Optimization of ultrasound image acquisition according to different breathing modes
The method and system address breathing-induced artifacts in ultrasound imaging by correlating image attributes with breathing modes using a neural network, enhancing image quality and user guidance for improved diagnostic outcomes.
Patent Information
- Application Number
- FR2020000964
- Authority / Receiving Office
- FR · FR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2020-01-31
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2040-01-31
AI Technical Summary
Ultrasound imaging is hindered by the challenges of breathing-induced artifacts and organ movement, requiring skilled user manipulation to achieve quality images, especially near lung areas with air interference and organ displacement.
A method and system utilizing a deep neural network or image association table to correlate ultrasound image attributes with breathing modes, providing real-time feedback on optimal breathing patterns for improved image acquisition.
Enhances ultrasound image quality by automatically determining and guiding optimal breathing modes, reducing user dependency and improving image clarity and diagnostic accuracy.
Smart Images

Figure 00000015_0000 
Figure 00000016_0000 
Figure 00000016_0001
Abstract
Description
Title of the invention: Optimization of ultrasound image acquisition according to different breathing modes Field of the invention
[0001] The present invention relates to ultrasound imaging and, more particularly, to the acquisition of ultrasound images.
[0002] Description of the prior art
[0003] Ultrasound imaging, also known as sonography, is a medical imaging technique that uses high-frequency sound waves to view three-dimensional structures inside the body of a living being. Because they are captured in real time, ultrasound images also show the movements of the body's internal organs as well as blood flowing through the human body's blood vessels and the stiffness of tissues. Unlike X-ray imaging, ultrasound imaging does not involve ionizing radiation, which allows for prolonged use of ultrasound imaging without the risk of damaging tissues and internal organs through prolonged exposure to radiation.
[0004] To acquire ultrasound images, during an ultrasound examination, a transducer, generally referred to as a probe, is placed directly on the skin or within a body opening. The probe is coupled to image generating circuitry that includes circuitry designed to transmit and receive signals to and from the probe, and may include a beam former, although synthetic aperture imaging systems may utilize retrospective imaging which reduces the need for beam former and scan conversion functions. A thin layer of gel is applied to the skin such that ultrasound waves are transmitted from the probe into the body through the gel medium. The ultrasound image is produced based on a measurement of the reflection of the ultrasound waves from body structures.The intensity of the ultrasound signal, measured as the amplitude of the detected sound wave reflection, and the time taken for the sound wave to pass through the body, provide the information needed to calculate an image of target body structures. The "Doppler" effect can also be used in ultrasound imaging to measure the speed and direction of fluid flow in body structures (i.e., blood), as well as the speed and direction of movement of moving tissues such as muscles or heart valves.
[0005] Compared to other well-known medical imaging methods, ultrasound imaging offers several advantages to both diagnosticians and patients. First and foremost, ultrasound imaging provides real-time images. In addition, ultrasound imaging requires equipment that is portable and can be brought to the patient's bedside. Furthermore, from a practical point of view, ultrasound imaging equipment is considerably less expensive than other medical imaging equipment, and as mentioned, it does not use dangerous ionizing radiation. Nevertheless, ultrasound imaging is not without its drawbacks.
[0006] In this regard, unlike most diagnostic imaging modalities, such as X-rays, magnetic resonance imaging (MRI), computed tomography (CT), and the like, ultrasound imaging depends on the careful and dynamic manipulation of a handheld transducer applied to the patient. For good results, this scanning process requires highly skilled and trained users. These users must learn how to adjust the position and angle of the transducer on the patient to obtain usable images. These users must further know how to position the patient for different clinical applications and targets. However, this positioning can be difficult and must often be altered both grossly and subtly during the examination to obtain an acceptable view for use in medical diagnosis.
