer is capable of at least partially beamforming signals received by sub-arrays of transducers (often referred to as "groups" or "tiles"), as described in U.S. Pat. Nos. 5,997,479 (Savord et al.), 6,013,032 (Savord), and 6,623,432 (Powers et al.).

[0037] In an alternative embodiment, instead of the microbeamformer 12, the transducer array may be provided by a main system beamformer ( Figure 2 ) directly operated.

[0038] The system 200 may also include a transmit / receive (T / R) switch 16 to which the microbeamformer 12 may be coupled and which switches the array between a transmit mode and a receive mode. Transmission of ultrasound beams from the transducer array 6 is directed by a transducer controller 18 coupled to the microbeamformer through the T / R switch 16 and to a main transmit beamformer (not shown), which may receive input from a user operating a user interface or control panel 38. The controller 18 may include transmit circuitry arranged to drive the transducer elements of the array 6 (directly or via the microbeamformer) during the transmit mode.

[0039] It should be noted that in an alternative embodiment, instead of the microbeamformer 12, the transducer array is operated directly by the main system beamformer, and the T / R switch 16 can protect the main beamformer 20 from high energy transmit signals.

[0040] In a typical line-by-line imaging sequence, the beamforming system within the probe may operate as follows. During transmit, the beamformer (which may be a microbeamformer or a main system beamformer, depending on the implementation) activates a transducer array or a subaperture of a transducer array. A subaperture may be a one-dimensional line of transducers or a two-dimensional patch of transducers within a larger array. In transmit mode, the focusing and steering of the ultrasound beam generated by the array or a subaperture of the array is controlled as described below.

[0041] After receiving the backscattered echo signal from the object, the received signal undergoes receive beamforming (described below) to align the received signal, and in the case where a sub-aperture is being used, the sub-aperture is then shifted, for example, by one transducer element. The shifted sub-aperture is then activated, and the process repeats until all transducer elements of the transducer array have been activated.

[0042] For each line (or sub-aperture), the total received signal for the associated line used to form the final ultrasound image will be the sum of the voltage signals measured by the transducer elements of a given sub-aperture during the receive period. After the beamforming process below, the resulting line signal is typically referred to as radio frequency (RF) data. Each line signal (RF data set) generated by each sub-aperture then undergoes additional processing to generate a line for the final ultrasound image. The change in amplitude of the line signal over time will contribute to the change in brightness of the ultrasound image with depth, where high amplitude peaks will correspond to bright pixels (or sets of pixels) in the final image. Peaks that appear near the beginning of the line signal will represent echoes from shallow structures, while peaks that gradually appear later in the line signal represent echoes from structures at increasing depths within the object.

[0043] One of the functions controlled by the transducer controller 18 is the direction of beam steering and focusing. The beam can be steered straight ahead (orthogonal to) the transducer array, or at different angles for a wider field of view. The steering and focusing of the transmit beam can be controlled based on the transducer element actuation time.

[0044] In general ultrasound data acquisition two methods can be distinguished: plane wave imaging and "beam steering" imaging. The two methods are distinguished by the presence of beam forming in the transmit mode ("beam steering" imaging) and / or in the receive mode (plane wave imaging and "beam steering" imaging).

[0045] Looking at the focusing function first, by activating all transducer elements simultaneously, the transducer array generates a plane wave that diverges as it travels through the object. In this case, the beam of ultrasound waves remains unfocused. By introducing a position-dependent time delay to the activation of the transducers, the wavefront of the beam can be made to converge at a desired point, which is called the focal zone. The focal zone is defined as the point where the lateral beamwidth is less than half the transmit beamwidth. In this way, the lateral resolution of the final ultrasound image is improved.

[0046] For example, if the time delay causes the transducer elements to be activated in series starting with the outermost elements and ending at the center element(s) of the transducer array, a focal zone will be formed at a given distance from the probe, coinciding with the center element(s). The distance of the focal zone from the probe will vary depending on the time delay between each subsequent round of transducer element activation. After the beam passes through the focal zone, it will begin to diverge, forming a far-field imaging region. It should be noted that for a focal zone positioned close to the transducer array, the ultrasound beam will diverge rapidly in the far field, resulting in beam width artifacts in the final image. Typically, the near field located between the transducer array and the focal zone shows little detail due to the large overlap in the ultrasound beam. Therefore, changing the position of the focal zone can result in significant changes in the quality of the final image.

