Echocardiography-based compression guidance

Abstract

An ultrasound system includes a memory that stores instructions and a processor that executes the instructions. When executed by the processor, the instructions cause the ultrasound system to: receive a plurality of echocardiography images while compression is being performed; interpret each of the plurality of echocardiography images; output each of the plurality of echocardiography images; and generate and output real-time feedback for compression quality based on interpreting each of the plurality of echocardiography images.

Description

ECHOCARDIOGRAPHY-BASED COMPRESSION GUIDANCEGOVERNMENT INTEREST

[0001] This invention was made with United States government support awarded by the United States Department of Health and Human Services under the grant number HHS / ASPRZBARDA 75A50120C00097. The United States has certain rights in this invention.BACKGROUND

[0002] Sudden cardiac arrest is one of the primary causes of death globally, with a survival rate for patients outside of the hospital that may be below 10%. For patients inside of the hospital, echocardiography is sometimes used as a bedside modality to determine causes of sudden cardiac arrest and guide cardiac arrest resuscitation (CAR). Cardiac arrest resuscitation may involve cardiopulmonary resuscitation (CPR) during emergencies. CPR consists of chest compressions combined with ventilation. The ventilation is either mouth-to-mouth or artificial ventilation.

[0003] Transesophageal echocardiography (TEE) is a form of echocardiography and involves passing a specialized probe with an ultrasound transducer through a patient’s mouth and into the patient’s esophagus to monitor the patient’s heart. Recent advances in TEE also include insertion through the transnasal cavity and into the esophagus to monitor the patient’s heart. Transnasal TEE involves administering a monoplane TEE through a patient’s nose and into the esophagus. Transthoracic echocardiography (TTE) is another form of echocardiography and involves placing a specialized probe with an ultrasound transducer on a patient’s chest or abdomen to monitor the patient’s heart. The use of TEE in cardiac arrest resuscitation (CAR) has been demonstrated to have clinically impactful outcomes in critically ill and hemodynamically unstable patients in extremis compared to TTE. TEE provides continuous monitoring of cardiopulmonary activity, an unhindered view of continuous myocardial activity, and superior image quality for diagnosing disease states and identifying potential reversible causes of cardiac arrest. The American College of Emergency Physicians (ACEP) has endorsed use of echocardiography with TEE as the standard tool for ultrasound-informed resuscitative care.

[0004] Medical professionals in the context of emergency medicine and critical care environments may leverage focused cardiac ultrasound (FoCUS) as a goal-directed framework toquickly determine causes of cardiac arrest and guide resuscitative care. FoCUSed transthoracic echocardiography is the diagnostic modality most commonly used by emergency physicians today.

[0005] The current guidelines for CPR recommend proper hand placement or machine placement for chest compressions to be at “the center of the victim’s chest” to promote ventricular blood flow. However, human radiologic studies of chest computerized tomography (CT) and cardiac magnetic resonance imaging (MRI) have found that the left ventricle (LV) is not always located at the center of the sternum; instead, the left ventricular outflow tract (LVOT), aortic valve or aortic root are located in that position in 50-80% of patients. Blind compressions over the aortic root / LVOT can lead to outflow obstruction and are associated with poorer prognosis and survival rates due to suboptimal forward blood flow in the heart. Emerging studies suggest that compression directly over the LV may improve survival and outcomes, but rapid and reliable localization of the LV is a major obstacle for physicians first responding to cardiac arrest.

[0006] Studies under TEE guidance have confirmed these findings that medical professionals are often inappropriately compressing in a location associated with outflow obstruction. A prospective study in patients undergoing cardiac arrest found that when compressing at the center of the victim’s chest, the area of maximal compression (AMC) was inappropriately located over the LVOT in 41% of patients and at the aorta (including the aortic valve) in 59% of patients. Another more recent study in out-of-hospital cardiac arrest patients found that the inappropriate AMC was found in the aortic root / LVOT in 53% of cases. Both studies highlighted the fact that a high percentage of patients may not be receiving the proper compressions in the right place to meet the goal for coronary and cerebral profusion. When comparing compressions over the aortic root / LVOT versus the LV, research studies have found that compressions directed over the LV resulted in improved hemodynamic efficiency and a higher survival rate.

[0007] Although the optimal location for hand placement or machine placement to produce the most effective compression may vary between patients, leveraging TEE to redirect hand placement away from the aortic root or LVOT and towards an area of higher hemodynamic response has been shown to improve outcomes by generating higher rates of spontaneous circulation. By developing a guidance solution that assesses the hemodynamic variables of thepatient to direct the user to the proper area of maximal compression, CPR may be tailored to the individual and patient outcomes for those undergoing cardiac arrest resuscitation may be greatly improved.

[0008] For either TEE or TTE, a need exists to improve optimization of chest compression quality to improve resuscitation outcomes. Real-time guidance that improves overall quality of resuscitative care does not exist, whereas even medical professionals are performing chest compressions incorrectly up to 70% of the time due to improper hand placement. This is partly true because the LV is not always in the same place for every patient. This is also partly true because current solutions do not monitor the location of chest compression. A more individualized approach is needed to optimize chest compression in CPR.

[0009] Automated software solutions may enhance workflow efficiency and clinical performance of cardiac ultrasound. However, a need exists to develop echocardiography applications for point of care users in the context of emergency medicine and critical care environments, where exams are time-constrained, decisions are immediate, and there is greater variability in user experience. One particular need is to provide real time feedback and assessment to users to optimize the quality of chest compressions.SUMMARY

[0010] According to an aspect of the present disclosure, an ultrasound system includes a memory that stores instructions and a processor that executes the instructions. When executed by the processor, the instructions cause the ultrasound system to: receive a plurality of echocardiography images while compression is being performed; interpret each of the plurality of echocardiography images; output each of the plurality of echocardiography images; and generate and output real-time feedback for compression quality based on interpreting each of the plurality of echocardiography images.

[0011] According to another aspect of the present disclosure, a method of operating an ultrasound system comprising a memory that stores instructions and a processor that executes the instructions includes receiving a plurality of echocardiography images while compression is being performed. The method also includes interpreting each of the plurality of echocardiography images; outputting each of the plurality of echocardiography images; andgenerating and outputting real-time feedback for compression quality based on interpreting each of the plurality of echocardiography images.

[0012] According to another aspect of the present disclosure, a tangible, non-transitory computer-readable medium stores instructions. When executed by a processor, the instructions cause the processor to receive a plurality of echocardiography images while compression is being performed; interpret each of the plurality of echocardiography images; output each of the plurality of echocardiography images; and generate and output real-time feedback for compression quality based on interpreting each of the plurality of echocardiography images.BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The example embodiments are best understood from the following detailed description when read with the accompanying drawing figures. It is emphasized that the various features are not necessarily drawn to scale. In fact, the dimensions may be arbitrarily increased or decreased for clarity of discussion. Wherever applicable and practical, like reference numerals refer to like elements.

[0014] FIG. 1 illustrates a system for echocardiography -based resuscitative guidance, in accordance with a representative embodiment.

[0015] FIG. 2 illustrates another system for echocardiography-based resuscitative guidance, in accordance with a representative embodiment.

[0016] FIG. 3 illustrates a method for echocardiography-based resuscitative guidance, in accordance with a representative embodiment.

[0017] FIG. 4 illustrates another method for echocardiography-based resuscitative guidance, in accordance with a representative embodiment.

[0018] FIG. 5 illustrates another method for echocardiography -based resuscitative guidance, in accordance with a representative embodiment.

[0019] FIG. 6 illustrates a user interface for echocardiography -based resuscitative guidance, in accordance with a representative embodiment.

