Ultrasound examination tracking

Abstract

Ultrasound imaging devices, systems, and methods are provided. The system is configured to determine and track manipulation of an ultrasound probe during an ultrasound examination. The tracked probe manipulation may be synchronized with recorded user inputs received by the system during the examination. Probe manipulations paired with user input are stored as a full log file that records inspection, and then the full log file is converted into a narrative text summary for viewing by a user. A neural network is implemented to determine the position and orientation of the probe utilized during the examination based on the landmarks identified in the acquired image frames. User input received by the system is filtered such that only input indicative of inspection performance is paired with the determined manipulation of the probe. External sensors are not necessary to track probe motion, but may be implemented to enhance or replace specific system features.

Description

Technical Field

[0001] The present disclosure relates to devices, systems and methods for capturing, storing and communicating information related to ultrasound probe manipulations performed during an imaging examination. Embodiments relate to determining probe position and orientation based on image frames acquired during an ultrasound examination, and recording this information along with discrete user inputs received by the imaging system during the examination to generate a comprehensive record of the user's performance. Background Art

[0002] Log files generated during ultrasound imaging exams provide insightful information about exam workflow and efficiency. In ultrasound imaging, every button and key pressed by the sonographer can be recorded and stored in workflows and utilization scripts. Thus, each individual exam can be recorded as a sequence of events that together captures a workflow narrative of the scan from start to finish. Ongoing log file analysis can be used to modify the layout of the ultrasound system to improve workflow, and design customizable dynamic keyboards and touch screens that mimic user preferences. The same analysis can inform modifications to underlying scan protocols that require unnecessary and inefficient user actions.

[0003] While usage information captured and stored in log files has proven valuable in shaping system and protocol design, additional improvements are needed to accurately monitor and record sonographer performance in a manner that can enhance user feedback and augment current data capture techniques. Summary of the invention

[0004] The present disclosure describes devices, methods, and systems configured to capture and store information related to ultrasound probe manipulations performed by a user during an ultrasound examination. Image frames acquired during an ultrasound examination can be used to determine probe manipulation data that may include a base probe position and orientation. Specifically, the image frames can be input to a neural network that is trained to estimate the associated probe position / orientation for acquiring the image frames based on landmarks identified within the frames. The probe manipulation data can be recorded in a log file along with recorded user inputs, such as button presses and keystrokes typically received by the imaging system during an examination. By pairing the probe manipulation data with the user inputs and the standard views associated with the selected imaging protocol, a comprehensive record of user performance and examination workflow can be generated. An embodiment can also convert the comprehensive record embodied by the log file into a narrative text description provided to ultrasound examiners, laboratory managers, and radiologists for review.

[0005] According to an embodiment of the present disclosure, an ultrasound imaging system may include an ultrasound probe configured to acquire echo signals in response to ultrasound pulses emitted toward an object during ultrasound. The system may also include an input unit for predefined user inputs associated with an inspection protocol similar to an ultrasound inspection. The system may also include one or more processors in communication with the ultrasound probe. The processor may be configured to determine and track manipulations of the ultrasound probe performed during the ultrasound inspection based on image frames generated according to the echo signals; identify meaningful user inputs received during the ultrasound inspection that indicate compliance with the inspection protocol; and generate a log file recording the manipulations and meaningful user inputs.

[0006] In some examples, meaningful user input may include adjustment of at least one image acquisition setting, including one or more of: gain, scan depth, image contrast level, color scale, probe type, frequency, or imaging mode. In some examples, meaningful user input may include one or more of: image snapshots, labels, or measurements of one or more features present in an image frame. In some examples, manipulation of the ultrasound probe includes changes in probe position and orientation.

[0007] In some examples, one or more processors may be configured to determine and track manipulation of an ultrasound probe by inputting image frames into a neural network. The neural network may be trained to identify at least one landmark present in one or more of the image frames, and determine one or more ultrasound probe orientations and / or positions used to obtain the one or more image frames based on at least one landmark identified in the one or more image frames. In some examples, the at least one landmark includes one or more of the following: an anatomical feature, an image artifact, a medical instrument, or a transducer marker. In some examples, the one or more processors may be configured to identify meaningful user inputs received during an ultrasound examination that indicate compliance with an examination protocol by comparing a total list of actual user inputs with a list of expected user inputs, the list of expected user inputs being associated with the examination protocol.

[0008] In some examples, one or more processors may be configured to generate a log file recording manipulation and meaningful user input by generating a first log file recording meaningful user input, generating a second log file recording manipulation of the ultrasound probe, and synchronizing the first log file with the second log file. In some examples, one or more processors may be configured to generate a log file recording manipulation and meaningful user input by generating a first log file recording meaningful user input, generating one or more target events recording manipulation of the ultrasound probe, and inserting the one or more target events into the first log file based on a unique timestamp associated with each of the one or more target events.

[0009] In some examples, the one or more processors may also be configured to generate narrative text describing the manipulations and meaningful user inputs recorded in the log file. In some examples, the one or more processors may also be configured to determine and track manipulation of the ultrasound probe based on input received from an external sensor that monitors the movement of the user manipulating the ultrasound probe. In some examples, the one or more processors may be configured to determine and track manipulation of the ultrasound probe by inputting input received from the external sensor into a neural network. The neural network may be configured to identify one or more of the following: a relative position, orientation, or angle between two or more anatomical features of the user, and determine one or more ultrasound probe orientations and / or positions corresponding to at least one relative position or angle.

[0010] According to an embodiment of the present disclosure, an ultrasound imaging method may involve: acquiring, by an ultrasound probe during an ultrasound examination, echo signals in response to ultrasound pulses transmitted into a target area of ​​an object; receiving input of predefined user inputs associated with an examination protocol similar to the ultrasound examination; determining and tracking manipulation of the ultrasound probe performed during the ultrasound examination based on image frames generated according to the echo signals; identifying meaningful user inputs received during the ultrasound examination that indicate compliance with the examination protocol; and generating a log file recording the manipulations and meaningful user inputs.

[0011] In some examples, meaningful user input may include adjustment of at least one image acquisition setting, the at least one image acquisition setting including one or more of the following: gain, scan depth, image contrast level, color scale, probe type, frequency, or imaging mode. In some examples, manipulation of the ultrasound probe may include changes in probe position and orientation. In some examples, determining and tracking manipulation of the ultrasound probe may involve identifying at least one landmark present in one or more of the image frames, and determining one or more ultrasound probe orientations and / or positions used to obtain the one or more image frames based on the at least one landmark identified in the one or more image frames. In some examples, the at least one landmark includes one or more of the following: anatomical features, image artifacts, medical instruments, or transducer markers.