[0047] It should be noted that in transmit mode, unless the ultrasound image is divided into multiple focal zones (each of which may have a different transmit focus), only one focus may be defined.

[0048] Furthermore, after receiving the echo signal from within the object, the inverse of the above process can be performed in order to perform receive focusing. In other words, the incoming signal can be received by the transducer elements and undergo an electronic time delay before being passed into the system for signal processing. The simplest example of this is called delay-and-sum beamforming. The receive focus of the transducer array can be adjusted dynamically over time.

[0049] Turning now to the function of beam steering, by properly applying time delays to the transducer elements, it is possible to impart a desired angle on the ultrasound beam as it leaves the transducer array. For example, by activating the transducers on a first side of the transducer array in a sequence ending on opposite sides of the array, followed by the remaining transducers, the wavefront of the beam will be angled towards the second side. The magnitude of the steering angle relative to the normal to the transducer array depends on the magnitude of the time delay between subsequent transducer element activations.

[0050] Additionally, focused steered beams are possible, where the total time delay applied to each transducer element is the sum of both the focusing and steering time delays. In this case, the transducer array is called a phased array.

[0051] In the case of CMUT transducers that require a DC bias voltage for activation thereof, the transducer controller 18 may be coupled to control a DC bias control 45 for the transducer array. The DC bias control 45 sets the DC bias voltage(s) applied to the CMUT transducer elements.

[0052] For each transducer element of the transducer array, an analog ultrasound signal, generally referred to as channel data, enters the system through a receive channel. In the receive channel, a partial beamformed signal is generated by the microbeamformer 12 based on the channel data and then passed to the main receive beamformer 20, where the partial beamformed signals from the individual tiles of the transducers are combined into a fully beamformed signal, referred to as radio frequency (RF) data. The beamforming performed at each stage may be performed as described above, or may include additional functionality. For example, the main beamformer 20 may have 128 channels, each of which receives a partial beamformed signal from a tile of tens or hundreds of transducer elements. In this way, the signals received by thousands of transducers of the transducer array may effectively contribute to a single beamformed signal.

[0053] The beamformed receive signals are coupled to a signal processor 22. The signal processor 22 can process the received echo signals in various ways, such as: bandpass filtering; decimation; I and Q component separation; and harmonic signal separation, which is used to separate linear signals from nonlinear signals, thereby enabling the identification of nonlinear (higher harmonics of the fundamental frequency) echo signals returned from tissue and microbubbles. The signal processor can also perform additional signal enhancement, such as speckle reduction, signal compounding, and noise removal. The bandpass filter in the signal processor can be a tracking filter whose passband slides from a higher frequency band to a lower frequency band as the echo signals are received from increasing depths, thereby rejecting noise at higher frequencies from greater depths, which generally lack anatomical information.

[0054] The beamformers for transmission and for reception are implemented in different hardware and may have different functions. Of course, the receiver beamformer is designed to take into account the characteristics of the transmit beamformer. Figure 2 Only the receiver beamformers 12, 20 are shown in FIG. In the overall system there will also be a transmit chain with a transmit microbeamformer and a main transmit beamformer.

[0055] The function of the microbeamformer 12 is to provide initial combining of the signals in order to reduce the number of analog signal paths. This is typically performed in the analog domain.

[0056] Final beamforming is done in the main beamformer 20 and is typically done after digitization.

[0057] The transmit and receive channels use the same transducer array 6 with fixed frequency bands. However, the bandwidth occupied by the transmit pulses can vary depending on the transmit beamforming used. The receive channel can capture the entire transducer bandwidth (which is the classical approach) or by using bandpass processing, which can only extract the bandwidth containing the desired information (e.g. harmonics of the main harmonic).

[0058] The RF signal can then be coupled to a B-mode (i.e., brightness mode or 2D imaging mode) processor 26 and a Doppler processor 28. The B-mode processor 26 performs amplitude detection on the received ultrasound signal to image structures (e.g., organ tissue and blood vessels) in the body. In the case of line-by-line imaging, each line (beam) is represented by an associated RF signal, the amplitude of which is used to generate a brightness value to be assigned to a pixel in the B-mode image. The exact position of the pixel within the image is determined by the position of the associated amplitude measurement along the RF signal and the number of lines (beams) of the RF signal. B-mode images of such structures can be formed in harmonic or fundamental image modes or a combination of the two, as described in U.S. Pat. No. 6,283,919 (Roundhill et al.) and U.S. Pat. No. 6,458,083 (Jago et al.). The Doppler processor 28 processes the temporally different signals generated by tissue movement and blood flow to detect moving matter, such as the flow of blood cells in the image field. The Doppler processor 28 typically includes a wall filter having parameters set to pass or reject echoes returning from selected types of material within the body.

