Method and system for enhancing visualization of myoma relative to uterus and endometrium in ultrasound imaging

Abstract

Methods for enhancing the visualization of a myoma relative to the uterus and endometrium in ultrasound imaging are provided. The method includes receiving, by at least one processor, an ultrasound volume including ultrasound image data of a region of interest, automatically segmenting the uterus and endometrium in the ultrasound volume, segmenting one or more myomas in the ultrasound image data, and outputting the one or more myomas. A classification of each of the one or more myomas is generated based on a position of each of the one or more myomas relative to the endometrium and the uterus such that the display system presents at least one image identifying the segmented uterus, endometrium, and one or more myomas. The application also provides a system for enhancing the visualization of a myoma relative to the uterus and endometrium during ultrasound imaging.

Description

Technical Field

[0001] Certain embodiments relate to ultrasound imaging. More specifically, certain embodiments relate to methods and systems for enhancing visualization and documentation of fibroid number, size, and location relative to the uterus and endometrium during ultrasound imaging. Background Art

[0002] Ultrasound imaging is a medical imaging technique used to image organs and soft tissues in the human body. Ultrasound imaging uses real-time, non-invasive, high-frequency sound waves to produce a series of two-dimensional (2D) images and / or three-dimensional (3D) images.

[0003] Myoma is a noncancerous growth in the uterus, which is common in women of all ages. Myoma can cause several gynecological and obstetric problems, such as infertility. Myoma can appear in the form of clusters, and can cause physical discomfort when the size of the myoma increases. The spatial position of myoma relative to the endometrium and uterine serosa plays a key role in determining severity and treatment approaches. For example, if myoma compresses the endometrium near the endometrium, surgery may be required to treat myoma. In the case of surgical treatment, the quantity, size and position of myoma relative to the uterus and endometrium are important for surgical planning purposes. The quantity, size and position of myoma are also important for monitoring the changes (i.e., longitudinal analysis) of myoma over time.

[0004] Although performing a 3D ultrasound scan ensures that the 3D context is preserved, drawing the 3D outline of each fibroid is tedious with high skill barriers. In addition, manually forming the outline of the uterus and endometrium is very time consuming, resulting in reduced productivity. Therefore, the recording of the number, size and location of fibroids for surgical planning purposes and / or fibroid monitoring over time is typically performed by hand drawing with pen and paper, or if applicable, using magnetic resonance imaging (MRI). However, performing an MRI is expensive and not always applicable. In addition, the accuracy of hand drawing using pen and paper is limited, particularly with respect to fibroid size and specific location.

[0005] Further limitations and disadvantages of conventional and traditional approaches will become apparent to those skilled in the art by comparing such systems with certain aspects of the present disclosure as set forth in the remainder of this application with reference to the accompanying figures. Summary of the invention

[0006] A system and / or method for enhancing visualization and documentation of fibroids relative to the uterus and endometrium during ultrasound imaging is provided, the system and / or method substantially as shown and / or described in conjunction with at least one of the accompanying drawings, as more fully set forth in the claims.

[0007] These and other advantages, aspects and novel features of the present disclosure, as well as details of illustrated embodiments thereof, will be more fully understood from the following description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 is a block diagram of an exemplary ultrasound system operable to enhance visualization and documentation of fibroids relative to the uterus and endometrium during ultrasound imaging in accordance with various embodiments.

[0009] Figure 2 is a block diagram of an exemplary medical workstation operable to enhance visualization and documentation of fibroids relative to the uterus and endometrium during ultrasound imaging in accordance with various embodiments.

[0010] Figure 3 is a screen shot of an exemplary display including a mid-sagittal ultrasound plane of the uterus according to various embodiments.

[0011] Figure 4 is a screenshot of an exemplary display including a mid-sagittal ultrasound plane of the uterus with a uterine trace through the endometrium in accordance with various embodiments.

[0012] Figure 5 Screen shot of an exemplary display of A-plane, B-plane, C-plane, and volume rendering including uterus and endometrium segmented in an ultrasound volume according to various embodiments.

[0013] Figure 6 Screen shot of an exemplary display of A-plane, B-plane, C-plane, and volume rendering including uterus, endometrium, and fibroids segmented in an ultrasound volume according to various embodiments.

[0014] Figure 7 In response to a parallel movement operation for scrolling between ultrasound image slices extending from a first end to a second end of an ultrasound volume according to various embodiments, Figure 6 A screenshot of an updated exemplary display of an exemplary display including A-plane, B-plane, C-plane, and volume rendering of the uterus, endometrium, and fibroids segmented in an ultrasound volume.

[0015] Figure 8 is a flow chart illustrating exemplary steps that may be used to enhance visualization and documentation of fibroids relative to the uterus and endometrium during ultrasound imaging, according to various embodiments. DETAILED DESCRIPTION

[0016] Certain embodiments can be found in methods and systems for enhancing visualization and recording of the number, size, and position of fibroids relative to the uterus and endometrium during ultrasound imaging. Various aspects of the present disclosure have the technical effect of acquiring an ultrasound volume of the uterus based on a two-dimensional (2D) ultrasound acquisition of the midsagittal plane of the uterus. Various embodiments have the technical effect of automatically segmenting the uterus and endometrium depicted in the ultrasound volume. Certain embodiments have the technical effect of enabling the ultrasound volume of the uterus to be scrolled from beginning to end to display parallel A-plane ultrasound slices separately. Various aspects of the present disclosure have the technical effect of providing automatic fibroid segmentation in the ultrasound volume based on color Doppler ultrasound data, semi-automatic fibroid segmentation in the ultrasound volume based on a user-selected seed point, and / or manual fibroid segmentation based on a manual trace of the fibroid. Various embodiments have the technical effect of classifying each segmented fibroid relative to the uterus and endometrium and / or prompting the user to classify. Certain embodiments have the technical effect of presenting a volume rendering of the segmented uterus, endometrium, and fibroids. Various aspects of the present disclosure have the technical effect of automatically performing volume measurements and / or estimated diameter measurements of the uterus, endometrium, and / or each fibroid. Various embodiments have the technical effect of facilitating longitudinal analysis of the number, size, and position of fibroids relative to the uterus and endometrium during ultrasound imaging. Certain embodiments have the technical effect of enhancing surgical planning and / or fibroid monitoring over time via ultrasound imaging. Various aspects of the present disclosure have the technical effect of generating and storing reports including ultrasound image data and / or volume renderings of the endometrium, uterus, and fibroids, fibroid classification, and measurement results.