[0012] In some examples, generating a log file that records the manipulation and meaningful user input may involve generating a first log file that records the meaningful user input, generating a second log file that records the manipulation of the ultrasound probe, and synchronizing the first log file with the second log file. In some examples, generating a log file that records the manipulation and meaningful user input may involve generating a first log file that records the meaningful user input, generating one or more target events that record the manipulation of the ultrasound probe, and inserting the one or more target events into the first log file based on a unique timestamp associated with each of the one or more target events.

[0013] Any method or steps thereof described herein may be embodied in a non-transitory computer-readable medium comprising executable instructions which, when executed, may cause one or more hardware processors to perform the method or steps embodied herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a block diagram illustrating an example of an ultrasound system configured for comprehensive tracking and recording of user performance during an imaging examination in accordance with an embodiment of the present disclosure.

[0015] Figure 2 is a block diagram of a collection of computing modules that may be implemented according to embodiments of the present disclosure.

[0016] Figure 3 is a series of ultrasound images analyzed according to an embodiment of the present disclosure.

[0017] Figure 4 is a collection of example graphics representing utilization of external sensors according to embodiments of the present disclosure.

[0018] Figure 5 is an example record of user input received during an ultrasound imaging examination in accordance with an embodiment of the present disclosure.

[0019] Figure 6 is a representation of an abbreviated log file that may be generated according to embodiments disclosed herein.

[0020] Figure 7 is a schematic diagram of generating and using a workflow log file that records ultrasound system usage and probe manipulation to generate a narrative examination summary according to embodiments disclosed herein.

[0021] Figure 8 is a block diagram illustrating an example processor implemented according to an embodiment of the present disclosure.

[0022] Fig. 9 is a block diagram illustrating additional components of an ultrasound system configured for comprehensive tracking and recording of user performance during an imaging examination in accordance with an embodiment of the present disclosure.

[0023] Fig.10 is a flow chart of a method implemented according to at least one embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] Various embodiments are described more fully below with reference to the accompanying drawings, which form a part of the present invention and illustrate specific exemplary embodiments. However, the embodiments can be implemented in many different forms and should not be construed as being limited to the embodiments set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be thorough and complete, and the scope of the embodiments will be fully conveyed to those skilled in the art. The embodiments can be practiced as methods, systems, or devices. Therefore, the embodiments can take the form of hardware implementations, complete software implementations, or implementations combining software and hardware aspects. Therefore, the following detailed description should not be considered as limiting.

[0025] References in the specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present invention. The appearance of the phrase "in one embodiment" in various places in the specification does not necessarily refer to the same embodiment.

[0026] As used herein, a "user" may include various medical professionals, clinicians, and personnel, a non-limiting example of which may include a sonographer.

[0027] As used herein, "user input" may refer to discrete manual inputs received by an ultrasound imaging system before, during, and / or after an imaging examination. The user inputs may be implemented to perform various actions required for examination performance, such as taking a snapshot of an image containing specific features, marking various features, measuring specific features, indicating completion of one or more steps set forth in an examination protocol, initiating ultrasound image acquisition, and / or adjusting various image acquisition parameters, such as image gain, scan depth, image contrast, image brightness, color scale, imaging mode, etc. Non-limiting examples of discrete user inputs may include button presses, keystrokes, trackball adjustments, switch actuations, touch screen engagements, etc.

[0028] As used herein, "probe steering" may refer to adjustments of the probe position and orientation performed by a user during an ultrasound examination, including translational and rotational movements. Probe steering may be defined relative to a stationary object being imaged.

[0029] As used herein, a "subject" may refer to a patient receiving outpatient or inpatient medical care, which may involve a medical treatment or examination. The term "subject" is not limited to medical patients; it may also refer to a human or animal being imaged by an imaging system for various reasons in various settings.

[0030] Some parts of the following description are presented in terms of symbolic representations of operations on non-transient signals stored in computer memories. These descriptions and representations are means by which those skilled in the art of data processing use the essence of their work to most effectively communicate to other skilled in the art. Such operations typically require physical manipulation of physical quantities. These quantities can take the form of electrical, magnetic, or optical signals that can be stored, transmitted, combined, compared, and otherwise manipulated. Sometimes, primarily for reasons of common use, it is convenient to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, etc. In addition, it is sometimes also convenient to refer to specific arrangements of steps that require physical manipulation of physical quantities as modules or code devices without loss of generality.

[0031] However, all of these and similar terms will be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless otherwise specified, as will be apparent from the following discussion, it should be understood that throughout this specification, discussions utilizing terms such as "processing," "computing," "calculating," "determining," "displaying," etc. refer to the actions and processes of a computer system or similar electronic computing device that manipulates and transforms data represented as physical electronic quantities within a computer system memory or registers or other such information storage, transmission or display device.

[0032] Certain aspects of the invention include process steps and instructions that can be embodied in software, firmware, or hardware, and when embodied in software, can be downloaded to reside on and be operated from different platforms used by various operating systems. Embodiments can include one or more applications available on the Internet, such as software as a service (SaaS), which is accessible using various computer devices (e.g., smart phones, tablet computers, desktop computers, etc.).

[0033] The present invention also relates to at least one device configured to perform one or more operations disclosed herein. The device may be specially constructed for the desired purpose, or it may include a general-purpose computer selectively activated or reconfigured by a computer program stored in the computer. Such a computer program may be stored in a computer-readable storage medium, and its non-limiting examples may include a read-only memory (ROM), a random access memory (RAM), an EPROM, an EEPROM, a magnetic card or an optical card, an application-specific integrated circuit (ASIC), an optical disk, a CD-ROM, a floppy disk, a magneto-optical disk, or any type of medium suitable for storing electronic instructions, and each is coupled to a computer bus. In addition, the computer mentioned herein may include a single processor, or may be an architecture designed with multiple processors to improve computing power.

[0034] Ultrasound systems according to the present disclosure may implement one or more neural networks, such as at least one deep neural network (DNN), convolutional neural network (CNN), etc., which may be uniquely synchronized with data acquisition hardware and at least one user interface. The example system may utilize at least one neural network to identify various anatomical and / or artificial features present in the acquired ultrasound images and output corresponding ultrasound probe positions / or orientations. Analysis of the neural network output on a frame-by-frame, frame stack, and / or movie loop basis may be used to determine probe manipulations in the form of changes in probe position and / or orientation.

[0035] In various examples, a neural network can be trained using any of a variety of currently known or later developed machine learning techniques to obtain a neural network (e.g., a machine-trained algorithm or a hardware-based node system) that is configured to analyze input data in the form of ultrasound image frames and identify specific features, such as anatomical features, ultrasound artifacts (e.g., A-lines or B-lines), medical equipment, etc.

