Analysis of ultrasound image data of the rectus abdominis muscle
By acquiring ultrasound image sequences from different angles and automatically selecting the clearest rectus abdominis region for measurement, the accuracy and operator dependence issues of rectus abdominis diastasis measurement in existing technologies have been resolved, achieving efficient and accurate RAD monitoring.
Patent Information
- Application Number
- CN202180081368.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2021-01-22
- Filing Date
- 2021-12-01
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2041-12-01
AI Technical Summary
Existing technologies struggle to accurately measure diastasis recti (RAD) without requiring specialized training, especially in monitoring RAD during pregnancy. Physical examinations lack precision, while ultrasound imaging relies on experienced sonographers.
By acquiring ultrasound image sequences of the rectus abdominis muscle using ultrasound transducers at different angles, and selecting the clearest image data for measurement, the processor automatically selects the clearest rectus abdominis muscle area for measurement, reducing reliance on the operator.
It enables automatic selection of the clearest rectus abdominis muscle image from different angles, improving the accuracy and reliability of measurements, reducing reliance on the experience of ultrasound physicians, and making it suitable for new users.
Smart Images

Figure CN116546926B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to ultrasound systems. In particular, but not exclusively, this disclosure relates to ultrasound image data of the rectus abdominis muscle of the subject of analysis. Background Technology
[0002] Abdominal muscles are important stabilizers of the spine. Diastasis recti (DRA) (also known as rectus abdominis diastasis (RAD)) is a condition in which the two rectus abdominis muscles separate along the linea alba (LA), and it is commonly associated with postpartum women. RAD is usually diagnosed when the gap is greater than 2 cm, while a gap greater than or equal to 5 cm is considered a severe condition. RAD can lead to weakness in the abdominal muscles, which affects biomechanical posture and causes back pain. RAD is often associated with low back pain (LBP), abdominal and pelvic dysfunction (see the article entitled "Classification of rectus diastasis - A proposal by the German Hernia Society (DHG) and the International Endohernia Society (IEHS)" by Wolfgang R et al. (Frontiers in Surgery, 2019, Vol. 6: Article 1)). The prevalence of RAD after pregnancy has been reported to be between 35% and 100%, and women who deliver large babies at term or twins are particularly susceptible.
[0003] The measurement of the interrectus distance (IRD) is used for screening for conditions and monitoring treatment. Methods for measuring IRD fall into two main categories: 1) physical examination and 2) medical imaging, especially ultrasound imaging, because of its low cost and real-time capability.
[0004] Physical examinations can provide a rough estimate of the extent of RAD, but due to a lack of measurement precision, they are generally unsuitable for monitoring purposes. The prevalence of mild RAD is high during pregnancy and postpartum, requiring high measurement precision (e.g., measurement error less than 5 mm) for longitudinal comparisons during management.
[0005] US 20170319107 A1 discloses a method for quantifying the separation distance between rectus abdominis muscles based on infrared images. RU 0002692974C1 discloses a method for preoperatively marking all enterostomies on the anterior abdominal wall of a patient using ultrasound imaging. Summary of the Invention
[0006] As mentioned above, diastasis recti (RAD) is a condition characterized by the separation of the rectus abdominis muscles, and it is often associated with pregnancy. Physical examinations, where clinicians manually locate and determine the degree of separation of the abdominal muscles, are generally unsuitable for monitoring purposes due to the subjectivity of the examination and the lack of precision in the measurements obtained. Routine physical examinations in this manner are also inadvisable, as they may exacerbate the muscle separation. Therefore, physical examinations play a limited role in monitoring RAD.
[0007] Ultrasound is generally considered more suitable for monitoring recurrent arterial disease (RAD); however, ultrasound imaging requires experienced sonographers and significant investment in training new sonographers to obtain images of sufficient quality for RAD monitoring. Even after obtaining images, image processing is necessary, which requires time and extensive experience to achieve reliable results.
[0008] Therefore, it is desirable to provide improved methods and apparatus for processing images of the rectus abdominis muscle, enabling efficient and accurate processing of measurement results from ultrasound images.
[0009] According to a first aspect, an apparatus is provided for analyzing ultrasound image data of the rectus abdominis muscle of a subject. The apparatus includes a memory and a processor, the memory including instruction data representing a set of instructions, the processor being configured to communicate with the memory and execute the set of instructions. When executed by the processor, the set of instructions causes the processor to: i) acquire a sequence of ultrasound images of the rectus abdominis muscle, the sequence of ultrasound images being acquired using ultrasound transducers tilted at different angles relative to the surface of the subject's skin, thus having different angles at which ultrasound waves enter the skin; ii) select ultrasound image data from the sequence of ultrasound image data, the selected ultrasound image data including image data in which the region of the rectus abdominis muscle appears clearest compared to other image data in the sequence of ultrasound image data; and iii) measure the rectus abdominis muscle in the selected ultrasound image data.
[0010] According to the second aspect, there exists an ultrasound imaging system comprising the apparatus of the first aspect and an ultrasound transducer for acquiring the sequence of ultrasound images thereon.
[0011] According to a third aspect, there is a computer-implemented method for analyzing ultrasound image data of the rectus abdominis muscle of a subject. The method includes: i) obtaining a sequence of ultrasound images of the rectus abdominis muscle, the sequence of ultrasound images being obtained using ultrasound transducers tilted at different angles relative to the surface of the subject's skin, thus having different angles at which ultrasound waves enter the skin; ii) selecting ultrasound image data from the sequence of ultrasound image data, the selected ultrasound image data including image data in which the region of the rectus abdominis muscle appears clearest compared to other image data in the sequence of ultrasound image data; and iii) measuring the rectus abdominis muscle in the selected ultrasound image data.
[0012] According to the fourth aspect, there exists a computer program product comprising a computer-readable medium having computer-readable code embodied therein, the computer-readable code being configured to cause the computer or processor to perform the method of the third aspect when run by a suitable computer or processor.
[0013] Typically, optimal measurements of the rectus abdominis muscle are obtained when the transducer of the probe used to acquire ultrasound data is positioned at a 90-degree angle to the surface of the target organ (e.g., the rectus abdominis muscle in this context). In this position, the probe images a slice (e.g., along the shortest axis of the muscle) directly through the muscle wall. This allows for accurate determination of muscle thickness. Since the muscle is not directly visible, the surface of the skin is often used as a reference for determining the angle of incidence (provided the surface is relatively flat). Obtaining a 90-degree angle (e.g., at a 90-degree angle to the skin, where the skin is used as a reference surface, or more preferably, at a 90-degree angle to the rectus abdominis muscle) is often difficult for novice users because the internal structures of the rectus abdominis muscle are below the surface, and ultrasound waves must penetrate superficial soft tissue to reach the target rectus abdominis muscle.