[0017] When reading in conjunction with the accompanying drawings, the aforementioned summary of the invention and the following detailed description of certain embodiments will be better understood. In terms of the scope of the figures of the functional blocks of each embodiment shown in the accompanying drawings, these functional blocks do not necessarily represent the division between hardware circuits. Therefore, for example, one or more functional blocks (e.g., processors or memory) can be implemented in a single piece of hardware (e.g., a general signal processor or random access memory block, a hard disk, etc.) or multiple pieces of hardware. Similarly, a program can be an independent program, can be included in an operating system as a subroutine, can be a function in an installed software package, etc. It should be understood that each embodiment is not limited to the arrangement and tools shown in the accompanying drawings. It should also be understood that embodiments can be combined, or other embodiments can be utilized, and structural, logical and electrical changes can be made without departing from the scope of each embodiment. Therefore, the following detailed description should not be considered as a restrictive meaning, and the scope of the present disclosure is limited by the attached claims and their equivalents.

[0018] As used herein, elements or steps listed in the singular and beginning with the word "one" or "an" should be understood not to exclude a plurality of said elements or steps, unless such exclusion is expressly stated. In addition, references to "exemplary embodiments," "various embodiments," "certain embodiments," "representative embodiments," etc. are not intended to be interpreted as excluding the presence of additional embodiments that also include the features of the narration. In addition, unless expressly stated to the contrary, embodiments that "comprise," "include," or "have" an element or multiple elements having a particular attribute may include additional elements that do not have that attribute.

[0019] In addition, as used herein, the term "image" refers to both visible images and data representing visible images in a broad sense. However, many embodiments generate (or are configured to generate) at least one visible image. In addition, as used herein, the phrase "image" is used to refer to an ultrasound mode, which can be one-dimensional (1D), two-dimensional (2D), three-dimensional (3D) or four-dimensional (4D), and includes brightness mode (B mode), motion mode (M mode), color motion mode (CM mode), color flow mode (CF mode), pulsed wave (PW) Doppler, continuous wave (CW) Doppler, contrast enhanced ultrasound (CEUS) and / or B mode and / or CF mode sub-mode, such as harmonic imaging, shear wave elastic imaging (SWEI), strain elastic imaging, tissue velocity imaging (TVI), power Doppler imaging (PDI), B flow, microangiography (MVI), ultrasound guided attenuation parameters (UGAP) etc.

[0020] Furthermore, as used herein, the term processor or processing unit refers to any type of processing unit that can perform the required computations required by various embodiments, such as a single-core or multi-core central processing unit (CPU), an accelerated processing unit (APU), a graphics processing unit (GPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a system on a chip (SoC), an application-specific integrated circuit (ASIC), or a combination thereof.

[0021] It should be noted that various embodiments of generating or forming an image described herein may include a process for forming an image that includes beamforming in some embodiments and does not include beamforming in other embodiments. For example, an image may be formed without beamforming, such as by multiplying a matrix of demodulated data by a matrix of coefficients such that the product is an image and wherein the process does not form any "beams." Additionally, the formation of an image may be performed using a combination of channels that may originate from more than one transmit event (e.g., synthetic aperture techniques).

[0022] In various embodiments, ultrasound processing to form images, including ultrasound beamforming, such as receive beamforming, is performed, for example, in software, firmware, hardware, or a combination thereof. One specific implementation of an ultrasound system having a software beamformer architecture formed according to various embodiments is described in Figure 1 Shown in.

[0023] Figure 1 FIG. 1 is a block diagram of an exemplary ultrasound system 100 operable to enhance visualization and documentation of fibroids relative to the uterus and endometrium during ultrasound imaging in accordance with various embodiments. Figure 1 , an ultrasound system 100 and a training system 200 are shown. The ultrasound system 100 includes a transmitter 102, an ultrasound probe 104, a transmit beamformer 110, a receiver 118, a receive beamformer 120, an A / D converter 122, an RF processor 124, an RF / IQ buffer 126, a user input device 130, a signal processor 132, an image buffer 136, a display system 134, and an archive 138.

[0024] The transmitter 102 may include suitable logic, circuitry, interfaces, and / or code that may be operable to drive the ultrasound probe 104. The ultrasound probe 104 may include a two-dimensional (2D) array of piezoelectric elements. The ultrasound probe 104 may include a set of transmitting transducer elements 106 and a set of receiving transducer elements 108 that are generally constructed of the same elements. In certain embodiments, the ultrasound probe 104 may be operable to acquire ultrasound image data covering at least a majority of an anatomical structure, such as a uterus or any suitable anatomical structure. In a representative embodiment, the ultrasound probe 104 may be a transvaginal probe, a transabdominal probe, and / or any suitable ultrasound probe.

[0025] The transmit beamformer 110 may include suitable logic, circuitry, interfaces and / or code that may be operable to control the transmitter 102 to drive the set of transmit transducer elements 106 via the transmit sub-aperture beamformer 114 to transmit ultrasound transmit signals into a region of interest (e.g., a human, an animal, an underground cavity, a physical structure, etc.). The transmitted ultrasound signals may be backscattered from structures (such as blood cells or tissue) in the object of interest to generate echoes. The echoes are received by the receive transducer elements 108.