[0020] FIG. 7 illustrates model development and deployment for echocardiography -based resuscitative guidance, in accordance with a representative embodiment.

[0021] FIG. 8 illustrates a computer system, on which a method for echocardiography -basedresuscitative guidance is implemented, in accordance with another representative embodiment.DETAILED DESCRIPTION

[0022] In the following detailed description, for the purposes of explanation and not limitation, representative embodiments disclosing specific details are set forth in order to provide a thorough understanding of embodiments according to the present teachings. However, other embodiments consistent with the present disclosure that depart from specific details disclosed herein remain within the scope of the appended claims. Descriptions of known systems, devices, materials, methods of operation and methods of manufacture may be omitted so as to avoid obscuring the description of the representative embodiments. Nonetheless, systems, devices, materials, and methods that are within the purview of one of ordinary skill in the art are within the scope of the present teachings and may be used in accordance with the representative embodiments. It is to be understood that the terminology used herein is for purposes of describing particular embodiments only and is not intended to be limiting. Definitions and explanations for terms herein are in addition to the technical and scientific meanings of the terms as commonly understood and accepted in the technical field of the present teachings.

[0023] It will be understood that, although the terms first, second, third etc. may be used herein to describe various elements or components, these elements or components should not be limited by these terms. These terms are only used to distinguish one element or component from another element or component. Thus, a first element or component discussed below could be termed a second element or component without departing from the teachings of the inventive concept.

[0024] As used in the specification and appended claims, the singular forms of terms ‘a,’ ‘an’ and ‘the’ are intended to include both singular and plural forms, unless the context clearly dictates otherwise. Additionally, the terms "comprises", and / or "comprising," and / or similar terms when used in this specification, specify the presence of stated features, elements, and / or components, but do not preclude the presence or addition of one or more other features, elements, components, and / or groups thereof. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0025] Unless otherwise noted, when an element or component is said to be “connected to,” “coupled to,” or “adjacent to” another element or component, it will be understood that theelement or component can be directly connected or coupled to the other element or component, or intervening elements or components may be present. That is, these and similar terms encompass cases where one or more intermediate elements or components may be employed to connect two elements or components. However, when an element or component is said to be “directly connected” to another element or component, this encompasses only cases where the two elements or components are connected to each other without any intermediate or intervening elements or components.

[0026] The present disclosure, through one or more of its various aspects, embodiments and / or specific features or sub-components, is thus intended to bring out one or more of the advantages as specifically noted below.

[0027] As described herein, real time assessment and feedback of cardiopulmonary compression quality may be provided based on anatomical location of compression, depth of compression, frequency of compression, hemodynamic measurements, and / or anatomical images. The assessment and feedback may be provided to optimize coronary perfusion and individualize chest compression in CPR for a patient. Echocardiography-based assessment and compression guidance may be used to provide an efficient user experience to support resuscitation efforts by optimizing the quality of chest compressions for improved patient survival.

[0028] FIG. 1 illustrates a system 100 for echocardiography -based compression guidance, in accordance with a representative embodiment.

[0029] The system 100 in FIG 1 is a system for echocardiography -based compression guidance and includes components that may be provided together or that may be distributed. System 100 includes an ultrasound probe 110, an ultrasound base 120, and a display 180.

[0030] The ultrasound probe 110 includes a processing circuit 115 and a transducer array 113. The ultrasound probe 110 may comprise a TEE ultrasound probe or a TTE ultrasound probe. The processing circuit 115 may comprise a memory for storing data and instructions, an applicationspecific integrated circuit (ASIC) and / or a processor for processing data and instructions. The transducer array 113 includes an array of transducer elements including at least a first transducer element 1131, a second transducer element 1132, and an Xth transducer element 113X. The transducer array 113 converts electrical energy into sound waves which bounce off of body tissue and receives echoes of the sound waves and converts the echoes into electrical energy. Thetransducer array 113 may include dozens, hundreds, or thousands of individual transducer elements. The ultrasound probe 110 may transmit a beam to produce images and may detect echoes. The processing circuit 115 may process ultrasound images captured by the transducer array 113 of the ultrasound probe 110.

[0031] The ultrasound base 120 may comprise an ultrasound cart. The ultrasound base 120 includes a first interface 121, a second interface 122, a third interface 123, and a controller 150. A computer that can be used to implement the ultrasound base 120 is depicted in FIG. 8, though an ultrasound base 120 may include more elements than depicted in FIG. 1 and more or fewer elements than depicted in FIG. 8. One or more of the interfaces may include ports, disk drives, wireless antennas, or other types of receiver circuitry that connect the controller 150 to other electronic elements. The first interface 121 connects the ultrasound base 120 to the ultrasound probe 110, and may comprise a port, an antenna, and / or another type of physical component for wired or wireless communications. The second interface 122 connects the ultrasound base 120 to the display 180, and may also comprise a port, an antenna, and / or another type of physical component for wired or wireless communications. The third interface 123 is a user interface, and may comprise buttons, keys, a mouse, a microphone, a speaker, switches, a touchscreen, or other type of display separate from the display 180, and / or other types of physical components that allow medical personnel to interact with the ultrasound base 120 such as to enter instructions and receive output.

[0032] Controller 150 includes at least a memory 151 that stores instructions and a processor 152 that executes the instructions. The instructions stored in the memory 151 may comprise one or more software program(s) for generating and outputting feedback for compression quality (e.g., via the display 180) based on interpreting each of a plurality of echocardiography images captured by the ultrasound probe 110. The software program(s) in the memory 151 may include digital signal processing algorithms that can process 2D or 3D volumetric data to classify ultrasound images, detect features within ultrasound images, segment ultrasound images to extract a region of interest, calculate cardiac measurements, render 3D reconstructions of the heart, and model the spatiotemporal characteristics of compression. The features may include, for example, location of a left ventricle, and a detected location, depth, and frequency of compression relative to the location of compression. Tn system 100, the user interface may begenerated by the instructions stored in the memory 151 and may be displayed on the display 180.

[0033] Display 180 may be local to the ultrasound base 120 or may be remotely connected to the ultrasound base 120, such as wirelessly. Display 180 includes a graphical user interface 181 (GUI) that displays ultrasound images and guidance to users.

[0034] Display 180 may be connected to the ultrasound base 120 via a local wired interface such as an Ethernet cable or via a local wireless interface such as a Wi-Fi connection. Display 180 may be interfaced with other user input devices by which medical personnel can input instructions, including mouses, keyboards, thumbwheels and so on. Display 180 may be a monitor such as a computer monitor, a display on a mobile device, an augmented reality display, a television, an electronic whiteboard, or another screen configured to display electronic imagery. Display 180 may also include one or more input interface(s) such as those noted above that may connect to other elements or components, as well as an interactive touch screen configured to display prompts to medical personnel and collect touch input from medical personnel.

[0035] Controller 150 may perform some of the operations described herein directly and may implement other operations described herein indirectly. For example, controller 150 may indirectly control operations such as by generating and transmitting content to be displayed on the display 180. The controller 150 may directly control other operations such as logical operations performed by the processor 152 executing instructions from the memory 151 based on input received from electronic elements and / or medical personnel via the interfaces. Accordingly, the processes implemented by the controller 150 when the processor 152 executes instructions from the memory 151 may include steps not directly performed by the controller 150.