[0036] Neural networks can provide advantages over traditional forms of computer programming algorithms because they can be generalized and trained to identify data set features by analyzing data set samples rather than by relying on dedicated computer code. By presenting appropriate input and output data to the neural network training algorithm, the (one or more) neural networks of an ultrasound system according to the present disclosure can be trained to identify multiple anatomical and / or artificial features present within an ultrasound image frame and output an indication of the probe position and / or orientation used to acquire the image frame.

[0037] Neural networks utilized in accordance with the present disclosure may be hardware (e.g., neurons represented by physical components) or software-based (e.g., neurons and pathways implemented in a software application), and may be capable of using a variety of topologies and learning algorithms to train the neural network to produce a desired output. For example, a software-based neural network may be implemented using a processor (e.g., a single-core or multi-core CPU, a single GPU or GPU cluster, or multiple processors arranged for parallel processing) configured to execute instructions that may be stored in a computer-readable medium and, when executed, cause the processor to execute a machine-trained algorithm.

[0038] The ultrasound system may include a display or graphics processor operable to arrange the ultrasound image and / or additional graphical information in a display window for display on a user interface of the ultrasound system, the additional graphical information may include a work list of features to be imaged and / or measured and previously measured features, feature labels, annotations, tissue information, patient information, indicators, and other graphical components. In some embodiments, the ultrasound image, received user input, probe manipulation data, and / or a log file recording the same may be provided to a storage device and / or memory device, such as a picture archiving and communication system (PACS), for reporting purposes, user guidance instructions, development progress tracking, or future machine training (e.g., to continue to enhance the performance of the neural network). In some examples, the ultrasound image obtained during the scan may be selectively or automatically transmitted, for example, via a communications network, to an expert trained to interpret the information embodied in the image, such as a radiologist, ultrasound expert, physician, or other clinician.

[0039] Figure 1An example ultrasound system 100 according to an embodiment of the present disclosure is shown. As shown, the ultrasound system 100 may include an ultrasound data acquisition unit 110, which includes an ultrasound probe 111, which includes an ultrasound transducer array 112, which is configured to transmit ultrasound pulses 114 into a region 116 of a subject (e.g., an abdomen), and receive ultrasound echoes 118 in response to the transmitted pulses. As further shown, the ultrasound data acquisition unit 110 can include a beamformer 120 and a signal processor 122, which can be configured to generate a stream of discrete ultrasound image frames 124 from the ultrasound echoes 118 received at the array 112. The system can also include at least one data processor 126, such as a computing module or circuit, which can be configured to implement at least one deep neural network 128.

[0040] The neural network 128 may be configured to receive the image frames 124 directly from the signal processor 122 or via the data processor 126 and determine the corresponding view represented by each frame and the position and / or orientation of the ultrasound probe 111 that may have been used to acquire the image frames. The neural network 128 may operate in real time or substantially real time during an ultrasound examination by identifying one or more features or markers present in the image frames 124 on a frame-by-frame basis. In embodiments, the neural network 128 may also operate based on a frozen buffer or based on a review study. By analyzing the output of the neural network 128 in the context of a selected scanning protocol, the data processor 126 may be configured to determine user manipulation of the probe 111 in the form of probe motion, e.g., changes in probe position and orientation relative to the region 116 of the imaged object. In some embodiments, two or more neural networks 128 may be implemented by the data processor 126. Examples may include neural networks specifically trained to analyze image frames of a particular type and / or image frames generated according to a particular examination type.

[0041] In some examples, the system 100 also includes a display processor 130 coupled to the data processor 126 and the graphical user interface 132. The display processor 130 can link the neural network 128 and the data processor 126 to the user interface 132 so that outputs generated by one or both components can be displayed on the user interface 132. The user interface 132 can be configured to display an ultrasound image 134 of the region 116 in real time or substantially real time as the ultrasound examination is performed. Additional graphics displayed on the user interface 132 can include anatomical measurements obtained by the system and / or user, labeled anatomical and / or artificial features visible in the acquired image frames, bounding boxes generated around specific features, and the like.

[0042] The user interface 132 may also be configured to receive various user inputs 136 at any time before, during, and / or after the ultrasound examination. As described above, the user inputs 136 may include discrete manual inputs implemented to perform the ultrasound examination, such as button presses or keystrokes. With respect to the user interface 132, such inputs may include tapping or dragging various displayed icons. In addition, the user inputs 136 may include user requests to view acquisition parameters and / or probe manipulations implemented to obtain a given image. Such inputs may include manually clicking, tapping, or otherwise selecting a particular image of interest displayed on the user interface 132 during or after the ultrasound examination. In addition, the system 100 may include at least one hardware component 138, such as a keyboard, a mouse, a trackball, etc., which is configured to receive user inputs 136 and is coupled to the data processor 126 and the acquisition unit 110.

[0043] As further shown, the system 100 may include a memory 140 configured to store various data, such as neural network outputs, data processor outputs, image frames, etc. The memory 140 may also store log files generated during and after an ultrasound examination. The log files may include information recording time-stamped user inputs, such as button presses, and corresponding probe positions / orientations, probe manipulations, landmarks identified by the neural network, and image views associated therewith.

[0044] In some embodiments, the system 100 may additionally or alternatively include an external sensor 142 configured to detect and monitor the movement of a user operating the ultrasound probe 111. The external sensor 142 may include a camera that may be installed in the examination room. The data processor 126 may be communicatively coupled to the external sensor 142 and configured to determine the manipulation of the probe 111 using the corresponding movement of the user detected by the sensor 142. As described below in conjunction with Figure 2 Further elaborated, one or more additional neural networks may be trained using input received from sensor 142 to output probe position / orientation / motion. In various examples, sensor 142 may be omitted. In other cases, sensor 142 may replace or augment the image-based operation of neural network 128.

[0045] Figure 1The configuration of the system 100 shown can vary. For example, at least a portion of the system 100 can be portable or fixed. Various portable devices (e.g., laptops, tablets, smart phones, or other handheld devices) can be used to implement one or more functions of the system 100. In an embodiment incorporating such a device, the ultrasound probe 111 can be connected via a USB interface. Various transducer arrays can be used, such as linear arrays, convex arrays, or phased arrays. The number and arrangement of the transducer elements included in the sensor array 112 can vary in different examples. For example, the ultrasound sensor array 112 can include a 1D or 2D array of transducer elements, corresponding to a linear array and a matrix array probe, respectively. The 2D matrix array can be configured to electronically scan (via phased array beamforming) in both the elevation dimension and the azimuth dimension for 2D or 3D imaging. In addition to B-mode imaging, the imaging modality implemented according to the disclosure herein can also include, for example, shear waves and / or Doppler.

