Ultrasound image acquisition optimization according to different breathing patterns

Abstract

The present invention provides methods, systems, and computer program products for ultrasound image acquisition optimization according to different breathing patterns. A method for ultrasound image acquisition optimization according to different breathing patterns includes acquiring an ultrasound image of a target organ by an ultrasound imaging device. The method further includes comparing attributes of the acquired ultrasound image to correlation data in a correlation data store that correlates attributes of previously acquired ultrasound imagery of the target organ to different breathing patterns. Finally, the method includes determining a breathing pattern exhibited in the acquired ultrasound image according to the comparison and presenting the determined pattern in the ultrasound imaging device.

Description

TECHNICAL FIELD

[0001] The present invention relates to ultrasound imaging, and more particularly to ultrasound image acquisition. BACKGROUND

[0002] Ultrasound imaging, also known as sonography, is a medical imaging technique that uses high frequency sound waves to view three-dimensional structures within a living body. Ultrasound images are captured in real time, and thus also show the motion of internal organs of the body, as well as blood flowing through the body's blood vessels and the stiffness of tissues. Unlike x-ray imaging, ultrasound imaging does not involve ionizing radiation, and thus can be used for extended periods of time without threatening tissue or damaging internal organs from long term radiation.

[0003] To acquire ultrasound images, during an ultrasound examination, a transducer, often called a probe, is placed directly on the skin or within a body opening. The probe is coupled to image generation circuitry, which includes circuitry adapted to transmit signals to the probe and receive signals from the probe, and can include a beamformer, while synthetic aperture imaging systems can use retrospective image formation, reducing the need for beamforming and scan conversion functions. A thin layer of gel is applied to the skin, allowing ultrasound waves to travel from the probe through the gel medium to the body. Ultrasound images are generated based on measuring the reflections of the ultrasound waves from the body structures. The strength of the ultrasound signals, measured as the amplitude of the detected sound wave reflections, as well as the time it takes for the sound waves to travel through the body, provide the information needed to calculate an image of the body's target structures. Also, the "Doppler" effect can be used in ultrasound imaging to measure the speed and direction of fluid flow, such as blood flow, within the body structures, as well as the speed and direction of tissue motion, such as the heart muscle or valves.

[0004] Ultrasound brings many advantages to the diagnostic physician and patient compared to other important medical imaging methods. First, ultrasound imaging provides images in real time. Also, ultrasound imaging requires a portable device that can be brought to the patient's bedside. Additionally, ultrasound imaging devices are significantly less expensive than other medical imaging devices, and, as mentioned above, do not use harmful ionizing radiation. Even so, ultrasound imaging is not without its problems.

[0005] In this regard, unlike most other diagnostic imaging modalities, such as x-ray, magnetic resonance imaging (MRI), computed tomography (CT), etc., ultrasound imaging depends on careful and dynamic manipulation of the hand-held transducer applied to the patient. This scanning process requires a well-trained, skilled user in order to obtain good results. These users must learn how to adjust the position and angle of the transducer on the patient to obtain usable images. These users must also understand how to position the patient for different clinical applications and targets. However, this positioning can be extremely challenging, and often must be varied in both gross and subtle ways during the examination to obtain medically diagnostic acceptable views.

[0006] For a large number of clinical applications, respiration of the ultrasound scanning subject can play a key role in the quality of the acquired ultrasound images. That is, respiration affects ultrasound images as long as there is a visible impedance mismatch between soft tissue and air in the body. It is well known that air in the ultrasound path is a strong reflector, which can obstruct the transmission of ultrasound waves and create reverberation artifacts. This effect can be most pronounced in anatomical targets adjacent to the lungs, but can also occur in other locations, such as the intestines where intestinal gas occurs. In targets near the lungs, the expansion and contraction of the lungs during respiration can cause air to enter and exit the ultrasound beam path, causing interference with the respiration cycle. Another effect is that the target organ, such as the heart, is pushed to or pulled to different positions with the expansion and contraction of the lungs, causing the heart to move with respect to the respiration cycle. This can cause the target to move in and out of the ultrasound beam, so that the target cannot be seen correctly. Even if respiration does not directly bring air into the ultrasound path, this effect can be problematic. SUMMARY

[0007] Embodiments of the present invention can solve the deficiencies in the art related to ultrasound imaging and provide novel and non-obvious methods, systems and computer program products for ultrasound image acquisition optimization according to different breathing patterns.