[0059] The structure and motion signals generated by the B-mode and Doppler processors are coupled to the scan converter 32 and the multi-plane reformatter 44. The scan converter 32 arranges the echo signals in a spatial relationship, and the echo signals are received in a desired image format according to the spatial relationship. In other words, the scan converter is used to convert the RF data from a cylindrical coordinate system to a Cartesian coordinate system suitable for displaying an ultrasound image on the image display 40. In the case of B-mode imaging, the brightness of the pixel at a given coordinate is proportional to the amplitude of the RF signal received from the position. For example, the scan converter can arrange the echo signals into a two-dimensional (2D) sector format or a cone three-dimensional (3D) image. The scan converter can superimpose a color corresponding to the motion at a point in the image field to the B-mode structural image, where the Doppler estimated velocity produces a given color. The combined B-mode structural image and color Doppler image can depict tissue motion and blood flow within the structural image field. As described in U.S. Pat. No. 6,443,896 (Detmer), the multi-plane reformatter converts the echoes received from points in a common plane in a volumetric region of the body into an ultrasound image of the plane. The volume renderer 42 converts the echo signals of the 3D data set into a projected 3D image as viewed from a given reference point, as described in US Pat. No. 6,530,885 (Entrekin et al.).

[0060] The 2D or 3D images are coupled from the scan converter 32, the multiplanar reformatter 44, and the volume renderer 42 to the image processor 30 for further enhancement, buffering, and temporary storage for display on the image display 40. The imaging processor may be adapted to remove certain imaging artifacts from the final ultrasound image, such as, for example: acoustic shadowing, e.g., caused by strong attenuators or refraction; post-enhancement, e.g., caused by weak attenuators; reverberation artifacts, e.g., where highly reflective tissue interfaces are located in close proximity; etc. In addition, the image processor may be adapted to process certain speckle reduction functions in order to improve the contrast of the final ultrasound image.

[0061] In addition to being used for imaging, the blood flow values ​​produced by the Doppler processor 28 and the tissue structure information produced by the B-mode processor 26 are coupled to a quantification processor 34. The quantification processor can be used to make measurements in the images. The quantification processor can receive input from a user control panel 38.

[0062] Output data from the quantization processor is coupled to a graphics processor 36 for reproducing measurement graphs and values ​​on a display 40 together with the image, and for audio output from the display device 40. The graphics processor 36 may also generate graphic overlays for display with the ultrasound image. These graphic overlays may contain standard identification information, such as the patient's name, the date and time of the image, imaging parameters, etc. For these purposes, the graphics processor receives input from a user interface 38, such as the patient's name. The user interface is also coupled to the transmit controller 18 to control the generation of ultrasound signals from the transducer array 6, and therefore the images produced by the transducer array and the ultrasound system. The transmit control function of the controller 18 is only one of the functions performed. The controller 18 also takes into account the operating mode (given by the user) and the corresponding desired transmitter configuration and bandpass configuration in the receiver analog-to-digital converter. The controller 18 may be a state machine with fixed states.

[0063] The user interface is also coupled to a multi-planar reformatter 44 for selecting and controlling the planes of a plurality of multi-planar reformatted (MPR) images, which may be used to perform quantitative measurements in the image fields of the MPR images.

[0064] It should be understood that Figure 2 The illustrated US image system is merely an example, and the US image system may include components different from those described above.

[0065] Steering Figure 3 , there is a computer-implemented method 300 that may be performed as part of a US examination of a subject. Embodiments of the method 300 may be used to provide directional guidance to a user (eg, a sonographer) to image targets through a subject during an ultrasound US examination.

[0066] In brief, in a first step 302, the method 300 includes: i) causing a three-dimensional 3D ultrasound probe to acquire a first 2D US image, wherein the first 2D US image is acquired in a first scanning plane of the probe. In a second step 304, the method 300 includes: ii) causing the US probe to acquire one or more other 2D US images in a sub-volume surrounding the first scanning plane, wherein the span angle of the sub-volume is smaller than the span angle of the 3D mode of the probe. In a third step 306, the method 300 includes: iii) determining whether the target is closer to the first 2D US image or closer to one of the one or more other 2D US images.