[0014] The inventors of the disclosure herein have recognized that muscle walls (e.g., the outer edges of muscle fibers) appear clearest (e.g., brighter and narrower in a manner similar to optical focusing) when the probe is correctly positioned because ultrasound waves are most strongly and coherently reflected from the muscle boundaries when the probe is positioned at 90 degrees. Therefore, by acquiring ultrasound image data using the probe within a certain angular range relative to the skin surface and selecting the clearest image data, image data providing the most appropriate cross-section through the muscle can be selected for muscle measurements, such as muscle thickness and intermuscular spacing measurements for monitoring RAD. Consequently, measurements of muscle thickness in the selected images are more robust and reliable (with better repeatability), and this also avoids the need for the sonographer to independently determine the correct angle of incidence.
[0015] These and other aspects will become apparent and clarified with reference to one or more embodiments described below. Attached Figure Description
[0016] Example embodiments will now be described by way of example only, with reference to the following figures, in which:
[0017] Figure 1 Example apparatuses according to some embodiments herein are shown;
[0018] Figure 2 Example ultrasound systems according to some embodiments herein are shown;
[0019] Figure 3 Example methods according to some embodiments described herein are shown;
[0020] Figure 4 An example method for obtaining a sequence of ultrasound image data according to some embodiments herein is illustrated;
[0021] Figure 5A The axial intensity projection curves in an example ultrasound image frame are shown;
[0022] Figure 5B The average intensity of each frame in the example ultrasound image frame sequence is shown;
[0023] Figure 5C The intensity difference between adjacent image pairs in the example ultrasound image sequence is shown;
[0024] Figure 6 Four example two-dimensional ultrasound image frames from the example ultrasound image sequence are shown; and
[0025] Figure 7 An exemplary selection of ultrasound image frames is shown, and the boundaries of the rectus abdominis muscle can be determined using seed points. Detailed Implementation
[0026] As described above, the apparatus and method described herein allow for improved measurements of the rectus abdominis muscle, for example, for monitoring diastasis recti (RAD).
[0027] Turn now Figure 1 , Figure 1 An apparatus 100 for analyzing ultrasound image data of the rectus abdominis muscle of a subject is illustrated according to some embodiments herein. Generally, this apparatus may be part of a computer device or system (e.g., a laptop computer, desktop computer, or other computing device). In some embodiments, apparatus 100 may be part of a distributed computing deployment or a cloud.
[0028] Generally, the apparatus can be adapted or configured to perform any embodiment of the methods described herein, for example, as referenced below. Figure 3 Method 300 is described.
[0029] The device includes a memory 104 and a processor 102 (e.g., processing circuitry or logic unit). The memory 104 includes instruction data representing a set of instructions 106, and the processor 102 is configured to communicate with the memory and execute the set of instructions 106. In short, when executed by the processor 102, the set of instructions 106 causes the processor 102 to: i) obtain a sequence of ultrasound images of the rectus abdominis muscle, the sequence of ultrasound images being obtained using ultrasound transducers tilted at different angles relative to the surface of the skin of the object, thus having different angles at which ultrasound waves enter the skin; ii) select an ultrasound image from the sequence of ultrasound images, the selected ultrasound image including the image in which the region of the rectus abdominis muscle appears clearest compared to other images in the sequence of ultrasound images; and iii) measure the rectus abdominis muscle in the selected ultrasound image.
[0030] As mentioned above, a major problem with conventional 2D ultrasound imaging is its operator dependence, which makes it difficult to monitor RAD. The device proposed in this paper guides new or inexperienced users to obtain ultrasound images of optimal quality for RAD measurements, and then helps them obtain key parameters with minimal effort. Users only need to obtain a sequence of ultrasound images at a certain tilt / angle, and the device 100 will select the appropriate image from which the muscle boundary is clearest (similar to optical focusing) (this image corresponds to a probe at approximately 90 degrees to the muscle boundary, within which measurements are taken). Therefore, the device 100 can minimize operator dependence and has a potential role in the evaluation of RAD management.
[0031] More specifically, processor 102 may include one or more processors, processing units, multi-core processors, or modules configured or programmed to control device 100 in the manner described herein. In certain embodiments, processor 102 may include multiple software modules and / or hardware modules, each configured to perform or be used to perform one or more steps of the methods described herein. Processor 102 may include one or more processors, processing units, multi-core processors, and / or modules configured or programmed to control device 100 in the manner described herein. For example, in some embodiments, processor 102 may include multiple (e.g., interoperable) processors, processing units, multi-core processors, and / or modules configured for distributed processing. Those skilled in the art will recognize that such processors, processing units, multi-core processors, and / or modules may be located in different locations and may perform different steps and / or different portions of a single step of the methods described herein.
[0032] Memory 104 is configured to store program code that can be executed by processor 102 to perform the methods described herein. Alternatively or additionally, one or more memories 104 may be external to device 100 (i.e., separate from or remote from device 100). For example, one or more memories 104 may be part of another device. Memory 104 can be used to store ultrasound image data, sequences of ultrasound images, and / or any other information or data received, calculated, or determined by processor 102 of device 100 or received, calculated, or determined from any interface, memory, or device external to device 100. Processor 102 may be configured to control memory 104 to store ultrasound image data, sequences of ultrasound images, and / or any other information or data received, calculated, or determined by the processor.
[0033] In some embodiments, memory 104 may include a plurality of sub-memories, each capable of storing one instruction data. For example, at least one sub-memory may store instruction data representing at least one instruction in the set of instructions, while at least one other sub-memory may store instruction data representing at least one other instruction in the set of instructions.
[0034] Will realize, Figure 1Only the components required to illustrate this aspect of the disclosure are shown, and in practical implementations, device 100 may include additional components besides those shown. For example, device 100 may also include a display. The display may include, for example, a computer screen and / or a screen on a mobile phone or tablet. The device may also include a user input device, such as a keyboard, mouse, or other input device that enables a user to interact with the device, for example, by providing initial input parameters to be used in the methods described herein. Device 100 may include a battery or other power source for powering device 100, or a device for connecting device 100 to a mains power source.
[0035] In some embodiments, the device 100 may be included in an ultrasound system. For example, the ultrasound system may include the device 100 described above, and may also include a transducer for recording ultrasound image data and / or sequences of ultrasound images.
[0036] Figure 2 An example ultrasound system 200 is shown. The ultrasound system 200 may include the aforementioned device 100. In other embodiments, components of the ultrasound system 200 may be adapted to perform the method 300 described below.