[0008] In one embodiment of the present invention, a method for ultrasound image acquisition optimization according to different breathing patterns comprises acquiring one or more ultrasound images of a target organ by an ultrasound imaging device. The method further comprises comparing properties of the acquired ultrasound images with associated data in a property data store that associates properties of previously acquired ultrasound images of different images of the target organ with different breathing patterns. Finally, the method comprises determining a breathing pattern that is present in the acquired ultrasound images according to the comparison and presenting the determined pattern in the ultrasound imaging device, for example by employing a visual display mode in a display of the imaging device by means of an audible or even tactile method. It is important to note that the determination is based on the compared properties of the acquired ultrasound images and not on an external physiological signal input that provides data about the respiration.

[0009] In one aspect of this embodiment, the associated data store is a deep neural network trained to associate different breathing patterns with corresponding previously acquired ultrasound images of different images of the target organ. In this way, the acquired ultrasound images can be presented to the neural network and a correlation probability between the acquired ultrasound images and a specific breathing pattern can be returned. In another aspect of this embodiment, the associated data store is a table that associates each different image with a corresponding breathing pattern. In this way, a pixel-by-pixel image comparison can be performed to produce a specific breathing pattern assigned to the highest percentage matching image in the data store.

[0010] In yet another aspect of this embodiment, the method additionally comprises: determining a quality of the acquired ultrasound images; identifying a change in the determined breathing pattern that is associated with an improvement in the quality of the ultrasound imagery of the target organ; and presenting the determined change in the pattern in a display of the ultrasound image acquisition device. In still another aspect of this embodiment, the method additionally comprises: determining a physiological condition, such as a prospective abnormality or disease, from the acquired ultrasound images; identifying a change in the determined breathing pattern that is associated with an improvement in the quality of the ultrasound imagery of the target organ to diagnose the prospective abnormality or disease; and presenting the determined change in the pattern in the ultrasound image acquisition device. In this regard, the change can be presented visually in a display of the device, audibly from a speaker of the device, or haptically in a probe of the device.

[0011] In another embodiment of the present application, a data processing system is configured for ultrasound image acquisition optimization according to different breathing patterns. The system comprises: a computer having a memory and at least one processor; a display coupled to the computer; an image generation circuit coupled to both the computer and the display; and an ultrasound imaging probe having a transducer connected to the image generation circuit. The system further comprises an ultrasound image acquisition optimization module executing in the memory of the computer. The module comprises program code which, when executed by the processor of the computer, functions to: acquire one or more ultrasound images of a target organ by an ultrasound imaging device; compare attributes of the acquired ultrasound images to data in a data store that associates attributes of ultrasound imagery of different images of the target organ previously acquired with different breathing patterns; determine a breathing pattern exhibited in the acquired ultrasound images from the comparison; and present the determined pattern in the ultrasound imaging device.

[0012] Additional aspects of the application will be set forth in part by the description that follows, and in part will be apparent from the description, or can be learned by practice of the application. The aspects of the application will be realized and attained by means of the elements and combinations specifically pointed out in the appended claims and will not be limited by the foregoing description. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application, as claimed. BRIEF DESCRIPTION OF DRAWINGS

[0013] The accompanying drawings are incorporated in and constitute a part of this specification, illustrate embodiments of the application, and, together with the description, explain the principles of the application. The embodiments shown in the drawings are presently preferred, but it should be understood that the application is not limited to the precise arrangements and instrumentalities shown, in the drawings:

[0014] Figure 1 is a schematic illustration of an ultrasound image acquisition optimization process according to different breathing patterns;

[0015] Figure 2 is a schematic diagram of a data processing system adapted for ultrasound image acquisition optimization according to different breathing patterns; and

[0016] Figure 3 is a flowchart illustrating a process of ultrasound image acquisition optimization according to different breathing patterns. DETAILED DESCRIPTION

[0017] Embodiments of the present invention provide for ultrasound image acquisition optimization according to different breathing patterns. According to an embodiment of the present invention, different images of different organs are associated with different breathing patterns, including inhale and exhale in an association data store. In this regard, the association data store can be an image table associating different images with different breathing patterns, or a deep neural network trained to associate each different image with a respective one of the different breathing patterns.

