Resuscitation guidance based on tee

Abstract

An ultrasound system for resuscitation transesophageal echocardiography includes a memory storing instructions and a processor executing the instructions. When executed by the processor, the instructions cause the ultrasound system to perform the following operations: receive multiple transesophageal echocardiogram images during resuscitation transesophageal echocardiography; interpret each of the multiple transesophageal echocardiogram images; output each of the multiple transesophageal echocardiogram images; and generate and output guidance for capturing additional transesophageal echocardiogram images based on the interpretation of each of the multiple transesophageal echocardiogram images.

Description

[0001] Government rights This invention was carried out with the support of the United States government, granted by the U.S. Department of Health and Human Services under authorization number HHS / ASPR / BARDA75A50120C00097. The United States enjoys certain rights to this invention. Background Technology

[0002] Cardiac arrest is a leading cause of death worldwide, with out-of-hospital survival rates often below 10%. For in-hospital patients, echocardiography is sometimes used as a bedside modality to determine the cause of cardiac arrest and guide cardiac arrest resuscitation (CAR). Transesophageal echocardiography (TEE) is a form of echocardiography that involves inserting a specialized probe with an ultrasound transducer through the patient's mouth and into the esophagus to monitor the heart. Transthoracic echocardiography (TTE) is another form of echocardiography that involves placing a specialized probe with an ultrasound transducer on the patient's chest or abdomen to monitor the heart. The use of TEE in cardiac arrest resuscitation (CAR) has been shown to have clinically impactful outcomes for critically ill and hemodynamically unstable patients in extreme conditions compared to TTE. TEE can guide the resuscitation process by optimizing chest compressions, minimizing chest compression interruptions, and reducing CPR interruptions. TEE also provides continuous monitoring of cardiopulmonary activity, unobstructed observation of continuous myocardial activity, and superior image quality for diagnosing disease states and identifying potential reversible causes of cardiac arrest. While TEE is considered a standard of care for improving resuscitation outcomes, current barriers to its introduction into emergency resuscitation include a lack of technical experience and time pressure to incorporate TEE into practice within workflows. For example, it can be difficult to quickly obtain appropriate views and images, especially for inexperienced users.

[0003] In emergency medicine and intensive care settings, healthcare professionals can utilize focused cardiac ultrasound (FoCUS) as a goal-oriented framework to rapidly determine the cause of cardiac arrest and guide resuscitation. In these settings, transthoracic echocardiography (TEE) is relatively focused, and compared to the 28 views used by experienced healthcare professionals in non-emergency and non-intensive care practice, TEE use may involve 4 to 12 views in a resuscitation TEE protocol (for a goal-oriented protocol recommended by ACEP). Transthoracic echocardiography (TTE) via FoCUS is the most commonly used diagnostic modality by emergency physicians today, but it has significant limitations in managing critically ill patients who have experienced cardiac arrest.

[0004] Automated software solutions can improve workflow efficiency and clinical performance in cardiac ultrasound. Spatial orientation and a thorough understanding of cardiac anatomy are fundamental to TEE acquisition capabilities. Inexperienced users often encounter difficulties transitioning from TTE to TEE due to differences in spatial orientation. For example, the mid-esophageal four-chamber view in TEE is a posterior equivalent of the apical four-chamber view in TTE, and the mid-esophageal long-axis view is a mirror image of the parasternal long-axis (PLAX) view. Inexperienced users also struggle to obtain the appropriate acoustic window for TEE imaging due to a lack of the required fine motor skills. There is an urgent need to develop appropriate TEE applications for bedside users in emergency medicine and intensive care settings to address situations with tight examination times, the need for immediate decision-making, and significant differences in user experience. Summary of the Invention

[0005] According to one aspect of this disclosure, an ultrasound system for resuscitation transesophageal echocardiography includes a memory storing instructions and a processor executing the instructions. When executed by the processor, the instructions cause the ultrasound system to: receive a plurality of transesophageal echocardiogram images during resuscitation transesophageal echocardiography; interpret each of the plurality of transesophageal echocardiogram images; output each of the plurality of transesophageal echocardiogram images; and generate and output guidance for capturing additional transesophageal echocardiogram images based on the interpretation of each of the plurality of transesophageal echocardiogram images.

[0006] According to another aspect of this disclosure, a method of operating an ultrasound system for resuscitation transesophageal echocardiography, the ultrasound system including a memory storing instructions and a processor executing the instructions, the method including receiving a plurality of transesophageal echocardiography images during resuscitation transesophageal echocardiography. The method further includes: interpreting each transesophageal echocardiography image from the plurality of transesophageal echocardiography images; outputting each transesophageal echocardiography image from the plurality of transesophageal echocardiography images; and generating and outputting guidance for capturing additional transesophageal echocardiography images based on the interpretation of each transesophageal echocardiography image from the plurality of transesophageal echocardiography images.

[0007] According to another aspect of this disclosure, a tangible, non-transient computer-readable medium stores instructions for transesophageal echocardiography. When executed by a processor, these instructions cause the processor to perform the following operations: receive multiple transesophageal echocardiogram images during resuscitation transesophageal echocardiography; interpret each of the multiple transesophageal echocardiogram images; output each of the multiple transesophageal echocardiogram images; and generate and output instructions for capturing additional transesophageal echocardiogram images based on the interpretation of each of the multiple transesophageal echocardiogram images. Attached Figure Description

[0008] The exemplary embodiments can be best understood in conjunction with the accompanying drawings and the following detailed description. It should be emphasized that the various features are not necessarily drawn to scale. In fact, dimensions may be arbitrarily increased or decreased for clarity of discussion. In all applicable and feasible instances, the same reference numerals refer to the same elements.

[0009] Figure 1 The illustration shows a system for TEE-based recovery guidance according to a representative embodiment.

[0010] Figure 2 Another system for TEE-based recovery guidance is illustrated according to a representative embodiment.

[0011] Figure 3 The illustration depicts a method for TEE-based recovery guidance according to a representative embodiment.

[0012] Figure 4A The illustration shows a user interface in a TEE-based recovery guide according to a representative embodiment.

[0013] Figure 4B The illustration shows another user interface in a TEE-based recovery guide according to a representative embodiment.

[0014] Figure 4C The illustration depicts a hybrid process for TEE-based recovery guidance according to a representative embodiment.

[0015] Figure 5 The illustration shows a user interface according to a representative embodiment, which displays a table with a corresponding set of information for TEE-based recovery guidance.

[0016] Figure 6 The illustration shows a computer system according to another representative embodiment, on which a method for TEE-based recovery guidance is implemented. Detailed Implementation

[0017] In the following detailed description, representative embodiments with specific details disclosed are set forth for purposes of explanation and not limitation to provide a thorough understanding of embodiments according to this teaching. However, other embodiments consistent with the disclosure of this invention but departing from the specific details disclosed herein are still within the scope of the appended claims. Descriptions of known systems, devices, materials, methods of operation, and methods of manufacture may be omitted to avoid obscuring the description of representative embodiments. Nevertheless, systems, devices, materials, and methods that are within the scope of knowledge of those skilled in the art are all within the scope of this teaching and can be used according to representative embodiments. It should be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. The definitions and interpretations of terms herein supplement the scientific and technical meanings commonly understood and accepted in the art to which this teaching pertains.

[0018] It should 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. Therefore, without departing from the teachings of the inventive concept, the first element or component discussed below may be referred to as the second element or component.