[0026] The set of receive transducer elements 108 in the ultrasound probe 104 may be operable to convert the received echoes into analog signals, sub-aperture beamformed by the receive sub-aperture beamformer 116, and then transmitted to the receiver 118. The receiver 118 may include suitable logic, circuitry, interfaces, and / or code that may be operable to receive the signals from the receive sub-aperture beamformer 116. The analog signals may be transmitted to one or more A / D converters 122.

[0027] The plurality of A / D converters 122 may include suitable logic, circuitry, interfaces, and / or code that may be operable to convert analog signals from the receiver 118 into corresponding digital signals. The plurality of A / D converters 122 are disposed between the receiver 118 and the RF processor 124. Nevertheless, the present disclosure is not limited in this regard. Therefore, in some embodiments, the plurality of A / D converters 122 may be integrated within the receiver 118.

[0028] The RF processor 124 may include suitable logic, circuitry, interfaces, and / or code that may be operable to demodulate the digital signals output by the plurality of A / D converters 122. According to an embodiment, the RF processor 124 may include a complex demodulator (not shown) that may be operable to demodulate the digital signals to form I / Q data pairs representing corresponding echo signals. The RF or I / Q signal data may then be transferred to the RF / IQ buffer 126. The RF / IQ buffer 126 may include suitable logic, circuitry, interfaces, and / or code that may be operable to provide temporary storage of the RF or I / Q signal data generated by the RF processor 124.

[0029] The receive beamformer 120 may comprise suitable logic, circuitry, interfaces, and / or code operable to perform digital beamforming processing to, for example, sum delayed channel signals received from the RF processor 124 via the RF / IQ buffer 126 and output a beam summed signal. The resulting processed information may be a beam summed signal output from the receive beamformer 120 and communicated to the signal processor 132. According to some embodiments, the receiver 118, the plurality of A / D converters 122, the RF processor 124, and the beamformer 120 may be integrated into a single beamformer, which may be a digital beamformer. In various embodiments, the ultrasound system 100 comprises a plurality of receive beamformers 120.

[0030] The user input device 130 may be used to input patient data, image acquisition and scanning parameters, settings, configuration parameters, select protocols and / or templates, change scanning modes, select seed points in ultrasound images corresponding to fibroids, perform manual drawing of fibroid traces in ultrasound images, select probe orientation, provide fibroid classification based on the location of the fibroid relative to the uterus and endometrium, etc. In an exemplary embodiment, the user input device 130 is operable to configure, manage, and / or control the operation of one or more components and / or modules in the ultrasound system 100. In this regard, the user input device 130 is operable to configure, manage, and / or control the operation of the transmitter 102, ultrasound probe 104, transmit beamformer 110, receiver 118, receive beamformer 120, RF processor 124, RF / IQ buffer 126, user input device 130, signal processor 132, image buffer 136, display system 134, and / or archive 138. The user input device 130 may include one or more buttons, one or more rotary encoders, a touch screen, motion tracking, voice recognition, a mouse device, a keyboard, a camera, and / or any other device capable of receiving user commands. In some embodiments, for example, one or more of the user input devices 130 may be integrated into other components such as the display system 134 or the ultrasound probe 104. For example, the user input device 130 may include a touch screen display.

[0031] The signal processor 132 may include suitable logic, circuitry, interfaces and / or codes that are operable to process ultrasound scan data (i.e., summed IQ signals) to generate an ultrasound image for presentation on a display system 134. The signal processor 132 is operable to perform one or more processing operations based on a plurality of selectable ultrasound modalities on the acquired ultrasound scan data. In an exemplary embodiment, the signal processor 132 may be used to perform display processing and / or control processing, etc. The acquired ultrasound scan data may be processed in real time during a scanning session as echo signals are received. Additionally or alternatively, the ultrasound scan data may be temporarily stored in the RF / IQ buffer 126 during a scanning session and processed in a less real-time manner in an online operation or an offline operation. In various embodiments, the processed image data may be presented at the display system 134 and / or may be stored at the archive 138. The archive 138 may be a local archive, a picture archiving and communication system (PACS), or any suitable device for storing images and related information.

[0032] The signal processor 132 may be one or more central processing units, graphics processing units, microprocessors, microcontrollers, etc. For example, the signal processor 132 may be an integrated component, or may be distributed in various locations. In an exemplary embodiment, the signal processor 132 may include a uterine segmentation processor 140, an endometrial segmentation processor 150, a fibroid segmentation processor 160, a fibroid classification processor 170, a mapping processor 180, and a measurement processor 190, and may be capable of receiving input information from the user input device 130 and / or the archive 138, generating output that can be displayed by the display system 134, and manipulating the output in response to the input information from the user input device 130, etc. For example, the signal processor 132, the uterine segmentation processor 140, the endometrial segmentation processor 150, the fibroid segmentation processor 160, the fibroid classification processor 170, the mapping processor 180, and the measurement processor 190 may be capable of performing any of the methods and / or instruction sets discussed herein according to various embodiments.

[0033] The ultrasound system 100 is operable to continuously acquire ultrasound scan data at a frame rate suitable for the imaging situation under consideration. Typical frame rates are in the range of 20 to 120, but may be lower or higher. The acquired ultrasound scan data may be displayed on a display system 134 at a display rate that is the same as the frame rate, or at a display rate that is slower or faster than the frame rate. An image buffer 136 is included to store processed frames of acquired ultrasound scan data that are not scheduled for immediate display. Preferably, the image buffer 136 has sufficient capacity to store ultrasound scan data frames equivalent to at least several minutes. The frames of ultrasound scan data are stored in a manner that is easy to retrieve from them according to their acquisition order or time. The image buffer 136 may be embodied as any known data storage medium.