[0007] In addition to positioning, for many clinical applications, the subject's breathing during ultrasound can play a key role in the quality of an acquired ultrasound image. Namely, breathing can affect an ultrasound image to the extent that there is a significant impedance mismatch between soft tissue and air within the body. As is well known, air in the ultrasound path is a strong reflector that prevents transmission of ultrasound waves and creates reverberation artifacts. This effect is most common on anatomical targets adjacent to the lungs, although it can be found in other locations, such as the intestine where intestinal gas is found.On targets near the lungs, the expansion and contraction of the lungs during breathing can cause air to move in and out of the path of the ultrasound beam, causing interference that follows the breathing cycle. Another effect is that a target organ, such as the heart, will move in association with the breathing cycle, as the expansion and contraction of the lungs push and pull the heart into different positions. This can cause a target to move in and out of the ultrasound beam in such a way that it is impossible to properly visualize the target. This effect can be a problem even if breathing does not directly move air into the path of the ultrasound.
[0008] BRIEF SUMMARY OF THE INVENTION
[0009] Embodiments of the present invention address deficiencies in the art with respect to ultrasound imaging and provide a novel and non-obvious method, system, and computer program product for optimizing ultrasound image acquisition across different breathing modes. In one embodiment of the invention, a method for optimizing ultrasound image acquisition across different breathing modes includes acquiring, by an ultrasound imaging device, one or more ultrasound images of a target organ. The method further includes comparing attributes of the acquired ultrasound images to association data contained in an attribute data store that associates previously acquired ultrasound images of different views of the target organ with different breathing modes.Finally, the method comprises determining, from the comparison, a breathing mode emerging from the acquired ultrasound image and presenting the determined mode on the ultrasound imaging device, for example by means of a visual display of the mode on a display screen of the imaging device, by audible methods or even tactile methods. Importantly, the determination is based on the comparison of attributes of the acquired ultrasound images and not on the introduction of an external physiological signal providing data concerning breathing.
[0010] According to one aspect of the embodiment, the association data store is a deep neural network trained to associate different breathing modes with corresponding previously acquired ultrasound images of the different views of the target organ. As such, the acquired ultrasound image can be presented to the neural network and the neural network can return a probability of correlation between the acquired ultrasound image and a particular breathing mode. According to another aspect of the embodiment, the association data store is an array associating different individual views with corresponding breathing modes. As such, a pixel-level image comparison can be performed to produce a particular breathing mode assigned to an image having the highest percentage match in the data store.
[0011] According to yet another aspect of the embodiment, the method further comprises determining a quality of the acquired ultrasound image, identifying a change in the determined breathing pattern correlated with an improvement in quality of the ultrasound images of the target organ and presenting the change in the determined pattern on the display screen of the ultrasound image acquisition device. According to yet another aspect of the embodiment, the method further comprises determining a physiological condition, such as an abnormality or a disease potential, from the acquired ultrasound image, identifying a change in the determined breathing pattern correlated with an improvement in the quality of the ultrasound images of the target organ to diagnose the potential abnormality or disease, and presenting the change in the determined pattern on the ultrasound image acquisition device. In this regard, the change may be presented visually on a display screen of the device, audibly by a speaker of the device, or tactilely on a probe of the device.
[0012] According to another embodiment of the invention, a data processing system is configured for optimizing ultrasound image acquisition according to different breathing modes. The system includes a computer having a memory and at least one processor, a display screen coupled to the computer, image generation circuitry coupled to the computer as well as to the display screen, and an ultrasound imaging probe that has a transducer connected to the image generation circuitry. The system further includes an ultrasound image acquisition optimization module executing in the memory of the computer.The module contains program code activated upon execution by the computer processor for acquiring, by an ultrasound imaging device, one or more ultrasound images of a target organ, comparing attributes of the acquired ultrasound image to data contained in a data store that associates attributes of previously acquired ultrasound images of different views of the target organ with different breathing patterns, determining, from the comparison, a breathing pattern evident from the acquired ultrasound image, and presenting the determined pattern on the ultrasound imaging device.