[0019] As used in the specification and appended claims, the singular forms of the terms “a,” “an,” and “the” are intended to include both the singular and plural forms unless the context clearly specifies otherwise. Additionally, when used herein, the terms “comprising” and / or “including” and / or similar terms indicate the presence of the stated features, elements, and / or components, but do not exclude the presence or addition of one or more other features, elements, components, and / or groups thereof. The term “and / or” as used herein includes any and all combinations of one or more of the associated listed items.

[0020] Unless otherwise stated, when an element or component is referred to as "connected to," "coupled to," or "proximity to" another element or component, it should be understood that the element or component may be directly connected to or coupled to the other element or component, or that there may be intermediate elements or components. That is, these and similar terms cover situations where one or more intermediate elements or components may be used to connect two elements or components. However, when an element or component is referred to as "directly connected" to another element or component, this only covers situations where two elements or components are connected to each other without any intermediate or intervening elements or components.

[0021] Therefore, through various aspects, embodiments, and / or one or more of specific features or sub-components of this disclosure, this disclosure is intended to achieve one or more advantages specifically pointed out below.

[0022] As described herein, workflow guidance can be provided to healthcare professionals to address immediate needs in situations requiring focused TEE-guided cardiac arrest resuscitation. Resuscitation as described herein may include interventional strategies for managing critically ill / hemodynamically unstable patients, patients in shock, patients in cardiac arrest, or patients requiring workflow guidance. The scope of resuscitation may include peri-arrest, during-arrest, or post-arrest management. Workflow guidance can help lower barriers to TEE use in emergency and intensive care settings for identifying cardiac disease states by providing guidance to healthcare professionals on TEE acquisition and interpretation, and can improve patient outcomes for patients experiencing cardiac arrest by standardizing the quality of resuscitation through guided resuscitation.

[0023] Figure 1 The illustration shows a system 100 for TEE-based recovery guidance according to a representative embodiment.

[0024] Figure 1 System 100 is a system for TEE-based resuscitation guidance and includes components that can be supplied together. System 100 includes an ultrasound probe 110, an ultrasound base 120, and a display 180.

[0025] The ultrasound probe 110 includes processing circuitry 115 and a transducer array 113. Processing circuitry 115 may include a memory for storing data and instructions, an application-specific integrated circuit (ASIC), and / or a processor for processing data and instructions. 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. Transducer array 113 converts electrical energy into sound waves, which are reflected from body tissue, and receives echoes of the sound waves and converts the echoes back into electrical energy. Transducer array 113 may include tens, hundreds, or thousands of individual transducer elements. Ultrasound probe 110 may emit a beam to generate an image and may detect echoes. Processing circuitry 115 may process the ultrasound images captured by transducer array 113 of ultrasound probe 110. Figure 1 The processing circuit 115 is shown in the ultrasonic probe 110, but the processing circuit 115 may alternatively be placed in the processor 152 in the ultrasonic base or otherwise coupled to the processor 152 in the ultrasonic base.

[0026] The ultrasonic base 120 may include an ultrasonic trolley. The ultrasonic base 120 includes a first interface 121, a second interface 122, a third interface 123, and a controller 150. Figure 6 The document describes a computer that can be used to implement the ultrasonic base 120, but the ultrasonic base 120 may include more than Figure 1 More elements and more than depicted in Figure 6 The interface may include more or fewer elements as depicted. One or more interfaces may include ports, disk drives, wireless antennas, or other types of receiver circuitry that connect controller 150 to other electronic components. First interface 121 connects ultrasound base 120 to ultrasound probe 110 and may include ports, antennas, and / or another type of physical component for wired or wireless communication. Second interface 122 connects ultrasound base 120 to display 180 and may also include ports, antennas, and / or another type of physical component for wired or wireless communication. Third interface 123 is a user interface and may include buttons, keys, a mouse, microphone, speaker, switch, touchscreen, or other types of displays separate from display 180, and / or other types of physical components that allow medical personnel to interact with ultrasound base 120 to input commands and receive outputs.

[0027] The controller 150 includes at least a memory 151 storing instructions and a processor 152 executing those instructions. The instructions stored in the memory 151 may include one or more software programs for generating and (e.g., via a display 180) outputting instructions for capturing one or more additional transesophageal echocardiograms based on interpreting each of multiple transesophageal echocardiograms captured by the ultrasound probe 110. The software programs(s) in the memory 151 may include image classification models and / or feature detection models for classifying ultrasound images and detecting features within them. In system 100, a user interface may be generated from the instructions stored in the memory 151 and may be displayed on the display 180.

[0028] The display 180 can be local to the ultrasound base 120 or can be remotely (e.g., wirelessly) connected to the ultrasound base 120. The display 180 includes a graphical user interface 181 (GUI) that displays ultrasound images and instructions to the user.

[0029] Display 180 can be connected to ultrasound base 120 via a local wired interface (e.g., Ethernet cable) or via a local wireless interface (e.g., Wi-Fi connection). Display 180 can interface with other user input devices (including mouse, keyboard, thumbwheel, etc.) that medical personnel can use to input commands. Display 180 can be a monitor (e.g., computer monitor, display on mobile device, augmented reality display, television, electronic whiteboard, or another screen configured to display electronic images). Display 180 may also include one or more input interfaces (e.g., those mentioned above that can connect to other components or parts, and an interactive touchscreen configured to display prompts to medical personnel and collect touch input from medical personnel).

[0030] Controller 150 can directly perform some of the operations described herein, and can indirectly implement other operations described herein. For example, controller 150 can indirectly control operations (e.g., by generating and sending content to be displayed on display 180). Controller 150 can directly control other operations, such as logical operations performed by processor 152 based on input received via an interface from electronic components and / or medical personnel from memory 151. Therefore, when processor 152 executes instructions from memory 151, the process implemented by controller 150 may include steps not directly performed by controller 150.

[0031] As described above, system 100 may include an ultrasound system having a memory 151 for storing instructions and a processor 152 for executing those instructions. When executed by processor 152, the instructions cause the ultrasound system to perform actions as described above. Figure 3 The method described herein is based on some or all of the features of the method described in the document. The method performed by system 100 may include a controller 150 of ultrasound base 120 receiving multiple transesophageal echocardiogram images from ultrasound probe 110. The transesophageal echocardiogram images may be received in real-time or near real-time and interpreted by controller 150. Instructions stored in memory 151 may be executed by processor 152 to cause controller 150 to interpret each of the multiple transesophageal echocardiogram images received from ultrasound probe 110. The method performed by system 100 may also include outputting the output of each of the multiple transesophageal echocardiogram images on a graphical user interface 181 of display 180. The method performed by system 100 may also include controller 150 generating instructions for capturing additional transesophageal echocardiogram images based on the interpretation of each of the multiple transesophageal echocardiogram images and outputting such instructions on display 180.

[0032] Figure 2 Another system for TEE-based recovery guidance is illustrated according to a representative embodiment.

[0033] exist Figure 2 In the process, the ultrasonic probe 210, as well as smart devices A and B, are connected via network 201.

[0034] Network 201 may include a local wireless network (such as a WiFi network), but network 201 may also or alternatively include wired elements (such as wires connected to smart device A and smart device B via USB cables).