[0034] In various embodiments, the ultrasound probe 104 of the ultrasound system 100 can be manipulated by an ultrasound operator to identify the correct endometrial plane via a two-dimensional (2D) ultrasound scan before starting a three-dimensional (3D) ultrasound image acquisition. Identifying the correct endometrial plane via a 2D scan ensures that the midsagittal plane of the 3D acquisition is aligned with the endometrium of the uterus. Figure 3 FIG. 4 is a screen shot 400 of an exemplary display 402 including a mid-sagittal ultrasound plane 410 of a uterus 420 according to various embodiments. Figure 3 , screenshot 400 shows a display 402 depicting a mid-sagittal ultrasound plane 410 of the uterus 420 and the endometrium 430. In an exemplary embodiment, the ultrasound operator may optionally perform a uterine trace through the endometrium 430 in the correct endometrial plane (i.e., mid-sagittal plane) 410 of the 2D image before starting a 3D ultrasound acquisition. Figure 45 is a screenshot 500 of an exemplary display 502 according to various embodiments, which includes a mid-sagittal ultrasound plane 510 of a uterus 520 with a uterine trace 536 passing through the endometrium 530. The uterine trace 536 can be provided by an ultrasound operator via a user input device 130, such as a mouse device or a touch screen display. For example, the ultrasound operator can manipulate the mouse device to drag a pointer across the display device 134 through the endometrium 530 to mark the uterine trace 536. As another example, the ultrasound operator can drag a finger or a stylus across the display device 134 through the endometrium 530 to mark the uterine trace 536. The uterine trace 536 allows the ultrasound operator to confirm that the mid-sagittal plane 510 has been acquired before switching to 3D image acquisition. In certain embodiments, the uterine trace 536 can be provided to the uterine segmentation processor 140 and / or the endometrium segmentation processor 150 to assist in segmenting the uterus 420, 520 and / or the endometrium 430, 530. For example, the uterine trace 536 may be used by the uterine segmentation processor 140 and / or the endometrial segmentation processor 150 to test the alignment of the segmented output. As another example, the endometrial segmentation processor 150 may use the uterine trace 536 to complete the cervical canal as an extension of the endometrial segmentation. In an exemplary embodiment, the uterine trace 536 may not be performed.

[0035] The signal processor 132 may include a uterus segmentation processor 140, which includes suitable logic components, circuits, interfaces and / or codes, which may be operable to receive a three-dimensional (3D) ultrasound volume image. The uterus segmentation processor 140 may be configured to automatically segment the uterus 420, 520 from the ultrasound volume image. The ultrasound volume image may be a gynecological uterine ultrasound scan, etc. For example, the uterus segmentation processor 140 may include an image analysis algorithm, an artificial intelligence algorithm, one or more deep neural networks (e.g., convolutional neural networks), and / or may utilize any suitable form of image analysis technology or machine learning processing functions configured to automatically segment the uterus 420, 520 from the ultrasound volume image (i.e., 3D). In various embodiments, the uterus segmentation processor 140 may be provided as a deep neural network, which may be composed of, for example, an input layer, an output layer, and one or more hidden layers between the input layer and the output layer. Each layer may be composed of a plurality of processing nodes, which may be referred to as neurons. For example, the uterus segmentation processor 140 may include an input layer having a neuron for each voxel or a group of voxels of an ultrasound volume image, such as a gynecological uterine ultrasound scan. The output layer may have neurons corresponding to the segmented uterus. Each neuron of each layer may perform a processing function and pass the processed ultrasound image information to one of the multiple neurons in the downstream layer for further processing. For example, the neurons of the first layer may learn to identify structural edges in the ultrasound image data. The neurons of the second layer may learn to recognize shapes based on the detected edges from the first layer. The neurons of the third layer may learn the positions of the recognized shapes relative to the landmarks in the ultrasound image data. The processing performed by the deep neural network (e.g., convolutional neural network) of the uterus segmentation processor 140 may segment the uterus 420, 520 depicted in the ultrasound volume image with a high probability. The uterus segmentation processor 140 may provide the ultrasound volume with the segmented uterus to the endometrial segmentation processor 150, and / or may store the ultrasound volume with the segmented uterus in the archive 138 and / or any suitable data storage medium.

[0036] The signal processor 132 may include an endometrial segmentation processor 150, which includes suitable logic components, circuits, interfaces and / or codes, which may be operable to receive a three-dimensional (3D) ultrasound volume image with a segmented uterus. The endometrial segmentation processor 150 may be configured to automatically segment the endometrium 430, 530 from the ultrasound volume image with the segmented uterus. For example, the endometrial segmentation processor 150 may include an image analysis algorithm, an artificial intelligence algorithm, one or more deep neural networks (e.g., convolutional neural networks), and / or may utilize any suitable form of image analysis technology or machine learning processing functions configured to automatically segment the endometrium 430, 530 from the ultrasound volume image (i.e., 3D). In various embodiments, the endometrial segmentation processor 150 may be provided as a deep neural network, which may be composed of, for example, an input layer, an output layer, and one or more hidden layers between the input layer and the output layer. Each layer may be composed of a plurality of processing nodes, which may be referred to as neurons. For example, the endometrium segmentation processor 150 may include an input layer having a neuron for each voxel or a group of voxels in the ultrasound volume image. The output layer may have neurons corresponding to the segmented endometrium. Each neuron of each layer may perform a processing function and pass the processed ultrasound image information to one of the multiple neurons of the downstream layer for further processing. For example, the neurons of the first layer may learn to identify structural edges in the ultrasound image data. The neurons of the second layer may learn to identify shapes based on the detected edges from the first layer. The neurons of the third layer may learn the positions of the identified shapes relative to the landmarks in the ultrasound image data. The processing performed by the endometrium segmentation processor 150 deep neural network (e.g., convolutional neural network) may segment the endometrium 430, 530 depicted in the ultrasound volume image with a high probability. The endometrium segmentation processor 150 may provide the ultrasound volume with the segmented uterus and endometrium to the rendering processor 180 for presenting the ultrasound image and volume rendering at the display system 134, as described below, and / or may store the ultrasound volume with the segmented uterus and endometrium at the archive 138 and / or any suitable data storage medium.