[0036] As set forth above, system 100 may comprise an ultrasound system with a memory 151 that stores instructions and a processor 152 that executes the instructions. When executed by processor 152, the instructions cause the ultrasound system to implement a method as described with respect to some or all features of the method in FIG. 3. The methods performed by system 100 may include the controller 150 of the ultrasound base 120 receiving a plurality of echocardiography images from the ultrasound probe 110 while compression is being performed. The echocardiography images may be, for example, TEE ultrasound images or TTE ultrasoundimages. The echocardiography images may be received in real-time or near real-time and interpreted by the controller 150. The instructions stored in memory 151 may be executed by processor 152 to cause the controller 150 to interpret each of the plurality of echocardiography images received from the ultrasound probe 110. The methods performed by system 100 may also include outputting each of the plurality of echocardiography images on the graphical user interface 181 of the display 180. The methods performed by system 100 may further include the controller 150 generating and outputting real-time feedback for compression quality on the display 180 based on interpreting each of the plurality of echocardiography images.

[0037] FIG. 2 illustrates another system for echocardiography -based resuscitative guidance, in accordance with a representative embodiment.

[0038] Network 201 may comprise a local wireless network such as a WiFi network, though the network 201 may also or alternatively include wired elements such as wires connected to smartphone A and smartphone B via USB cables. The smartphone A and smartphone B are representative of mobile devices such as smartphones and tablets or other networked / networkable devices with logical processing capabilities. Additionally, smartphone A and smartphone B are used as examples to show that system 200 may include multiple different smart devices with applications or other functional capabilities that can be functionally integrated with ultrasound probes in overall systems for ultrasound imaging even though they are not necessarily dedicated only to the ultrasound imaging.

[0039] The ultrasound probe 210 may comprise a portable transducer. The ultrasound probe 210 includes a transducer array 213, a lens 214, a user interface 223, a controller 250 and a wireless communication circuit 290. The transducer array 213 includes at least a first transducer element 2131, a second transducer element 2132, and an Xth transducer element 213X. The transducer array 213 converts electrical energy into sound waves which reflect off of body tissue and receives echoes of the sound waves and converts the echoes into electrical energy. The transducer array 213 may include dozens, hundreds, or thousands of individual transducer elements. The ultrasound probe 210 may transmit a beam to produce images and may detect echoes. Processor 252 may process ultrasound images captured by the transducer array 213 of the ultrasound probe 210. The lens 214 may be used to transmit the ultrasound beams and to receive echoes of ultrasound beams. User interface 223 may be used by medical personnel tointeract with the ultrasound probe 210. The wireless communication circuit 290 may be used to communicate with smartphone A and smartphone B via the network 201. The ultrasound probe 210 may be configured to link to an external device such as the smartphone A and smartphone B via applications installed on the external device(s).

[0040] Smartphone A stores and executes an ultrasound application 299A. Smartphone B stores and executes an ultrasound application 299B. The ultrasound application 299A and the ultrasound application 299B may be configured to enable smartphone A and smartphone B to interact with the ultrasound probe 210 via network 201. For example, ultrasound application 299A and ultrasound application 299B may be configured to enable displays of ultrasound images from the ultrasound probe 210. Ultrasound application 299A and ultrasound application 299B may also be configured to generate and output real-time feedback for compression quality based on interpreting each of the plurality of echocardiography images captured by the ultrasound probe 210. In some embodiments, the controller 250 may generate the output and send the output to the ultrasound application 299A and / or the ultrasound application 299B for outputting on screen(s) of smartphone A and / or smartphone B.

[0041] Controller 250 includes at least a memory 251 that stores instructions and a processor 252 that executes the instructions. Memory 251 may store one or more software program(s). The software program(s) may include signal processing techniques that aid in the detection of cardiogenic events and evaluation of the compression quality. Such software programs may include image classification models used to classify ultrasound images / pre-image data, feature detection models to detect features within the ultrasound images, segmentation models to segment cardiac structures, and / or quantification algorithms to calculate measurements that inform the user on cardiac functionality and compression quality from ultrasound images / pre- image data and / or post processed images. In FIG. 2, the user interface may be generated by the instructions stored in memory 251 and may be displayed on a display of smartphone A or smartphone B.

[0042] Controller 250 may perform some of the operations described herein directly and may implement other operations described herein indirectly. For example, controller 250 may indirectly control operations such as by generating and transmitting content to be displayed on a display of the smartphone A or smartphone B. Controller 250 may directly control otheroperations such as logical operations performed by the processor 252 executing instructions from the memory 251 based on input received from electronic elements and / or medical personnel via the interfaces. Accordingly, the processes implemented by the controller 250 when the processor 252 executes instructions from the memory 251 may include steps not directly performed by the controller 250.

[0043] The system 100 in FIG. 1 and the system 200 in FIG. 2 are provided to optimize chest compressions, such as after potential causes of cardiac arrest are ruled out. Real-time feedback may be provided to the user on the quality of the compression based on the location of compression and associated hemodynamic response. There are multiple ways to measure compression success. The system designs described herein provide solutions wherein compression success may be defined by multiple variables and each of the variables may serve as an independent measure of compression success. The result of the processing described herein may provide a user interface that supports the detection of the compression success.

[0044] The ultrasound probe 110 in FIG. 1 and the ultrasound probe 210 in FIG. 2 may operate as a CPR monitoring device to provide real-time feedback and assessment of compression quality to a user. System 100 and system 100 may operate to provide a feedback loop as compressions are applied, assessed, and corrected. Feedback may be provided in real time to users, so that compression may be adjusted as needed, whether by adjusting placement of hands / mechanical device, adjustment of compression depth, and / or adjustment of compression frequency. As an example, a feedback loop may be provided to external devices that provide information on hemodynamic parameters, automated compression machines that perform compression, and / or automated robotic systems that control imaging systems that perform echocardiography such as TEE acquisition.

[0045] The system 100 of FIG. 1 and / or the system 200 of FIG. 2 may each also include one or more controllable robot and one or more sensor. For example, the controller 150 and / or the controller 250 may provide feedback to an automatic compression device, feedback to wearable or invasive sensors monitoring hemodynamics pressures, and / or feedback to a robotic TEE imaging system for adapting echocardiography images for improved feedback. For example, system 100 and / or system 200 may include a robot such as an automated chest compression apparatus configured to perform the compression. Instructions executed by the controller 150 orthe controller 250 may further cause the system 100 or the system 200 to provide the real-time feedback for compression to the automated chest compression apparatus to adjust positioning of the compression by the automated chest compression apparatus. Another example of a robot that may be included in system 100 or the system 200 is a robotic system configured to control positioning of a source of the echocardiography images. The real-time feedback from the system 100 and / or the system 200 may include feedback to the robotic system to adjust views in the echocardiography images. A robotic system may be configured to maneuver an imaging system such as in a TEE ultrasound probe or a TTE ultrasound probe in one or more dimensions including anterior / posterior, right / left, clockwise or counterclockwise, or advance / retract. Image characteristics such as one or more imaging angles of an ultrasound imaging system may also be controlled using a robotic system. The controller 150 and / or the controller 250 may provide feedback to control maneuvering of the robotic system and a corresponding ultrasound imaging system. As another example, system 100 and / or the system 200 may include one or more sensor that interacts with the system 100 and / or the system 200. A sensor may be a sensor configured to measure hemodynamic variables of the patient and provide feedback to a controller that includes the memory and the processor. An example of such a sensor may comprise an interventional sensor configured to receive instructions from the controller to stimulate the hemodynamic variables. A sensor may also or alternatively be a wearable sensor that receives feedback from the controller 150 or the controller 250, and that provides measurements to the controller 150 or the controller 250. A sensor may also be an interventional sensor such as a Swanz-Gantz catheter for measuring / monitoring hemodynamic variables such as cardiac output or stroke volume. A sensor may also be a monitor such as a wearable for measuring and monitoring vital signs.