[0037] System 200 includes an array transducer probe 4 having a transducer array 6 for emitting ultrasonic waves and receiving echo information. The transducer array 6 may include: a CMUT transducer; a piezoelectric transducer formed of a material such as PZT or PVDF; or any other suitable transducer technology. In this example, the transducer array 6 is a two-dimensional array of transducers 8 capable of scanning a two-dimensional plane or a three-dimensional volume of a region of interest. In another example, the transducer array may be a 1D array.
[0038] The transducer array 6 can be coupled to a microwave beamformer 12, which controls the signal reception performed by the transducer elements. The microwave beamformer is capable of performing at least partial beamforming on the signals received by the subarrays of transducers (often referred to as “groups” or “patchworks”), as described in U.S. Patents US 5,997,479 (Savord et al.), US 6,013,032 (Savord), and US 6,623,432 (Powers et al.).
[0039] In an alternative embodiment, instead of microwave beamformer 12, the main system beamformer ( Figure 2 (Not shown in the image) can directly operate the transducer array.
[0040] System 200 may also include a transmit / receive (T / R) switch 16, which is coupled to microwave beamformer 12 and switches the array between transmit and receive modes.
[0041] The emission of the ultrasonic beam from transducer array 6 is guided by transducer controller 18, which is coupled to a microwave beamformer via T / R switch 16 and to a main transmitting beamformer (not shown), which can receive input from user operation from user interface or control panel 38. Controller 18 may include transmitting circuitry arranged to drive the transducer elements of array 6 during transmitting mode (directly or via the microwave beamformer).
[0042] Please note that in an alternative embodiment (wherein the main system beamformer directly operates the transducer array instead of the microwave beamformer 12), the T / R switch 16 can protect the main beamformer 20 from high-energy transmitted signals.
[0043] In a typical line-by-line imaging sequence, the beamforming system within the probe can operate as follows. During transmission, a beamformer (which may be a microwave beamformer or a main system beamformer, depending on the implementation) activates the transducer array or sub-apertures of the transducer array. The sub-apertures can be one-dimensional transducer rows or two-dimensional transducer patches within a larger array. In transmission mode, the focusing and steering of the ultrasonic beam generated by the array or its sub-apertures are controlled as described below.
[0044] Upon receiving the backscattered echo signal from the object, the received signal is subjected to receive beamforming (as described below) to align the received signal, and, in the case of a sub-aperture, the sub-aperture is then shifted, for example, through a transducer element. The shifted sub-aperture is then activated and the process is repeated until all transducer elements of the transducer array are activated.
[0045] For each row (or each sub-aperture), the total received signal for the associated row used to form the final ultrasound image will be the sum of the voltage signals measured by the transducer elements of the given sub-aperture during the reception period. Following the beamforming process below, the resulting row signals are typically referred to as radio frequency (RF) data. Each row signal (RF dataset) generated from the individual sub-apertures then undergoes additional processing to generate the row of the final ultrasound image. The amplitude variation of the row signal over time will contribute to the brightness variation of the ultrasound image with depth, where high amplitude peaks will correspond to bright pixels (or sets of pixels) in the final image. Peaks appearing near the beginning of the row signal will represent echoes from shallow structures, while peaks appearing gradually later in the row signal will represent echoes from structures of increasing depth within the object.
[0046] One of the functions controlled by the transducer controller 18 is the direction of beam steering and focusing. The beam can be steered straight forward (orthogonal to) the transducer array, or steered at different angles to obtain a wider field of view. The steering and focusing of the transmitted beam can be controlled based on the actuation time of the transducer elements.
[0047] In general ultrasound data acquisition, two methods can be distinguished: plane wave imaging and beam steering imaging. The difference between these two methods lies in the presence of beamforming in the transmit mode (beam steering imaging) and / or receive mode (plane wave imaging and beam steering imaging).
[0048] First, let's look at the focusing function. By simultaneously activating all transducer elements, the transducer array generates a plane wave, which diverges as it travels across an object. In this case, the ultrasound beam remains unfocused. By introducing a location-dependent time delay into the transducer activation, the wavefront of the beam can be converged to the desired point, called the focal zone. The focal zone is defined as the point where the lateral beamwidth is less than half the width of the emitted beam. In this way, the lateral resolution of the final ultrasound image is improved.
[0049] For example, if a time delay causes the transducer elements to activate sequentially from the outermost element and terminate at one or more central elements of the transducer array, a focal zone will be formed at a given distance from the probe, aligned with the central element(s). The distance between the focal zone and the probe will vary depending on the time delay between each subsequent round of transducer element activation. After the beam passes through the focal zone, it will begin to diverge, forming a far-field imaging region. It should be noted that for focal zones located close to the transducer array, the ultrasonic beam will diverge rapidly in the far field, resulting in beamwidth artifacts in the final image. Typically, the near field between the transducer array and the focal zone shows little detail due to significant overlap in the ultrasonic beam. Therefore, changing the position of the focal zone can cause a significant change in the quality of the final image.
[0050] It should be noted that in emission mode, only one focus can be defined unless the ultrasound image is divided into multiple focal zones (each of which may have a different emission focus).
[0051] Furthermore, upon receiving an echo signal from within the object, the reverse process described above can be executed to perform receiver focusing. In other words, the incoming signal can be received by the transducer elements and undergoes an electronic time delay before being transmitted to the system for signal processing. The simplest example of this is called delay-summation beamforming. The receiver focusing of the transducer array can be dynamically adjusted according to time.
[0052] Now consider the function of beam steering. By correctly applying a time delay to the transducer elements, a desired angle can be assigned to the ultrasonic beam as it leaves the transducer array. For example, by activating the transducers on the first side of the transducer array and then sequentially ending the remaining transducers on the opposite side of the array, the beamfront will form an angle toward the second side. The magnitude of the steering angle relative to the normal of the transducer array depends on the magnitude of the time delay between subsequent transducer element activations.
[0053] Furthermore, it is possible to focus a steered beam, where the total time delay applied to each transducer element is the sum of the focusing time delay and the steerable time delay. In this case, the transducer array is called a phased array.
[0054] When a DC bias voltage is required for the activated CMUT transducer, the transducer controller 18 can be coupled to control the DC bias control 45 for the transducer array. The DC bias control 45 sets one or more DC bias voltages applied to the CMUT transducer elements.