[0013] Additional aspects of the invention will be set forth in part in the following description, and in part will be obvious from the description, or may be learned by practice of the invention. Aspects of the invention will be realized and attained by means of the elements and combinations particularly pointed out in the appended claims. It will be understood that the above general description and the following detailed description are provided by way of example and explanation only and are not restrictive of the invention as claimed.
[0014] BRIEF DESCRIPTION OF THE DIFFERENT VIEWS OF THE DRAWINGS
[0015] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention. The embodiments illustrated herein are presently preferred, it being understood, however, that the invention is not limited to the precise arrangements and instruments shown. In the drawings:
[0016] [Fig-1] is a schematic illustration of a process for the optimization of a acquisition of ultrasound images according to different breathing modes;
[0017] [Fig.2] is a schematic illustration of a suitable data processing system for the optimization of ultrasound image acquisition according to different breathing modes; and
[0018] [Fig.3] is a flowchart illustrating a process for the optimization of a acquisition of ultrasound images according to different breathing modes. DETAILED DESCRIPTION OF THE INVENTION
[0019] Embodiments of the invention provide optimization of ultrasound image acquisition according to different breathing modes. According to one embodiment of the invention, different views of different organs are associated, in an association data store, with different breathing modes, including inspiration and expiration. In this regard, the association data store may be an array of images correlating different views with different breathing modes, or a deep neural network trained to associate each of the different views with a corresponding one of the different breathing modes.
[0020] Next, an ultrasound imaging device acquires ultrasound images of a target organ and compares characteristics of the different views to the association data store to determine a breathing mode for the acquired images. The breathing mode is then presented on the ultrasound imaging device to assist an operator of the ultrasound imaging device in acquiring correct images of the target organ. Optionally, a quality of the acquired view is determined along with a change in the breathing mode previously associated with an improvement in image quality of a target image.Therefore, the change in breathing mode may be presented as a guidance signal on the device, such as a visual indication on the display screen of the device, an auditory indication presented by the device, or a tactile view transmitted by the device to the probe of the device, in order to assist an operator of the ultrasound imaging device in acquiring correct images of the target organ.
[0021] By way of further illustration, [Fig. 1] schematically illustrates a process for optimizing ultrasound image acquisition according to different breathing modes. As shown in [Fig. 1], an ultrasound operator 110 manipulates an ultrasound imaging system 120 to acquire ultrasound images 170 of a target organ of a patient 100. A display screen 140 of the ultrasound imaging system 120 provides guiding feedback to the ultrasound operator 110. In particular, a quality measurement scale 150 is placed on the display screen 140 and indicates a moving quality value of the acquired ultrasound images 170 relative to a known view desired to be acquired for the target organ. For example, in connection with cardiac imaging, the known view may include a parasternal long axis view, a parasternal short axis view, an apical two, three, four or five chamber view, or a subcostal view. In the event that it is determined that the acquired ultrasound images 170 have a corresponding quality value that meets or exceeds a quality threshold for the specified view, a "Success" icon 165 is displayed in connection with the quality measurement scale 150 and the acquired ultrasound images 170 are displayed in a window as the most recently acquired satisfactory quality video clip.
[0022] During acquisition of the acquired ultrasound images 170, attributes of the acquired ultrasound images 170 are compared to attributes of previous images contained in a data store 180 and associated with different breathing modes 160 of the breathing cycle. In this regard, the different breathing modes 160 range from a full expiration with inhalation prevention 160A to a full inspiration with expiration prevention 160F, through intermediate modes including a full expiration 160B, a partial expiration with blocking of any additional inspiration or expiration 160C, a partial inspiration with blocking of any additional inspiration or expiration 160D, and a full inspiration 160E.Optionally, the data store 180 is an array of images and associated breathing modes such that a pixel-level comparison of the acquired ultrasound images 170 to the images in the array identifies sufficient pixel-level commonalities to establish a content-based correspondence between the acquired ultrasound images 170 and an image in the array associated with a particular one of the breathing modes 160. Alternatively, the data store 180 is a convolutional neural network trained with different images annotated with different ones of the breathing modes 160. In either circumstance, however, depending on the comparison, a common breathing mode 130 is identified among the different breathing modes 160 in response to a submission of the acquired ultrasound images 170 to the data store 180.
