An ultrasonic imaging system with automatic image saving

Abstract

To provide ultrasound imaging systems for automatically identifying and saving ultrasound images relevant to a needle injection procedure, and associated systems and methods.SOLUTION: For example, an ultrasound imaging system includes a transducer for transmitting / receiving ultrasound signals during a needle injection procedure, and receiving circuitry configured to convert the received ultrasound signals into ultrasound image data. The image data can be stored in a buffer memory. A processor can analyze the image data stored in the buffer memory to identify image data for depicting a specified injection event of the needle injection procedure, and the identified image data can be stored in a memory for archival purposes.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The disclosed technology relates to an ultrasonic imaging system, and more particularly to a system for improving the workflow in a clinical setting where an ultrasonic imaging system is used.

Background Art

[0002] In ultrasonic imaging, the operator of the system uses a transducer probe to acquire ultrasonic images of a patient during an examination. The images captured by the system can be observed, printed, and / or included in a patient report for diagnosis and record-keeping. Additionally, selected images can be included in a written and / or electronic report used to bill the patient or their insurance for the services rendered. Depending on the examination procedure being performed, the number and subject of the images required in the examination report can be standardized or defined. For example, in a needle injection procedure such as an ultrasound-guided local anesthetic injection, images of the needle at the target position, images of the needle during injection, etc. may be required.

[0003] In a typical one-operator examination, a physician or sonographer uses the imaging system to acquire all the images necessary to complete the examination. However, during some needle procedures where the provider of care cannot stop midway through the procedure or has no free hand to control the system, a second person may assist in controlling the system settings and collecting the images required during the procedure. The acquired images are typically stored in a buffer memory and need to be reviewed after the examination is complete to mark or identify the images to be used in creating the examination record. Often, the clinician collects an image loop ("clip") and reviews the loop after the examination is complete to select the images to be used in creating the examination record. This additional step requires extra time. When a single image rather than a loop is collected, it may be difficult for the operator to know at the time of the procedure whether all the images required for the examination have been captured.

Brief Description of the Drawings

[0004]

Figure 1

Figure 2

Figure 3

Figure 4

DETAILED DESCRIPTION OF THE INVENTION

[0005] Certain detailed embodiments of an ultrasonic system for automatically storing ultrasonic images generated during an ultrasonic imaging procedure using an intervention device, as well as related devices and methods, are described below with reference to FIGS. 1-4. In one embodiment, for example, an ultrasonic imaging system includes a transducer configured to transmit ultrasonic signals to a region of interest and receive ultrasonic signals therefrom during an ultrasonic guided needle injection procedure. The ultrasonic imaging system further includes a receiving circuit configured to convert the received ultrasonic signals into an image frame of ultrasonic data, and a buffer memory in which the image frames are stored. The ultrasonic imaging system also includes a processor configured to analyze the image frames stored in the buffer memory and identify and mark one or more of the image frames depicting events of the needle injection procedure, such as the transport of liquid from the needle used during the procedure. In some embodiments, the processor can be further configured to save, for archival purposes, the image frames depicting the injection event in a memory other than the buffer memory.

[0006] Many of the embodiments described below are described in connection with a device, system, and method for automatically storing ultrasound images during a needle injection procedure in which a needle is used to transport an anesthetic or other drug to a desired location. However, in addition to these described herein, other uses and other embodiments are within the scope of this technology. For example, at least some embodiments of this technology may be useful in procedures using other invasive medical devices. It should be noted that in addition to these described herein, other embodiments are within the scope of this technology.

[0007] Furthermore, embodiments of the technology can have configurations, components, and / or procedures that are different from those shown or described herein. Additionally, those skilled in the art will understand that embodiments of the technology can have configurations, components, and / or procedures in addition to those shown or described herein, and that these and other embodiments can be without some of the configurations, components, and / or procedures shown or described herein without departing from the technology. Phrases such as "in some embodiments," "according to some embodiments," "in a given embodiment," "in the illustrated embodiment," "in other embodiments," etc., generally mean that the particular feature, structure, or characteristic following the phrase is included in at least one embodiment of the technology and may be included in two or more embodiments. Additionally, such phrases do not necessarily refer to the same embodiment or different embodiments.