[0035] Ultrasound probe 210 may include a portable transducer. Ultrasound probe 210 includes a transducer array 213, a lens 214, a user interface 223, a controller 250, and wireless communication circuitry 290. Transducer array 213 includes at least a first transducer element 2131, a second transducer element 2132, and an Xth transducer element 213X. Transducer array 213 converts electrical energy into sound waves, which are reflected from body tissue, and receives echoes of the sound waves and converts the echoes back into electrical energy. Transducer array 213 may include tens, hundreds, or thousands of individual transducer elements. Ultrasound probe 210 can emit a beam to generate an image and can detect echoes. Processor 252 can process ultrasound images captured by transducer array 213 of ultrasound probe 210. Lens 214 can be used to focus the emitted ultrasound beam and receive echoes of the ultrasound beam. Medical personnel can use user interface 223 to interact with ultrasound probe 210. Wireless communication circuitry 290 can be used to communicate with smart devices A and B via network 201. Ultrasonic probe 210 can be configured to link to external devices (e.g., smart devices A and B) via an application installed on one or more external devices. In some embodiments, instead of wireless communication circuitry 290, ultrasonic probe 210 can be connected to smart devices A and / or B via an alternative interface for ultrasonic probe 210 using one or more wires.

[0036] Smart device A stores and executes ultrasound application 299A. Smart device B stores and executes ultrasound application 299B. Ultrasound applications 299A and 299B can be configured to enable smart devices A and B to interact with ultrasound probe 210 via network 201. For example, ultrasound applications 299A and 299B can be configured to display ultrasound images from ultrasound probe 210. Ultrasound applications 299A and 299B can also be configured to generate and output guidance for capturing additional transesophageal echocardiograms based on interpreting each of multiple transesophageal echocardiograms captured by ultrasound probe 210. In some embodiments, controller 250 can generate output and send it to ultrasound applications 299A and / or 299B for display on the screens of smart devices A and / or B.

[0037] The controller 250 includes at least a memory 251 for storing instructions and a processor 252 for executing instructions. The memory 251 may store one or more software programs. The software programs may include image classification models and / or feature detection models for classifying ultrasound images and detecting features in the ultrasound images. Figure 2In this context, the user interface can be generated by instructions stored in memory 251 and can be displayed on the display of smart device A or smart device B.

[0038] Controller 250 can directly perform some of the operations described herein, and can indirectly perform other operations described herein. For example, controller 250 can indirectly control operations (e.g., by generating and sending content to be displayed on the display of smart device A or smart device B). Controller 250 can directly control other operations, such as logical operations performed by processor 252 based on input received via an interface from electronic components and / or medical personnel from memory 251. Therefore, when processor 252 executes instructions from memory 251, the process implemented by controller 250 may include steps not directly performed by controller 250.

[0039] supply Figure 1 System 100 and Figure 2 System 200 addresses the lack of experience and technical expertise among users in TEE acquisition and interpretation for cardiac arrest resuscitation. Compared to TTE, TEE offers several advantages, such as superior image quality that can provide valuable diagnostic information about reversible causes in cardiac arrest. Procedures executed by controller 150 and / or controller 250 can help lower the barriers to introducing TEE acquisition and interpretation into cardiac arrest resuscitation, including in the somewhat chaotic emergency and intensive care settings where medical personnel are simultaneously attempting resuscitation while administering TEE to / inside the patient.

[0040] As described in this article, in emergency and intensive care settings, passive and active guidance can enable new and / or inexperienced users to successfully use TEE in cardiac arrest resuscitation. The guidance solution features can be provided by procedures executed by controllers 150 and / or 250, including features such as automatic chamber marking, view quality detection, acquisition support, and interpretation assistance. Therefore, TEE-based resuscitation guidance can shorten the learning curve for new and inexperienced users by providing support when experts are not present. TEE-based resuscitation guidance can also enhance diagnostic confidence and help standardize the quality of resuscitation care.

[0041] Figure 3 The illustration depicts a method for TEE-based recovery guidance according to a representative embodiment.

[0042] Figure 3 The method can be executed by system 100 including controller 150 or by system 200 including controller 250.

[0043] At S310, the ultrasound procedure begins with probe insertion and esophageal cannulation. Initiating the ultrasound procedure at S310 can be appropriate when the patient presents with instability and suspected cardiac arrest. This can be targeted at... Figure 1 System 100 or by Figure 2 The ultrasound procedure begins in system 200. It can be activated at S310. Figure 1 The ultrasound probe 110 and / or ultrasound base 120 in the middle, or by activating Figure 2 Use the ultrasound probe 210 and / or ultrasound application 299A and / or ultrasound application 299B to start the ultrasound procedure.

[0044] At S315, the patient is intubated, and the TEE transducer is inserted into the esophagus. When the user begins the cardiac ultrasound procedure, Figure 1 System 100 or Figure 2 The intelligent device A or intelligent device B can use verbal prompts to assist with cannulation and TEE transducer insertion.

[0045] At S320, one or more transesophageal echocardiogram (TEE) images are received. Multiple TEE images can be received from the ultrasound base 120. Figure 1 The ultrasound probe 110 in the middle receives, or is received by Figure 2 The controller 250 and / or either or both of smart device A and / or smart device B are received. Figure 2 In this context, S320 can be executed by either controller 250 or one or more intelligent devices performing the logic processing described herein. Once... Figure 1 System 100 or Figure 2The acquisition assistance workflow can be activated when smart device A or smart device B begins receiving one or more TEE images. In addition to providing the user with proactive guidance on obtaining a good view, the workflow can automatically adjust to include the correct cardiac chambers in the frame if the user deviates slightly from the axis. Once the first TEE image (one or more) is received, the image acquisition workflow is activated, providing the user with proactive guidance to obtain a suitable view. At S330, one or more TEE images are interpreted. Interpretation at S330 helps ensure that ultrasound probe 110 or ultrasound probe 210 is in the correct position, as such feedback can be useful in reassuring the user or prompting the user to correct the position. Interpretation at S330 can include an assessment of view quality. View quality assessment at S330 can include: the ultrasound images appear to reflect the patient's cardiac anatomy, each ultrasound image is properly focused, and each ultrasound image has appropriate resolution. View quality assessment at S330 can also include examining the characteristics of different cardiac disease states, allowing for the detection of clinical disease states based on this interpretation. The view quality assessment at S330 may also include examining features of cardiac arrest to trigger a measurement of the duration of cardiac arrest upon detection. Each transesophageal echocardiogram (TEE) image in a set of multiple TEE images may be interpreted individually or as a set. For example, the set of ultrasound images may be compared to detect differences, such as ensuring they are not completely or substantially identical. The view quality assessment at S330 may include detecting and quantifying predetermined anatomical features in each TEE image in a set of multiple TEE images to determine the guidance to be output.

[0046] Interpretation can be performed at S330 by applying an image classification model to each of the multiple transesophageal echocardiogram images and detecting and quantifying predetermined anatomical features. The guided output based on the interpretation at S330 can include instructions to improve view quality by making the acoustic window suitable for interpretation. For example, a physician could begin by acquiring a four-chamber view of the mid-esophagus to obtain a full view of the heart, where all four chambers are visible.

[0047] The system can provide visual and / or voice guidance to the user to advance the probe to the appropriate depth and ensure the center of the heart is in the middle of the sector, thus avoiding chamber shortening. If the user approaches obtaining a suitable view but that view is slightly off-axis, Figure 1 The ultrasonic base 120 in system 100 or Figure 2 Smart device A or smart device B can automatically adjust the view to fit it. If the transducer is moved out of the plane during pressing, then Figure 1The ultrasonic base 120 in system 100 or Figure 2 Intelligent device A or intelligent device B can guide the user to correct transducer positioning or automatically adjust the view to keep the image centered by re-triggering the view quality acquisition workflow. In some embodiments, automated scanning can be achieved through robotic probe manipulation and signal path control feedback, for example, when ultrasound probe 110 or ultrasound probe 210 is manipulated by a robot. For example, the robot can be configured to automatically control the ultrasound probe to acquire a set of transesophageal echocardiogram images. The optimal imaging plane for observing cardiac anatomy can be identified based on the interpretation of this set of transesophageal echocardiogram images.