[0046] FIG. 3 illustrates a method for echocardiography-based resuscitative guidance, in accordance with a representative embodiment.

[0047] The method of FIG. 3 may be performed by system 100 including the controller 150 or by the system 200 including the controller 250.

[0048] At S310, an ultrasound procedure is started. The ultrasound procedure may be started for system 100 in FIG. 1 or by the system 200 in FIG. 2. The ultrasound procedure may be started at S310 by activating the ultrasound probe 110 and / or the ultrasound base 120 in FIG. 1, or by activating the ultrasound probe 210 and / or ultrasound application 299A and / or ultrasoundapplication 299B in FIG. 2. After starting the ultrasound procedure at S310, intubation assistance may be provided when the echocardiography involves TEE.

[0049] At S320, one or more echocardiography image(s) is / are received. A plurality of echocardiography images may be received by the ultrasound base 120 from the ultrasound probe 110 in FIG. 1, or by either or both of the controller 250 and / or smartphone A and / or smartphone B in FIG. 2. In FIG. 2, S320 may be performed by whichever of the controller 250 or the smartphone(s) is performing the logical processing described herein. The echocardiography image(s) may be TEE-based or TTE-based echocardiography images.

[0050] At S330, echocardiography image(s) and / or pre- imaging data are interpreted. The interpretation at S330 may help ensure that the ultrasound probe 110 or the ultrasound probe 210 is in a correct position, as such feedback may be useful in reassuring a user or prompting a user to correct the position. The interpretation at S330 may be performed before an echocardiography image is formed on the display 180 or on Smartphone A or Smartphone B, though interpretation at S330 may also include identifying and classifying anatomical features in each of a plurality of views, such as by applying an object recognition model to each echocardiography image. The interpretation at S33O may include checking that each ultrasound image is properly focused, that each ultrasound image has a proper resolution, and that each ultrasound image appears to reflect cardiological anatomy of a patient. The interpretation at S330 may also include checking for characteristics of compression, including location of compression, depth of compression, and frequency of compression. Interpretation at S330 may also include checking for different cardiological disease states and / or characteristics of cardiac standstill. Interpretation at S330 may also include quantification of hemodynamic variables to assess the quality of the compression delivered. Each of a plurality of echocardiography images may be interpreted individually or as a set. For example, a set of ultrasound images may be compared to detect differences, such as to ensure that they are not entire or substantial duplicates.

[0051] The method of FIG. 3 may also include the controller 150 or the controller 250 identifying potential causes of cardiac arrest from interpreting each of the plurality of echocardiography images. At least one potential cause of cardiac arrest may also be included in real-time feedback provided to the user performing the compression. Accordingly, real-time feedback may include a suggestion to move the anatomical location of compression to align withthe anatomical location of optimal compression that is individualized to a hemodynamic response of a patient being subjected to the compression, as well as an announcement of one or more potential causes of cardiac arrest. After interpreting the echocardiography image(s) at S330, view quality may be detected and, if the view quality is poor, guidance may be generated, and the process may return to S320. If the view quality is detected at S330 and the view quality is determined to be acceptable, the process may proceed.

[0052] At S340, an anatomical location of compression is identified. The controller 150 or the controller 250 may identify an anatomical location of optimal compression in the echocardiography images / pre-imaging data by interpreting data acquired from each of the plurality of echocardiography images / pre-image data. Anatomical location of compression may also be identified using pre-acqui sition data such as from volume imaging. The anatomical location of maximal compression may be identified as the area of the heart most prominently compressed during the compression. Quantification mechanisms for identifying the location of compression include but are not limited to volumetric changes, sonographic vector quantification which quantifies the spatial location and force delivered at the time of compression, pressure gradient quantification or mechanisms that detect for tissue deformation within a 2D or 3D volumetric imaging dataset. This may include speckle tissue tracking, tissue Doppler imaging, shear wave elastography, strain elastography, compression elastography, or tissue displacement modeling. These mechanism may also be deep learning based, such as using Left Ventricle segmentation. In addition, compression location may be identified when pairing the ultrasound device with an external device that monitors compression delivery or hemodynamic parameters. Such devices may include automated compression devices, such as a mechanical compression device or robotic devices, or a wearable or invasive device, such as a sensor, on the person providing compressions which would provide hemodynamic feedback. Mechanisms that may derive the location of the applied compression force from these devices may include gyroscopes, accelerometers, IMU, RF signaling, or other integrated sensors (force sensors, proximity sensors, light, pressure).

[0053] Although compression location identification is described primarily as being based on image feedback, compression location may also or alternatively be identified using other inputs. For example, magnitude of the force used in compression may be quantified and matched withdeformation resulting from the compression to identify location, potentially without image feedback. Pre-imaging data such as detected flow / strain measurements may be derived from radio frequency (RF) data which is part of a pre-beamformed data acquisition.

[0054] At S350, compression characteristic(s) are detected. Compression characteristics may include frequency of compression and depth of compression. Individual echocardiography images and sets of multiple echocardiography images may be assessed at S350 to assess compression depth and a rate of compression. For example, frequency may be detected from a set of multiple echocardiography images, so as to detect whether compression is being performed too quickly or too slowly. Depth may be detected to determine whether a user should be compressing a patient more or less deep.

[0055] At S360, potential corrections are selected. Potential corrections may include an adjustment to the placement of hands / mechanical device, so that compression is performed at the location of the left ventricle when the hands are not placed at the location of the left ventricle currently. Optimal placement may also or alternatively be based on a patient’s hemodynamic response, or other factors besides placement of hands relative to the left ventricle. Potential corrections may also include an adjustment to depth, such as to suggest that the compression depth be adjusted to reflect more depth or less depth. Potential corrections may also include an adjustment to frequency, such as to suggest that the compression be performed at a faster pace or a slower pace.

[0056] At S370, feedback is generated. The feedback may be visual and / or may be audible. The feedback may indicate where the compression is being placed currently and suggest that a user move hands in one or more direction(s) and by how much, such as left 3 cm, or down 3 cm. The feedback may suggest that compression be performed more or less quickly, such as once per second. The feedback for frequency may be audible and / or visual and may also indicate how fast the compression is being performed currently. Thus, the feedback for frequency may indicate please increase the rate from once per two seconds to once per second.

[0057] At S380, echocardiography image(s) and feedback are output. The echocardiography image(s) are output visually, such as via the display 180 or on user interfaces of smartphone A and / or smartphone B. The feedback may be output visually and / or audibly. For example, instructions to adjust locations of hands or speed or slow the compression and / or compressdeeper or shallower may be audible and visual, or simply audible or visual.

[0058] While the steps of FIG. 3 are shown as a method flow, some, or all of the steps in FIG. 3 may be performed in a different order or simultaneously. For example, echocardiography image(s) may be received one at a time and individually processed so that a first echocardiography image is being interpreted at S330 as a second echocardiography image is being received at S320. The output at S380 may be performed more than once, such as every two seconds or every five seconds to indicate adjustments to the compression being performed.

[0059] FIG. 4 illustrates another method for echocardiography -based resuscitative guidance, in accordance with a representative embodiment.

[0060] In FIG. 4, a feedback loop is provided when compressions are applied, assessed, and corrected. Feedback is provided to the user in real-time. As compression is applied, data is acquired and fed into an algorithm implemented by the controller 150, the controller 250, or smartphone A or smartphone B as representatives of networked / networkable mobile devices with logical processing capabilities. The algorithm classifies the quality of the compression. Data of poor compressions may be fed into a compression correction algorithm to determine how the compression should be corrected, and any suggestion(s) is or are communicated to the user as a recommendation.