[0067] In some embodiments, the method may be performed by a computing device such as device 100. Method 300 may be performed by an ultrasound imaging system such as US imaging system 200 described above. It should also be understood that method 300 may be performed by a computing system remote from the US imaging system (e.g., in the cloud), for example, the US imaging system may communicate with a remote computing system by sending the first 2D US image and one or more other 2D US images to the remote imaging system for processing. The remote computing system may send one or more outputs (such as directional guidance) back to the US imaging system.

[0068] The method 300 may be used to image a target through a subject during a US examination. The subject may be a human subject, such as a fetus, a child, or an adult. The subject may be an animal subject.

[0069] The US examination may be, for example, a fetal examination, such as a fetal growth scan or a fetal anomaly scan. In other embodiments, the US examination may be a cardiac scan, a brain scan, or any other type of US examination. In general, a US examination may be any type of examination in which a sonographer (e.g., a clinical user of an ultrasound system) attempts to image a particular plane or slice through a subject.

[0070] The target can be input by a user. For example, method 300 can also include receiving user input indicating the target. For example, the user input can be received from a user input device such as a keyboard, a mouse, or any other user input device. Alternatively, the target can be obtained from a database or other clinical system. For example, such as from a database, a medical guide, or a medical model.

[0071] The target may be a target structure in the subject (e.g., a target anatomical structure). For example, the target may be the head, legs, abdomen, heart, or any other organ or body part of a fetus. The method 300 may be used to guide a user of the probe to obtain an image of the target. For example, the method 300 may be used to guide a user of the probe from imaging a current anatomical feature to imaging a target structure (e.g., from the abdomen to the head of a fetus).

[0072] In some embodiments, the target can be a target plane passing through the object. The target plane can be a specific plane, such as a plane of interest passing through the object. In some embodiments, the target plane can be a standardized imaging plane. For example, an imaging plane for which specific measurements are to be made according to medical guidelines or medical standards.

[0073] Examples of target planes include, but are not limited to, the transthalamic plane, the circumferential ventral plane, and the femoral biometric plane, which are standardized planes used in fetal examinations.

[0074] The target plane may be associated with (e.g., defined by) a first plurality of anatomical features. In other words, the first plurality of features may need to be present in the image so that the image has correctly captured the target plane. Conversely, the target plane may be defined by the absence of a second plurality of anatomical features. In other words, the second plurality of features may need to be absent in the image so that the image has correctly captured the target plane.

[0075] Some example normalization planes (which may be target planes in a US examination) are given in the first column of Table 1 in Appendix I. Example first plurality of anatomical features (e.g., anatomical features that should be present in order for the normalization plane to have been correctly imaged) are given in the second and third columns of Table 1 for each respective normalization plane. Example second plurality of anatomical features (e.g., anatomical features that should not be present in order for the normalization plane to have been correctly imaged) are given in the fourth column of Appendix 1. Additional examples of normalization planes are described in the paper by ATPapageorghiou et al. (2003) cited in the Background section of this document.

[0076] As described above, in some embodiments, the method 300 may be used to provide directional guidance that a sonographer (or any other user) may use to assist the sonographer in moving the US probe to image a target plane through a subject.

[0077] In step i), the 3D US probe is caused to obtain 302 a first 2D US image in a first scanning plane of the probe. For example, step i) may include sending a message to the probe to instruct the probe to obtain the first 2D US image. In other words, the first 2D image is obtained using the 3D probe. The first 2D US image is obtained in the first scanning plane of the probe.

[0078] The first scan plane generally corresponds to the plane viewed by a sonographer when performing a US examination (e.g., as displayed by a display associated with the US imaging system described above). Thus, when a 3D probe is used in 2D mode, the first scan plane of the probe may correspond to a "default" plane scanned by the 3D probe. For example, the primary plane of the probe.

[0079] The main plane may correspond to a plane that is the center of or among all possible planes that the 3D probe may image in 3D mode.Thus, the purpose of method 300 may be to capture a target (which is viewed, for example, by a sonographer) in a first scanning plane of the probe.

[0080] The first 2D US image may be obtained from the 3D probe in real-time, for example as part of a sequence of ultrasound images (or frames) received from the probe.

[0081] In step ii), the US probe is caused to acquire 302 one or more other 2D US images in a sub-volume surrounding the first scan plane. For example, step ii) may include sending a message to the probe to instruct the probe to acquire one or more other 2D US images. In other words, the one or more other 2D US images may be acquired in a sub-portion of the 3D field of view (e.g., a portion around the central 2D view) (rather than in a normal 3D operation mode (i.e., scanning the entire field of view)). The sub-volume has a smaller span angle than the span angle of the full 3D mode.