[0046] Various users may manipulate and operate the ultrasound data acquisition unit 110 to perform the methods described herein. In some examples, the user may be an inexperienced, novice ultrasound operator who may not be able to effectively identify every anatomical or artifactual feature that needs to be acquired in a given scan.

[0047] Figure 2 1 is a block diagram of an example set of computing modules that may be embodied or implemented by the data processor 126 alone or by one or more data processors operating simultaneously or sequentially with the data processor 126. The modules may include an image-based probe position / orientation module 202 that runs at least one deep neural network 204, an image-based motion tracker module 206, a sensor-based probe position / orientation module 207, a sequence pattern analysis module 208, a log file generation module 210, and a narrative module 212. As depicted, the modules may be separate and distinct, or two or more of the modules may be combined into a single module, circuit, or processor. For example, the image-based probe position / orientation module 202 and the motion tracker module 206 may constitute a single module configured to perform multiple functions. Additional embodiments may feature a processor (e.g., a signal path processor) dedicated to running at least one deep neural network and / or identifying ultrasound probe position, orientation, and / or movement. One or more additional processors may be configured to generate a log file that records user actions during an ultrasound examination, identify significant user inputs received during the examination, and / or convert the generated log file into a narrative text description.

[0048] The image-based probe position / orientation module 202 may be configured to implement at least one deep neural network 204 that is trained to determine and extract the position and orientation of the ultrasound probe relative to an object being imaged during an ultrasound examination. In an embodiment, the neural network 204 may be trained to recognize various landmarks present within a particular ultrasound image and / or image cycle acquired during an ultrasound examination. Non-limiting examples of such landmarks may include anatomical features, such as organs, bones, and the like, and characteristics thereof, such as the shape of an organ, the adjacency of two or more organs, and the like. Additional landmarks recognized by the neural network 204 may include artificial features, such as ultrasound imaging artifacts (e.g., A-lines or B-lines), medical instruments, transducer markers, and the like.

[0049] Using the (one or more) identified landmarks present in a given image frame, the neural network 204 can determine the associated probe position / orientation used to acquire the image. At the beginning of the examination, the neural network 204 output related to the probe view / position / orientation can provide an initial context for a particular scanning protocol, so that subsequent determinations of probe manipulation can be predicted and / or determined in view of the remaining steps required by the protocol. Once the initial imaging context has been estimated, the motion of the probe can be "tracked" by performing frame-to-frame analysis and accumulating the estimated motion vectors together. Other analytical or non-analytical (AI-based) methods of motion tracking are also possible. Such motion tracking can increase the confidence of the initial context estimate, or if the probe moves to a new location, it can extend / update the context to the new scanning area.

[0050] In some examples, the neural network 204 can be configured to operate on a frame-by-frame basis so that the determination of the probe position / orientation can be repeated in real time or substantially real time throughout the ultrasound examination. Rapidly operating the neural network 204 in this manner can enable detection of subtle changes in the probe position / orientation, thereby improving the sensitivity of the system as a whole, which may be particularly important for accurately capturing probe manipulations performed when examining relatively small target areas (such as the heart).

[0051] The image-based motion tracker module 206 can be configured to determine probe manipulation, such as adjustment of probe position and orientation, by comparing the determined position and orientation of the probe across multiple image frames using the frame-by-frame output generated by the neural network 204. In some examples, the determination of probe manipulation can be performed at least in part without analyzing the neural network output. For example, one or more signal processing techniques employed during ultrasound scanning can be used to initiate and / or perform motion tracking. Additionally or alternatively, the motion tracker module 206 can be configured to determine probe manipulation and the resulting probe position / orientation by serially linking the estimated motion vectors from one image frame to the next image frame using the initial context provided by the neural network 204 as a starting point. By cumulatively adding motion vectors in this manner, information indicating how the user navigates the scanning protocol can be obtained without using external sensors (e.g., mounted cameras, electromagnetic sensors, or optical trackers). External or inefficient probe manipulations can also be identified and marked for subsequent inspection. Motion tracking can also increase the confidence of the initial context estimate or update and / or expand the context to a new scanning area when the probe moves.

[0052] Some embodiments may include a sensor-based probe position / orientation module 207 configured to augment or replace the image-based modules 202 and / or 206 by extracting the probe position / orientation / motion using at least one external sensor coupled thereto. For embodiments where the external sensor includes a camera mounted in the examination room, the sensor module 207 may be configured to identify and track key anatomical features of a user manipulating the ultrasound probe to interpret user movements in six degrees of freedom (6DoF) and thus perform probe manipulation. For example, the user's arm, wrist, and hand may all be associated with probe manipulation. The external sensor may detect the position and movement of any or all of these anatomical features of the user throughout the examination, which the sensor-based probe position / orientation module 207 may then utilize to determine the corresponding probe position / orientation / motion during the examination. The sensor-based probe position / orientation module 207 may also be configured to mask one or more features visible to the sensor, such as sensitive anatomical features of the subject that are not to be recorded due to privacy concerns. In some examples, the sensor-based probe position / orientation module 207 may also be configured to operate a deep neural network 209 trained to recognize specific positions of the user and link those positions to corresponding image views and / or probe positions / orientations / motions.

[0053] The sequence pattern analysis module 208 can be configured to identify, filter, and select the most meaningful user inputs, such as button presses and keystrokes, received by the imaging system during a given examination to include in a final log file summary of the examination. Meaningful user inputs can include inputs required to perform a particular scanning protocol, including one or more operations, steps, or acquisitions implemented in conjunction with it. Meaningful inputs can also include inputs that may not be required to implement the scanning protocol, but which can indicate specific user actions that can be captured and recorded to accurately record significant details of the user's performance. For example, meaningful inputs can include user inputs indicating incidental findings and their subsequent examination.

[0054] As an illustration, a specific button sequence is typically pressed during a given ultrasound examination for image optimization, quantification, and feature measurement. For example, an abdominal imaging scan typically involves marking of the kidneys, aorta, and inferior vena cava, as well as obtaining measurement feature length, width, height, circumference, and / or stenosis. Each of the aforementioned actions can be associated with one or more meaningful user inputs. It is also possible to initiate color Doppler imaging, shear wave elastic imaging, and microflow imaging examinations during the examination to obtain one or more recorded measurements / markers. The initiation and termination of these additional imaging modes can also constitute meaningful user inputs. In a particular embodiment, the sequence pattern analysis module 208 can be configured to extract N user inputs that jointly summarize the workflow associated with image acquisition and final probe orientation. Extraction can be triggered based on the current image view and the remaining steps to be followed according to the selected scanning protocol. In some embodiments, the sequence pattern analysis module 208 can be configured to perform sequential pattern mining to pre-select the most frequent button usage patterns implemented by the user during a given ultrasound scan based on real-time imaging context and clinical operations.