[0061] In more detail, compression is applied by a user at S410. Data acquisition is input at S420. The compression is classified at S430, such as by a first algorithm that classifies quality of the compression. When the compression is classified as bad, a compression correction algorithm is applied at S440 to determine how the compression should be corrected. When the compression is classified as good, the system 100 or the system 200 may output reassurance to the user that the compression is being performed well. When the compression is classified as bad, the feedback to the user S450 is part of a loop so that the compression applied next at S410 may reflect the recommendations from the system 100 or the system 200 as to how to correct the compression. The method of FIG. 4 is a real-time compression feedback method and may be performed during focused TEE or otherwise during TTE.

[0062] A classification model may be used to detect location and quality of compression. The classification model may include an input layer, hidden layers, and an output layer with an activation function. The output layer may output indications of whether compression is good orbad, and an output of bad compression may be used as an input to a separate optimization algorithm that provides compression correction and user feedback. The feedback may be used in a loop to review chest compression quality and improve the chest compression quality when potential improvements are identified.

[0063] A detailed mechanism for compression detection, classification, and optimization feedback is next shown and explained with respect to FIG. 5. In FIG. 5, compression optimization feedback may be performed using a deep-learning mechanism. In other embodiments, alternative signal processing techniques may be used to perform the compression optimization feedback in FIG. 5.

[0064] FIG. 5 illustrates a method for echocardiography-based resuscitative guidance, in accordance with a representative embodiment.

[0065] FIG. 4 intends to illustrate an overview concept of a real-time compression feedback system. FIG. 5 provides a detailed explanation of one way in which this may be achieved. FIG. 5 is representative of a detailed example of FIG. 4. The following diagram shows an example of how this may work. As the user applies compression / decompression, image data is acquired from the system and features of the compression are computed as an input vector into the first system (x = [xl, x2, x3, xn]) where each independent variable xn contains information regarding compression quality. These parameters can then be fed into a classification algorithm, such as a deep learning algorithm that outputs a binary classified on compression quality (good / poor). The output of this step is a binary classification Y of compression quality whether it is good or poor. Poor compressions (Y=l) are sent through a secondary model that determines how the compressions should be corrected and communicates this to the user in real-time.

[0066] In FIG. 5, a user applies chest compression and decompression at S510. Data is received on the compression and decompression and a set of input features are extracted from the dataset to assess compression and decompression quality.

[0067] At S520, inputs to a classification algorithm are computed based on compression and decompression. Multiple different inputs may be computed including at different points in time during compression and decompression and including diverse types of inputs.

[0068] At S530, a classification algorithm is applied to detect location and quality of the compression. The classification algorithm may include a trained machine learning model with aninput layer, one or more hidden layers, and an output layer. The trained machine learning model may include a deep neural network for the hidden layers. The classification algorithm outputs either a good classification or a bad classification at S535 as a result of an activation function.

[0069] At S540, the system 100 or the system 200 computes a correction. The correction may be computed at S540 by an optimization algorithm that provides compression corrections and user feedback.

[0070] At S550, feedback to correct the compression is provided to the user from the optimization algorithm executed by system 100 or system 200. The feedback is provided to correct the compression when the algorithm outputs a bad classification. In FIG. 5, the method may be performed using a first subsystem and a second subsystem. The first subsystem may use an Artificial Neural network to assess compression quality. For example, a multilayer perceptron model with backpropagation or a convolutional neural network (CNN) may be used as the first subsystem.

[0071] The method of FIG. 5 may be performed by the controller 150 or the controller 250 and may involve a single integrated system implemented by a single algorithm or two separate subsystems implemented by different algorithms. A first subsystem may detect location and quality of compression using a deep learning classification algorithm as shown for S53O in FIG. 5. The deep learning classification model illustrates a feedback loop for monitoring compression quality. Several inputs may serve as independent variables for monitoring compression quality. In FIG. 5, the inputs serving as independent variables include xl for identifying an area of maximal compression; x2 for calculating hemodynamic variables, x3 for classifying image features in each of a plurality of views such as ResusTEE views; x4 for assessing compression depth and rate; and xn for other potential inputs. The output of the model makes a decision on the compression quality based on the inputs. This output from the classification model may be a binary classifier Y of compression as either a good compression classification or a bad compression classification.

[0072] A second algorithm may be applied to identify an optimal compression location and characteristics, and to correct the user. Compressions classified as bad compressions may be fed into a secondary model that assesses how the compressions could be corrected. The secondary model may use a deep learning algorithm and may relay this information to the user in real-timeas the compressions are being delivered. The secondary optimization model may be machine learning based, such as a backpropagation algorithm that leverages stochastic gradient descent to iteratively update the learning rate and vector weights to identify the optimum compression location / quality. The user may be provided with real-time feedback as to whether they are compressing in the correct location and may also be provided feedback as to compression quality based on compression depth, rate, and location that are tailored to the patient’s hemodynamic response.

[0073] FIG. 6 illustrates a user interface for echocardiography -based resuscitative guidance, in accordance with a representative embodiment.

[0074] FIG. 6 illustrates three user interfaces including a first user interface 681 A, a second user interface 68 IB and a third user interface 681C. The three user interfaces in FIG. 6 illustrate how compression feedback may be detected and provided in a scenario of aortic root compression.

[0075] The user interface in FIG. 6 illustrates a concept of how compression feedback may be provided in a scenario where compression is taking place in an improper location. The three user interfaces follow a user interface workflow to showcase an example scenario of aortic root compression in the mid-esophageal long axis view. The first user interface 681A is from an image taken in a relaxed state and includes automated cardiac chamber labelling. The second user interface 68 IB is from an image taken in a compression state in which a CPR detector is enabled. The ascending aorta is narrowing in the image on the second user interface 68 IB as the compression phase progresses and the right ventricle deforms. Morphological changes in the heart associated with good / poor compression are detected. The second user interface 68 IB warns the user to indicate improper compression is being applied and redirects the user towards an area of proper compression, such as the left ventricle. The third user interface 681C notifies the user that the area of maximal compression is detected at the ascending aorta which has collapsed completely and redirects the user towards the proper compression location in real-time.

[0076] Before proceeding, a detailed explanation of how inputs may be determined is provided next. The process of determining inputs may include broadly identifying an area of maximal compression, calculating hemodynamic variables to assess the quality of compression / decompression being delivered, image classification for cardiac features associated with compression / decompression performance, and detection of compression depth andfrequency.

[0077] Identifying an area of maximal compression may involve defining an area of maximal compression and quantifying an area of maximal compression among candidates. The area of maximal compression may be defined as the area of the heart most prominently compressed at the end of the compression phase. Quantification mechanisms may be based on, for example, sonographic compression vector quantification, pressure gradient mechanisms or similar tissue deformation detection mechanisms, calculated distance from an aortic root, or left ventricle segmentation. Sonographic compression vector quantification quantifies the spatial location and force delivered at the time of compression. Tissue deformation detection mechanisms other than pressure gradient mechanisms may include speckle tissue tracking, sheer wave elastography, compression elastography, or tissue Doppler imaging. Calculation of the distance from the aortic root is in m-mode. Left ventricle segmentation may be performed using neural networks.

[0078] Calculating hemodynamic variables may broadly include calculations during the compression phase and quantitative measurements of quality decompression. Examples of relevant TEE views which may be used to measure quality of compression include the TEE ME 4C view, the TEE ME RV Inflow-Outflow view, or the TEE Bicaval view. General measurements may be taken in all views. Deviation from the mean of these measurements may inform the model on the quality of hemodynamic response.