[0008] The terms used below should be interpreted in the broadest reasonable manner even when used in conjunction with a detailed description of a given example of an embodiment of the technology. Certainly, certain terms may even be emphasized below. However, terms intended to be interpreted in a limiting way are so clearly and specifically defined in the section of the form for carrying out this invention.

[0009] FIG. 1 shows a representative ultrasonic imaging system 100 (“system 100”) for performing the present technique to image the tissue of a subject or patient 1. In one embodiment, system 100 can be a handheld, portable or cart-based system that uses a transducer probe 102 to transmit ultrasonic signals into a region of interest to generate an image of the tissue being scanned and receive corresponding echo signals. The transducer probe 102 can be a one-dimensional or two-dimensional linear or curved transducer, a phased array transducer, or another type of ultrasonic transducer as is well known in the art. System 100 converts the characteristics of the received echo signals (e.g., their amplitude, phase, power, frequency shift, etc.) into data that is quantified and displayed to the user as an image on a video monitor, screen, or other display 104 (“display 104”). As will be described in detail below, the created image can be electronically stored for digital record keeping or transmitted to another device or location via a wired or wireless communication link.

[0010] In some embodiments, system 100 can be used during a needle injection procedure in which an operator of system 100 guides an intervention instrument such as needle 3 to patient 1 with one hand and holds transducer probe 102 with the other hand. In certain embodiments, the operator can observe a composite image 106 of the tissue and a representation 107 of where needle 3 is located within the tissue. The composite image 106 can be updated on display 104 while needle 3 is being guided within the target region within patient 1. The target location can be a specific nerve site (e.g., if the needle injection procedure is a local anesthetic procedure) or a result or a specific organ (e.g., uterus, prostate, tumor, cardiovascular, etc.). In some embodiments, both needle 3 and the injectate (e.g., drug) transported through needle 3 are visible in composite image 106. For example, if the injection is made at a low resistance location (e.g., appears dark in composite image 106), the injectate can fill the space such that characteristic fluid movement is visible in composite image 106. In some embodiments, the material removed by needle 3 (e.g., during a biopsy procedure) is visible in composite image 106.

[0011] FIG. 2 is a simplified block diagram of a system 100 configured in accordance with an embodiment of the present technology. As will be understood by those skilled in the art, system 100 can be constructed using components different from those shown in FIG. 2. Additionally, system 100 can include components not discussed (e.g., a power source) and components not necessary for understanding how the present technology is made and used.

[0012] In an exemplary embodiment, the transducer probe 102 is connected to a high-voltage multiplexer / demultiplexer (HV mux / demux) 208 that is used to select individual or groups of transducer elements within the transducer probe 102. The signal transmitted by the transducer probe 102 is generated by a transmit (TX) beamformer 210 that adjusts the timing of the signal to direct the signal in a particular direction and focus the signal at a particular depth within the tissue. Alternatively, an unfocused (plane) wave can be transmitted by the transducer probe 102. The signal from the TX beamformer 210 is amplified by one or more high-voltage amplifiers (HV amps) 212 before being applied to the HV mux / demux 208 and the transducer probe 102. However, in other embodiments, the signal from the TX beamformer 210 can be passed directly to the transducer probe 102 without using an intervening multiplexer / demultiplexer.

[0013] A transmit / receive (T / R) switch 214 operates to disconnect the electronics of the system 100 from the transducer probe 102 when a higher-output transmit pulse is being transmitted. The T / R switch 214 is closed when the system 100 detects a return echo signal. The signal received by the T / R switch 214 is amplified by a low-noise receive amplifier (RX amp) 216 that implements a gain function that typically varies according to the depth at which the echo signal is generated. If the system 100 is a directional ultrasound system, the output of the RX amp 216 feeds a receive (RX) beamformer 218 that delays and sums the amplified received echo signals. In some embodiments, the analog received signal is amplified and then converted to a corresponding digital signal using some analog-to-digital converters (not shown) located between the RX amp 216 and the RX beamformer 218.