[0023] The method described in connection with [Fig.l] may be implemented in a data processing system. As a further illustration, [Fig.2] schematically illustrates a data processing system suitable for optimizing ultrasound image acquisition according to different breathing modes. The system comprises a host computer system 210 which comprises a computer having at least one processor, a memory and a display screen. The host computer system 210 also comprises a data store 250. The system Host computer 210 is further coupled to an ultrasound imaging system 220 adapted to store in memory ultrasound images acquired by positioning an imaging probe 230 proximate a target organ of interest of a mammalian subject by actuation of the image generation circuitry 220.
[0024] Importantly, the host computer system 210 is communicatively coupled with a fixed storage means 260, either local or remote ("cloud"), on which are stored a neural network and a programmatic interface of the neural network. The neural network is trained to characterize one or more characteristics of the target organ, for example, an ejection fraction value of the heart, or the presence or absence of aortic stenosis. To do this, video clip images 270 of a specified view of the target organ acquired by the ultrasound imaging system 220 are provided to the neural network, which then accesses the programmatic interface so as to be able to output the characterization of the video clip images along with a confidence index of this characterization.The ultrasound imaging system 220 then renders on the display screen of the host computer system 210 not only the video clip images 270, but also the characterization, and possibly the confidence index.
[0025] According to one embodiment of the invention, a respiration mode optimization module 300 is included in the ultrasound imaging system 220. The module 300 includes computer program instructions enabled, when executed in the host computer system 210, to compare the video clip images 270 to a data store of image attributes 250 that have each been correlated to a different respiration mode. The data store of image attributes 250 may be a neural network trained with images of the target organ, annotated with different respiration modes. Upon correlating the video clip images 270 to a particular respiration mode, the program instructions present the respiration mode on the display screen of the ultrasound imaging system 220.Optionally, the program instructions query the data store 260 to determine a quality of the video clip images 270 and retrieve a specific breathing pattern associated with an improvement in the quality. Alternatively, the program instructions query the data store 260 to identify a specific physiological condition evident from the video clip images 270 and retrieve a specific breathing pattern associated with an improvement in the images of the physiological condition. In either circumstance, the specific breathing pattern is presented on the ultrasound imaging system 220, either visually, audibly, or by tactile means (haptic feedback on the imaging pen 230).
[0026] As a further illustration of the operation of the breathing mode optimization module 300, [Fig. 3] is a flowchart illustrating a process for optimizing ultrasound image acquisition according to different breathing modes. Beginning at block 310, an image clip of a target organ is acquired. At block 320, the image clip is subjected to a neural network trained to correlate specific ultrasound images of the target organ to a specific breathing mode. As such, at block 360, the neural network produces a breathing mode having the highest probability of association with the acquired image clip for the target organ.At the same time, at block 330, the image clip is subjected to a neural network trained to correlate specific ultrasound images of the target organ with a specific image quality and, at block 350, the neural network produces a particular quality having the highest probability of association with the image clip acquired for the target organ. Finally, at block 340, the image clip is subjected to a neural network trained to correlate specific ultrasound images of the target organ with specific physiological conditions and, at block 370, the neural network produces a particular physiological condition having the highest probability of association with the image clip acquired for the target organ.
[0027] Next, at decision block 380, it is determined whether or not a change in breathing mode is warranted in light of the specific image quality, the specific physiological condition, or both. If it is determined that no change in breathing mode is warranted, at block 390, the breathing mode produced by the neural network is presented on the ultrasound imaging system to assist the operator. On the other hand, at decision block 380, if it is determined that a change in breathing mode is warranted, either because of the specified quality or because of the particular physiological condition, at block 400, a change in breathing mode associated with either the specific quality, the particular condition, or both, is presented on the ultrasound imaging system.