[0055] For each transducer element in the transducer array, an analog ultrasonic signal, typically referred to as channel data, enters the system through a receiving channel. In the receiving channel, a microwave beamformer 12 generates a partially beamformed signal based on the channel data. This partially beamformed signal is then passed to a main receiving beamformer 20, where the partially beamformed signals from individual transducer patches are combined into a fully beamformed signal (referred to as radio frequency (RF) data). The beamforming performed at each stage can be performed as described above, or may include additional functionality. For example, the main beamformer 20 may have 128 channels, each receiving partially beamformed signals from patches of dozens or hundreds of transducer elements. In this way, signals received by thousands of transducers in the transducer array can be effectively contributed to a single beamformed signal.
[0056] The beamformed received signal is coupled to signal processor 22. Signal processor 22 can process the received echo signal in various ways, such as bandpass filtering; decimation; I and Q component separation; and harmonic signal separation, which separates linear and nonlinear signals, thereby enabling the identification of nonlinear (higher harmonics of the fundamental frequency) echo signals returning from tissue and microbubbles. The signal processor can also perform additional signal enhancement, such as speckle reduction, signal recombination, and noise cancellation. The bandpass filter in the signal processor can be a tracking filter; as the echo signal is received from increasingly deeper depths, the passband of the tracking filter slides from higher to lower frequency bands, thereby suppressing higher-frequency noise from greater depths (which typically lacks anatomical information).
[0057] The beamformer used for transmission and the beamformer used for reception are implemented in different hardware and are capable of different functions. Of course, the design of the receiver beamformer must take into account the characteristics of the transmission beamformer. For simplicity, in... Figure 2 Only receiver beamformers 12 and 20 are shown in the diagram. Throughout the system, there will also be a transmit chain, which includes a transmit microwave beamformer and a main transmit beamformer.
[0058] The function of microwave beamformer 12 is to provide an initial combination of signals in order to reduce the number of analog signal paths. This is typically performed in the analog domain.
[0059] The final beamforming is performed in the main beamformer 20, and is typically done after digitization.
[0060] The transmit and receive channels use the same transducer array 6 with a fixed frequency band. However, the bandwidth occupied by the transmit pulse can vary depending on the transmit beamforming used. The receive channel can capture the entire transducer bandwidth (this is the classic approach), or it can use bandpass processing so that it only extracts the bandwidth containing the desired information (e.g., harmonics of the main harmonic).
[0061] The RF signal can then be coupled to a B-mode (i.e., brightness mode or 2D imaging mode) processor 26 and a Doppler processor 28. The B-mode processor 26 performs amplitude detection on the received ultrasound signal to image structures in the body, such as organs, tissues, and blood vessels. In the case of line-by-line imaging, each line (beam) is represented by an associated RF signal whose amplitude is used to generate a brightness value to be assigned to a pixel in the B-mode image. The exact location of a pixel within the image is determined by measuring its position along the associated amplitude of the RF signal and the number of lines (beams) of the RF signal. As described in U.S. Patent US 6283919 (Roundhill et al.) and U.S. Patent US 6458083 (Jago et al.), B-mode images of such structures can be formed in a harmonic imaging mode or a fundamental imaging mode, or a combination of both. The Doppler processor 28 processes signals that differ in time due to tissue movement and blood flow for the detection of moving material (e.g., blood cell flow in the image field). Doppler processor 28 typically includes a wall filter whose parameters are set to allow or reject echoes returning from a selected type of material in the body.
[0062] The structural and motion signals generated by the B-mode processor and the Doppler processor are coupled to a scan converter 32 and a multi-plane reformer 44. The scan converter 32 arranges the echo signals in the desired image format according to the spatial relationships at which the echo signals are received. In other words, the scan converter is used to convert RF data from a cylindrical coordinate system to a Cartesian coordinate system suitable for displaying an ultrasound image on an image display 40. In the case of B-mode imaging, the brightness of a pixel at a given coordinate is proportional to the amplitude of the RF signal received from that location. For example, the scan converter can arrange the echo signals into a two-dimensional (2D) fan-shaped format or a pyramidal three-dimensional (3D) image. The scan converter can overlay colors on the B-mode structural image corresponding to motion at various points in the image field, where Doppler-estimated velocities produce the given colors. The combined B-mode structural image and color Doppler image can depict tissue motion and blood flow within the structural image field. As described in U.S. Patent US 6443896 (Detmer), the multi-plane reformer converts echoes received from points in a common plane of a volumetric region of the body into an ultrasound image of that plane. As described in U.S. Patent 46530885 (Entrekin et al.), the volume plotter 42 converts the echo signal of the 3D dataset into a 3D image of the projection as seen from a given reference point.
[0063] 2D or 3D images are coupled from the scan converter 32, multiplane reformer 44, and volume plotter 42 to the image processor 30 for further enhancement, buffering, and temporary storage for display on the image display 40. The image processor may be adapted to remove some imaging artifacts from the final ultrasound image, such as acoustic shadowing caused by strong attenuators or refraction; post-enhancement caused by weak attenuators; and reverberation artifacts at locations adjacent to highly reflective tissue interfaces. Additionally, the image processor may be adapted to perform certain speckle reduction functions to improve the contrast of the final ultrasound image.
[0064] In addition to being used for imaging, the blood flow values generated by the Doppler processor 28 and the tissue structure information generated by the B-mode processor 26 are also coupled to the quantization processor 34. The quantization processor can be used to perform measurements in the image. The quantization processor can receive input from the user control panel 38 (e.g., seed points for locating the surface of the muscle, as described in detail below).
[0065] Output data from the quantization processor is coupled to the graphics processor 36 for reproducing the image along with measurement graphics and values on the display 40 and for outputting audio signals from the display device 40. The graphics processor 36 is also capable of generating graphic overlays for display alongside ultrasound images. These graphic overlays can include criterion identification information (e.g., patient name), the date and time of the image, imaging parameters, etc. For this purpose, the graphics processor receives input (e.g., patient name) from the user interface 38. The user interface is also coupled to the transmission controller 18 to control the generation of ultrasound signals from the transducer array 6 and thus control the images generated by the transducer array and the ultrasound system. The transmission control function of the controller 18 is only one of the functions performed. The controller 18 also considers the operating mode (given by the user) and the corresponding required transmitter and bandpass configurations in the receiver analog-to-digital converter. The controller 18 can be a state machine with fixed states.
[0066] The user interface is also coupled to a multiplane reformer 44 for selecting and controlling planes of multiple multiplane reformatted (MPR) images, which can be used to perform quantization measurements in the image field of the MPR image.
[0067] Those skilled in the art will recognize that the details provided above and Figure 2 The components shown in the illustrations are merely examples, and an ultrasound system may have different components than those shown in this document.