[0014] In some embodiments, the system processor 220, which can be implemented as one or more programmed microprocessors, is configured to execute program instructions stored in internal or external computer-readable memory (not shown) to control the operation of the system 100. As further shown in FIG. 2, the beamformed ultrasonic signal generated by the RX beamformer 218 is delivered to the image processor 222. The image processor 222, which may include one or more general-purpose microprocessors (including the system processor 220), one or more digital signal processors (DSPs), one or more graphics processor units (GPUs), application specific integrated circuits (ASICs), etc., stores the raw beamformed signal in memory and converts it into a two-dimensional image frame of pixel data that can be shown to the user on the display 104.

[0015] The image frames generated by the image processor 222 are stored in a buffer memory 224 (also known as a cine buffer), which in one embodiment operates as a circular buffer of memory elements that stores a selected number of image frames when generated during an ultrasonic imaging procedure using the system 100. The image frames can be captured using either a retrospective or prospective capture mode known in the art. In one embodiment, the buffer memory 224 can store 2 - 5 minutes of data or over 3600 - 9000 image frames of ultrasonic data. In one embodiment, when the buffer memory 224 is full, the oldest image frame stored in the buffer memory 224 is cyclically overwritten with a new image frame. In the illustrated embodiment, the memory 228 is used to store image frames for archival purposes. The contents of the memory 228 can be transferred to a remote patient record - keeping system after the imaging procedure is complete. In some embodiments, at least some of the image frames stored in the memory 228 are compressed to save space and may lack some details compared to the image frames stored in the buffer memory 224. In one embodiment, image data other than image frames (e.g., raw image data, image data before conversion, etc.) can be stored in the buffer memory 224.

[0016] In the illustrated embodiment, the system 100 includes several operator input units 230 such as a control unit configured in software, a key, a button, a knob, a microphone for receiving voice commands, a camera for capturing gestures, or a touch - screen control unit. The operator input unit 230 enables an operator to change the operating characteristics of the system 100 and input commands to the system processor 220.

[0017] In some embodiments, an ultrasonic imaging procedure (e.g., an examination) is initiated by using the operator input unit 230 to select a procedure type from several predefined procedure types that may be shown on the display 104 or have dedicated control units on the keyboard or other input devices of the system 100. For example, the imaging procedure can be a local anesthetic injection or other ultrasonic-guided needle injection procedure. Each procedure type may be associated with specific images and / or measurement results captured by the operator during a particular procedure. For example, some needle injection procedures may require images of the needle in the patient's target area, images of the needle during injection of a drug or other injectate, etc. For example, in a nerve block procedure, it may be necessary to record three or more different image frames including (i) the needle approaching the target nerve, (ii) the needle at the location of the target nerve, and (iii) an image of the anesthetic transported around the target nerve. Such images may need to be stored (e.g., archived) by the medical facility or the operator for insurance billing purposes. In the illustrated embodiment, the images and / or measurement results required by the various procedure types are stored in a knowledge base 232 (e.g., a memory, a database, etc.) accessible to the system processor 220. In some embodiments, the knowledge base 232 can further store one or more parameters, image frames, or other data from previous examinations that can be compared to, for example, the image frames stored in the buffer memory 224 as described in detail below.

[0018] After selecting a particular imaging procedure, the operator can use one or more of the operator input units 230 (e.g., on-screen buttons, foot switches, control units of the imaging probe, etc.) to initiate the capture of ultrasonic image frames using the system 100. These image frames are generated until the operator uses one or more of the operator input units 230 to stop the image capture process and are stored in the buffer memory 224. In some embodiments, the image capture process can be stopped based on other criteria such as, for example, a timer, an electrocardiogram signal, etc. As will be appreciated, the buffer memory 224 can be constructed to store thousands of image frames of ultrasonic data.