[0028] The present invention may be implemented in a system, a method, a computer program product, or any combination thereof. The computer program product may include one or more computer-readable storage media containing computer-readable program instructions for causing a processor to execute aspects of the present invention. The computer-readable storage media may be a tangible device that can retain and store instructions for use by an instruction-executing device. The computer-readable storage media may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, a storage device electromagnetic, a semiconductor storage device, or any suitable combination thereof.
[0029] The computer-readable program instructions described herein may be downloaded into respective computing / processing devices from a computer-readable storage medium or onto an external computer or external storage device, via a network. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. Aspects of the present invention are described herein in connection with flowcharts and / or functional diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the invention.It will be understood that each block of the flowcharts and / or block diagrams, and combinations of the blocks of the flowcharts and / or block diagrams, may be implemented by computer-readable program instructions.
[0030] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing device, create means for implementing the functions / actions specified in the block(s) of the flowcharts and / or functional diagrams.These computer-readable program instructions may also be stored in a computer-readable storage medium that can control a computer, a programmable data processing apparatus and / or other devices to operate in a particular manner, such that the computer-readable storage medium on which instructions are stored comprises an article of manufacture including instructions that implement aspects of the function / action specified in the block(s) of the flowcharts and / or block diagrams.
[0031] The computer-readable program instructions may be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be executed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, such that the instructions that execute on the computer, other programmable apparatus, or other device implement the functions / actions specified in the block(s) of the flowcharts and / or block diagrams.
[0032] The flowchart and block diagrams of the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products in accordance with various embodiments of the present invention. In this regard, each block of the flowchart or block diagrams may represent a module, segment, or portion of instructions, which includes one or more executable instructions for implementing one or more specified logical functions. In certain other embodiments, the functions noted in the block may be executed in an order other than that noted in the figures. For example, two blocks shown consecutively may, in fact, be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order, depending on the functionality involved.It will also be noted that each block of the block diagrams and / or flowchart, and combinations of blocks of the block diagrams and / or flowchart, may be implemented by special-purpose hardware systems that perform the specified functions or actions or combinations of computer instructions and special-purpose hardware.
[0033] Finally, the terminology used herein is for the sole purpose of describing particular embodiments and is not intended to limit the invention. It is understood that the terms "comprises" and / or "comprising," as used herein, specify the presence of the features, entities, steps, operations, elements, and / or components mentioned, but do not exclude the presence or addition of one or more other features, entities, steps, operations, elements, components, and / or groups thereof.
[0034] The structures, materials, actions and corresponding equivalents of all means or steps and functional elements mentioned in the following claims are intended to include any and all structures, materials or actions for performing the function in combination with other claimed elements, as specifically claimed. The description of the present invention has been given by way of illustration and description, but is not intended to be exhaustive or to limit the invention to the form disclosed. Numerous modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the invention.The embodiment has been selected and described in order to better explain the principles of the invention and the practical application, and to enable others skilled in the art to understand the invention for different embodiments having different modifications as appropriate for the particular use contemplated.
[0035] The invention having thus been described in detail and with reference to its embodiments, it will be obvious that modifications and variants are possible without departing from the scope of the invention as defined in the claims below.
Claims
Claims
1. A method for optimizing an acquisition of ultrasound images according to different breathing modes, the method comprising: - acquiring, by an ultrasound imaging device (120), one or more ultrasound images (170) of a target organ; - comparing attributes of the one or more acquired ultrasound images (170) with association data contained in an association data store (180) which associate attributes of previously acquired ultrasound images of different views of the target organ with different breathing modes (160); - determining, from the comparison of the one or more acquired ultrasound images with the association data, a breathing mode determined by the association data, such that the mode determined for the association data of the previously acquired ultrasound images is assigned to the one or more acquired ultrasound images;and - presenting on the ultrasound imaging device (120) the determined mode, as a mode of the one or more ultrasound images.;
2. The method of claim 1, wherein the association data store (180) is a deep neural network trained to associate different ones of the breathing modes (160) with corresponding certain ones of the previously acquired ultrasound images of the different views of the target organ.