[0037] The signal processor 132 may include a rendering processor 180 comprising suitable logic, circuitry, interfaces, and / or code that may be operable to receive an ultrasound volume having a segmented uterus and endometrium from the uterus segmentation processor 140 and / or the endometrium segmentation processor 150, or retrieve an ultrasound volume having a segmented uterus and endometrium from the archive 138 and / or any suitable data storage medium. The rendering processor 180 may be configured to generate one or more renderings from the segmented ultrasound volume. For example, the rendering processor 180 may include suitable logic, circuitry, interfaces, and / or code that may be operable to generate a volume rendering, a cross-sectional image, an A-plane (i.e., a plane parallel to the acquisition plane), a B-plane (i.e., a plane perpendicular to the A-plane but still parallel to the ultrasound beam), a C-plane (i.e., a two-dimensional slice at different depths from the transducer face and parallel to the transducer face and perpendicular to the ultrasound beam), a curved slice (e.g., a 2D image slice extracted from a 3D volume along a curved anatomical structure such as the endometrium of a uterus), and / or any suitable ultrasound image. The rendering processor 180 may be configured to cause the display system 134 to present the generated image and / or store the generated image in the archive 138 and / or any suitable data storage medium.

[0038] Figure 5 600 is a screen shot of an exemplary display 602 including an A-plane 610, a B-plane 612, a C-plane 614, and a volume rendering 616 of a uterus 620, 622, 624 and endometrium 630, 632, 634 segmented in an ultrasound volume according to various embodiments. Figure 5, the screenshot 600 shows a display 602 with an A plane 610, a B plane 612, a C plane 614, and a volume rendering 616. The A plane 610 may correspond to a mid-sagittal plane of a volume ultrasound image of the uterus 620. The B plane 612 may correspond to a transverse plane of a volume ultrasound image of the uterus 620. The C plane 614 may correspond to a coronal plane of a volume ultrasound image of the uterus 620. The volume rendering 616 is a two-dimensional (2D) projection of a three-dimensional (3D) ultrasound volume and includes a rendering of the uterus 624 and the endometrium 634. The A plane 610, the B plane 612, and the C plane 614 are ultrasound image slices extracted from the acquired 3D ultrasound volume. The A plane 610, the B plane 612, and the C plane 614 depict the uterus 620 and the endometrium 630. The A plane 610, the B plane 612, and the C plane 614 may include markers 622, 632, color pixels, etc. that identify the segmentation of the uterus 622 and the segmentation of the endometrium 632. In various embodiments, the 3D ultrasound volume image includes a plurality of parallel A-plane ultrasound image slices 610 spanning from one end of the 3D ultrasound volume to the opposite end of the 3D ultrasound volume. An ultrasound operator or other medical professional may operate the user input device 130 to scroll through the parallel A-plane ultrasound image slices 610 of the 3D ultrasound volume.

[0039] The signal processor 132 may include a fibroid segmentation processor 160 including suitable logic, circuitry, interfaces and / or code that may be operable to automatically, semi-automatically and / or manually segment fibroids in a 3D ultrasound volume image and / or a 2D ultrasound image slice 610, 612, 614 extracted from the 3D ultrasound volume image. The fibroid segmentation processor 160 may be configured to manually segment fibroids from the 3D ultrasound volume image and / or the 2D ultrasound image slices 610, 612, 614 extracted from the 3D ultrasound volume image. For example, the fibroid segmentation processor 160 may be configured to receive a manual trace provided by an ultrasound operator or other medical professional via the user input device 130. For example, the ultrasound operator or other medical professional may scroll through the parallel A-plane ultrasound image slices 610 and manually draw a trace of the outline of the identified fibroid using a mouse device, a touch screen and / or any suitable user input device 130. As another example, an ellipse tool may be used to perform manual segmentation of a fibroid. As another example, manual segmentation of a fibroid may be performed using one, two, or three orthogonal caliper measurements.

[0040] Additionally and / or alternatively, the fibroid segmentation processor 160 may be configured to automatically segment fibroids from the 3D ultrasound volume image and / or 2D ultrasound image slices 610, 612, 614 extracted from the 3D ultrasound volume image with the aid of color Doppler ultrasound data. For example, fibroids may be difficult to distinguish from endometriosis, polyps, and other structures. Therefore, the ultrasound system 100 may be operable to perform color Doppler acquisition. For example, color Doppler ultrasound data provides blood flow characteristics that allow fibroids to be distinguished from other structures (such as endometriosis and polyps). As another example, a contrast agent may be used to visually enhance the fibroids for automatic segmentation. The fibroid segmentation processor 160 may include an image analysis algorithm, an artificial intelligence algorithm, one or more deep neural networks (e.g., convolutional neural networks), and / or may utilize any appropriate form of image analysis technology or machine learning processing functions, which are configured to automatically segment fibroids from ultrasound volume images and / or 2D ultrasound image slices 610, 612, 614 extracted from 3D volume images using color Doppler ultrasound image data. In various embodiments, the fibroid segmentation processor 160 may be provided as a deep neural network, which may be composed of, for example, an input layer, an output layer, and one or more hidden layers between the input layer and the output layer. Each layer may be composed of a plurality of processing nodes, which may be referred to as neurons. For example, the fibroid segmentation processor 160 may include an input layer having a neuron for each pixel, voxel, group of pixels, or group of voxels from ultrasound image data. The output layer may have neurons corresponding to the segmented fibroids. Each neuron of each layer may perform a processing function and pass the processed ultrasound image information to one of the plurality of neurons in the downstream layer for further processing. For example, the neurons of the first layer may learn to identify structural edges in ultrasound image data. The neurons of the second layer may learn to recognize shapes based on detected edges from the first layer. The neurons of the third layer may learn the positions of the recognized shapes relative to landmarks in the ultrasound image data. The neurons of the fourth layer may learn the blood flow characteristics of the detected shapes. The processing performed by the fibroid segmentation processor 160 deep neural network (e.g., a convolutional neural network) may segment the fibroids depicted in the ultrasound image data with a high probability. The fibroid segmentation processor 160 may provide the ultrasound volume with the segmented uterus 620, 622, endometrium 630, 632, and fibroids to the rendering processor 180 for presenting the ultrasound image and volume rendering at the display system 134, and / or may store the ultrasound volume with the segmented fibroids, uterus 620, 622, and endometrium 630, 632 at the archive 138 and / or any suitable data storage medium.