[0055] In addition to performing sequence analysis to identify meaningful user inputs that describe or add value to an examination, the sequence pattern analysis module 208 may also determine various indicators of user performance, such as the "percent usefulness" of user actions. For example, the system may determine that 70% of user button presses are necessary for an examination, or that a user completes an examination with an average export view time of T minutes, which may be faster or slower than X% of users who perform the same examination on the same or similar objects. These determinations may be made by comparing the actual user inputs received during the examination to a set of predefined expected inputs associated with a particular examination protocol. These and other similar statistics may be particularly valuable for determining and monitoring changes in user performance over time. Similar performance statistics may also be used to modify one or more components of the imaging system and / or protocols associated with a particular examination type to improve workflow. Such adjustments may be made in response to common performance inefficiencies detected across multiple users.

[0056] The log file generation module 210 can be configured to pair the probe position / orientation / movement determined by modules 202, 206 and / or 207 with the log file of the meaningful user input selected by the sequence pattern analysis module 208, so that the meaningful user input recorded in the log file is enhanced by the probe manipulation data. Probe manipulation data can be paired with meaningful user input in a variety of ways. In some embodiments, for example, the log file generation module 210 can be configured to create a new target event in an existing XML / CDF workflow log file, wherein each new target event can record the probe view, position, orientation and / or motion corresponding to a specific timestamp. According to such an embodiment, the log file generation module 210 can insert the newly created event into the existing log file of the associated user input with the same timestamp. Additionally or alternatively, the log file generation module 210 can be configured to generate a brand new log file specifically for probe position, orientation and motion, and then merge or synchronize via the timestamp with the acquisition workflow embodied by the meaningful user input. Thus, embodiments may involve obtaining or receiving a predetermined scan protocol that may be associated with predefined user inputs required to execute the protocol, identifying meaningful user inputs from a current examination, pairing the meaningful user inputs with probe position / orientation data, and in some cases, comparing the paired data to the predetermined scan protocol.

[0057] A comprehensive log file that records both probe manipulations and meaningful user inputs performed during a given ultrasound examination can provide a detailed record of the examination for further review and a detailed set of instructions for users to perform the same or similar examinations on the same or similar objects in the future. Future users can, for example, use the log file associated with a given image to determine which user inputs and probe manipulations were required to obtain the image. In particular, a comprehensive log file can also facilitate radiologist review, which may be particularly useful for analyzing challenging instances associated with low image quality (e.g., instances involving high BMI objects).

[0058] Because the raw data embodying the user input and probe manipulation recorded in the log file may not be particularly helpful to the clinician trying to interpret the inspection workflow and performance, the narrative module 212 can be configured to convert the log file into a readable narrative of the inspection. In some examples, the user-friendly narrative may include a text summary of the inspection generated via natural language processing of the log file script. The written summary of the most meaningful steps that can include a step-by-step narrative of discrete steps or user actions implemented during a specific scan and the scan can be easily read by a person reviewing the inspection (such as a radiologist). Therefore, the review made possible by the operation of the narrative module 212 can enable the reviewer to determine whether the user follows the scanning protocol and interpret whether an incidental finding is obtained. The narrative generated for a specific inspection can also provide improved guidance to future users performing the same inspection by revealing how the previous user performed the inspection (e.g., by showing what probe operation was performed to collect a specific image). Considering that the same user cannot always perform the same inspection of the same object in reality, the instructions provided by the generated narrative can improve the accuracy of the inspection findings and the conclusions drawn therefrom, while also improving the speed and efficiency of the inspection. To convert the log file into narrative text, the narrative module 212 may access and retrieve the log file from a memory (eg, the memory 140 ).

[0059] Figures 3 to 7 Included are images, schematics, and sample log files illustrating various operations of the above-described modules, which, as noted above, may each be separate and distinct or unified into one or more processors, such as data processor 126 .

[0060] Figure 3 Various image snapshots taken during an abdominal scan according to embodiments disclosed herein are shown. Image 302 includes various features, one or more of which can be identified by a deep neural network configured to output the position and orientation of the ultrasound probe used to acquire image 302. In the particular snapshot shown, the system determines that the probe is in a transverse orientation at the lower right side of the abdomen, given the features shown in the image, including transducer marker 303.

[0061] Image 302 can be used by the system to determine the initial context of the ultrasound examination, taking into account the associated scanning protocol received via user input or extracted by one or more processors in view of the examination type. In some examples, the examination selection may include a user selecting a tissue preset (TSP) indicating which part of the body is being imaged. By limiting the examination to a specific TSP, the search space to be analyzed by the (one or more) underlying neural networks can be reduced, thereby facilitating the navigation of the scanning protocol and the prediction of possible user inputs, probe positions / orientations / motions, and corresponding views for performing the examination. The search space can vary significantly across different examination types. For example, for abdominal scans, the search space is typically much larger than for cardiac scans, and therefore, the type and degree of probe manipulation performed by the user may be significantly different between the two examinations. It is worth noting that an embodiment can identify an instance of incorrectly selecting a TSP, for example, by determining that the selected TSP is not aligned with a transducer marker, an imaged anatomical feature, an organ shape, and / or an organ proximity. The problem can be marked to the user in real time, for example, via displaying a graphic or an alert on the user interface, so that the necessary adjustments to the TSP selection or probe position / orientation can be made before starting the examination. Additionally or alternatively, the issue can be flagged for inclusion in the final log file record and narrative inspection summary.

[0062] Moving to the right, images 304, 306, and 308 depict various features that may appear and be identified by the image-based probe position / orientation module 202 and / or motion tracker module 206 when manipulating the probe to perform the examination. For example, the module(s) may determine that as the gallbladder enters the view (image 304), the probe must move upward and inward. As the kidneys and liver enter the view (images 306 and 308), the probe must move backward. These determinations can be made by identifying both near-field structures and far-field structures present in the image, and because it is generally observed that the near-field structures visible in each ultrasound image may only change slightly during an abdominal examination, a deep neural network can be trained to focus on landmarks located deeper in the far field. As is apparent from the displayed images, a variety of different features ranging from barely visible hyperechoics can complicate the analysis of each image. Therefore, the automatic identification of specific features indicating probe position / orientation / motion performed by the system herein may be particularly valuable.

[0063] In some examples, the system can be configured to select one of a plurality of deep neural networks given a selected examination protocol. Preselecting a network specifically trained to process images from a particular examination can improve the speed and accuracy of probe position / orientation / motion interpretation.