[0048] At S335, it is determined whether the view quality obtained from interpreting one or more TEE images at S330 is good. If the view quality is determined to be poor (S335 = poor), then guidance is generated and output at S337, and Figure 3 The method returns to S320. In some embodiments, if the view is close to appropriate but slightly off-axis, the system can automatically adjust the view to be appropriate without the guidance at S337. A key characteristic of view quality is the clear visualization of chambers, valves, and surrounding tissues for interpretation. For example, for a mid-esophageal four-chamber view, all four chambers should be adequately visible to accurately label the image, identify the presence of cardiac activity, identify potential treatable pathologies, characterize the type of cardiac activity, and perform quantitative analysis. View quality can also be determined based on transducer positioning and image sharpness. For example, a good-quality mid-esophageal long-axis image should have proper alignment to display the long axis of the heart in a single plane without excessive angularity or shortening. Furthermore, a mid-esophageal long-axis view can be defined by having sufficient image depth to visualize the entire length of the heart and surrounding structures (e.g., the ascending aorta and aortic arch) and the absence of significant artifacts (e.g., shadows, noise, or reverberation) that could interfere with interpretation.

[0049] Once it is determined at S335 that the first view has good quality, Figure 1 System 100 or Figure 2 Smart device A or smart device B can enable a preset called "Focused View," which triggers some or all of the default enabled auxiliary features, such as: customized display, tagging, disease state detection, compression monitoring, cardiac monitoring, and automatic saving. If the transducer is positioned outside the frame at any time, the acquisition auxiliary workflow can be retried. The enabled customized display can vary based on whether the transducer in ultrasound probe 110 or ultrasound probe 210 is a 2D or 3D transducer. If the view quality is determined to be good (S335 = Good), the view reflected in the TEE image is classified at S339.

[0050] Once a suitable view for interpretation is obtained and categorized, it is determined at S340 whether to generate one or more labels. This determination at S340 can be based on, for example, whether the current TEE image is both focused and includes relevant anatomical cardiac features of the patient. The labels to be generated can be targeted at different cardiac anatomical features, such as different cardiac chambers.

[0051] At S345, if one or more labels are to be generated (S340 = Yes), then one or more labels are generated. The labels(s) generated at S345 can automatically generate cardiac labels as anatomical cardiac features of the patient. Based on the determination at S340, the marking at S345 can be automatic and selective cardiac chamber marking in the relevant resuscitation TEE view.

[0052] Once the user has obtained a suitable view, they can select a view acquisition tool tailored to their resuscitation TEE protocol. Imaging in multiple planes can be used to create a customized display of the resuscitation TEE view for resuscitation monitoring. If a FoCUS TEE view is selected, a customized display of the resuscitation TEE view and diagnostic information can be presented to the user to provide continuous monitoring of myocardial activity and guide decision-making. By utilizing the multiplanar imaging capabilities of a 3D TEE transducer, the user can obtain simultaneous views of relevant imaging planes for the FoCUS TEE via volumetric scanning. This allows the user to identify reversible causes of cardiac arrest (potentially found in the ME4 Chamber view) and subsequently begin observing / optimizing compressions in the MELAX view without having to move the transducer. If using a full-planar TEE without 3D imaging capabilities, the user can select an "automatic scanning mechanism," where automatic scanning is performed across the entire plane, and the software selects the optimal view of myocardial activity based on clinical interpretation. For example, automated scanning can be performed between the ME4CH and MELAX views by having the software automatically rotate the entire plane from 0 degrees to 130 degrees and select the optimal plane for resuscitation. The 2D workflow can also implement a “FoCUS view,” in which an automated workflow tailored for resuscitation is present. For example, a workflow could begin in the ME4CH view to examine reversible causes of cardiac arrest and then automatically transition to the next view to begin chest compressions without user manipulation of the transducer. In some embodiments, automated scanning can be achieved through robotic probe manipulation, such as when ultrasound probe 110 or ultrasound probe 210 is manipulated by a robot. For example, the robot can be configured to automatically control the ultrasound probe to capture a set of transesophageal echocardiogram images. The optimal imaging plane for observing cardiac anatomy can be identified based on the interpretation of this set of transesophageal echocardiogram images.

[0053] Customized displays for 2D and 3D TEE imaging can be found by referring to the following references respectively. Figure 4A and Figure 4B The changes are shown as described below. If the user has a 3D TEE ultrasound probe, volumetric imaging allows for the simultaneous display of multiple planes of the heart. Each plane can represent an imaging view within the TEE resuscitation protocol and convey information about the heart. Figure 5 The table in the document indicates relevant information about the disease state / clinical decision. As an example, you can first look at... Figure 4A The ME4CH view, shown in user interface 481, is used to detect reversible causes of cardiac arrest. The user can then begin chest compressions and move the transducer to MELAX, as shown in second view 481B, to view the left ventricle and other disease conditions (boxes indicate information about disease conditions). In the FoCUS view, soft button 481J is preset and can be selected as a FoCUS view button. These two views can be displayed side-by-side with information about disease conditions, compression quality, and cardiac event detection, as shown in [example image / image]. Figure 4A As shown. If technically feasible, all relevant TEE views can be displayed simultaneously by utilizing the multi-planar imaging capabilities of a 3D TEE ultrasound probe. If the transducer is moved out of plane during compression, the user can be guided to correct transducer positioning by re-triggering the view quality acquisition workflow provided by window 481H for acquisition guidance, or the view can be automatically adjusted to keep the image centered. If the user has a 2D TEE ultrasound probe, the customized display can be more biased towards workflow automation, in which the display automatically advances to the next view in the protocol by automatically adjusting the entire plane instead of requiring the user to adjust the transducer. This can be discussed on... Figure 4B As shown. For example, two common views in resuscitation protocols are the ME4CH view for identifying the disease state and the MELAX view for performing chest compressions. The only difference between these two views is the adjustment of the entire plane from 0 degrees to 130 degrees. Therefore, for example, at the start of the protocol, Figure 1 System 100 or Figure 2 Smartphone A or Smartphone B can attempt to detect any reversible causes of cardiac arrest in the ME4CH view. If none are identified, the entire plane can be automatically tilted to the MELAX view, and the user can be notified to begin compressions.

[0054] At S350, if one or more labels are not generated (S340 = No), or after one or more labels are generated at S345, it is determined whether a disease state can be identified. Processor 152 or processor 252 or smart device A or smart device B can be configured to detect clinical disease states associated with cardiac arrest based on interpreting each of multiple transesophageal echocardiogram images at S330. The determination at S350 can be based on the view quality from S335, such as whether anatomical features are in the view, whether the view is properly focused, and other qualitative characteristics of the view. Examples of detectable disease states include those associated with cardiac arrest. Such disease states include, for example, right ventricular (RV) collapse, left ventricular (LV) collapse, ventricular fibrillation (VF), cardiac arrest, cardiac tamponade, hemothorax, pulmonary embolism, and pericardial effusion. Similarly, the determination at S350 can reflect whether cardiac arrest can be identified. Figure 5 An example of a marker at S350 is shown, and the use of the marker at S350 is automated, which can reduce the time users spend on it during critical life-saving events.