[0041] Additionally and / or alternatively, the fibroid segmentation processor 160 may be configured to semi-automatically segment the fibroid from the 3D ultrasound volume image and / or the 2D ultrasound image slices 610, 612, 614 extracted from the 3D ultrasound volume image with the aid of a seed point provided by the user to identify the fibroid. For example, the fibroid segmentation processor 160 may include an image analysis algorithm, an artificial intelligence algorithm, one or more deep neural networks (e.g., a convolutional neural network) and / or may utilize any suitable form of image analysis technology or machine learning processing function, which is configured to semi-automatically segment the fibroid from the ultrasound volume image and / or the 2D ultrasound image slices 610, 612, 614 extracted from the 3D volume image based on a user-selected point in the ultrasound image data of the fibroid to be segmented. In various embodiments, the fibroid segmentation processor 160 may be provided as a deep neural network, which may be composed of, for example, an input layer, an output layer, and one or more hidden layers between the input layer and the output layer. Each layer may be composed of a plurality of processing nodes, which may be referred to as neurons. For example, the fibroid segmentation processor 160 may include an input layer having a neuron for each pixel, voxel, group of pixels, or group of voxels from the ultrasound image data. The output layer may have neurons corresponding to the segmented fibroids. Each neuron of each layer may perform a processing function and pass the processed ultrasound image information to one of the multiple neurons in the downstream layer for further processing. For example, the neurons of the first layer may learn to identify the edges of structures with selected seed points in the ultrasound image data. The neurons of the second layer may learn to identify shapes based on the detected edges from the first layer. The neurons of the third layer may learn the positions of the identified shapes relative to the landmarks in the ultrasound image data. The processing performed by the deep neural network (e.g., a convolutional neural network) of the fibroid segmentation processor 160 may segment the fibroids depicted in the ultrasound image data with a high probability based on the seed points provided by the user. The fibroid segmentation processor 160 may provide the ultrasound volume with the segmented uterus, endometrium, and fibroids to the rendering processor 180 for presenting the ultrasound image and volume rendering at the display system 134, and / or may store the ultrasound volume with the segmented fibroids, uterus, and endometrium at the archive 138 and / or any suitable data storage medium.

[0042] Figure 6 700 is a screen shot of an exemplary display 702 including an A-plane 710, a B-plane 712, a C-plane 714, and a volume rendering 716 of a uterus 720, 722, 724, an endometrium 730, 732, 734, and a fibroid 740, 742, 744 segmented in an ultrasound volume according to various embodiments. Figure 6, the screenshot 700 shows a display 702 with an A plane 710, a B plane 712, a C plane 714, and a volume rendering 716. The A plane 710 may correspond to a mid-sagittal plane of a volume ultrasound image of the uterus 720. The B plane 712 may correspond to a transverse plane of a volume ultrasound image of the uterus 720. The C plane 714 may correspond to a coronal plane of a volume ultrasound image of the uterus 720. The volume rendering 716 is a two-dimensional (2D) projection of a three-dimensional (3D) ultrasound volume and includes renderings of the uterus 724, the endometrium 734, the first fibroid 744-1, and the second fibroid 744-2. The A plane 710, the B plane 712, and the C plane 714 are ultrasound image slices extracted from the acquired 3D ultrasound volume. The A plane 710, the B plane 712, and the C plane 714 depict the uterus 720, the endometrium 730, and the fibroid 740. The A plane 710, the B plane 712, and the C plane 714 may include markers 722, 732, 742-1, 742-2, color pixels, etc. that identify the segmentation of the uterus 722, the segmentation of the endometrium 732, the segmentation of the first fibroid 742-1, and the segmentation of the second fibroid 742-2. In various embodiments, the 3D ultrasound volume image includes a plurality of parallel A-plane ultrasound image slices 710 spanning from one end of the 3D ultrasound volume to the opposite end of the 3D ultrasound volume. The ultrasound operator or other medical professional may operate the user input device 130 to scroll through the parallel A-plane ultrasound image slices 710 of the 3D ultrasound volume. For example, the ultrasound operator or other medical professional may operate the user input device 130 to scroll through and select seed points of the fibroids 740-1, 740-2 for semi-automatic segmentation by the fibroid segmentation processor 160 using the seed points provided by the user. As another example, the ultrasound operator or other medical professional may operate the user input device 130 to scroll through and manually outline the fibroids 740 - 1 , 740 - 2 for manual segmentation.

[0043] Figure 7 In response to a parallel movement operation for scrolling between ultrasound image slices 710, 810 extending from a first end to a second end of the ultrasound volume according to various embodiments, Figure 6 Screen shot 800 of an updated exemplary display 802 of the exemplary display 702 including an A plane 810, a B plane 812, a C plane 814, and a volume rendering 816 of a uterus 820, 822, 824, an endometrium 830, 832, 834, and a fibroid 840, 842, 844 segmented in an ultrasound volume. Figure 7 , screen shot 800 shows a display 802 with an A plane 810, a B plane 812, a C plane 814, and a volume rendering 816. The A plane 810, the B plane 812, the C plane 814, and the volume rendering 816 are similar to those described above. Figure 5and Figure 6 The A plane 610, 710, B plane 612, 712, C plane 614, 714, and volume rendering 616, 716 of the 3D ultrasound volume image share various characteristics. The A plane 810, B plane 812, and C plane 814 may include markings 822, 832, 842-1, 842-2, 842-3, color pixels, etc. that identify the segmentation of the uterus 822, the segmentation of the endometrium 832, the segmentation of the first fibroid 842-1, the segmentation of the second fibroid 842-2, and the segmentation of the third fibroid 842-3. In various embodiments, the 3D ultrasound volume image includes a plurality of parallel A-plane ultrasound image slices 810 spanning from one end of the 3D ultrasound volume to the opposite end of the 3D ultrasound volume. An ultrasound operator or other medical professional may operate the user input device 130 to scroll through the parallel A-plane ultrasound image slices 810 of the 3D ultrasound volume. For example, the ultrasound operator or other medical professional may operate the user input device 130 to scroll through and select seed points of the fibroids 840-1, 840-2, 840-3 for semi-automatic segmentation using the user-provided seed points by the fibroid segmentation processor 160. For another example, the ultrasound operator or other medical professional may operate the user input device 130 to scroll through and manually draw the outlines of the fibroids 840-1, 840-2, 840-3 for manual segmentation.