3. The method of claim 1, wherein the association data store (180) is a table associating individual views of the different views with certain corresponding ones of the breathing modes (160).
4. The method of claim 1, further comprising: - determining a quality of the acquired ultrasound image; - identifying a change in the determined breathing mode correlated with an improvement in the quality of the ultrasound images of the target organ; and - presenting the change in the determined mode on the ultrasound image acquisition device.
5. A data processing system configured for optimizing ultrasound image acquisition according to different breathing modes, the system comprising: - a computer having a memory and at least one processor; - a display screen coupled to the computer; - image generation circuitry (220) coupled to the computer and the display screen; - an ultrasound imaging probe (230) which has a transducer connected to the image generation circuitry (220); and - an ultrasound image acquisition optimization module (300) executing in the memory of the computer, the module containing program code activated upon execution by the processor of the computer to execute: - the acquisition, by an ultrasound imaging device (220), of an ultrasound image of a target organ;- comparing attributes of the one or more acquired ultrasound images (270) with association data contained in an association data store (260) which associate attributes of previously acquired ultrasound images of different views of the target organ with different breathing modes; - determining, from the comparison of the one or more acquired ultrasound images with the association data, a breathing mode determined by the association data, such that the mode determined for the association data of the previously acquired ultrasound images is assigned to the one or more acquired ultrasound images (270); and - presenting on the ultrasound imaging device the determined mode, as a mode of the one or more ultrasound images.;
6. The system of claim 5, wherein the association data store (260) is a deep neural network trained to associate different ones of the breathing patterns with corresponding certain ones of the previously acquired ultrasound images of different views of the target organ.
7. The system of claim 5, wherein the association data store (260) is a table associating individual views of the different views with certain corresponding breathing modes.
8. The system of claim 5, wherein the program code further performs: - determining a quality of the acquired ultrasound image; - identifying a change in the determined breathing mode correlated with an improvement in the quality of the ultrasound images of the target organ; and - presenting the change in the determined mode on the ultrasound image acquisition device.
9. The system of claim 5, wherein the program code further performs: - determining a potential disease from the acquired ultrasound image; - identifying a change in the determined breathing pattern correlated with an improvement in the quality of the ultrasound images of the target organ to diagnose the potential disease; and - presenting the change in the determined pattern on the ultrasound image acquisition device.
10. A computer-readable storage medium containing program instructions for optimizing ultrasound image acquisition according to different breathing modes, the program instructions being executable by a device to cause the device to perform a method including: - acquiring, by an ultrasound imaging device, an ultrasound image of a target organ; - comparing attributes of the one or more acquired ultrasound images to association data contained in an association data store that associates attributes of previously acquired ultrasound images of different views of the target organ with different breathing modes;- determining, from the comparison of the one or more acquired ultrasound images with the association data, a breathing mode determined by the association data, such that the mode determined for the association data of the previously acquired ultrasound images is assigned to the one or more acquired ultrasound images; and - presenting on the ultrasound imaging device the determined mode, as a mode of the one or more ultrasound images.;
11. The computer-readable storage medium of claim 10, wherein the association data store is a deep neural network trained to associate different ones of the breathing modes with corresponding certain ones of the previously acquired ultrasound images of the different views of the target organ.
12. The computer-readable storage medium of claim 10, wherein the association data store is a table associating individual views of the different views with certain corresponding breathing modes.
13. The computer-readable storage medium of claim 10, wherein the method further comprises: - determining a quality of the acquired ultrasound image; - identifying a change in the determined breathing pattern correlated with an improvement in quality of the ultrasound images of the target organ; and - presenting the change in the determined pattern on the ultrasound image acquisition device.