[0018] Thereafter, the ultrasound imaging device acquires an ultrasound video of the target organ and compares features of the different images to the association data store to determine the breathing pattern of the acquired image. The breathing pattern is then presented in the ultrasound imaging device to assist an operator of the ultrasound imaging device in acquiring a suitable image of the target organ. Optionally, the quality of the acquired image is determined and a change in breathing pattern is determined that was previously associated with an improvement in image quality of the target image. Thus, the change in breathing pattern can be presented as a guidance signal in the device, such as a visual cue in a display of the device, an audible cue presented by the device, or a haptic view communicated by the device to the probe, to assist an operator of the ultrasound imaging device in acquiring a suitable image of the target organ.

[0019] In a further illustration, Figure 1 a process of ultrasound image acquisition optimization according to different breathing patterns is schematically illustrated. As Figure 1 shown, an ultrasound operator 110 manipulates an ultrasound imaging system 120 to acquire an ultrasound video 170 of a target organ of a patient 100. A display 140 of the ultrasound imaging system 120 provides guidance feedback to the ultrasound operator 110. In particular, a quality meter 150 is deployed in the display 140 and indicates a quality scale of the acquired ultrasound video 170 relative to known views that are sought to be acquired for the target organ. For example, with respect to imaging of a heart, the known views can include parasternal long axis, parasternal short axis, apical two, three, four, or five chamber views, or subcostal views. Insofar as the acquired ultrasound video 170 is determined to have a respective quality value that meets or exceeds a threshold quality of a specified view, a success icon 165 is displayed in conjunction with the quality meter 150 and the acquired ultrasound video 170 is displayed in a window as a recently acquired quality-satisfactory video clip.

[0020] During acquisition of the acquired ultrasound imagery 170, attributes of the acquired ultrasound imagery 170 are compared to attributes of prior imagery deployed in the data store 180 and associated with different breathing patterns 160 within a breathing cycle. In this regard, the different breathing patterns 160 range from full expiration with inhibition of inspiration 160A to full inspiration with inhibition of expiration 160F, with intermediate patterns including full expiration 160B, partial expiration with inhibition of further inspiration or expiration 160C, partial inspiration with inhibition of further inspiration or expiration 160D, and full inspiration 160E. Optionally, the data store 180 is a table of imagery and associated breathing patterns, such that the acquired ultrasound imagery 170 is compared to the images in the table on a pixel-by-pixel basis to identify sufficient pixel commonality to match the acquired ultrasound imagery 170 by content to the image in the table associated with a particular one of the breathing patterns 160. Alternatively, the data store 180 is a convolutional neural network trained with different imagery annotated with the different breathing patterns 160. In any case, however, based on the comparison, the current breathing pattern 130 is identified among the different breathing patterns 160 in response to submission of the acquired ultrasound imagery 170 to the data store 180.

[0021] The processes described in connection with Figure 1 the drawings can be implemented within a data processing system. In further Figure 2 illustrations, a data processing system adapted to ultrasound image acquisition optimization according to different breathing patterns is schematically shown. The system includes a host computing system 210 including a computer having at least one processor, memory, and a display. The host computing system 210 also includes a data store 250. The host computing system 210 is further coupled to an ultrasound imaging system 240 adapted to store ultrasound images acquired by operating image generation circuitry 220 with an imaging probe 230 placed in proximity to a target organ of interest in a mammalian subject in memory.