[0044] The signal processor 132 may include a fibroid classification processor 170 that includes suitable logic, circuitry, interfaces, and / or code that may be operable to classify the segmented fibroids 742-1, 742-2, 842-1, 842-2, 842-3 (collectively, 742, 842). For example, the fibroid classification processor 170 may be configured to prompt an ultrasound operator or other medical professional to select a classification for each segmented fibroid 742, 842. For another example, the fibroid classification processor 170 may be configured to automatically classify each segmented fibroid 742, 842. In various embodiments, the classification can be the International Federation of Gynecology and Obstetrics (FIGO) uterine leiomyoma classification system, which is assigned a classification based on the location of the fibroids 740, 742, 840, 842 relative to the uterus 620, 622, 720, 722, 820, 822 and the endometrium 630, 632, 730, 732, 830, 832. However, any suitable fibroid classification system can be applied, such as classifying fibroids relative to the patient (e.g., left / right, front / back, etc.). The FIGO uterine leiomyoma classification system is organized according to the location of the fibroids 740, 742, 840, 842 between the submucosal layer (0-2), the intramural layer (3-5), and the subserosa (6-7) of the uterus. Category "0" corresponds to pedunculated intracavitary. Category "1" corresponds to less than 50% of the intramural. Category "2" corresponds to greater than or equal to 50% of the intramural. Category "3" corresponds to 100% intramural and endometrial contact. Category "4" corresponds to 100% intramural. Category "5" corresponds to subserosal and greater than or equal to 50% intramural. Category "6" corresponds to subserosal and less than 50% intramural. Category "7" corresponds to subserosal pedunculated. Category "8" corresponds to "other" locations, such as cervical fibroids. In an exemplary embodiment, the fibroid classification processor 170 may present a pop-up window or any suitable prompt for receiving a selection of one of the classifications for each of the segmented fibroids 742, 842.

[0045] In certain embodiments, the fibroid classification processor 170 may include an image analysis algorithm, an artificial intelligence algorithm, one or more deep neural networks (e.g., convolutional neural networks) and / or may utilize any suitable form of image analysis technology or machine learning processing function, which is configured to automatically classify the fibroids 740, 840 segmented from the ultrasound volume image 742, 842 and / or the 2D ultrasound image slices 610, 612, 614, 710, 712, 714, 810, 812, 814 extracted from the 3D volume image based on the spatial location of each of the segmented fibroids 742, 842 relative to the segmented uterus 622, 722, 822 and the segmented endometrium 632, 732, 832. In various embodiments, the fibroid classification processor 170 may be provided as a deep neural network, which may be composed of, for example, an input layer, an output layer, and one or more hidden layers between the input layer and the output layer. Each layer may be composed of a plurality of processing nodes, which may be referred to as neurons. For example, the fibroid classification processor 170 may include an input layer having a neuron for each pixel, voxel, group of pixels, or group of voxels from the ultrasound image data. The output layer may have neurons corresponding to the classification of each segmented fibroid 742, 842. Each neuron of each layer may perform a processing function and pass the processed ultrasound image information to one of the multiple neurons in the downstream layer for further processing. The processing performed by the fibroid classification processor 170 deep neural network (e.g., convolutional neural network) can classify the fibroids 740-1, 740-2, 840-1, 840-2, 840-3 (collectively referred to as 740, 840) depicted in the ultrasound image data with a high probability. The fibroid classification processor 170 may present the classification of fibroids 740, 840 at the display system 134 and / or may store the classification of fibroids 740, 840 at the archive 138 and / or any suitable data storage medium.

[0046] The signal processor 132 may include a measurement processor 190 including suitable logic, circuitry, interfaces, and / or code that may be operable to perform measurements on the segmented uterus 622, 722, 822, endometrium 632, 732, 832, and fibroids 742, 842. For example, the measurement processor 190 may be configured to perform volume measurements, estimated diameter measurements, length measurements, width measurements, and / or any suitable measurements on the segmented anatomical structures. For purposes of this application, an estimated diameter is defined as the maximum distance between points of the boundaries of the segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842. The measurement processor 190 may be configured to cause the display system 134 to present the measurement results. The measurement processor 190 may be configured to store the measurement results at the archive 138 and / or any suitable data storage medium.

[0047] In various embodiments, the signal processor 132 may be configured to receive the probe orientation of the ultrasound probe 104. For example, the ultrasound probe 104 may include an orientation indicator, such as a knob. The signal processor 132 may be configured to receive the probe and / or acquisition type (e.g., transvaginal, transabdominal, etc.), the ultrasound probe orientation (e.g., the angle in degrees of the knob), and the tilt (if applicable) from the ultrasound operator via the user input device 130. The probe orientation information may be applied by the signal processor 132 to present markings (e.g., left, right, front, back, etc.) to the ultrasound image views (e.g., A plane 610, 710, 810, B plane 612, 712, 812, C plane 614, 714, 814, and volume rendering 616, 716, 816) presented at the display system 134, thereby providing spatial context information to the ultrasound operator.