[0068] Now back Figure 1 In addition to the functions of processor 102 as described above, in step i), processor 102 acquires a sequence of ultrasound images of the rectus abdominis muscle, the sequence of ultrasound images having been acquired using an ultrasound transducer tilted at different angles relative to the surface of the skin of the object (e.g., the patient), thus having different angles at which ultrasound waves enter the skin. Alternatively or additionally, processor 102 may acquire ultrasound image data acquired using an ultrasound transducer tilted at different angles relative to the surface of the skin of the object. The ultrasound image data may include raw ultrasound image data, such as RF data acquired by an ultrasound probe, beamformed RF data, etc., as referenced above. Figure 2 In some embodiments, the apparatus 100 may also be configured to process such raw ultrasound image data to obtain a sequence of ultrasound images or frames.
[0069] In some embodiments, the sequence of ultrasound images may include a sequence of ultrasound images or "frames" (e.g., formatted images) (e.g., serial 2D B-mode data frames). In such an example, individual images correspond to the respective angle at which the ultrasound waves enter the skin.
[0070] Sequences of ultrasound images can be obtained from databases of ultrasound image data, such as those stored in the cloud.
[0071] In other embodiments, the device can be configured to acquire, for example, near-real-time ultrasound image data from an ultrasound probe. The ultrasound probe can be included in or separate from (but in communication with) device 100. As described above, suitable ultrasound probes include, but are not limited to, high-frequency linear array transducers. Such sensors can acquire higher resolution muscle imaging data because they are located superficially, with an imaging depth set to 3–5 cm. In another example, a high-frequency linear / bending probe (e.g., set in resolution mode) can be used to acquire serial 2D ultrasound image data.
[0072] Typically, a sequence of ultrasound images should consist of images obtained with the patient in a supine position, along the midline of the anterior abdomen towards the pubic symphysis. In other words, to obtain a sequence of ultrasound images, the sonographer can be instructed to position the transducer in the transverse plane of a short-axis view above the midline of the anterior abdomen on the umbilicus (Um) ring, and scan downwards towards the pubic symphysis. The center of the umbilicus can usually be used as a reference to ensure proper probe placement.
[0073] The sequence of ultrasound images comprises data obtained using ultrasound transducers tilted at different angles relative to the surface of the subject's skin, thus resulting in different angles at which ultrasound waves enter the skin. The sequence of ultrasound images may include image data obtained using an ultrasound transducer tilted at different angles spanning a range greater than approximately -10 degrees to approximately +10 degrees with respect to the transverse plane; or a range greater than approximately -20 degrees to approximately +20 degrees with respect to the transverse plane. In other words, in one example, the image sequence may cover angles ranging from 75 degrees to 105 degrees or from 85 degrees to 95 degrees (wherein the probe is defined as being at 90 degrees when perpendicular to the skin; as mentioned above, the goal is to image the muscle wall at a 90-degree angle; however, since the muscle wall is not visible to the sonographer, the skin is used as a reference surface).
[0074] The processor can be configured to instruct the display (e.g., the screen) to provide instructions to the user or ultrasound physician on how to place the transducer on the object and how to move the transducer through an appropriate angular range in order to obtain an appropriate sequence of images.
[0075] Figure 4An example of how a sequence of ultrasound images can be obtained is illustrated. In this example, an ultrasound probe is placed on the skin 400 of the object. The probe can be positioned at the umbilical region to image a transverse plane across the object. In this example, a sequence of ultrasound images is then obtained by moving the probe from an inclined position 404 to an upright position 402 (also referred to herein as the probe at a 90-degree angle to the skin) up to angle 406. Thus, the probe moves around the vertical position through angles 406, 408.
[0076] Generally, it is important to note that obtaining images within a precise angular range is not important; rather, the goal is usually to obtain ultrasound image data within a 90-degree angle entering the skin.
[0077] After the sequence of ultrasound images has been obtained, in step ii), the processor selects ultrasound image data from the sequence of ultrasound images, the selected ultrasound images being the images in which the region of the rectus abdominis muscle (e.g., muscle fibers) appears clearest compared to other images in the sequence of ultrasound images.
[0078] The region of the rectus abdominis muscle may include, for example, the outer edge or outer surface of the muscle fibers of the rectus abdominis muscle.
[0079] As described above, to measure muscle thickness, it is desirable to obtain ultrasound image data when the probe is at a 90-degree angle (or as close to 90 degrees) to the surface of the rectus abdominis muscle. The inventors have recognized here that the outer surface of the rectus abdominis muscle appears clearer at a 90-degree angle compared to other angles. This is because anisotropy makes the ultrasound image data less clear when the ultrasound probe is not at 90 degrees. When the ultrasound probe is not at a 90-degree angle to the linear structure being imaged (e.g., not perpendicular to the axis of the structure of interest), the anisotropy of the tissue is associated with a low-echo focal zone. Anisotropy is an inherent property of some anatomical structures that alters their ability to reflect ultrasound waves relative to the angle of incidence of the ultrasound beam. If the ultrasound beam is not reflected perpendicularly from a linear structure (e.g., muscles, tendons, and ligaments), the reflection is not specular. As a result, the returned echo has low intensity: and the structure incorrectly displays even lower echo (this artifact causes a loss of echo generation in the structure). The ability to identify and correct anisotropic artifacts is important for improved image quality and optimal patient care. This is particularly evident when imaging tendons / muscles. Ultrasound physicians can compensate for this by maintaining a 90-degree angle; however, as mentioned above, this requires a high level of training. By acquiring a sequence of ultrasound images at different tilt angles, the images in which the probe is correctly or optimally tilted (e.g., close to / most close to 90 degrees) can thus be selected as the image frames with the clearest boundaries. Therefore, optimal images for muscle measurements can be obtained without requiring excessive training for the ultrasound physician.
[0080] The sharpest images typically correspond to those in which the muscle surface (e.g., muscle fibers appearing as the upper / lower boundaries of two separate rectus abdominis muscles) appears brightest and narrowest (sharpest). Therefore, in some embodiments, processor 102 may be configured to select the sharpest ultrasound image data in a sequence of ultrasound images by determining (and subsequently selecting) the ultrasound image data in which the region of the rectus abdominis muscle (e.g., muscle fibers) appears brightest and / or sharpest compared to other image data in the sequence of ultrasound images. In this sense, sharpest can indicate ultrasound image data with the highest contrast between the muscle boundary and the surrounding soft tissue. It can also indicate that the structure appears narrowest (e.g., not “blurred”). Therefore, typically, selecting the sharpest image data may include selecting image data or frames in the selected ultrasound image data that show the region of the rectus abdominis muscle as brightest and sharpest (e.g., similar to optical focusing).