[0019] Heretofore, when using conventional ultrasonic systems, the operator has been required to take the time to review / search through all of the stored image frames to select which frames to include in the patient's record and / or submit for billing purposes. Further, the review / search of the relevant images was performed after the imaging procedure was completed. That is, it was impossible for the operator to be certain whether they had captured the images necessary during a needle injection procedure (e.g., for billing purposes). In some other conventional ultrasonic systems, the operator could press a button on the ultrasonic probe or use voice control to print or save a particular image, e.g., an image acquired approximately at the time of injection, during the procedure. Such systems can reduce the amount of review required by the operator to identify the relevant image frames, but the button may be pressed accidentally or the voice control may be accidentally activated in a noisy environment. Further, it is often cumbersome for the operator to trigger the ultrasonic system to save a predetermined image during the procedure while performing a needle injection procedure.

[0020] In contrast to conventional systems, the system 100 of the present technology is configured to automatically identify (e.g., select, determine, etc.) and store image frames related to or required by a needle injection procedure (referred to herein as an "injection event"), such as image frames depicting a particular event, trigger, or situation. For example, the system 100 can be configured to automatically identify image frames depicting a particular injection event, such as the needle being located at or approaching a target position, the position where the injection is being performed. Specifically, the system processor 220, the image processor 222, and / or another suitable processor such as a DSP or GPU can execute several program instructions to analyze the image frames stored in the buffer memory 224 and identify one or more of the image frames likely to depict a particular injection event. In other embodiments, image data other than image frames (e.g., image data before conversion) can be analyzed to identify a portion of the image data that depicts or is related to a particular injection event.

[0021] The identified image frames can be stored in the memory 228 for archival or other purposes. In some embodiments, the identified image frames are stored in the memory 228 in lossless compression or with little or no compression compared to the unselected image frames generated during the examination to retain more details of the images. In certain embodiments, the identified image frames are included in or marked to be automatically entered into the examination patient report. In some embodiments, the system 100 can generate an indication (e.g., sound, display, etc.) to provide the operator with feedback in real-time or near real-time that an image frame indicating a particular injection event has been successfully captured.

[0022] The system processor 220 (or another processor) can automatically identify image frames stored in the buffer memory 224 that are likely to depict a particular injection event in several different ways. For example, FIG. 3 is a process or method flow diagram of a method 300 executed by one or more of the processors within the system 100 to identify an image frame that depicts an injection event using comparison between frames, according to an embodiment of the present technology. Starting at block 302, as detailed above, method 300 includes generating an ultrasonic signal and receiving an echo signal corresponding to a needle injection procedure and storing an image frame of the ultrasonic data related to the procedure in the buffer memory 224. At block 304, the method includes comparing and / or analyzing the image frames stored in the buffer memory 224 to identify an image frame that depicts a particular injection event. For example, in some embodiments, the system processor 220 correlates and / or compares the image frames stored in the buffer memory 224 to detect changes between the image frames such as those caused by movement of the needle and / or the liquid being injected from the needle.

[0023] For example, the system processor 220 can use well-known image processing methods to estimate and characterize the correspondence of points from one image frame near the needle to the next image frame. For example, the system processor 220 can estimate the correspondence (or motion) of each point of interest by maximizing a performance index of the match between a patch of one image frame centered on the point in question and a sliding window of the next image frame for each image frame stored in the buffer memory 224. That is, the system processor 220 can estimate the flow vector of each or a subset of pixels between two or more image frames. Potential performance indices include 2D phase correlation, mutual information, or structural similarity. In some embodiments, regularization or preprocessing may be applied to assist in estimating the correspondence of each point of interest (e.g., to reduce processing cost). In other embodiments, optical flow methods such as Lucas-Kanade or Horn-Schunck may be used to establish the correspondence of points (e.g., flow vectors). In any case, the characteristics of the flow vectors can be classified to indicate the needle and / or the injection.

[0024] Regardless of the particular image processing method used, the system processor 220 can identify that a given image frame stored in the buffer memory 224 is likely to depict a particular injection event based on the estimated optical flow / motion between image frames. For example, in some embodiments, the system processor 220 can determine that the needle is stationary or generally stationary in a given image frame, and thus that the needle is located at the target position and / or that an injection is being performed in those image frames. Similarly, detection of the motion of the liquid around the tip of the needle in a given image frame can indicate that an injection is being depicted in those frames.