[0055] If a disease state can be identified (S350 = Yes), it is determined at S360 whether the patient is experiencing cardiac arrest. Cardiac arrest is referred to as cardiac arrest, and once identified, visual and audio cues regarding the timing of the arrest can be provided to medical personnel. When the timer is started, the timing can begin at S365. In the event of cardiac arrest, system 100 or system 200 can detect the absence of cardiac activity, alert the user, and automatically time the duration of the cardiac arrest.

[0056] If a disease state cannot be identified (S350 = No), guidance is generated at S380. Guidance can be generated and output to assure medical personnel that a cardiological disease state cannot be identified from TEE imaging, but if there is a possibility that the lack of disease state identification is based on a defect in TEE imaging, the guidance can also indicate when TEE imaging can be improved.

[0057] At S365, if the patient is experiencing cardiac arrest (S360 = Yes), a timer is started to measure the duration of cardiac arrest. The timer can be used as a cardiac event monitor to alert the patient when cardiac arrest (stopping of heartbeats) is detected and to track the duration. The indication of the duration of cardiac arrest can be output once in a guide for each transesophageal echocardiogram image, or continuously as a run output.

[0058] If the patient is not experiencing cardiac arrest (S360 = No), or after a timer is started at S365, disease status information is generated at S370. The disease status information can simply reflect the identified disease status at S350.

[0059] If the disease state cannot be identified (S350 = No), or after generating disease state information at S370, guidance is generated at S380. Guidance may include suggestions to capture additional transesophageal echocardiography images based on the interpretation at S330, or may include... Figure 3 Transesophageal echocardiography failed to identify any confirmed cardiac disease state.

[0060] At S385, automatic saving instructions are provided. Automatic saving at S385 can be used for record keeping. TEE can be used for differential diagnosis between ventricular fibrillation and cardiac arrest (cardiac arrest). Automatic saving is enabled and triggered when a cardiac event is detected. Automatic saving saves users time in acquiring and recording files, allowing them to focus more on effective resuscitation of patients in extreme conditions. Automatic saving can be performed on a subset of transesophageal echocardiogram images corresponding to the detected cardiac event and on metadata for that subset. For example, metadata may include the time and date each image was taken, the sequential position of each image in the sequence, the patient's name or other identifying information, the identified disease state, and any instructions provided with the images.

[0061] At S390, output one or more TEE images and instructions. Each transesophageal echocardiogram (TEE) image from a set of multiple TEE images can be output individually or as a ensemble. The instructions can be used to capture additional TEE images based on the interpretation of each TEE image from the set of multiple TEE images. For example, one or more first TEE images can be used as the basis for capturing one or more subsequent second TEE images. The output at S390 can provide automatic acquisition assistance in real-time or near real-time to obtain the appropriate acoustic window during a single TEE imaging session. Figure 3 The assistance provided in the method can be automated to help users obtain appropriate acoustic views as feedback during emergency or intensive care settings. Figure 3 The steps in the methodology can be developed for acquisition and interpretation within each of the 4 to 12 views of a resuscitation TEE protocol, and together provide guidance tailored to improve the quality of TEE resuscitation.

[0062] In some embodiments, the clinical disease state identified at S350 may also be output as part of the guidance at S390. Identifying a clinical disease state as part of the guidance in the emergency department can lead to an immediate change in treatment. For example, when performing a resuscitation TEE protocol on a patient presenting with symptoms associated with cardiogenic or obstructive shock (e.g., shortness of breath, chest pain, or arthroscopy), the user may begin with a mid-esophageal four-chamber view to rule out the presence of pericardial effusion or tamponade. Pericardial effusion is a condition in which an excessive amount of fluid accumulates in the pericardial sac surrounding the heart. This accumulation of fluid can cause cardiac tamponade, a life-threatening condition in which increased pressure from the surrounding fluid in the pericardial sac impairs ventricular filling, and the heart is unable to pump enough blood. In cases associated with tamponade, the physician may choose to perform pericardiocentesis, a life-saving procedure that uses a needle or small catheter to remove excess fluid from the pericardial sac. Relieving this pressure can help reduce the risk of cardiac arrest and help alleviate symptoms of cardiogenic shock by restoring stroke volume to normal levels. This allows doctors more time to determine the cause of the condition.

[0063] In some embodiments, identifying the disease state at S350 can lead to a change in the selection of a treatment plan or a previous selection of a treatment plan for resuscitating the patient. Additionally, or alternatively, in some embodiments, checking the view quality at S335 can detect if the placement of the TEE probe can be improved to enhance view quality.

[0064] Although Figure 3 The steps are shown as a method flow, but Figure 3 Some or all of the steps in the process can be performed in a different order or simultaneously. For example, one or more TEE images can be received and processed individually, such that the first TEE image is interpreted at S330 while the second TEE image is received at S320. As another example, the automatic saving at S385 can be performed after the process is completed or after a set number of TEE images (one or more) have been processed, or both simultaneously and sequentially. As yet another example, the determination of whether a disease state can be identified can be performed individually for each TEE image at S350 and / or together for a set of multiple TEE images at S350.

[0065] Although Figure 3The method is primarily shown as a sequence, but some features can be performed simultaneously and repeatedly. For example, one or more TEE images can continue to be received at S320 and interpreted at S330, while feedback for the previous TEE image is generated at S380. Similarly, functions such as automatic scanning can be performed automatically based on the interpretation at S330, but the result of such automatic scanning can be one or more new TEE images to be received at S320. Additionally, Figure 3 Some or most of the features can be implemented as a preset configuration in which all the various auxiliary features are enabled by default, and the user can begin performing resuscitation.

[0066] use Figure 3 The resuscitation TEE protocol can involve multiple cycles of CPR and pulse monitoring. During each CPR cycle, TEE imaging can be used to check for any signs of reversible causes of cardiac arrest, allowing the user to be notified and feedback on the quality of compressions to be provided. While CPR is in progress, the user can check for any reversible causes of cardiac arrest in ME4CH. Although Figure 3 No FoCUS view is specified, but it is based on Figure 3 Some embodiments of the method may include options for one or more FoCUS views. For example, if no signs of a reversible cause of cardiac arrest are identified, one or more FoCUS views may highlight the MELAX view and CPR compressions may begin. Compression quality may be monitored, a countdown to the compressions may be provided to the user, and relevant hemodynamic information may be displayed. The user may be directed back to the ME4CH view (a) and assist in performing a pulse check to determine the presence of a shockable rhythm. If no shockable rhythm is identified, the presence of a potential arrhythmia (e), such as cardiac arrest, pseudo-pulseless electrical activity, or pulseless electrical activity, may be highlighted. If cardiac arrest is detected, cardiac events may be detected until a timer expires and the information is automatically saved. The user may perform additional cycles of CPR, and the same workflow may be triggered to monitor compression quality and monitor other parts of the body for other causes of cardiac arrest. If cardiac arrest is detected, System 100 or Smart Device A or Smart Device B may recommend that the user terminate resuscitation. If the restoration of spontaneous circulation is detected, the user may be instructed on post-cardiac arrest care.

[0067] Figure 4A A user interface according to a representative embodiment is shown, which illustrates the results of multiplanar scanning in TEE-based resuscitation guidance.