[0082] One or more other 2D US images may be acquired by oscillation about the central scanning plane of the probe.

[0083] Obtaining one or more other 2D images in a sub-volume of the full 3D volume allows for a higher frame rate than scanning the entire 3D volume. This allows obtaining US images along a first scan plane and displaying them to the user of the probe in real-time, while also obtaining one or more other images for (internal) analysis and guidance purposes, without the user being aware of the delay.

[0084] As an example, in some embodiments, the subvolume may be a volume adjacent to the first scan plane and / or a volume on either side of the first scan plane. In some embodiments, in step ii), one or more other 2D US images may be in a scan plane adjacent to the first scan plane. For example, one or more other 2D images may include a second 2D US image and / or a third 2D US image in a second scan plane and / or a third scan plane of the probe. The second and / or third scan planes are planes different from the first scan plane of the probe. The second and / or third scan planes may be adjacent to the first scan plane (e.g., next to the first scan plane). For example, the second and third scan planes may be located on either side of the first scan plane. The second scan plane and the third scan plane may be adjacent to the first scan plane.

[0085] This is Figure 4 is shown in the figure, Figure 4 An example according to some embodiments of the present invention is shown. In this embodiment, there is a first scanning plane 402, a second scanning plane 404, and a third scanning plane 406 of the probe 400. When the probe is used in its 2D mode, the first scanning plane 402 is along the central axis of the probe, which is used as a default axis. The probe 400 sends a first 2D US image obtained in the first scanning plane 402 to the US imaging system for display on a display associated with the US imaging system. The probe 400 also obtains second and third 2D US images along the second and third planes 402, 404 for step iii), for example, for determining whether the target plane is closer to the first, second or third scanning plane. Although in Figure 4 , but it should be understood that this is merely an example and that the one or more other 2D US images may include any number of 2D US images in a subvolume surrounding the first image plane. Figure 4 The placement of the 2D US images in is also merely an example, and one or more other 2D US images may alternatively all be on the same side of the first image plane, or in any other configuration.

[0086] In step iii), the method 300 includes determining whether the target is closer to the first 2D US image or closer to one of the other 2D US images. As used herein, closer may refer to a distance, or a degree of proximity, for example, in terms of feature correspondence. For example, a 2D US image may be closer to the target plane if the 2D US image captures a higher proportion of anatomical features associated with the target plane than another 2D US image that captures a lower proportion of anatomical features associated with the target plane.

[0087] In some embodiments, the proximity of each 2D US image may be expressed in terms of a score, ranking, or other rating.

[0088] In some embodiments, step 306 (determination step) includes using a machine learning model to determine a first confidence score that describes how closely the first 2D US image corresponds to the target plane, and a second confidence score that describes how closely one of the one or more other 2D US images corresponds to the target plane.

[0089] The skilled person will be familiar with machine learning (ML) and machine learning processes for training machine learning models. ML models can be trained in a supervised manner, for example, using a training data set comprising training examples (each training example comprising an example input and a corresponding "correct" ground truth output). The model is trained on the training data using a machine learning process.

[0090] In such an embodiment, the confidence score can be an aggregation (e.g., a sum, mean, or median) of multiple confidence scores, each of which reflects the confidence with which the machine learning model detected a corresponding anatomical feature associated with the target in the corresponding image.

[0091] The machine learning process includes a process that is run on training data to create a machine learning model. The machine learning process includes processes and / or instructions by which the training data can be processed or used in the training process to generate a machine learning model. The machine learning process learns from the training data. For example, the process can be used to determine how one set of parameters in the training data (the input parameters of the model) is related to another set of parameters in the training data (the output parameters of the model). The machine learning process can be used to fit the model to the training data.

[0092] A model or machine learning model can include data and a process of how to use the data, such as to make predictions as described herein. The model is the result (e.g., output) of a machine learning (e.g., training) process, such as a set of rules or data processing steps that can be performed on input data to produce an output. As such, a model can include, for example, rules, numbers, and any other algorithm-specific data structures or architectures required, such as to make predictions.

[0093] Different types of models take different forms. Some examples of machine learning processes and models that can be used in this article include, but are not limited to: a linear regression process that produces a model that includes a vector of coefficients (data), the values ​​of which are learned through training; a decision tree process that produces a model that includes a tree of if / then statements (e.g., rules) that include learned values; and a neural network model that includes a graphical structure of a vector or matrix of biases and weights with specific values, the values ​​of which are learned using machine learning processes such as backpropagation and gradient descent.