[0022] In particular, the host computing system 210 is communicably coupled to fixed storage 260 having stored therein a neural network and a programmatic interface to the neural network, either locally or remotely (“in the cloud”). The neural network is trained to characterize one or more features of the target organ, such as an ejection fraction value of the heart or the presence or absence of aortic valve stenosis. To this end, video clip imagery 270 of a specified view of the target organ acquired by the ultrasound imaging system 240 is provided to the neural network, which in turn accesses the programmatic interface so that the neural network can subsequently output a characterization of the video clip imagery 270 and a confidence indication of the characterization. The ultrasound imaging system 240 in turn renders not only the video clip imagery 270 but also the characterization and optionally the confidence indication on the display of the host computing system 210.

[0023] According to one embodiment of the present application, a breathing pattern optimization module 300 is incorporated with the ultrasound imaging system 240. The module 300 includes computer program instructions that, when executed in the host computing system 210, compare the video clip imagery 270 with a data store 250 of image attributes that have each been associated with a different breathing pattern. The data store 250 of image attributes can be a neural network trained using imagery of the target organ and labeled using different breathing patterns. After associating the video clip imagery 270 with a particular breathing pattern, the program instructions present the breathing pattern in a display of the ultrasound imaging system 240. Optionally, the program instructions interrogate the data store 260 to determine a quality of the video clip imagery 270 and retrieve a particular breathing pattern associated with an improvement in the quality. As another option, the program instructions interrogate the data store 260 to identify a particular physiological condition manifested in the video clip imagery 270 and retrieve a particular breathing pattern associated with an improvement in imaging of the physiological condition. In any case, the particular breathing pattern is presented in the ultrasound imaging system 240 visually, aurally, or haptically (haptic feedback in the imaging wand 230).

[0024] In a still further illustration of the operation of the breathing pattern optimization module 300, Figure 3 is a flowchart illustrating a process of ultrasound image acquisition optimization according to different breathing patterns. Beginning at block 310, an image clip of a target organ is acquired. At block 320, the image clip is submitted to a neural network trained to correlate particular ultrasound imagery of the target organ with a particular breathing pattern. In this way, at block 360, the neural network returns a breathing pattern having the highest probability of association with the acquired image clip for the target organ. Meanwhile, at block 330, the image clip is submitted to a neural network trained to correlate particular ultrasound imagery of the target organ with a particular image quality, and at block 350, the neural network returns a particular quality having the highest probability of association with the acquired image clip for the target organ. Finally, at block 340, the image clip is submitted to a neural network trained to correlate particular ultrasound imagery of the target organ with a particular physiological condition, and at block 370, the neural network returns a particular physiological condition having the highest probability of association with the acquired image clip for the target organ.

[0025] Then, at decision block 380, a determination is made whether to validate a breathing pattern change based on the particular image quality, the particular physiological condition, or both. If it is determined not to validate a breathing pattern change, then at block 390, the breathing pattern returned by the neural network is presented in the ultrasound imaging system for the benefit of the operator. However, if it is determined to validate a breathing pattern change based on either or both of the particular quality or the particular physiological condition, then at block 400, a breathing pattern change associated with either or both of the particular quality and the particular physiological condition is presented in the ultrasound imaging system.

[0026] The present application can be embodied in a system, a method, a computer program product, or any combination thereof. A computer program product can include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present application. The computer readable storage medium can be a tangible device that can retain and store instructions for execution by a processor. The computer readable storage medium can for example be, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.

[0027] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network. The computer readable program instructions can be executed by the user's computer, partially by the user's computer, as a stand-alone software package, partially by the user's computer and partially by a remote computer or entirely by a remote computer or server. The aspects of the present application are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0028] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including

[0029] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0030] The diagrams of the flowcharts and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical functions. In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by a hardware-based system that performs a particular function or functions, or combinations of hardware and software that perform a particular function or functions.