[0064] Images 310, 312, and 314 include bounding boxes 311, 313, 315 marking specific landmarks that may be utilized and / or generated by a neural network or associated processor and optionally displayed. The neural network(s) may be configured to recognize features present in a given bounding box or to recognize the presence or absence of one or more landmarks from a subset of landmarks. The bounding boxes may be extracted to determine the presence and location of various landmarks, as well as their location relative to each in image space. Cross-frame motion may then be assessed, for example, by the motion tracker module 206 by tracking the relative motion of the landmarks and, therefore, the manipulation of the ultrasound probe used to image them. The specific landmarks used for tracking and their features may vary and may include a mixture of anatomical features and ultrasound artifacts or effects. In some embodiments, relative motion may be determined by tracking speckle noise over a sequence of image frames.

[0065] Figure 4 Various graphics are shown that illustrate examples of key points that can be detected and tracked using external sensors (e.g., cameras) mounted or otherwise positioned in an examination room. As shown in graphic (a), the sensor can be configured to identify and monitor approximately 14 points on the user's body. It should be understood that this number is not limiting, as various sensors can be configured to identify less than or greater than 14 points.

[0066] In the illustrated embodiment, the points are located on the user's neck, shoulder, elbow, wrist, chest, hip, knee and ankle. Figures (b), (c), (d), (e) and (f) illustrate examples of lengths, angles and relative positions between various points that can be detected, measured and recorded during an examination to derive probe manipulations associated therewith. For example, Figures (c) and (d) show that the distance between the user's wrist and shoulder on the same side and the associated angle between the user's forearm and shoulder plane can be measured to determine the probe position. The absolute and relative measurements obtained via (one or more) sensors can be used together to determine and record probe position / orientation / motion with six degrees of freedom (6DoF). In some examples, a sensor-based probe position / orientation module 207 can enhance the determination made by the image-based probe position / orientation module 202 and motion tracker module 206.

[0067] Figure 5Depicted is the identification and selection of meaningful user inputs received during an imaging examination and recorded in the example format shown. As shown, the system can first extract an examination protocol 502 corresponding to an examination performed by a user, thereby also extracting or receiving a set of predefined expected user inputs 503 associated with the protocol 502. Using the extracted examination protocol 502 and expected user inputs 503 as templates, the system can identify which of the multiple actual user inputs 504 received during the examination are necessary to follow the protocol, thereby distinguishing such meaningful inputs (e.g., user inputs 506) from those that are not necessarily required to perform the examination (e.g., user inputs 508). As described above, in particular embodiments, the sequence pattern analysis module 208 can extract N meaningful user inputs, such as button presses, for a given clinical application and workflow associated with a particular scanning protocol.

[0068] Figure 6 An example of an abbreviated log file generated according to an embodiment disclosed herein is depicted. Target event 602 represents a log file event recording probe position / orientation, which is identified and timestamped for insertion into an existing workflow log file recording corresponding user input. As shown, specific event 602 is timestamped "2021-09-11T08:58:58.". The event type is "Probe Orientation" described as "Transverse Probe Orientation in Lower Abdomen - Kidney / Liver".

[0069] If 6DoF is available via operation of at least one external sensor and an associated processor (e.g., sensor-based probe position / orientation module 207), the log file event 604 recording probe position / orientation may further specify "x, y, z, α, β, θ" dimensions.

[0070] Figure 7is a schematic diagram of using a workflow log file that records system use and probe manipulation to generate a point-by-point narrative summary of an ultrasound examination. As shown, a workflow log 702 that records multiple meaningful user inputs can be integrated or synchronized with a newly generated log file or target event 704 created by the disclosed system via landmark recognition and tracking of the acquired ultrasound image 706 and / or external sensor-based tracking of the user performing the examination. The resulting comprehensive log file can then be converted into a narrative summary 708 of the examination, which includes a description of both user input and probe manipulation. The narrative summary 708 can include a list of acquired views and user actions, as well as an indication of whether a particular view and / or user action is considered to be inside or outside the selected scanning protocol. For example, the first listed narrative reads "Longitudinal gallbladder view, image is saved as 'outside the protocol', 2D depth and gain are frequently changed to acquire this view." The second listed narrative reads "Longitudinal common carotid view, image is saved as 'inside the protocol', color label and gain optimization." The third listed narrative reads "Low quality bifurcation transverse view, image is saved as 'inside the protocol'". The fourth narrative reads "Multiple views acquired before a longitudinal renal view and measurements taken after a long probe motion and a series of log changes." The narrative summary may be generated at any time after the log file of the present invention is generated, including after the exam or later.

[0071] Figure 8 800 is a simplified block diagram illustrating an example processor 800 in accordance with the principles of the present disclosure. One or more processors (such as the processor 126 of the system 100 ) for implementing the disclosed methods may be configured the same as or similar to the processor 800 .

[0072] Processor 800 may be any suitable processor type, including but not limited to a microprocessor, a microcontroller, a digital signal processor (DSP), a field programmable gate array (FPGA) in which the FPGA has been programmed to form a processor, a graphics processing unit (GPU), an application specific circuit (ASIC) in which an ASIC has been designed to form a processor, or a combination thereof.

[0073] Processor 800 may include one or more cores 802. Core 802 may include one or more arithmetic logic units (ALUs) 804. In some examples, core 802 may include a floating point logic unit (FPLU) 806 and / or a digital signal processing unit (DSPU) 808 in addition to or instead of ALU 804.

[0074] The processor 800 may include one or more registers 812 communicatively coupled to the core 802. The registers 812 may be implemented using dedicated logic gates (e.g., flip-flops) and / or any memory technology. In some instances, the registers 812 may be implemented using static memory. The registers may provide data, instructions, and addresses to the core 802.

[0075] In some examples, the processor 800 may include one or more levels of cache memory 810 communicatively coupled to the core 802. The cache memory 810 may provide computer readable instructions to the core 802 for execution. The cache memory 810 may provide data for processing by the core 802. In some examples, the computer readable instructions may have been provided to the cache memory 810 by a local memory (e.g., a local memory attached to the external bus 816). The cache memory 810 may be implemented with any suitable cache memory type, for example, a metal oxide semiconductor (MOS) memory such as a static random access memory (SRAM), a dynamic random access memory (DRAM), and / or any other suitable memory technology.

[0076] The processor 800 may include a controller 814 that may control inputs to one or more processors included herein (e.g., processor 126). The controller 814 may control data paths in the ALU 804, FPLU 806, and / or DSPU 808. The controller 814 may be implemented as one or more state machines, data paths, and / or dedicated control logic. The gates of the controller 814 may be implemented as independent gates, FPGAs, ASICs, or any other suitable technology.