[0094] In some embodiments herein, the You Only Look Once (YOLO) network described in the paper titled “You Only Look Once: Unified, Real-Time Object Detection” by Redmon et al. (2016) may be trained to detect objects in US images in real-time in a US image feed.

[0095] As another example, the U-net network described in the paper “U-Net: Convolutional Networks for Biomedical Image Segmentation” by Olaf Ronneberger et al. can be trained to segment out features corresponding to a target US image feed.

[0096] However, the skilled person will appreciate that these are merely examples and there are many ways in which targets can be detected in US images and US image feeds (eg, using techniques such as radial gradient index (RGI) filtering, multifractal filtering, rule-based region ranking).

[0097] In one embodiment, a YOLO network is trained to detect anatomical structures present on prenatal ultrasound images. Figure 5 As shown, the output of the YOLO network is the bounding boxes of the detected structures and the confidence values ​​for each detected structure. Each of the standardized anatomical views of the fetus is defined by a set of anatomical structures that must be visible or must not be visible in the view. Some examples are given in Appendix I below.

[0098] In this embodiment, when the user operates the ultrasound system in 2D mode (from the user's perspective), the central frame shown to the user (see Figure 1 and 2 b) YOLO network from above Figure 4 The first, second and third scan planes shown are operated on the first, second and third 2D US images obtained (according to the above steps 302 and 204). Based on the confidence values ​​of the detected individual anatomical structures, a combined score for the standardized view can be calculated for each of the first 2D US image, the second 2D US image and the third 2D US image. The combined score can be used to determine whether the target plane is closer to the first scan plane, closer to the second scan plane or closer to the third scan plane.

[0099] In one example, the combined score can be a weighted sum of the "must have" and "must not have" anatomical structures associated with the target plane (must not have structures with negative weights). In such an example, a higher score would indicate that the corresponding plane is closer to the target plane than a lower score.

[0100] Thus, in this way, it may be determined whether the first scan plane is closer to the target than one of the one or more other scan planes associated with one or more other 2D US images in a subvolume surrounding the first scan plane.

[0101] Returning to method 300 , after step iii) determining whether the target is closer to the first 2D image (eg, closer to the first scan plane) or closer to one of the one or more other 2D US images (or their associated scan planes), the determination may be used in a variety of different ways.

[0102] In some embodiments, in a fourth step, iv) the method 300 may further include providing directional guidance including a direction to move the US probe to image the target based on the result of step iii).

[0103] For example, in an embodiment where a machine learning model determines a first confidence score describing how close a first 2D US image corresponds to a target and a second confidence score describing how close one or more other 2D US images correspond to the target, if the second confidence score is greater than the first confidence score, the directional guidance can indicate a direction toward a second scanning plane associated with one of the one or more other 2D US images (or vice versa).

[0104] Thus, the confidence scores as output from the above machine learning model can be used to identify the target (or target plane) that the user is currently aiming at / searching for as the 2D US image with the highest combined score. The confidence scores can also be used to provide directional guidance, as described above, for example, they can be used to identify the view improvement direction if one of the other 2D US images has a higher score for the target than the first 2D US image (center view).

[0105] Directions may be provided to the user in any manner, e.g. Figure 6 As shown, the estimated direction of the refined view can thus be shown to the user by a set of icons displayed on the control screen, which indicate shift 602, 604, rotation 606, 608 and tilt.

[0106] Another option is a display (small screen or LED) directly on the transducer.

[0107] As described above, in some embodiments, one or more other 2D US images may not be displayed to the sonographer, but may be used (only) for the purpose of internal processing by the US imaging system to provide, for example, directional guidance to the sonographer. Therefore, in some embodiments, the method 300 may include sending a message to cause the display to display only the first US image, with the one or more other 2D US images being used to determine directional guidance and not being displayed.

[0108] For example, the US imaging system 200, the image acquisition process can alternate between steps i) and ii), for example, it can alternate between obtaining a first 2D US image in a first scanning plane and obtaining one or more other 2D US images in a subvolume around the first image plane. The first 2D US image in each iteration can be displayed to the user, and the one or more other 2D US images can be used only for the purpose of determining the direction guidance.