[0081] Image sharpness can be assessed in a region or portion (e.g., a region including muscle boundaries) of each image data / frame in a sequence of ultrasound images. Figure 5A The diagram illustrates this situation. Figure 5A The average intensity of an example ultrasound image frame obtained along the transverse direction is shown, resulting in an axial intensity projection curve 502. For this example ultrasound image, the minimum value at a depth region of [350 to 380] pixels on the projection curve corresponds to the peritoneal cavity (PC). A depth region of [381 to 535] pixels corresponds to imaging artifacts. A depth region of [1 to 50] pixels corresponds to the near field from the ultrasound probe. Therefore, in this example, a depth region of [51 to 380] pixels can be used to compare different images in a sequence of ultrasound images.
[0082] Image sharpness can be assessed at muscle boundaries in image data. For example, the sharpness of muscle fibers of the rectus abdominis (RAM) appearing as the upper / lower boundaries of two separate RAMs (left and right) can be assessed.
[0083] In some embodiments, the sharpness of image data (e.g., within the image region defined above) is evaluated based on the maximum average intensity. Therefore, in some embodiments, causing the processor to select ultrasound image data from a sequence of ultrasound images includes causing the processor to select ultrasound image data with the maximum average intensity.
[0084] exist Figure 5BThe graph shows the average intensity of 504 for each frame in an example sequence of ultrasound image frames. The average intensity of a selected depth of [51 to 380] pixels and the overall width of [1 to 586] pixels are plotted relative to the frame number when the probe is tilted approximately 90 degrees within a range of 15–20 degrees. The peak at frame 106 corresponds to the ultrasound image data closest to 90 degrees of the angle of entry to the target organ being examined. Therefore, in this example, frame 106 is selected. This illustrates that if the probe is at the selected optimal frame (closest to 90 degrees), the muscle boundaries in the ultrasound image data are brighter and narrower, while if it deviates from the selected optimal frame (90 degrees), the muscle boundaries are wider and more blurred.
[0085] In some embodiments, the sharpness of image data is evaluated based on the intensity differences between different images in the sequence (e.g., intensity differences within a region of each image as described above). Therefore, in some embodiments, causing the processor to select ultrasound image data from a sequence of ultrasound images includes: additionally or alternatively causing the processor to determine a measure of the intensity difference between adjacent image pairs in the sequence of ultrasound images, and selecting the ultrasound image with the largest measure of intensity difference. In this example, adjacent image pairs may refer to adjacent image pairs in the sequence of ultrasound images where the angle of ultrasound waves entering the skin increases or decreases sequentially between images in the sequence.
[0086] Determining the intensity difference between adjacent image pairs can involve determining the waveform of the two-dimensional average result of adjacent frames, mathematically represented as: mean2(frame_image(i+1)-frame_image(i)), where i is the frame number (from the first frame to the largest frame - 1). Therefore, the ultrasound image with the largest intensity difference metric can correspond to the largest difference peak.
[0087] exist Figure 5C The diagram illustrates this situation. Figure 5C The figures show the average intensity of 506 pixels (51 to 380 pixels) and the overall width of 1 to 586 pixels (1 to 586 pixels) of a selected depth region in an example sequence of ultrasound image frames acquired at a full tilt of approximately 90 degrees, covering a range of several degrees (e.g., 10 to 15 degrees). The maximum difference peak is located at approximately 90 degrees in the range of frames 100 to 118, and the best frame corresponds to a zero / near-zero intensity difference at frame 106, which corresponds to a scan performed at 90 degrees. Therefore, in this example, the clearest image frame is determined to be frame 106 (which is the same result obtained by the maximum intensity method described above).
[0088] In another example, correlation can be used to determine the clearest image in a sequence. For instance, additionally or alternatively, enabling a processor to select ultrasound images from a sequence of ultrasound images may include: enabling the processor to determine a correlation metric between adjacent image pairs in the sequence of ultrasound images, and selecting the ultrasound image with the highest correlation metric. This works because ultrasound waves have the highest correlation in images at approximately a 90-degree angle.
[0089] Therefore, in the above manner, sequences of ultrasound images can be processed to obtain the clearest images corresponding to ultrasound waves entering the skin / rectus abdominis at approximately 90 degrees, without requiring, for example, extensive training of ultrasound physicians, or the use of specialized and expensive hardware (accelerometers, etc.) to measure the angle.
[0090] In some embodiments, the processor can be configured to determine whether suitable ultrasound imaging data (e.g., appropriate frames) for rectus abdominis muscle measurement has been obtained, such as whether ultrasound imaging data sufficiently close to a 90-degree angle has been obtained. If not, the processor can send a message to the display to prompt the user for another sequence of imaging data. This can be repeated until suitable ultrasound imaging data is obtained.
[0091] Therefore, in one embodiment, the processor is also made to compare the brightness of the selected ultrasound image data with a threshold brightness. If the brightness is less than the threshold brightness, the processor is also made to send an instruction to the user display to indicate that a new sequence of ultrasound image data of the rectus abdominis muscle should be obtained. The processor can then repeat steps i) and ii) for the new sequence of ultrasound image data.
[0092] The threshold brightness can be set, for example, based on the maximum intensity, which can be obtained based on the settings of the ultrasound machine. For example, the threshold brightness can be set as a percentage of the maximum achievable brightness. For instance, if the maximum intensity is 255, the threshold brightness can be set to 200.
[0093] In other embodiments, other thresholds (e.g., threshold coherence levels between adjacent images) can be used to determine whether a suitable image sequence has been obtained.
[0094] Figure 6 Four example two-dimensional ultrasound image frames are shown, corresponding to (a) Figure 5A The first frame of the sequence shown in -C, (b) as referenced above. Figure 5A -C describes the selected or "best" or "optimal" frame, frame number 106, (c) frame 147 and frame 200. It can be seen that in Figure 6 In (b), the boundary of rectus abdominis 602 (bright, high-echo rectus abdominis sheath) is the clearest (e.g., the brightest and narrowest).
[0095] In some embodiments, the processor may prompt the user to acquire two or more image sequences at different locations on the stomach of the object / patient. In some examples, the processor may prompt the user to acquire sequences of ultrasound imaging data at a) the umbilical cord site, b) approximately 2.5 cm or 3 cm above the umbilical cord ring, and c) approximately 2.5 cm or 3 cm below the umbilical cord ring. The processor may then perform steps i) and ii) above for each sequence of ultrasound imaging data to select the clearest ultrasound image data at each site.
[0096] Once step ii) has been completed, the processor iii) measures the rectus abdominis muscle in the selected ultrasound image data.