[0025] In other embodiments, the system processor 220 may execute instructions to implement a trained neural network or machine learning algorithm to analyze / compare the image frames stored in the buffer memory 224 to identify image frames depicting a particular injection event. The machine learning algorithm can be an artificial neural network or deep learning algorithm trained to recognize movements indicating an injection event within the image frame (e.g., swirling or swelling of the injection fluid around the tip of the needle). For example, in some embodiments, the neural network can be used to detect an injection event based on differences between image frames within the buffer memory 224 (e.g., based on the time series of the image frames). In some embodiments, the machine learning algorithm can be trained based on one or more image frames generated and stored in one or more previous examinations and similar to the image frames that need to be stored in the current examination. These previous images can be stored, for example, in the knowledge base 232. Based on the previous images, the machine learning algorithm can, for example, determine an image frame within the buffer memory 224 that has the highest similarity to the previous images and thus is likely to depict an injection event. In this way, the system processor 220 can identify image frames likely to depict an injection event based on historical data / examples from previous examinations.

[0026] In certain embodiments, the system processor 220 can further mark or identify a particular region (e.g., a sub-region) within one or more of the image frames likely to depict an injection. For example, the system processor 220 can automatically determine a bounding box around the region likely to be an injection based on the classification of flow vectors calculated or determined for the image frame.

[0027] In some embodiments, system processor 220 can be configured to analyze only a portion (e.g., a specific region) of an image frame and / or only a subset of the total number of image frames to detect a particular injection event. For example, system processor 220 can be configured to analyze only a portion (e.g., a region) of an image frame proximate to a determined position of the needle. Similarly, system processor 220 can use different levels or types of image processing methods for different subsets of the image frames stored in buffer memory 224. For example, the system processor can analyze the image frames stored in buffer memory 224 until it detects that the needle has stopped moving in order to depict these image frames depicting the liquid from the injection around the needle, and then analyze the subsequently generated / stored image frames. Such embodiments can advantageously reduce the processing burden of system 100 by localizing some of the image processing steps to subsets of the image frames stored in buffer memory 224.

[0028] In block 306, method 300 includes automatically storing in memory an image frame identified as depicting an injection event for archival purposes (e.g., for inclusion in a patient report, billing record, or other report). For example, the image frame can be stored in memory 228 and / or another memory accessible to system processor 220. In some embodiments, the identified image frame can be marked or flagged in buffer memory 224 in addition to, or instead of, being stored in memory for archival purposes.

[0029] In some embodiments, system processor 220 can automatically identify image frames stored in buffer memory 224 in other ways (e.g., ways other than comparison between frames). For example, FIG. 4 is a flow diagram of a process or method 400 executed by one or more of the processors within system 100 to identify an image frame depicting an injection event based on flow information within the image frame, according to an embodiment of the present technology. Starting at block 402, method 400 includes generating an ultrasonic signal, receiving a corresponding echo signal of the needle injection procedure, and storing an image frame of the ultrasonic data related to the procedure in buffer memory 224, as detailed above. More specifically, in some embodiments, system 100 can operate in a Doppler mode, or in another color flow imaging mode that generally correlates multiple ultrasonic signal pulses to a single image frame containing motion or flow information (often displayed in color), as known in the art. In some embodiments, color flow imaging does not need to use the entire color flow processing chain, and instead, segmentation and classification of a subset of the signals (e.g., lag 0 correlation, lag 1 correlation, etc.) can be used to generate the flow information. At block 304, system processor 220 proceeds to analyze the flow information of the image frames stored in buffer memory 224 and can identify these image frames that depict a particular injection event.