[0077] Registers 812 and cache 810 may communicate with controller 814 and core 802 via internal connections 820A, 820B, 820C, and 820D. The internal connections may be implemented as a bus, multiplexer, crossbar switch, and / or any other suitable connection technology.

[0078] Input and output of the processor 800 may be provided via a bus 816, which may include one or more conductive lines. The bus 816 may be communicatively coupled to one or more components of the processor 800, such as the controller 814, cache 810, and / or registers 812. The bus 816 may be coupled to one or more components of the system.

[0079] The bus 816 may be coupled to one or more external memories. The external memory may include a read-only memory (ROM) 832. The ROM 832 may be a masked ROM, an electrically programmable read-only memory (EPROM), or any other suitable technology. The external memory may include a random access memory (RAM) 833. The RAM 833 may be a static RAM, a battery-backed static RAM, a dynamic RAM (DRAM), or any other suitable technology. The external memory may include an electrically erasable programmable read-only memory (EEPROM) 835. The external memory may include a flash memory 834. The external memory may include a magnetic storage device such as a disk 836.

[0080] Fig. 9 is a block diagram of another ultrasound system 900 in accordance with the principles of the present disclosure. Fig. 9 One or more of the components shown may be included in a system that is configured to determine and track a series of probe manipulations and user inputs performed during a particular ultrasound examination. One or more of the components may also be configured to generate a log file that records the tracked manipulations and user inputs. For example, one or more of the above-described functions of the data processor 126 and / or the ultrasound data acquisition unit 110 may be performed by Fig. 9 One or more of the processing components shown (including, for example, a signal processor 926, a B-mode processor 928, a scan converter 930, a multi-planar reformatter 932, a volume renderer 934 and / or an image processor 936) implement and / or control.

[0081] exist Fig. 9In the system, the ultrasound probe 912 includes a transducer array 914 for transmitting ultrasound waves into a target area of ​​an object according to a scanning protocol and receiving echo information in response to the transmitted waves. In various embodiments, the transducer array 914 can be a matrix array or a one-dimensional linear array. The transducer array 914 can be coupled to a microbeamformer 916 in the probe 912, which can control the transmission and reception of signals by the transducer elements in the array. In the example shown, the microbeamformer 916 is coupled to a transmit / receive (T / R) switch 918 via a probe cable, which switches between transmission and reception and protects the main beamformer 922 from high-energy transmission signals. In some embodiments, the T / R switch 918 and other elements in the system can be included in the transducer probe rather than in a separate ultrasound system component. The transmission of ultrasound beams from the transducer array 914 under the control of the microbeamformer 916 can be directed by a transmit controller 920 coupled to the T / R switch 918 and the beamformer 922, which receives input, for example, from user operation of a user interface or control panel 924. A function that can be controlled by the transmit controller 920 is the direction in which the beam is steered. The beam can be steered directly forward from the transducer array (orthogonal to the transducer array), or at different angles for a wider field of view. The partially beamformed signal produced by the microbeamformer 916 is coupled to the main beamformer 922, where the partially beamformed signals from the individual patches of transducer elements are combined into a fully beamformed signal.

[0082] The beamformed signals may be transmitted to a signal processor 926. The signal processor 926 may process the received echo signals in various ways, such as bandpass filtering, decimation, I and Q component separation, and / or harmonic signal separation. The signal processor 926 may also perform additional signal enhancement via speckle reduction, signal compounding, and / or noise elimination. In some examples, the data generated by the different processing techniques employed by the signal processor 926 may be used by a data processor and / or at least one neural network. The processed signals may be coupled to a B-mode processor 928, which may employ amplitude detection for imaging structures in the body. The signals generated by the B-mode processor 928 may be coupled to a scan converter 930 and a multi-plane reformatter 932. The scan converter 930 may arrange the echo signals in a desired image format in a spatial relationship from which the echo signals are received. For example, the scan converter 930 may arrange the echo signals into a two-dimensional (2D) sector format. The multiplanar reformatter 932 may convert echoes received from points in a common plane in a volumetric region of the body into an ultrasound image of the plane, as described in U.S. Pat. No. 6,443,896 (Detmer). In some examples, the volume renderer 934 may convert echo signals of a 3D data set into a projected 3D image viewed from a given reference point, for example, as described in U.S. Pat. No. 6,530,885 (Entrekin et al.). The 2D or 3D image may be transmitted from the scan converter 930, the multiplanar reformatter 932, and the volume renderer 934 to an image processor 936 for further enhancement, buffering, and / or temporary storage for display on an image display 937.

[0083] The graphics processor 940 can generate graphic overlays for display with the processed ultrasound image. These graphic overlays can contain, for example, standard identification information, such as the name of the subject, the date and time of the image, imaging parameters, etc. The overlay can also include one or more indicators of the probe position, orientation, and / or manipulation generated by at least one neural network 938 in conjunction with a particular image frame. In some examples, the graphics processor 940 can receive input from the user interface 924, such as a typed patient name or a confirmation that an instruction displayed or issued from the interface has been confirmed and / or implemented by a user of the system 900. The user interface 924 can also receive input regarding subject characteristics, selection of a particular imaging modality and operating parameters included in such a modality, input prompting adjustments to settings and / or parameters used by the system 900, input requesting additional instructions or assistance for performing an ultrasound scan, and / or input requesting that one or more ultrasound images be saved and / or sent to a remote receiver. The user interface 924 can also be coupled to the multi-plane reformatter 932 for selecting and controlling the display of multiple multi-plane reformatted (MPR) images.

[0084] Fig.10 is a flow chart illustrating an example method for ultrasound imaging involving probe manipulation and received user input determined and tracked during a given ultrasound examination. Example method 1000 shows steps that can be utilized by the systems and / or devices described herein in any order to perform the method, which can further involve storing probe manipulation data along with user input in a comprehensive log file, and converting the log file to narrative text to improve readability. Method 1000 can be performed by an ultrasound imaging system (such as system 100) or other systems including, for example, a mobile system (such as LUMIFY by Koninklijke Philips NV ("Philips")). Additional example systems can include SPARQ and / or EPIQ, also produced by Philips.

[0085] In the illustrated embodiment, the method begins at block 1002 by acquiring echo signals in response to ultrasound pulses transmitted by an ultrasound probe into a target region of a subject during an ultrasound examination.

[0086] At block 1004, the method involves "determining and tracking manipulations of an ultrasound probe performed during an ultrasound examination based on image frames generated from echo signals."

[0087] At block 1006 , the method involves “recognizing user input received during an ultrasound examination indicating compliance with an examination protocol.”

[0088] At block 1008, the method involves "generating a log file recording manipulations and user inputs."

[0089] Of course, it should be understood that according to the present systems, devices and methods, any of the examples, embodiments or processes described herein may be combined with one or more other examples, embodiments and / or processes, or separated and / or performed between separate devices or device portions.