[0097] This can involve determining the location of the surface of the rectus abdominis muscle in selected image data. This can be performed in various ways, such as segmentation (e.g., model-based segmentation or machine learning-based segmentation). Technicians will be familiar with segmentation, but simply put, image segmentation involves extracting shape / form information about a target or shape captured in an image. This can be achieved by converting the image into constituent blocks or "fragments". In some methods, image segmentation may include fitting a model to one or more features in the image.
[0098] Examples of segmentation include model-based segmentation (MBS) (see, for example, the 2008 article by Ecabert, O. et al. entitled "Automatic Model-Based Segmentation of the Heart in CT Images" (IEEE Trans. Med. Imaging, Vol. 27, No. 9, pp. 1189–1201)). Another segmentation approach uses machine learning (ML) models to transform an image into multiple constituent shapes (e.g., block shapes or block volumes) based on similar pixel / voxel values and image gradients.
[0099] In one embodiment, model-based segmentation can be used to determine the boundaries of the rectus abdominis (RAM) by modeling the RAM in ultrasound images / data as a hyperbolic function (e.g., X^2 / a^2 - y^2 / b^2 = 1).
[0100] In other embodiments, the surface / boundary of the rectus abdominis muscle can be determined by determining the orientation of each surface in the selected images relative to the surface of the skin. Based on the determined orientation, a surface can be selected as the surface of the rectus abdominis muscle. For example, it is expected that the surfaces of both rectus abdominis muscles will slope towards the linea alba (LA), and this can be used to distinguish them from the surface of the skin, which is closer to horizontal. For example, a threshold slope can be used to determine whether a surface identified in the selected ultrasound image data is a surface of the rectus abdominis muscle. For example, the threshold slope can be set to 12 degrees, such that only lines with a slope greater than 12 degrees are classified as corresponding to the muscle surface.
[0101] If the slope is too small (e.g., less than 12 degrees), it means the line structure is close to a horizontal line, which is inconsistent with the line structure corresponding to the rectus abdominis muscle boundary. If the slope of the line structure exceeds a predetermined threshold (e.g., more than 12 degrees) and the length of the line structure is long enough (e.g., greater than 1 / 3 of the entire imaging width), then the line structure can be classified as corresponding to the rectus abdominis muscle boundary.
[0102] In another embodiment, one or more user-input locations on the surface of the rectus abdominis muscle can be used as seed points to track the surface of the rectus abdominis muscle in selected image data. Those skilled in the art will be familiar with methods for using seed points to trace lines in an image (e.g., to determine the location of lines). Figure 7 The diagram illustrates this situation. Figure 7 It shows Figure 7 The exemplary ultrasound image frame 702 selected in a, the exemplary seed point 704 indicated by the user (e.g., using a user input device), and the location of the determined boundary of the rectus abdominis muscle 706. In this example, note that LA is located within a depth range of [85 120] pixels and a width range of [150 200] pixels, and the boundary of the two rectus abdominis muscles is clearly visible within a depth range of [60 160] pixels.
[0103] In this example, the four user-selected seed points 704 are located at [82 102], [128 102], [79 273], and [144 273]. These seed points are used as the initial points for the boundary search. IRD and muscle thickness can be determined from... Figure 7 Determined in c.
[0104] In another embodiment, a model trained using a machine learning process can be used to predict the location of the surface of the rectus abdominis muscle. Such a model can be trained on training data including ultrasound images of the rectus abdominis muscle in which the surface is correctly labeled (e.g., by a human expert). For example, a convolutional neural network can be trained (e.g., using backpropagation / gradient descent) based on the training dataset to perform such a task. Those skilled in the art will be familiar with methods for training machine learning models to label images and will recognize that convolutional neural networks are merely an example, and a wide variety of different models can be trained for such tasks.
[0105] Once the muscle boundaries have been determined, the method can proceed to step iii) and measure the rectus abdominis muscle in the selected ultrasound image data. The measurement results of the rectus abdominis muscle may include measurements of muscle thickness and / or the spacing between the rectus abdominis muscles. As described above, these measurements can be used to monitor rectus abdominis muscle separation in a subject.
[0106] Therefore, in this way, ultrasound imaging can be used to effectively monitor RAD in patients without requiring excessive training for ultrasound physicians to obtain appropriate image data.
[0107] Go to Figure 3 There is a computer-implemented method 300 for analyzing ultrasound image data of the rectus abdominis muscle of a subject. Embodiments of method 300 can be performed, for example, by a device such as the described apparatus 100 or ultrasound system 200.
[0108] In summary, in the first step 302, the method includes obtaining a sequence of ultrasound image data of the rectus abdominis muscle, the sequence of ultrasound image data being obtained using ultrasound transducers tilted at different angles relative to the surface of the skin of the object, thus having different angles at which ultrasound waves enter the skin. The sequence of obtaining ultrasound image data has been described in detail above with respect to apparatus 100, and the details therein will be understood to be equally applicable to method 300.
[0109] In the second step 304, the method includes selecting an ultrasound image from the sequence of ultrasound images, the selected ultrasound image being the image in which the region of the rectus abdominis muscle appears clearest compared to other images in the sequence of ultrasound images. The selection of the clearest ultrasound image from the sequence of ultrasound images has been described in detail above with respect to device 100, and the details therein will be understood to apply equally to method 300.
[0110] In the third step 306, the method includes measuring the rectus abdominis muscle in selected ultrasound image data. The measurement of the rectus abdominis muscle has been described in detail above with respect to device 100, and those details are to be understood to apply equivalently to method 300.
[0111] Therefore, a method is provided for measuring the rectus abdominis muscle to better facilitate the monitoring of rectus abdominis diastasis.
[0112] In another embodiment, a computer program product including a computer-readable medium having computer-readable code embodied therein, the computer-readable code being configured to cause the computer or processor, when run by a suitable computer or processor, to perform one or more methods described herein.
[0113] Therefore, it will be appreciated that this disclosure also applies to computer programs suitable for implementation in the embodiments, particularly computer programs on or in a carrier. The program may be in the form of source code, object code, intermediate source code, and object code in a partially compiled form, or any other form suitable for use in implementations of the methods according to the embodiments described herein.
[0114] It should also be recognized that such a program can have many different architectural designs. For example, the program code implementing the functionality of the method or system can be subdivided into one or more subroutines. Many different ways of distributing functionality among these subroutines will be apparent to those skilled in the art. Subroutines can be stored together in an executable file to form a self-contained program. Such an executable file may include computer-executable instructions, such as processor instructions and / or interpreter instructions (e.g., Java interpreter instructions). Alternatively, one or more or all of the subroutines may be stored in at least one external library file and linked to the main program, for example, statically or dynamically at runtime. The main program contains at least one call to at least one of the subroutines. Subroutines may also include function calls to each other.