[0079] As an example of how a model may be applied in a feedback loop for how measurements can guide compression improvement, a first step may involve detecting whether an area of maximal compression is over the atria of a patient to check the quality of compression. Checks may also be made for compression depth to optimize the compression depth. Chest recoil may be checked for slow or incomplete recoil so that chest recoil may be optimized. A second step may involve additional checks such as for whether a left ventricle is obstructed as an indication of ineffective cardiopulmonary resuscitation.

[0080] In the TEE ME 4C view, measurements may be taken of: i. a two-dimensional (2D) right ventricle (RV) fractional area of change (FAC) calculated as: [end diastolic area - end systolic area) / end-diastolic area xl00]. This is used to estimate the right ventricle (RV) function. The normal value right ventricle (RV) systolic function is 35% and the mean value of the fractional area of change (FAC) under chest compression is 59.6%;ii. a right ventricle (RV) lateral wall excursion (LWE) is measured in M-mode. iii. a left ventricle (LV) ejection fraction is measured to estimate left ventricle (LV) function calculated as: [(EDV - ESV) / EDV x 100], The mean value of LV-EF under chest compression is 53.5%; iv. left ventricle (LV) fractional area of change (FAC).

[0081] In the TEE ME RV Inflow-Outflow view, compression of the RVOT is assessed. RVOT fractional shortening (FS) is measured in M-mode. The mean value of RVOT-FS under chest compression is 45.3% (22.8-64.2%). These measurements may be used in a feedback loop to improve compression quality.

[0082] In the TEE Bicaval view, atrial compression is assessed. The assessment in the TEE Bicaval view may include identifying an area of maximal compression at xi, and the excursion of the right atrial wall under compression as observed through m-mode.

[0083] General measurements in all views may include cardiac output and stroke volume.

[0084] The quantitative measurements of the quality of decompression may include chest recoil quality. Good chest recoil creates negative intrathoracic pressure and creates lowered right atrial (RA) pressure. Mechanisms to detect changes in pressure may be Doppler based or quantitative in nature. Also, or alternatively, quantitative measurements may include, for example, looking for excursion of the right ventricle (RV) lateral wall shift, depression speed (DS), and / or relaxation time during decompression in m-mode in the TEE Mid-Esophageal 4 Chamber view.

[0085] Image classification for cardiac features associated with compression / decompression performance is explained next with respect to FIG. 7.

[0086] FIG. 7 illustrates model development and deployment for echocardiography -based resuscitative guidance, in accordance with a representative embodiment.

[0087] As set forth herein, defining compression quality may involve a multi-variable decision based on a series of inputs x=xl,x2,x3...xn. One of the inputs, x3, may define compression quality based on morphological changes within the heart that are indicative signs of good vs. poor compression. FIG. 7 illustrates a means of model development and deployment to determine this variable. The algorithm in FIG. 7 may represent one of the many steps involved in the “Computing inputs” step in FIG. 5. To develop the algorithm in FIG. 7, an annotated dataset of pre-labelled images associated with good / poor compression quality may be used to train animage classification algorithm to detect for signs of good / poor compression quality. Once the model is deployed, the model may be given an image associated with aortic root obstruction. In FIG. 7 the model detects the input image as a sign of Poor compression quality and assigns the output variable x3 = poor. This variable can then be fed into the compression classification algorithm in FIG. 5, where multiple inputs related to compression quality are used to make a binary classification on compression quality.

[0088] A deployed model shown at S730 on the right side of FIG. 7 is an example of a model for classifying good / poor compression quality. An image processing algorithm used by the deployed model may identify features indicating good quality compression or poor-quality compression and decompression of the cardiac chambers in all relevant imaging planes associated with echocardiograph resuscitation protocols such as for TEE. Classification may be performed through tissue tracking algorithms, deep learning image classification algorithms or any quantification mechanism that detects for morphological changes in cardiac chambers and trains a model for signs of good or poor compression quality. In general, signs of good compression include ventricular collapse and LVOT opening while signs of poor compression include collapse of the LVOT / AO during compression.

[0089] The set of six ultrasound images on the user interface 781 in FIG. 7 may represent a training dataset for a compression quality classification algorithm used for a model to be deployed. These images may be acquired from a dataset, pre-processed, and annotated for relevant features related to compression quality, denoted as an asterisk. The six images in the training set on user interface 781 are labelled in order C, D, E, F, G and H. Images in the training dataset on the user interface 781 are in the mid-esophageal long axis plane in a patient undergoing cardiac arrest CPR. The first three images (C, D, E) illustrate signs of good compression / decompression and the second set (F, G, H) shows signs of poor compression / decompression. The first image labeled C is for image classification features of good decompression. The first image is of a left ventricle during the decompression phase with mitral valve open (asterisk). The second image labeled D is for appropriate early left ventricle (LV) compression (asterisk) with no obstruction of the LVOT or aortic root. The third image labeled E is for aortic valve open (asterisk) during remainder of a compression phase, allowing stroke volume to be detected

[0090] The fourth image labeled F, the fifth image labeled G and the sixth image labeled H on the user interface 781 are for signs of poor decompression. These images depict an example of complete obstruction of the aortic root during the compression phase of CPR, effectively impeding forward blood flow. Asterisks show the location of the aortic root as it is progressively obstructed during the compression phase. As illustrated in FIG. 7, these features associated with good / poor compression decompression on an annotated dataset may be fed into a deep learning algorithm that utilizes supervised learning to detect these features. Once this algorithm has been successfully developed, it can take in new images during CPR and classify the compression / decompression quality based on morphological changes in the heart. The output of this classifier may be fed into an input node x3 wherein x3 represents the classification characteristics of good / poor compression / decompression. For example, x3 may be a subset of input parameters [xl, x2, x3.. .. xn] assessed to provide an overall classifier of compression quality.

[0091] At S702, the training dataset represented by the six images on the user interface 781 is classified and used for model development. At S730, the model is deployed. The inputs to the deployed model may be real image data deployed during resuscitation activities for patients. The deployed output may output binary classifications such as poor or good in FIG. 7. A poor classification will result in feedback and may be based on the x3 subset of input parameters. A good classification may result in reassurance. The deployed model may be used in a feedback loop so that feedback from poor classifications may be used to adjust the compression / decompression being performed, and the adjusted compression / decompression will be captured in real image data and again input to the deployed model at S730. Feedback may be provided audibly or visually, such as via audible language announcements, tones, or other mechanisms for communicating suggestions for adjustments.

[0092] Compression depth and frequency may also be detected. Current resuscitation guidelines recommend a compression depth of at least 5 cm but no more than 6 cm and rate of between 100 to 120 compressions per minute, allowing chest recoil between compressions. Detection of compression depth and frequency may be achieved through deformation measurement methods, such as tissue tracking, measuring changes in volume, Doppler imaging, compression elastography, or simplified accelerometer methods.

[0093] FIG. 8 illustrates a computer system, on which a method for echocardiography -based resuscitative guidance is implemented, in accordance with another representative embodiment.

[0094] Referring to FIG. 8, computer system 800 includes a set of software instructions that can be executed to cause the computer system 800 to perform any of the methods or computer-based functions disclosed herein. The computer system 800 may operate as a standalone device or may be connected, for example, using a network 801, to other computer systems or peripheral devices. In embodiments, a computer system 800 performs logical processing based on digital signals received via an analog-to-digital converter.