[0090] In various embodiments where components, systems and / or methods are implemented using a programmable device (e.g., a computer-based system or programmable logic), it should be understood that the above-described systems and methods can be implemented using any of a variety of known or later developed programming languages ​​(e.g., "C", "C++", "FORTRAN", "Pascal", "VHDL", etc.). Thus, various storage media can be prepared, such as magnetic computer disks, optical disks, electronic memory, etc., which can contain information that can direct a device such as a computer to implement the above-described systems and / or methods. Once the appropriate device is able to access the information and programs contained on the storage medium, the storage medium can provide the information and programs to the device, thereby enabling the device to perform the functions of the systems and / or methods described herein. For example, if a computer disk containing appropriate materials (such as source files, object files, executable files, etc.) is provided to a computer, the computer can receive the information, configure itself appropriately and perform the functions of the various systems and methods outlined in the above diagrams and flow charts to implement the various functions. That is, the computer can receive various portions of information related to different elements of the above-described systems and / or methods from the disk, implement the various systems and / or methods, and coordinate the functions of the various systems and / or methods described above.

[0091] Finally, the above discussion is intended to be illustrative only of the present system and should not be construed as limiting the claims to any particular embodiment or group of embodiments. Therefore, although the present system has been described in detail with reference to exemplary embodiments, it should also be understood that a person of ordinary skill in the art may devise numerous modifications and alternative embodiments without departing from the broader and intended spirit and scope of the present system as set forth in the claims. Accordingly, the description and drawings should be regarded as illustrative and are not intended to limit the scope of the claims.

Claims

1. An ultrasonic imaging system, comprising: An ultrasound probe (111) configured to acquire echo signals (118) in response to ultrasound pulses (114) emitted toward a subject during ultrasound examination; an input for predefined user input (503) associated with an examination protocol (502) similar to the ultrasound examination; as well as One or more processors (126) in communication with the ultrasound probe and configured to: determining and tracking manipulation of the ultrasound probe performed during the ultrasound examination based on image frames (124) generated from the echo signals; identifying meaningful user input received during the ultrasound examination that indicates compliance with the examination protocol (506); as well as A log file is generated recording the manipulation and meaningful user input (702, 704).

2. The system according to claim 1, wherein: The meaningful user input includes adjustments to at least one image acquisition setting, including one or more of: gain, scan depth, image contrast level, color scale, probe type, frequency, or imaging mode.

3. The system according to claim 1, wherein: The meaningful user input includes one or more of: an image snapshot, a label, or a measurement result of one or more features present in the image frame.

4. The system according to claim 1, wherein: The manipulation of the ultrasound probe includes changes in probe position and orientation.

5. The system according to claim 1, wherein: The one or more processors are configured to determine and track the manipulation of the ultrasound probe by inputting the image frames into a neural network, the neural network being trained to: identifying at least one landmark present in one or more of the image frames; as well as One or more ultrasound probe orientations and / or positions used to obtain the one or more image frames are determined based on the at least one landmark identified in the one or more image frames.

6. The system according to claim 5, wherein: The at least one landmark includes one or more of: an anatomical feature, an image artifact, a medical device, or a transducer marker.

7. The system according to claim 1, wherein: The one or more processors are configured to identify meaningful user inputs received during the ultrasound examination that indicate compliance with an examination protocol by comparing a total list of actual user inputs to a list of expected user inputs associated with the examination protocol.

8. The system according to claim 1, wherein: The one or more processors are configured to generate a log file recording the manipulation and the meaningful user input by: generating a first log file recording the meaningful user input; generating a second log file recording the manipulation of the ultrasound probe; as well as The first log file is synchronized with the second log file.

9. The system according to claim 1, wherein: The one or more processors are configured to generate a log file recording the manipulation and the meaningful user input by: generating a first log file recording the meaningful user input; generating one or more target events recording the manipulation of the ultrasound probe; as well as The one or more target events are inserted into the first log file based on a unique timestamp associated with each of the one or more target events.

10. The system according to claim 1, wherein: The one or more processors are further configured to generate narrative text describing the manipulations and meaningful user input recorded in the log file.

11. The system according to claim 1, wherein: The one or more processors are further configured to determine and track manipulation of the ultrasound probe based on input received from external sensors that monitor movement of a user manipulating the ultrasound probe.

12. The system according to claim 11, wherein: The one or more processors are configured to determine and track the manipulation of the ultrasound probe by inputting the input received from the external sensor into a neural network, the neural network being trained to: identifying one or more of: a relative position, orientation, or angle between two or more anatomical features of the user; and One or more ultrasound probe orientations and / or positions corresponding to at least one relative position or angle are determined.

13. A method for ultrasonic imaging, the method comprising: During an ultrasound examination, echo signals (118) are collected by an ultrasound probe (111) in response to ultrasound pulses (114) transmitted into a target region (116) of a subject; receiving input of a predefined user input (503) associated with an examination protocol (502) similar to the ultrasound examination; determining and tracking manipulation of the ultrasound probe performed during the ultrasound examination based on image frames (124) generated from the echo signals; identifying meaningful user input received during the ultrasound examination that indicates compliance with the examination protocol (506); as well as A log file is generated recording the manipulation and meaningful user input (702, 704).

14. The method according to claim 13, wherein: The meaningful user input includes adjustments to at least one image acquisition setting, including one or more of: gain, scan depth, image contrast level, color scale, probe type, frequency, or imaging mode.

15. The method according to claim 13, wherein: The manipulation of the ultrasound probe includes changes in probe position and orientation.

16. The method according to claim 13, wherein: Determining and tracking manipulation of the ultrasound probe includes identifying at least one landmark present in one or more of the image frames, and determining one or more ultrasound probe orientations and / or positions used to obtain the one or more image frames based on the at least one landmark identified in the one or more image frames.

17. The method according to claim 16, wherein: The at least one landmark includes one or more of: an anatomical feature, an image artifact, a medical device, or a transducer marker.

18. The method according to claim 13, wherein: Generating a log file recording the manipulation and meaningful user input includes: generating a first log file recording the meaningful user input; generating a second log file recording the manipulation of the ultrasound probe; and The first log file is synchronized with the second log file.

19. The method according to claim 13, wherein: Generating a log file recording the manipulation and meaningful user input includes: generating a first log file recording the meaningful user input; generating one or more target events recording the manipulation of the ultrasound probe; and The one or more target events are inserted into the first log file based on a unique timestamp associated with each of the one or more target events.

20. A non-transitory computer readable medium comprising executable instructions which, when executed, cause a processor of a system to perform any of the methods of claims 13-19.

Images