[0115] The carrier of a computer program can be any entity or device capable of carrying the program. For example, the carrier can include a data storage device, such as a ROM (e.g., a CD-ROM or semiconductor ROM), or a magnetic recording medium (e.g., a hard disk). Furthermore, the carrier can be a transmissible carrier, such as electrical or optical signals, which can be transmitted via cables or optical fibers or by radio or other means. When a program is implemented in such a signal, the carrier can include such a cable or other device or apparatus. Alternatively, the carrier can be an integrated circuit in which the program is embedded, the integrated circuit being adapted to perform the relevant method, or adapted to be used in performing the relevant method.
[0116] Those skilled in the art, through studying the accompanying drawings, disclosure, and claims, will be able to understand and implement variations of the disclosed embodiments in practice with respect to the principles and techniques described herein. In the claims, the word "comprising" does not exclude other elements or steps, and the words "a" or "an" do not exclude a plurality. A single processor or other unit can implement the functions of several items recited in the claims. Although certain measures are recited in dissimilar dependent claims, this does not imply that combinations of these measures cannot be advantageously used. Computer programs can be stored or distributed on suitable media, such as optical storage media or solid-state media supplied together with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. No reference numerals in the claims should be construed as limiting the scope.
Claims
1. An apparatus (100) for analyzing ultrasound image data of the rectus abdominis muscle of a subject, the apparatus comprising: The memory (104) includes instruction data (106) representing a set of instructions. as well as Processor (102), configured to communicate with the memory and execute the set of instructions, wherein the set of instructions, when executed by the processor, causes the processor to: A sequence of ultrasound images of the rectus abdominis muscle was obtained (302), the sequence of ultrasound images being obtained using ultrasound transducers tilted at different angles relative to the surface (400) of the skin of the object, thus having different angles at which ultrasound waves enter the skin. From the sequence of ultrasound images, (304) ultrasound images are selected, the selected ultrasound images including those in the sequence in which the region of the rectus abdominis muscle appears clearest compared to other images in the sequence of ultrasound images; and The rectus abdominis muscle is measured in the selected ultrasound images.
2. The apparatus of claim 1, wherein, Selecting an ultrasound image from the sequence of ultrasound images by the processor includes making the processor: The ultrasound image in which the region of the rectus abdominis muscle appears brightest is selected compared to other images in the sequence of ultrasound images.
3. The apparatus according to claim 1 or 2, wherein, The processor (102) also compares the brightness of the selected ultrasound image with a threshold brightness; and If the brightness is less than the threshold brightness, a command is sent to the user display to instruct the user display to indicate that a new sequence of ultrasound images of the rectus abdominis muscle should be obtained; and Repeat the process of selecting another ultrasound image from the new sequence of ultrasound images and measuring the rectus abdominis muscle in the selected ultrasound image.
4. The apparatus according to claim 1 or 2, wherein, Making the processor (102) select the ultrasound image from the sequence of ultrasound images includes making the processor: The ultrasound image in which the region of the rectus abdominis muscle appears sharpest is selected compared to other images in the sequence of ultrasound images.
5. The apparatus according to claim 1 or 2, wherein, Making the processor (102) select the ultrasound image from the sequence of ultrasound images includes making the processor: Select the ultrasound image with the highest average intensity.
6. The apparatus according to claim 1 or 2, wherein, Making the processor (102) select the ultrasound image from the sequence of ultrasound images includes making the processor: Determine a measure of the intensity difference between adjacent image pairs in the sequence of ultrasound images; and The ultrasound image with the largest intensity difference is selected.
7. The apparatus according to claim 1 or 2, wherein, Making the processor (102) select the ultrasound image from the sequence of ultrasound images includes making the processor: Determine a correlation measure between adjacent image pairs in the sequence of ultrasound images; and Select the ultrasound image with the highest correlation metric.
8. The apparatus according to claim 1 or 2, wherein, The sequence of ultrasound images includes images already obtained along the midline of the anterior abdomen toward the pubic symphysis.
9. The apparatus according to claim 1 or 2, wherein, The different angles include those spanning a range greater than -20 degrees to +20 degrees from the transverse plane.
10. The apparatus according to claim 9, wherein, The different angles include those spanning a range greater than -10 degrees to +10 degrees from the transverse plane.
11. The apparatus according to claim 1 or 2, wherein, The processor (102) also locates the surface of the rectus abdominis muscle in the selected image through the following steps: segmentation; Determine the orientation of each surface in the selected image relative to the surface of the skin, and select a surface as the surface of the rectus abdominis muscle based on the determined orientation; The surface of the rectus abdominis muscle in the selected image is traced using one or more user-input locations on the surface of the rectus abdominis muscle as seed points. And / or The position of the surface of the rectus abdominis muscle is predicted using a model trained through a machine learning process.
12. The apparatus according to claim 1 or 2, wherein, The measurements of the rectus abdominis muscle include measurements of muscle thickness and / or measurements of the spacing of the rectus abdominis muscles.
13. The apparatus according to claim 12, wherein, The measurement is used to monitor diastasis recti in the subject.
14. An ultrasound imaging system comprising the apparatus according to any one of claims 1-13 and an ultrasound transducer (4) for obtaining the sequence of ultrasound images therefrom.
15. A computer-implemented method (300) for analyzing ultrasound image data of the rectus abdominis muscle of a subject, the method comprising: A sequence of ultrasound images of the rectus abdominis muscle was obtained (302), the sequence of ultrasound images being obtained using ultrasound transducers tilted at different angles relative to the surface (400) of the skin of the object, thus having different angles at which ultrasound waves enter the skin. From the sequence of ultrasound images, (304) ultrasound images are selected, the selected ultrasound images including those in the sequence in which the region of the rectus abdominis muscle appears clearest compared to other images in the sequence of ultrasound images; and The rectus abdominis muscle is measured in the selected ultrasound images.
16. A computer program product comprising a computer-readable medium having computer-readable code embodied therein, the computer-readable code being configured to cause the computer or processor, when run by a suitable computer or processor, to perform the method of claim 15.
Citation Information
Patent Citations
Phased array acoustic systems with intra-group processors
US5997479A
Beamforming methods and apparatus for three-dimensional ultrasound imaging using two-dimensional transducer array
US6013032A
Ultrasonic diagnostic imaging with blended tissue harmonic signals
US6283919B1
Method for creating multiplanar ultrasonic images of a three dimensional object
US6443896B1
Ultrasonic harmonic imaging with adaptive image formation
US6458083B1