[0068] Figure 4A User interface 481 illustrates the focused TEE workflow for 3D TEE transducers. Figure 4A The user interface 481 may include a view shown as a first view 481A or a second view 481B, or multiple views showing both the first view 481A and the second view 481B simultaneously; a CPR timer 481E; a hemodynamic monitor 481F; a visualization of the interpretation of one or more TEE images or protocol guidance as feedback 481G; a window 481H for acquiring guidance to indicate view quality as good or poor; a soft button 481I for automatic labeling; a soft button 481J for selecting a FoCUS view; and a soft button 481K for saving one or more views on the user interface 481. For example, two planar views can be obtained simultaneously using a 3D TEE, and three views can be obtained using automatic probe manipulation to obtain a dual-lumen view. Figure 4A The first view 481A represents a four-lumen view of the mid-esophagus. Each view in the first view 481A and the second view 481B may include an image, and these images collectively illustrate the concept of automated scanning through two or more key views associated with focused TEE resuscitation. From top to bottom, the first view 481A shows a four-lumen view of the mid-esophagus (ME4C), the second view 481B shows a mid-esophagus long axis (MELAX) view, and the third view shows a dual-lumen view of the mid-esophagus. By utilizing the multi-planar imaging capabilities of a three-dimensional TEE transducer, the ultrasound probe can automatically scan and highlight the optimal imaging plane for the resuscitation range. For example, automated scanning can scan through two or more resuscitation TEE cardiac views when a physical / soft button is pressed, or it can occur automatically only with a highlighted display indicating that automated scanning is enabled, allowing the user to quickly assess any reversible causes of cardiac arrest and then intervene. By eliminating the need for the user to manipulate the transducer using the automated scanning capability, time can be saved in TEE examinations in emergency or intensive care settings, and the effectiveness of resuscitation interventions can be improved.

[0069] Figure 4A The user interface 481 includes three labeled images: image 481A, image 481B, and image 481C. Image 481A includes four labels for a four-luminal view of the mid-esophagus: LA, LV, RA, and RV. Image 481B includes four labels for a long-axis view of the mid-esophagus: LA, LV, Ao, and RV. Image 481C includes four labels for a two-luminal view of the mid-esophagus: LA, SVC, IAS, and RA. These labels can be applied automatically using a feature detection model that examines the views and features of each image and then applies the labels as shown on the user interface 581.

[0070] Figure 4AThe user interface 481 provides example automatic chamber marking in two or more views associated with the current resuscitation TEE protocol, and this automatic chamber marking is provided for resuscitation TEE. Feature marking can be preferentially performed in the four most commonly used views of focused transesophageal echocardiography (TEE) during cardiac arrest resuscitation. The four most commonly used views of focused TEE during cardiac arrest resuscitation include the mid-esophageal four-chamber view (ME4C), the mid-esophageal long axis (MELAX) view, the transgastric short axis (TGSAX) view, and the dual-chamber view. However, the marked views are not limited to this set.

[0071] Figure 4B The illustration shows another user interface in a TEE-based recovery guide according to a representative embodiment.

[0072] Figure 4B The user interface 491 illustrates the TEE workflow for a 2D TEE transducer, which switches between views by adjusting across the entire plane. User interface 491 includes a disease status window 491A, an instruction window 491B, and a CPR monitoring window 491C. Disease status window 491A includes a labeled TEE image, a view quality indicator, a disease status indicator, and a soft button at the top for executing a "FoCUS view." Instruction window 491B shows the progression of the order of TEE views to be obtained. CPR monitoring window 491C includes a CPR timer, compression count, compression feedback, and hemodynamic parameters.

[0073] Figure 4C The illustration depicts a hybrid process for TEE-based recovery guidance according to a representative embodiment.

[0074] Figure 4C The hybrid workflow includes 3D scanning capabilities. Figure 4C In the workflow, the user first achieves sufficient views so that the FoCUS scan can scan for reversible causes of cardiac arrest. The user can press the soft auto-scan button shown on the left. The auto-scan function initiates an automatic scan in the plane and obtains images a, b, and c. In other embodiments, auto-scan may be automatically enabled, and the soft button may be highlighted so that the user understands that auto-scan is on. Next, frames are processed for potential disease states. The optimal view is identified and selected. Figure 4C The user interface on the right shows a view of good quality and identifies the disease condition as a suspected right atrial thrombosis.

[0075] for Figure 4CIn the workflow, controller 150 or controller 250 can provide automated view selection to obtain a dual-chamber view by utilizing the multiplanar imaging capabilities of a three-dimensional transesophageal echocardiography probe (e.g., ultrasound probe 110 or ultrasound probe 210) and automated robot assistance. As a time-sensitive inspection, automated view selection can expand the use of resuscitation TEE acquisition by reducing the training entry barrier required to obtain the correct, appropriate acoustic window.

[0076] Figure 5 The illustration shows a user interface according to a representative embodiment, which displays a table with a corresponding set of information for TEE-based recovery guidance.

[0077] Figure 5 Table 1 on the user interface 581 provides information on the clinical application of the focused TEE view in cardiac arrest. Table 1 shows examples of clinicopathologies that can be detected in each of the four resuscitation views and how those detected clinicopathologies can be highlighted to the user.

[0078] Some clinicopathological conditions can be identified in one or more views among the different focused TEE views used for cardiac resuscitation. These disease states may include, but are not limited to, cardiac tamponade, ventricular fibrillation, cardiac arrest, cardiogenic shock, RV dilation, pericardial effusion, intracardiac thrombosis, pulmonary embolism, aortic dissection, ventricular wall motion abnormalities, hypovolemia, pulseless electrical activity (PEA), pseudoPEA, and ventricular arrhythmias.

[0079] Since the first step in a resuscitation TEE protocol is to detect potential reversible causes of cardiac arrest, the detection of abnormalities associated with cardiac disease states that can be found in each resuscitation TEE cardiac view can provide important information to the medical staff performing the resuscitation TEE. Figure 5 Table 1 provides examples of relevant structures identified, questions answered, and clinical decisions made in a focused TEE protocol. Feature detection of relevant cardiac states can support users in making decisions regarding the exclusion of potential causes of cardiac arrest. The identification of the presence or absence of some of these clinically significant disease states can be achieved through feature detection and image classification models, which are typically used in deep learning techniques and applied by controller 150 or controller 250. For example, a trained neural network algorithm can be trained to identify cardiac pathologies such as ventricular fibrillation or cardiac tamponade based on an annotated dataset of images acquired in a relevant resuscitation TEE view.

[0080] Figure 6 The illustration shows a computer system according to another representative embodiment, on which a method for TEE-based recovery guidance is implemented.

[0081] refer to Figure 6 The computer system 600 includes a set of software instructions executable to cause the computer system 600 to perform any of the methods or computer-based functions disclosed herein. The software instructions may include image classification models and / or feature detection models for classifying ultrasound images and detecting features in the ultrasound images. The computer system 600 may operate as a standalone device or may be connected to other computer systems or peripheral devices, for example, using a network 601. In embodiments, the computer system 600 performs logical processing based on digital signals received via an analog-to-digital converter.

[0082] In a networked deployment, computer system 600 operates as a server, as a client user computer in a server-client user network environment, or as a peer-to-peer (or distributed) computer system in a peer-to-peer (or distributed) network environment. Computer system 600 can also be implemented as or incorporated into various devices, such as an ultrasound base, ultrasound probe, smart device, workstation including a controller, fixed computer, mobile computer, personal computer (PC), laptop computer, tablet computer, or any other machine capable of (sequentially or otherwise) executing a set of software instructions specifying actions to be taken by that machine. Computer system 600 can be incorporated as or incorporated into a device, which in turn is part of an integrated system containing additional devices. In embodiments, computer system 600 can be implemented using electronic devices that provide voice, video, or data communications. Furthermore, although computer system 600 is illustrated in the singular, the term "system" should also be considered to include any collection of systems or subsystems that individually or collectively execute one or more sets of software instructions to perform one or more computer functions.