[0109] The method 300 may further include repeating steps i)-iv) for consecutive groups of the first 2D US image and one or more further 2D US images. Thus, the directional guidance may be updated in real time to provide real time guidance on the direction in which the US probe is to be moved to image the target.

[0110] In another embodiment, the 2D US image determined to be closest (e.g., having the highest score) may be displayed to the user, saved or marked as showing the target (or corresponding to the target plane). For example, if c-2 has the best score among the acquired 2D scan planes around the center plane c (such as c-3, c-2, c-1, c, c+1, c+2, c+3), then the closest image may be displayed to the user. This may be the case if one of the neighboring views provides a good enough image (e.g., an image with a high enough score).

[0111] It should also be understood that for an estimation of an improved view direction, the side view can be used not only to calculate a combined score, but also for a multi-planar reformat that can be calculated based on several frames and can indicate, for example, whether a tilt of the probe may result in an increased combined score. For example, the method 300 may also include obtaining an oblique 2D US image at an oblique angle for the first scan plane by performing a multi-planar reformat of the first 2D US image and one or more other 2D US images. In such an embodiment, the direction guidance also includes a tilt direction that has been determined based on the oblique angle and whether the target plane is closer to the first 2D US image or to the oblique 2D US image.

[0112] The above embodiments can be combined with a workflow guidance system to support users in following standardized screening protocols. Figure 7 is shown in the figure, Figure 7 A graphical user interface (GUI 700) with a visual workflow tracker for fetal screening is illustrated, showing coverage of a target frame (e.g., contours 702 and TG 704 planes have been obtained, but hand 706 and foot 708 contours have not been obtained). In the above display, the views identified based on the combined score can be indicated.

[0113] Guiding the user beyond fetal screening, the system can be used in any clinical ultrasound application where the acquisition of standardized view planes defined by a set of anatomical structures is required.

[0114] Turning now to other embodiments, there is also provided a computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured to, when executed by a suitable computer or processor, cause the computer or processor to perform one or more of the methods described herein.

[0115] It will therefore be appreciated that the present disclosure also applies to computer programs, in particular computer programs on or in a carrier, suitable for practicing the embodiments. The program may be in the form of source code, object code, a code intermediate source and object code, such as in a partially compiled form, or in any other form suitable for use in the implementation of the method according to the embodiments described herein.

[0116] It should also be understood that such a program can have many different architectural designs. For example, the program code implementing the function of the method or system can be subdivided into one or more subroutines. Many different ways of allocating functions between these subroutines will be apparent to the technician. The subroutines can be stored together in an executable file to form a self-contained program. Such an executable file can include computer executable instructions, such as processor instructions and / or interpreter instructions (such as Java interpreter instructions). Alternatively, one or more or all of the subroutines can be stored in at least one external library file and, for example, either statically or dynamically linked to the main program at runtime. The main program includes at least one call to at least one of the subroutines. The subroutines can also include function calls to each other.

[0117] The carrier of a computer program may be any entity or device capable of carrying the program. For example, the carrier may include a data storage device, such as a ROM, such as a CD ROM or a semiconductor ROM, or a magnetic recording medium, such as a hard disk. In addition, the carrier may be a transmissible carrier, such as an electrical or optical signal, which may be transmitted via an electrical or optical cable or by radio or other means. When the program is embodied in such a signal, the carrier may be composed of such a cable or other device or module. Alternatively, the carrier may be an integrated circuit in which the program is embedded, the integrated circuit being suitable for executing the relevant method or for executing the relevant method.

[0118] By studying the drawings, the disclosure and the claims, those skilled in the art can understand and implement variations to the disclosed embodiments when practicing the principles and techniques described herein. In the claims, the word "comprising" does not exclude other elements or steps, and the word "one" or "an" does not exclude multiple. A single processor or other unit can implement the functions of several items recorded in the claims. Although specific measures are recorded in mutually different dependent claims, this does not indicate that a combination of these measures cannot be used advantageously. The computer program may be stored or distributed on a suitable medium, such as an optical storage medium or solid-state medium provided together with other hardware or as part of other hardware, but the computer program may also be distributed in other forms, such as distributed via the Internet or other wired or wireless telecommunications systems. Any figure mark in the claims should not be interpreted as limiting the scope.