[0030] In some embodiments, since a plurality of ultrasonic signal pulses are used to generate each image frame, method 400 requires a relatively large amount of front-end processing by the processor compared to method 300 shown in FIG. 3. Thus, the frame rate of system 100 may be slower when executing method 400 compared to method 300. In certain embodiments, to improve the frame rate of system 100 while implementing method 400, system 100 can be configured to capture flow information for only a portion or region of each image frame (e.g., to generate, detect, and correlate a plurality of ultrasonic signal pulses). For example, in some embodiments, system 100 can determine a bounding box (e.g., a virtual color box) or other region for searching for a specific injection event that is smaller than the entire image frame. For example, system processor 220 can execute instructions to implement an image classification algorithm (e.g., a detection, trained neural network, or machine learning algorithm) to detect the position of the needle (e.g., by detecting a bright reflector that is stationary or moving) and / or the position of the needle tip (e.g., by detecting a transition from a bright reflector). System processor 220 can then specify a small region around the needle to search for the injection of liquid from the needle by generating flow information for the small region. In some embodiments, the detected position of the needle in one image frame can be used to facilitate the search for the needle in another image frame (e.g., a subsequent image frame). That is, once the needle is detected in one image frame, it is not necessary to classify the entire subsequent image frame thereafter. Finally, at block 406, method 400 includes storing in memory an image frame identified as depicting an injection event for archival purposes, or marking or flagging the image frame in buffer memory 224.

[0031] Generally, system 100 can automatically identify image frames stored in buffer memory 224 that are likely to depict a particular injection event using any of inter-frame image processing, image processing using trained neural networks or machine learning algorithms, optical flow (e.g., classification of flow vectors indicating the cessation of movement of a needle structure and / or the swirling or dilation of the flow pattern of an injectate), color flow imaging, or combinations thereof. For example, to detect the movement of a needle between image frames, a simple inter-frame comparison method can be used specifically to detect that the movement of the needle has stopped. Next, the tip of the needle within the subsequently generated image frames can be detected using a trained neural network or machine learning algorithm. Finally, the area surrounding the identified needle tip can be examined using color flow imaging to detect the injection of liquid from the needle tip. In this way, system 100 can automatically and accurately identify the image frames that depict a particular injection event while reducing the processing requirements of system 100 as compared to, for example, generating flow information for each complete image frame generated during a procedure.

[0032] In some embodiments, the system 100 is configured to analyze the image frames stored in the buffer memory 224 in real-time or near real-time as they are generated and added to the buffer memory 224. In such embodiments, after identifying that one or more of the image frames depict a particular injection event, the system 100 can be configured to generate a notification or display indicating that at least one of the image frames depicts an injection event. For example, in some embodiments, the system processor 220 can cause the notification to be displayed on the display 226 or cause an audio to be played via the speaker of the system 100. Thus, the system 100 can advantageously provide feedback to alert the operator of the system 100 that the necessary image frames have been captured during the examination. In other embodiments, the image frames from the entire ultrasound procedure are accessed and analyzed after the procedure is completed, and the image frames depicting a particular injection event can be automatically determined and saved.

[0033] In some embodiments, the image frames are associated with metadata (e.g., narrative information) regarding the image frames. The metadata can include the type of tissue being imaged used to acquire the image and one or more parameters of the system 100. Such parameters can include not only the operating mode of the ultrasound machine (e.g., B-mode, Doppler mode, power mode, etc.), but also power settings, pulse repetition rate, focal depth, the probe used, and the likelihood of the presence / movement of a needle. In some embodiments, the system processor 200 inserts one or more of the identified image frames into a patient record (e.g., a PACS system, a knowledge repository, etc.), the patient's chart, or other records, and at the same time, inserts (e.g., automatically inputs) the corresponding operating parameters of the ultrasound machine used to acquire the image frames and / or other metadata so that the operator does not need to manually enter them.

[0034] Embodiments of the subject matter and the operations described in this specification can be implemented in digital electronic circuitry, or in computer software, firmware, hardware, or in combinations of one or more of them, including the structures disclosed in this specification and their structural equivalents. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., as one or more modules of computer program instructions encoded on a computer storage medium for execution by, or to control the operation of, a data processing apparatus.