[0031] Finally, the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0032] The corresponding structure, material, act, or means for performing a function that are described in the claims are intended to include any structure, material, or act for performing that function described in connection with a specified additional element(s) intended to perform its function. The specification, including the claims, is to be construed as not limiting of the present application in any way except as set forth in the following claims. Specific embodiments of the application have been described herein for the purpose of illustrating the principles of the application and its practical application. Numerous modifications and variations have been omitted in order to not obscure the essential teachings of the application. It is intended for example only that replacement elements be substituted for those illustrated, and that certain procedural steps be rendered in different order, or performed simultaneously, in other steps be performed during different stages of the disclosure, or in other embodiments of the disclosure, without departing from the spirit and scope of the present application.

[0033] The application of the application has been described herein in detail for the purpose of clarity and understanding. It will be apparent to those of ordinary skill in the art that numerous modifications and variations can be made without departing from the scope of the application as defined in the appended claims.

Claims

1. A data processing system configured to optimize ultrasound image acquisition according to different breathing patterns, the system comprising: a computer having a memory and at least one processor; a display coupled to the computer; image generation circuitry coupled to the computer and the display; an ultrasound imaging probe comprising a transducer connected to the image generating circuit; as well as An ultrasound image acquisition optimization module executed in a memory of the computer, the module comprising program code that, when executed by a processor of the computer, enables the following: obtaining an ultrasound image of a target organ by using an ultrasound imaging device; comparing the attributes of the acquired ultrasound image with association data in the association data store, the association data associating attributes of previously acquired ultrasound images of different images of the target organ with different breathing patterns; determining a breathing pattern evident in the acquired ultrasound image based on the comparison; and presenting the determined pattern in the ultrasound imaging device; The program code further executes: determining the quality of acquired ultrasound images; identifying changes in the determined breathing pattern that correlate with improved quality of ultrasound images of the target organ; and The determined pattern of changes is presented in the ultrasound imaging device.

2. The system of claim 1, wherein, The association data store is a deep neural network trained to associate different breathing patterns with corresponding ultrasound images of different previously acquired images of the target organ.

3. The system of claim 1, wherein, The association data store is a table that associates different images with corresponding breathing patterns.

4. The system of claim 1, wherein, The program code further executes: Prospective disease was determined based on the ultrasound images obtained; identifying a change in the determined breathing pattern that correlates with an improvement in the quality of an ultrasound image of a target organ to diagnose the prospective disease; and The determined pattern of changes is presented in the ultrasound imaging device.

5. The system of claim 1, wherein, The determination is based on comparative properties of the acquired ultrasound images rather than on external physiological signal input providing data regarding respiration.

6. A computer program product for optimizing ultrasound image acquisition based on different breathing patterns, the computer program product comprising a computer-readable storage medium having program instructions embodied therein, the program instructions being executable by a device to cause the device to perform the following method steps: obtaining an ultrasound image of a target organ by using an ultrasound imaging device; comparing the attributes of the acquired ultrasound image with association data in the association data store, the association data associating attributes of previously acquired ultrasound images of different images of the target organ with different breathing patterns; determining a breathing pattern evident in the acquired ultrasound image based on the comparison; as well as presenting the determined pattern in the ultrasound imaging device; The method further comprises: determining the quality of acquired ultrasound images; identifying changes in the determined breathing pattern that correlate with improved quality of ultrasound images of the target organ; and The determined pattern of changes is presented in the ultrasound imaging device.

7. The computer program product of claim 6, wherein, The association data store is a deep neural network trained to associate different breathing patterns with corresponding ultrasound images of different previously acquired images of the target organ.

8. The computer program product of claim 6, wherein, The correlation data store is a table associating each different image with a corresponding breathing pattern.

9. The computer program product of claim 6, wherein, The method further comprises: determining a prospective disease from the acquired ultrasound images; identifying a change in the determined breathing pattern that is relevant to quality improvement of ultrasound imagery of a target organ to diagnose the prospective disease; and presenting the determined change in pattern in the ultrasound imaging device.

10. The computer program product of claim 6, wherein, The determination is based on a comparative property of the acquired ultrasound images, rather than on an external physiological signal input providing data about respiration.

Images