[0095] In a networked deployment, the computer system 800 operates in the capacity of a server or as a client user computer in a server-client user network environment, or as a peer computer system in a peer-to-peer (or distributed) network environment. The computer system 800 can also be implemented as or incorporated into various devices, such as a workstation that includes a controller, a stationary computer, a mobile computer, a personal computer (PC), a laptop computer, a tablet computer, or any other machine capable of executing a set of software instructions (sequential or otherwise) that specify actions to be taken by that machine. The computer system 800 can be incorporated as or in a device that in turn is in an integrated system that includes additional devices. In an embodiment, the computer system 800 can be implemented using electronic devices that provide voice, video, or data communication. Further, while the computer system 800 is illustrated in the singular, the term “system” shall also be taken to include any collection of systems or sub-systems that individually or jointly execute a set, or multiple sets, of software instructions to perform one or more computer functions.

[0096] As illustrated in FIG. 8, the computer system 800 includes a processor 810. Processor 810 may be considered a representative example of a processor of a controller and executes instructions to implement some, or all aspects of methods and processes described herein. The processor 810 is tangible and non -transitory. As used herein, the term “non-transitory” is to be interpreted not as an eternal characteristic of a state, but as a characteristic of a state that will last for a period. The term “non-transitory” specifically disavows fleeting characteristics such as characteristics of a carrier wave or signal or other forms that exist only transitorily in any place at any time. The processor 810 is an article of manufacture and / or a machine component. Processor 810 is configured to execute software instructions to perform functions as described inthe various embodiments herein. The processor 810 may be a general-purpose processor or may be part of an application specific integrated circuit (ASIC). The processor 810 may also be a microprocessor, a microcomputer, a processor chip, a controller, a microcontroller, a digital signal processor (DSP), a state machine, or a programmable logic device. The processor 810 may also be a logical circuit, including a programmable gate array (PGA), such as a field programmable gate array (FPGA), or another type of circuit that includes discrete gate and / or transistor logic. The processor 810 may be a central processing unit (CPU), a graphics processing unit (GPU), or both. Additionally, any processor described herein may include multiple processors, parallel processors, or both. Multiple processors may be included in, or coupled to, a single device or multiple devices.

[0097] The term “processor” as used herein encompasses an electronic component able to execute a program or machine executable instruction. References to a computing device comprising “a processor” should be interpreted to include more than one processor or processing core, as in a multi-core processor. A processor may also refer to a collection of processors within a single computer system or distributed among multiple computer systems. The term computing device should also be interpreted to include a collection or network of computing devices each including a processor or processors. Programs have software instructions performed by one or multiple processors that may be within the same computing device or which may be distributed across multiple computing devices.

[0098] The computer system 800 further includes a main memory 820 and a static memory 830, where memories in the computer system 800 communicate with each other and the processor 810 via a bus 808. Either or both of the main memory 820 and the static memory 830 may be considered representative examples of a memory of a controller, and store instructions used to implement some, or all aspects of methods and processes described herein. Memories described herein are tangible storage mediums for storing data and executable software instructions and are non-transitory during the time software instructions are stored therein. As used herein, the term “non-transitory” is to be interpreted not as an eternal characteristic of a state, but as a characteristic of a state that will last for a period. The term “non-transitory” specifically disavows fleeting characteristics such as characteristics of a carrier wave or signal or other forms that exist only transitorily in any place at any time. The main memory 820 and the static memory830 are articles of manufacture and / or machine components. The main memory 820 and the static memory 830 are computer-readable mediums from which data and executable software instructions can be read by a computer (e.g., the processor 810). Each of the main memory 820 and the static memory 830 may be implemented as one or more of random access memory (RAM), read only memory (ROM), flash memory, electrically programmable read only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, a hard disk, a removable disk, tape, compact disk read only memory (CD-ROM), digital versatile disk (DVD), floppy disk, blu-ray disk, or any other form of storage medium known in the art. The memories may be volatile or non-volatile, secure and / or encrypted, unsecure and / or unencrypted.

[0099] “Memory” is an example of a computer-readable storage medium. Computer memory is any memory which is directly accessible to a processor. Examples of computer memory include, but are not limited to RAM memory, registers, and register files. References to “computer memory” or “memory” should be interpreted as possibly being multiple memories. The memory may for instance be multiple memories within the same computer system. The memory may also be multiple memories distributed amongst multiple computer systems or computing devices.

[0100] As shown, the computer system 800 further includes a video display unit 850, such as a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid-state display, or a cathode ray tube (CRT), for example. Additionally, the computer system 800 includes an input device 860, such as a keyboard / virtual keyboard or touch-sensitive input screen or speech input with speech recognition, and a cursor control device 870, such as a mouse or touch-sensitive input screen or pad. The computer system 800 also optionally includes a disk drive unit 880, a signal generation device 890, such as a speaker or remote control, and / or a network interface device 840.

[0101] In an embodiment, as depicted in FIG. 8, the disk drive unit 880 includes a computer- readable medium 882 in which one or more sets of software instructions 884 (software) are embedded. The sets of software instructions 884 are read from the computer-readable medium 882 to be executed by the processor 810. Further, the software instructions 884, when executed by the processor 810, perform one or more steps of the methods and processes as described herein. In an embodiment, the software instructions 884 reside all or in part within the main memory 820, the static memory 830 and / or the processor 810 during execution by the computersystem 800. Further, the computer-readable medium 882 may include software instructions 884 or receive and execute software instructions 884 responsive to a propagated signal, so that a device connected to a network 801 communicates voice, video, or data over the network 801. The software instructions 884 may be transmitted or received over network 801 via the network interface device 840.

[0102] In an embodiment, dedicated hardware implementations, such as application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), programmable logic arrays and other hardware components, are constructed to implement one or more of the methods described herein. One or more embodiments described herein may implement functions using two or more specific interconnected hardware modules or devices with related control and data signals that can be communicated between and through the modules. Accordingly, the present disclosure encompasses software, firmware, and hardware implementations. Nothing in the present application should be interpreted as being implemented or implementable solely with software and not hardware such as a tangible non-transitory processor and / or memory.

[0103] In accordance with various embodiments of the present disclosure, the methods described herein may be implemented using a hardware computer system that executes software programs. Further, in an exemplary, non-limited embodiment, implementations can include distributed processing, component / object distributed processing, and parallel processing. Virtual computer system processing may implement one or more of the methods or functionalities as described herein, and a processor described herein may be used to support a virtual processing environment.

[0104] Accordingly, echocardiography-based compression guidance enables real time assessment and feedback of cardiopulmonary compression quality based on anatomical location of compression, depth of compression, frequency of compression, hemodynamic measurements, and / or anatomical images. The assessment and feedback may be provided to optimize coronary perfusion and individualize chest compression in CPR for a patient. Echocardiography -based assessment and compression guidance may be used to provide an efficient user experience to support resuscitation efforts by optimizing the quality of chest compressions for improved patient survival. For example, echocardiography -based compression guidance may be particularly useful for patients undergoing cardiac or high-risk surgery and post-surgery in the 1cardiac or surgical ICU as they are already intubated.

[0105] Although echocardiography -based compression guidance has been described with reference to several exemplary embodiments, it is understood that the words that have been used are words of description and illustration, rather than words of limitation. Changes may be made within the purview of the appended claims, as presently stated, and as amended, without departing from the scope and spirit of echocardiography-based compression guidance in its aspects. Although echocardiography-based compression guidance has been described with reference to particular means, materials and embodiments, echocardiography-based compression guidance is not intended to be limited to the particulars disclosed; rather echocardiography-based compression guidance extends to all functionally equivalent structures, methods, and uses such as are within the scope of the appended claims.

[0106] The illustrations of the embodiments described herein are intended to provide a general understanding of the structure of the various embodiments. The illustrations are not intended to serve as a complete description of all of the elements and features of the disclosure described herein. Many other embodiments may be apparent to those of skill in the art upon reviewing the disclosure. Other embodiments may be utilized and derived from the disclosure, such that structural and logical substitutions and changes may be made without departing from the scope of the disclosure. Additionally, the illustrations are merely representational and may not be drawn to scale. Certain proportions within the illustrations may be exaggerated, while other proportions may be minimized. Accordingly, the disclosure and the figures are to be regarded as illustrative rather than restrictive.