[0035] A computer storage medium can be, or can include, a computer-readable storage device, a computer-readable storage substrate, a random or serial access memory array or device, or a combination of one or more of them. Further, a computer storage medium can be, but is not a propagated signal, although a computer storage medium can be the source or destination of computer program instructions encoded in an artificially generated signal. A computer storage medium can be or can include one or more separate physical components or media (e.g., multiple CDs, disks, or other storage devices). The operations described in this specification can be implemented as operations stored in one or more computer-readable storage devices or as operations executed by a data processing apparatus on data received from other sources.

[0036] The term "processor" encompasses any kind of device, apparatus, and machine for processing data, including, by way of example, a programmable processor, a computer, a system-on-chip, or multiple ones of the foregoing, or combinations of the foregoing. The apparatus can include special-purpose logic circuitry, such as, for example, an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). The apparatus can also include code, in addition to the hardware, that creates an execution environment for the computer program in question, such as, for example, processor firmware, a protocol stack, a database management system, an operating system, a cross-platform runtime environment, a virtual machine, or code that constitutes one or a combination of two or more of them. The apparatus and the execution environment can implement various different computing model infrastructures, such as web services, distributed computing, and grid computing infrastructures.

[0037] A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and can be deployed in any form, including a stand-alone program or a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may or may not correspond to a file in a file system. The program can be stored as part of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), a single file dedicated to the program in question, or multiple prepared files (e.g., files that hold one or more modules, subprograms, or portions of code). A computer program can be executed on one computer or located at one site, or can be distributed across multiple sites and executed on multiple computers interconnected by a communication network.

[0038] The processes and logical flows described herein can be executed by one or more programmable processors executing one or more computer programs to perform operations by manipulating input data and generating output. The processes and logical flows can also be executed by, and the apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0039] Processors suitable for the execution of a computer program include, by way of example, general and special purpose microprocessors, as well as both one or more of any of the various types of digital computers. In general, a processor receives instructions and data from a read only memory or a random access memory, or both. The essential elements of a computer are a processor for executing operations in accordance with instructions and one or more memory devices for storing the instructions and data. In general, a computer also includes one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, for receiving data therefrom, transferring data thereto, or both, or is operatively coupled thereto. Devices suitable for storing computer program instructions and data include, by way of example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, magnetic disks such as internal hard disks or removable disks, magneto-optical disks such as CD-ROM, DVD-ROM, and any form of non-volatile memory, media, and memory devices. The processor and memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0040] To provide interaction with a user, embodiments of the subject matter described herein can be implemented in an imaging system having a display device, such as an LCD (liquid crystal display), LED (light emitting diode), or OLED (organic light emitting diode) monitor, to display information to an operator, and a keyboard and a pointing device, such as a mouse or trackball, by which the operator can provide input to a computer. In some embodiments, a touch screen can be used to display information and receive input from a user. Other types of devices can be used to provide interaction with a user. For example, the feedback provided to the operator can be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback, and the input from the operator can be received in any form, including acoustic, voice, or tactile input. Additionally, the computer can interact with the operator by sending a document to, and receiving a document from, a device used by the user, such as by sending a web page to a web browser on the user's client device in response to a request received from, for example, a web browser.

[0041] As described above, while specific embodiments of the technology are described herein for purposes of illustration, it should be understood that various modifications can be made without departing from the present disclosure. Accordingly, the invention is not limited except as by the appended claims. Further, certain aspects of the new technology described in the context of a particular embodiment can be combined or excluded in other embodiments. Moreover, while the advantages associated with a particular embodiment of the new technology have been described in the context of these embodiments, other embodiments may exhibit such advantages, and not all embodiments need necessarily exhibit such advantages in order to fall within the scope of the technology. Accordingly, the present disclosure and related technologies can encompass other embodiments not explicitly shown or described herein.