[0083] like Figure 6As illustrated herein, computer system 600 includes processor 610. Processor 610 can be considered a representative example of a processor of a controller and executes instructions to implement some or all aspects of the methods and processes described herein. Processor 610 is tangible and non-transient. As used herein, the term "non-transient" is not interpreted as a permanent state characteristic, but rather as a state characteristic that will last for a period of time. The term "non-transient" explicitly denies transient characteristics, such as the characteristics of a carrier wave or a signal, or other forms of characteristics that exist only briefly at any time and place. Processor 610 is an article of manufacture and / or a machine part. Processor 610 is configured to execute software instructions to perform the functions described in the various embodiments herein. Processor 610 may be a general-purpose processor or may be part of an application-specific integrated circuit (ASIC). Processor 610 may also be a microprocessor, microcomputer, processor chip, controller, microcontroller, digital signal processor (DSP), state machine, or programmable logic device. Processor 610 may also be logic circuitry, including programmable gate arrays (PGAs) (e.g., field-programmable gate arrays (FPGAs)) or another type of circuitry including discrete gate and / or transistor logic. The processor 610 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.

[0084] As used herein, the term "processor" encompasses an electronic component capable of executing programs or machine-executable instructions. References to computing devices that include "processor" should be interpreted as including more than one processor or processing core, as in a multi-core processor. A processor can also refer to a collection of processors within a single computer system or distributed across multiple computer systems. The term computing device should also be interpreted as a collection or network of computing devices, each comprising one or more processors. A program has software instructions that are executed by one or more processors, which may be located within the same computing device or distributed across multiple computing devices.

[0085] Computer system 600 also includes main memory 620 and static memory 630, wherein the memories in computer system 600 communicate with each other and with processor 610 via bus 608. Either or both of main memory 620 and static memory 630 can be considered representative examples of the memory of a controller and store instructions for implementing some or all aspects of the methods and processes described herein. The memory described herein is a tangible storage medium for storing data and executable software instructions, and is non-transient during the period in which the software instructions are stored. As used herein, the term "non-transient" should not be construed as a permanent state characteristic, but rather as a state characteristic that will persist for a period of time. The term "non-transient" explicitly denies transient characteristics, such as the characteristics of a carrier wave or a signal, or other forms of characteristics that exist only briefly at any time and place. Main memory 620 and static memory 630 are articles of art and / or machine parts. Main memory 620 and static memory 630 are computer-readable media from which data and executable software instructions can be read by a computer (e.g., processor 610). Each of the main memory 620 and static memory 630 may be implemented as one or more of the following: random access memory (RAM), read-only memory (ROM), flash memory, electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), register, hard disk, removable disk, magnetic tape, read-only optical disc (CD-ROM), digital versatile disc (DVD), floppy disk, Blu-ray disc, or any other form of storage medium known in the art. The memory may be volatile or non-volatile, secure and / or encrypted, insecure and / or unencrypted.

[0086] “Memory” is an example of a computer-readable storage medium. Computer memory is any memory that can be directly accessed by a processor. Examples of computer memory include, but are not limited to, RAM, registers, and register files. The reference to “computer memory” or “memory” should be interpreted as potentially referring to multiple memories. For example, the memory could be multiple memories within the same computer system. The memory could also be multiple memories distributed across multiple computer systems or computing devices.

[0087] As shown in the figure, the computer system 600 also includes a video display unit 650, 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). Additionally, the computer system 600 includes input devices 660, such as a keyboard / virtual keyboard or a touch-sensitive input screen or voice input with voice recognition, and cursor control devices 670, such as a mouse or a touch-sensitive input screen or touchpad. The computer system 600 also optionally includes a disk drive unit 680, a signal generation device 690 (e.g., a speaker or remote control), and / or a network interface device 640.

[0088] In one embodiment, such as Figure 6 As depicted herein, the disk drive unit 680 includes a computer-readable medium 682 in which one or more software instruction sets 684 (software) are embedded. The software instruction sets 684 are read from the computer-readable medium 682 for execution by the processor 610. Additionally, the software instructions 684, when executed by the processor 610, perform one or more steps of the methods and processes described herein. In embodiments, the software instructions 684 reside wholly or partially within main memory 620, static memory 630, and / or processor 610 during execution by the computer system 600. Furthermore, the computer-readable medium 682 may include, or receive and execute, the software instructions 684 in response to a propagation signal, causing a device connected to network 601 to transmit voice, video, or data through network 601. The software instructions 684 may be transmitted or received via network interface device 640 through network 601.

[0089] In the embodiments, 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 use two or more specific interconnected hardware modules or devices to implement the functionality, having associated control and data signals that can communicate between and through the modules. Therefore, this disclosure covers software, firmware, and hardware implementations. Nothing in this application should be construed as being implemented or implementable solely using software and not hardware (e.g., tangible non-transient processors and / or memory).

[0090] According to various embodiments of this disclosure, the methods described herein can be implemented using a hardware computer system that executes software programs. Additionally, in exemplary non-limiting embodiments, implementation may include distributed processing, component / object distributed processing, and parallel processing. Virtual computer system processing can implement one or more of the methods or functions described herein, and the processor described herein can be used to support a virtual processing environment.

[0091] Therefore, TEE-based resuscitation guidance enables automated instruction for users of TEEs. While the teachings described in this paper are primarily in an emergency context, such as for medical staff or emergency room professionals, they can be used in other contexts, such as for intubated patients undergoing cardiac or high-risk surgery, and for postoperative patients in cardiac or surgical intensive care units.

[0092] While TEE-based recovery guidance has been described with reference to several exemplary embodiments, it should be understood that the language used is descriptive and illustrative, not restrictive. Changes may be made within the scope of the present statement and the appended claims as amended, without departing from the scope and spirit of TEE-based recovery guidance in its aspects. Although TEE-based recovery guidance has been described with reference to specific means, materials, and embodiments, TEE-based recovery guidance is not intended to be limited to the disclosed details; rather, TEE-based recovery guidance extends to, for example, all functionally equivalent structures, methods, and uses within the scope of the appended claims.

[0093] The illustrations of the embodiments described herein are intended to provide a general understanding of the structure of various embodiments. The illustrations are not intended to be a complete description of all elements and features of this disclosure described herein. Many other embodiments will be apparent to those skilled in the art upon reading this disclosure. Other embodiments can be utilized and derived from this disclosure, allowing structural and logical substitutions and changes to be made without departing from the scope of this disclosure. Additionally, the illustrations are merely representative and may not be drawn to scale. Some scales in the illustrations may be exaggerated, while others may be minimized. Therefore, this disclosure and the accompanying drawings should be considered illustrative rather than restrictive.

[0094] The term "invention" may be used herein solely and / or collectively for convenience only, and is not intended to voluntarily limit the scope of this application to any particular invention or inventive concept. Furthermore, while specific embodiments have been illustrated and described herein, it should be understood that any subsequent arrangements designed to perform the same or similar purposes may replace the specific embodiments shown. This disclosure is intended to cover any and all subsequent modifications or variations of the various embodiments. Combinations of the above embodiments and other embodiments not specifically described herein will be apparent to those skilled in the art upon reading the specification.