[0107] One or more embodiments of the disclosure may be referred to herein, individually and / or collectively, by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any particular invention or inventive concept. Moreover, although specific embodiments have been illustrated and described herein, it should be appreciated that any subsequent arrangement designed to achieve the same or similar purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all subsequent adaptations or variations of various embodiments. Combinations of the above embodiments, and other embodiments not specifically described herein, will be apparent to those of skill in the art upon reviewing the description.

[0108] The Abstract of the Disclosure is provided to comply with 37 C.F.R. § 1.72(b) and is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, various features may be grouped together or described in a single embodiment for the purpose of streamlining the disclosure. This disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter may be directed to less than all of the features of any of the disclosed embodiments. Thus, the following claims are incorporated into the Detailed Description, with each claim standing on its own as defining separately claimed subject matter.

[0109] The preceding description of the disclosed embodiments is provided to enable any person skilled in the art to practice the concepts described in the present disclosure. As such, the above disclosed subject matter is to be considered illustrative, and not restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other embodiments which fall within the true spirit and scope of the present disclosure. Thus, to the maximum extent allowed by law, the scope of the present disclosure is to be determined by the broadest permissible interpretation of the following claims and their equivalents and shall not be restricted or limited by the foregoing detailed description.

Claims

CLAIMS1. An ultrasound system (100 / FIG. 2), comprising: a memory (151 / 251) that stores instructions; and a processor (152 / 252) that executes the instructions, wherein, when executed by the processor, the instructions cause the ultrasound system to: receive (S320) a plurality of echocardiography images while compression is being performed; interpret (S330) each of the plurality of echocardiography images; output (S380) each of the plurality of echocardiography images; and generate (S370) and output (S380) real-time feedback for compression quality based on interpreting each of the plurality of echocardiography images.

2. The ultrasound system of claim 1, wherein, when executed by the processor, the instructions cause the ultrasound system further to: identify (S340) an anatomical location of compression and assess the compression quality from interpreting each of the plurality of echocardiography images, wherein the compression quality is based on at least one of the anatomical location of compression, depth of the compression, frequency of the compression, hemodynamic measurements, or anatomical images.

3. The ultrasound system of claim 2, wherein the real-time feedback is provided to optimize coronary perfusion and individualize cardiopulmonary resuscitation for a patient being subjected to the compression.

4. The ultrasound system of claim 1, wherein, when executed by the processor, the instructions cause the ultrasound system further to: identify (S340) an anatomical location of optimal compression in the echocardiography images from interpreting each of the plurality of echocardiography images.

5. The ultrasound system of claim 4, wherein, when executed by the processor, the instructions cause the ultrasound system further to: identify (S340) a location of compression in the echocardiography images from interpreting each of the plurality of echocardiography images, wherein the real-time feedback is provided based on an anatomical location of optimal compression as compared to the anatomical location of the compression.

6. The ultrasound system of claim 5, wherein the real-time feedback comprises a suggestion to move the anatomical location of the compression to align with the anatomical location of optimal compression that is individualized to a hemodynamic response of a patient being subjected to the compression.

7. The ultrasound system of claim 1, wherein, when executed by the processor, the instructions cause the ultrasound system further to: identify (S330) potential causes of cardiac arrest from interpreting each of the plurality of echocardiography images; and include at least one potential cause of cardiac arrest in the real-time feedback.

8. The ultrasound system of claim 1, wherein, when executed by the processor, the instructions cause the ultrasound system further to: identify (S360) which of a plurality of potential corrections to output as feedback for compression quality based on interpreting each of the plurality of echocardiography images.

9. The ultrasound system of claim 1, wherein interpreting each of the plurality of echocardiography images includes identifying an area of maximal compression.

10. The ultrasound system of claim 1, wherein interpreting each of the plurality of echocardiography images includes calculating at least one hemodynamic variable.

11. The ultrasound system of claim 1, wherein interpreting each of the plurality of echocardiography images includes classifying anatomical features in each of a plurality of views.

12. The ultrasound system of claim 1, wherein, when executed by the processor, the instructions cause the ultrasound system further to: detect (S350) compression characteristics from the plurality of echocardiography images by assessing compression depth and a rate of compression.

13. The ultrasound system of claim 1, further comprising: a display (180 / Smartphone A and / or Smartphone B) for displaying the plurality of echocardiography images and the real-time feedback for compression quality.

14. A method of operating an ultrasound system comprising a memory that stores instructions and a processor that executes the instructions, the method comprising: receiving (S320) a plurality of echocardiography images while compression is being performed; interpreting (S330) each of the plurality of echocardiography images; outputting (S380) each of the plurality of echocardiography images; and generating (S370) and outputting (S380) real-time feedback for compression quality based on interpreting each of the plurality of echocardiography images.

15. The method of claim 14, further comprising: identifying (S340) an anatomical location of compression and assessing the compression quality from interpreting each of the plurality of echocardiography images, wherein the compression quality is based on at least one of the anatomical location of compression, depth of the compression, frequency of the compression, hemodynamic measurements, or anatomical images, and wherein the real-time feedback is provided to optimize coronary perfusion and individualize cardiopulmonary resuscitation for a patient being subjected to the compression.

16. The method of claim 14, further comprising: identifying (S360) an anatomical location of optimal compression in the echocardiography images from interpreting each of the plurality of echocardiography images; and identifying (S340) an anatomical location of compression in the echocardiography images from interpreting each of the plurality of echocardiography images, wherein the real-time feedback is provided based on the anatomical location of optimal compression and the anatomical location of compression, wherein the real-time feedback comprises a suggestion to move the anatomical location of compression to align with the anatomical location of optimal compression based on a hemodynamic response of a patient being subjected to the compression.

17. The method of claim 14, further comprising: identifying potential causes of cardiac arrest from interpreting each of the plurality of echocardiography images.

18. The method of claim 14, further comprising: identifying (S360) which of a plurality of potential corrections to output as feedback for compression quality based on interpreting each of the plurality of echocardiography images.

19. The method of claim 14, wherein interpreting each of the plurality of echocardiography images includes at least one of identifying an area of maximal compression, calculating at least one hemodynamic variable, classifying anatomical features in each of a plurality of views, or assessing compression depth and a rate of compression.

20. A tangible, non-transitory computer-readable medium that stores instructions, which when executed by a processor, cause the processor to: receive (S320) a plurality of echocardiography images while compression is being performed; interpret (S330) each of the plurality of echocardiography images; output (S380) each of the plurality of echocardiography images; andgenerate (S370) and output (S380) real-time feedback for compression quality based on interpreting each of the plurality of echocardiography images.

21. The ultrasound system of claim 1, further comprising: an automated chest compression apparatus configured to perform the compression, wherein the instructions further cause the ultrasound system to provide the real-time feedback for compression to the automated chest compression apparatus to adjust positioning of the compression by the automated chest compression apparatus.

22. The ultrasound system of claim 1, further comprising: a robotic system configured to control positioning of a source of the echocardiography images, wherein the real-time feedback also includes feedback to the robotic system to adjust views in the echocardiography images.

23. The ultrasound system of claim 1, further comprising: a sensor configured to measure hemodynamic variables of a patient and provide feedback to a controller that includes the memory and the processor.

24. The ultrasound system of claim 23, wherein the sensor comprises an interventional sensor configured to receive instructions from the controller to stimulate the hemodynamic variables.

Images