Claims

1. 1. An ultrasound imaging system comprising: a transducer configured to transmit ultrasound signals to and receive echo signals from a region of interest during a needle injection procedure; a receiver circuit configured to convert the received echo signals into ultrasound image data; a buffer memory for storing image frames of the ultrasound image data; a processor coupled to the buffer memory; Equipped with The processor, Obtaining a first subset of the image frames from the buffer memory; identifying a first image frame from said first subset indicative of a first injection event using a first image processing technique; obtaining from the buffer memory a second subset of the image frames generated subsequent to the first subset and stored in the buffer memory; identifying a second image frame indicative of a second injection event from the second subset using a second image processing technique, the second image processing technique being different from the first image processing technique; It is configured as follows: Ultrasound imaging systems.

2. 2. The ultrasound imaging system of claim 1, further comprising a first memory coupled to the processor, the processor further configured to store in the first memory the first image frame and the second image frame.

3. The ultrasound imaging system of claim 1 , wherein the first image processing technique is an image frame comparison technique and the second image processing technique is a machine learning algorithm image processing technique.

4. 2. The ultrasound imaging system of claim 1, wherein the processor is configured to obtain from the buffer memory a third subset of the image frames generated subsequent to the second subset and stored in the buffer memory, and to identify a third image frame from the third subset that is indicative of a third injection event using a third image processing technique that is different from the first image processing technique and the second image processing technique.

5. 5. The ultrasound imaging system of claim 4, wherein the third injection event is an injection being performed within the region of interest, and the third image processing technique is a color flow imaging technique.

6. The ultrasound imaging system of claim 1 , wherein the first injection event indicates a needle approaching a target location within a region of interest and the second injection event indicates the tip of the needle.

7. 10. The ultrasound imaging system of claim 1, further comprising a display for displaying the image frames, the processor configured to generate a notification on the display that the first image frame depicts the first injection event.

8. The ultrasound imaging system of claim 1 , wherein the processor is configured to include at least one of the first image frame and the second image frame in a patient record.

9. 2. The ultrasound imaging system of claim 1, wherein at least one of the first image processing technique and the second image processing technique includes a machine learning algorithm to detect motion, the motion being associated with at least one of a needle, a fluid transported by the needle, and a material removed by the needle.

10. 2. The ultrasound imaging system of claim 1, further comprising a display for displaying the image frames, and wherein the processor is configured to mark at least one of the first image frame and the second image frame in the buffer memory for inclusion in a patient record.

11. The ultrasound imaging system of claim 1 , wherein the transducer is configured to transmit the ultrasound signal in two or more pulses.

12. The processor, comparing the first subsets of the image frames to one another; identifying the first image frame from the first subset based on the comparison; The ultrasound imaging system of claim 1 , configured to:

13. 1. A method executed by a processor in an ultrasound system, comprising: receiving an ultrasound signal from a region of interest during a needle injection procedure; converting the ultrasound signals into image frames of ultrasound data; storing said image frames in a buffer memory; obtaining a first subset of the image frames from the buffer memory; identifying a first image frame from said first subset indicative of a first injection event using a first image processing technique; obtaining from the buffer memory a second subset of the image frames generated subsequent to the first subset and stored in the buffer memory; identifying a second image frame indicative of a second injection event from the second subset using a second image processing technique, the second image processing technique being different from the first image processing technique; A method comprising:

14. The method of claim 13 , further comprising storing the first image frame and the second image frame in a first memory.

15. The method of claim 13 , wherein the first image processing technique is an image frame comparison technique and the second image processing technique is a machine learning algorithm image processing technique.

16. obtaining from the buffer memory a third subset of the image frames generated subsequent to the second subset and stored in the buffer memory; identifying a third image frame indicative of a third injection event from the third subset using a third image processing technique different from the first image processing technique and the second image processing technique; The method of claim 13 further comprising:

17. The method of claim 16 , further comprising inserting at least one of the first image frame and the second image frame into a patient record.

18. The method of claim 16 , further comprising comparing the first subset of the image frames to one another to detect needle movement.

19. 17. The method of claim 16, wherein the first injection event indicates a needle approaching a target location within a region of interest and the second injection event indicates the tip of the needle.

20. 17. The method of claim 16, further comprising generating an indication to an operator that the first image frame depicts the first injection event.

Images