[0119] Appendix I

[0120]

[0121] Table 1

Claims

1. A computer-implemented method performed as part of an ultrasound (US) examination of a target of a subject, the method comprising: i) enabling (302) a three-dimensional 3D ultrasound probe (400) to obtain a first 2D US image, wherein the first 2D US image is obtained in a first scanning plane (402) of the probe; ii) causing (304) the US probe to obtain one or more other 2D US images in a sub-volume around the first scanning plane in the 3D field of view of the 3D mode of the US probe, wherein the sub-volume spans an angle smaller than the span of the 3D field of view of the 3D mode of the US probe; and iii) determining (306) whether the target is closer to the first 2D US image or closer to one of the one or more other 2D US images.

2. The method according to claim 1, further comprising: iv) determining directional guidance (602-608) based on the result of step iii), the directional guidance comprising the direction in which the US probe is to be moved to image the target.

3. The method according to claim 2, further comprising: A message is sent to cause a display to display the first 2D US image and not to display the one or more other 2D US images.

4. The method according to claim 2 or 3, wherein: Step iii) comprises using a machine learning model to determine a first confidence score describing how closely the first 2D US image corresponds to the target and a second confidence score describing how closely the one or more other 2D US images correspond to the target; and Wherein, if the second confidence score is greater than the first confidence score, the directional guidance indicates a direction towards a second scanning plane associated with the one or more other 2D US images.

5. The method according to claim 4, wherein: The first confidence score is an aggregation of multiple confidence scores, each of the multiple confidence scores reflecting the confidence of the machine learning model in detecting the corresponding anatomical feature associated with the target in the first 2D US image.

6. The method according to any one of claims 2 to 5, further comprising obtaining an oblique 2D US image at an oblique angle with respect to the first scanning plane by performing multi-planar reformatting on the first 2D US image and the one or more other 2D US images, in, The direction guidance further includes a tilt direction, which has been determined based on the tilt angle and whether the target plane is closer to the first 2D US image or closer to the oblique 2D US image.

7. The method according to any one of claims 2 to 6, further comprising: Repeating steps i)-iv) for consecutive groups of the first 2D US image and one or more further 2D US images; and The directional guidance is updated in real time to provide real time guidance regarding the direction in which the US probe is to be moved to image the target.

8. A method according to any one of the preceding claims, wherein: The target is a target structure in the object, or a target plane passing through the object.

9. A method according to any one of the preceding claims, wherein: The first scanning plane of the US probe is a central scanning plane of the US probe.

10. The method according to any one of the preceding claims, wherein: The one or more other 2D US images are in a scanning plane adjacent to the first scanning plane.

11. An apparatus (100) for performing an ultrasonic (US) inspection on a target of an object, the apparatus comprising: a memory (104) comprising instruction data representing an instruction set (106); as well as A processor (102) configured to communicate with the memory and execute the instruction set, wherein the instruction set, when executed by the processor, causes the processor to: i) using a three-dimensional 3D ultrasound imaging probe to obtain a first 2D US image, wherein the first 2D US image is obtained in a first scanning plane of the probe; ii) acquiring one or more further 2D US images in a sub-volume around the first scan plane in the 3D field of view of the 3D mode of the US probe, wherein the sub-volume spans an angle smaller than the span of the 3D mode of the probe; and iii) determining whether the target is closer to the first 2D US image or closer to one of the one or more other 2D US images.

12. An ultrasound (US) imaging system (200) for imaging a target of an object, comprising a three-dimensional (3D) ultrasound probe, wherein: The US imaging system is configured to operate the probe in a scanning mode, whereby the probe is configured to: i) obtaining a first 2D US image in a first scanning plane of the probe; ii) acquiring one or more further 2D US images in a sub-volume around the first scan plane in the 3D field of view of the 3D mode of the US probe, wherein the sub-volume spans an angle smaller than the span of the 3D mode of the probe; and Repeating steps i) and ii) in a continuous manner, The ultrasound imaging system is further configured to: iii) determining whether the target is closer to the first 2D US image or closer to one of the one or more other 2D US images.

13. The ultrasound imaging system according to claim 12, further comprising the apparatus according to claim 12 and a display for displaying the first 2D US image and the directional guidance, the directional guidance comprising a direction in which the US probe is to be moved to image the target and is determined based on the result of step iii); and in, Only the first 2D image is displayed on the display, and the one or more other 2D US images are not displayed.

14. The ultrasound system according to claim 12 or 13, wherein: The ultrasound system is configured to repeat steps i), ii) and iii), displaying the first 2D US image without displaying the one or more other 2D US images in each iteration.

15. A computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured such that when executed by a suitable computer or processor, the computer or processor is caused to perform the method according to any one of claims 1 to 10.

Images