[0095] This summary of disclosure is provided to comply with 37 C.FR § 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. Additionally, in the foregoing detailed description, various features may be combined together or described in a single embodiment for the purpose of simplifying this disclosure. This disclosure should not be construed as reflecting an intention that the claimed embodiments require more features than expressly recited in each claim. Rather, as reflected in the appended claims, the inventive subject matter may relate to fewer features than all of any of the disclosed embodiments. Therefore, the appended claims are incorporated into the detailed description, wherein each claim serves independently as a definition of a separately claimed subject matter.

[0096] The foregoing description of the disclosed embodiments is provided to enable any person skilled in the art to practice the concepts described in this disclosure. Therefore, the subject matter disclosed above is to be considered illustrative rather than restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other embodiments falling within the true spirit and scope of this disclosure. Accordingly, to the maximum extent permitted by law, the scope of this disclosure shall be determined by the broadest permissible interpretation of the appended claims and their equivalents, and shall not be bound or limited by the foregoing detailed description.

Claims

1. An ultrasound system (100 / 200) for resuscitation transesophageal echocardiography, comprising: Memory (151 / 251), which stores instructions; as well as A processor (152 / 252) executes the instructions, wherein the instructions, when executed by the processor, cause the ultrasound system to perform the following operations: Multiple transesophageal echocardiogram images were received during resuscitation transesophageal echocardiography (S320); Interpretation (S330) of each of the multiple transesophageal echocardiogram images; Output (S390) each of the multiple transesophageal echocardiogram images; as well as Guidelines for capturing additional transesophageal echocardiograms are generated (S380) and output (S390) based on the interpretation of each transesophageal echocardiogram image from the plurality of transesophageal echocardiogram images.

2. The ultrasound system according to claim 1, wherein, When executed by the processor, the instructions also cause the ultrasound system to perform the following operations: For at least one cardiac chamber in at least one of the multiple transesophageal echocardiogram images, generate (S345) at least one label; as well as Output (S390) the at least one transesophageal echocardiogram image having the at least one label of the at least one heart chamber.

3. The ultrasound system according to claim 2, wherein, When executed by the processor, the instructions also cause the ultrasound system to perform the following operations: Selective identification (S340) of which of the multiple transesophageal echocardiogram images should be labeled.

4. The ultrasound system according to claim 1, wherein, When executed by the processor, the instructions also cause the ultrasound system to perform the following operations: Based on the interpretation of each transesophageal echocardiogram image in the aforementioned transesophageal echocardiogram, the clinical disease state associated with cardiac arrest is detected (S350); and Output (S390) the clinical disease state described.

5. The ultrasound system according to claim 4, wherein, The clinical disease state is detected based on identifying abnormalities associated with the clinical disease state in at least one of the transesophageal echocardiogram images.

6. The ultrasound system according to claim 1, wherein, When executed by the processor, the instructions also cause the ultrasound system to perform the following operations: View quality is detected (S335) based on the interpretation of each of the multiple transesophageal echocardiogram images, wherein the guidance includes instructions for improving the view quality.

7. The ultrasound system according to claim 6, wherein, The view quality is detected by applying an image classification model to each of the multiple transesophageal echocardiogram images and detecting and quantifying predetermined anatomical features in each of the multiple transesophageal echocardiogram images to determine the guidance to be output.

8. The ultrasound system according to claim 1, wherein, The instructions include commands for obtaining the sound window.

9. The ultrasound system according to claim 1, wherein, When executed by the processor, the instructions also cause the ultrasound system to perform the following operations: Cardiac arrest is identified (S360) by interpreting each of the multiple transesophageal echocardiogram images. Measure the duration of cardiac arrest as described in (S365); as well as The guidance outputs (S390) an indication of the duration of the cardiac arrest.

10. The ultrasound system according to claim 1, further comprising: A display (180 / smart device A and / or smart device B) is used to output the multiple transesophageal echocardiogram images and the instructions.

11. The ultrasound system according to claim 1, wherein, When executed by the processor, the instructions also cause the ultrasound system to perform the following operations: Automatic control (S335 = No) of the ultrasound probe to capture a set of transesophageal echocardiogram images from the plurality of transesophageal echocardiogram images; and The optimal imaging plane for observing cardiac anatomy is identified by interpreting the set of transesophageal echocardiograms from the multiple transesophageal echocardiogram images.

12. The ultrasound system according to claim 1, wherein, When executed by the processor, the instructions also cause the ultrasound system to perform the following operations: Automatically save (S385) a subset of transesophageal echocardiogram images corresponding to the detected cardiac events, as well as metadata for the subset of transesophageal echocardiogram images.

13. A method of operating an ultrasound system for resuscitation transesophageal echocardiography, the ultrasound system comprising a memory storing instructions and a processor executing the instructions, the method comprising: Multiple transesophageal echocardiogram images were received during resuscitation transesophageal echocardiography (S320); Interpretation (S330) of each of the multiple transesophageal echocardiogram images; Output (S390) each of the multiple transesophageal echocardiogram images; as well as Guidelines for capturing additional transesophageal echocardiograms are generated (S380) and output (S390) based on the interpretation of each transesophageal echocardiogram image from the plurality of transesophageal echocardiogram images.

14. The method of claim 13, further comprising: For at least one cardiac chamber in at least one of the multiple transesophageal echocardiogram images, generate (S345) at least one label; Output (S390) the at least one transesophageal echocardiogram image having the at least one label of the at least one heart chamber; as well as Selective identification (S340) of which of the multiple transesophageal echocardiogram images should be labeled.

15. The method of claim 13, further comprising: Based on the interpretation of each transesophageal echocardiogram image in the aforementioned transesophageal echocardiogram, the clinical disease state associated with cardiac arrest is detected (S350); and Output (S390) the clinical disease state, wherein the clinical disease state is detected based on identifying abnormalities associated with the clinical disease state in at least one of the transesophageal echocardiogram images.

16. The method of claim 13, further comprising: View quality is detected (S335) based on the interpretation of each of the multiple transesophageal echocardiogram images, wherein the guidance includes instructions for improving the view quality, wherein the view quality is detected by: applying an image classification model to each of the multiple transesophageal echocardiogram images, and detecting and quantifying predetermined anatomical features in each of the multiple transesophageal echocardiogram images to determine the guidance to be output.

17. The method according to claim 13, wherein, The instructions include commands for obtaining the sound window.

18. The method of claim 13, further comprising: Cardiac arrest is identified (S360) by interpreting each of the multiple transesophageal echocardiogram images. Measure the duration of cardiac arrest as described in (S365); as well as The guidance outputs (S390) an indication of the duration of the cardiac arrest.

19. The method of claim 13, further comprising: An ultrasound probe is automatically controlled by a robot (S335 = No) to capture a set of transesophageal echocardiogram images from the plurality of transesophageal echocardiogram images; as well as The optimal imaging plane for observing cardiac anatomy is identified by interpreting the set of transesophageal echocardiograms from the multiple transesophageal echocardiogram images.

20. The method of claim 13, further comprising: Automatically save (S385) a subset of transesophageal echocardiogram images corresponding to the detected cardiac events, as well as metadata for the subset of transesophageal echocardiogram images.

21. A tangible, non-transient computer-readable medium storing instructions for resuscitation transesophageal echocardiography, the instructions causing the processor to perform the following operations when executed by a processor: Multiple transesophageal echocardiogram images were received during resuscitation transesophageal echocardiography (S320); Interpretation (S330) of each of the multiple transesophageal echocardiogram images; Output (S390) each of the multiple transesophageal echocardiogram images; and Guidelines for capturing additional transesophageal echocardiograms are generated (S380) and output (S390) based on the interpretation of each transesophageal echocardiogram image from the plurality of transesophageal echocardiogram images.

Images