[0048] In a representative embodiment, the signal processor 132 can be configured to generate a report that includes the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814, volume renderings 616, 716, 816, fibroid classifications, measurements, etc. The ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814 and volume renderings 616, 716, 816 included in the report provide the precise location of the fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830, which can be used for treatment planning, treatment monitoring, and clinical follow-up. The generated report including the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814, volume renderings 616, 716, 816, fibroid classifications and / or measurements allows for longitudinal analysis with reference to subsequently acquired ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814, volume renderings 616, 716, 816, fibroid classifications and measurements. For example, the signal processor 132 can be configured to present at the display system 134 a comparison showing relative changes in the fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830.

[0049] Still see Figure 1 The display system 134 may be any device capable of conveying visual information to a user. For example, the display system 134 may include a liquid crystal display, a light emitting diode display, and / or any suitable one or more displays. The display system 134 may be operable to present ultrasound images 610, 612, 614, 710, 712, 714, 810, 812, 814 extracted from the 3D ultrasound volume, volume renderings 616, 716, 816 of the segmented uterus 624, 724, 824, endometrium 634, 734, 834, and fibroids 744-1, 744-2, 844-1, 844-2, 844-3 (collectively 744, 844), fibroid classification, measurements, reports, longitudinal analysis, probe orientation markings, and / or any suitable information.

[0050] The archive 138 may be one or more computer-readable memories, such as a picture archiving and communication system (PACS), a server, a hard disk, a floppy disk, a CD, a CD-ROM, a DVD, a compact storage device, a flash memory, a random access memory, a read-only memory, an electrically erasable and programmable read-only memory, and / or any suitable memory, that are integrated with the ultrasound system 100 and / or communicatively coupled to the ultrasound system 100 (e.g., via a network). The archive 138 may include, for example, a database, a library, a collection of information, or other memory that is accessed by and / or in conjunction with the signal processor 132. For example, the archive 138 may be capable of storing data temporarily or permanently. The archive 138 may be capable of storing medical image data, data generated by the signal processor 132, and / or instructions readable by the signal processor 132, etc. In various embodiments, the archive 138 stores, for example, ultrasound images 610, 612, 614, 710, 712, 714, 810, 812, 814, segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842, volume renderings 616, 716, 816 of segmented anatomical structures 624, 634, 724, 734, 744, 824, 834, 844, measurements of the segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842, reports generated related to the segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842, instructions for generating a drawing 624, 634, 724, 734, 744, 824, 834, 844 of the segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842, instructions for classifying the fibroids 740, 840, instructions for taking measurements of the segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842, instructions for generating a report, instructions for presenting a longitudinal analysis of the fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830 over time, and / or any suitable images, information, and / or instructions.

[0051] The components of the ultrasound system 100 may be implemented in software, hardware, firmware, etc. The various components of the ultrasound system 100 may be communicatively connected. The components of the ultrasound system 100 may be implemented separately and / or integrated in various forms. For example, the display system 134 and the user input device 130 may be integrated into a touch screen display.

[0052] Still reference Figure 1, the training system 200 may include a training engine 210 and a training database 220. The training engine 210 may include suitable logic, circuitry, interfaces, and / or code that may be operable to train neurons of a deep neural network (e.g., an artificial intelligence model) inferred (i.e., deployed) by the uterus segmentation processor 140, the endometrium segmentation processor 150, the fibroid segmentation processor 160, and / or the fibroid classification processor 170. For example, the segmentation or classification network inferred by the uterus segmentation processor 140, the endometrium segmentation processor 150, the fibroid segmentation processor 160, and / or the fibroid classification processor 170 may be trained to automatically segment anatomical structures (e.g., uterus 620, 720, 820, endometrium 630, 730, 830, fibroids 740, 840) or automatically classify fibroids 740, 840 depicted in ultrasound images. For example, the training engine 210 may train a segmentation or classification network deployed by the uterus segmentation processor 140, the endometrium segmentation processor 150, the fibroid segmentation processor 160, and / or the fibroid classification processor 170 to automatically segment the uterus 620, 720, 820, the endometrium 630, 730, 830, and the fibroid 740, 840 using the database 220 of classified anatomical structures (e.g., the uterus 620, 720, 820, the endometrium 630, 730, 830, and the fibroid 740, 840), or automatically classify the fibroid 740, 840 depicted in the ultrasound images 610, 612, 614, 710, 712, 714, 810, 812, 814. The classified anatomical structures may include an input image and a ground truth binary image (e.g., a mask) of the anatomical structures after manual segmentation. The training engine 210 may be configured to optimize the segmentation or classification network by adjusting the weights of the segmentation or classification network to minimize a loss function between an input ground truth mask and an output predicted mask.

[0053] In various embodiments, the database 220 of training images may be a picture archiving and communication system (PACS) or any suitable data storage medium. In certain embodiments, the training engine 210 and / or the training image database 220 may be a remote system communicatively coupled to the ultrasound system 100 via a wired or wireless connection, such as Figure 1 Additionally and / or alternatively, components or all of the training system 200 may be integrated with the ultrasound system 100 in various forms.

[0054] Figure 2is a block diagram of an exemplary medical workstation 300 according to various embodiments, which is operable to enhance visualization and recording of fibroids 740, 840 relative to uterus 420, 520, 620, 720, 820 and endometrium 430, 530, 630, 730, 830 during ultrasound imaging. In a representative embodiment, components of the medical workstation 300 and training system 200 may share various features with components of ultrasound system 100 and training system 200, such as Figure 1 As shown and described above. Figure 2 , the medical workstation 300 includes a display system 134, a signal processor 132, a file 138, and a user input device 130, etc. The components of the medical workstation 300 can be implemented in software, hardware, firmware, etc. The various components of the medical workstation 300 can be communicatively linked. The components of the medical workstation 300 can be implemented separately and / or integrated in various forms. For example, the display system 134 and the user input device 130 can be integrated into a touch screen display.

[0055] The display system 134 can be any device capable of conveying visual information to a user. For example, the display system 134 can include a liquid crystal display, a light emitting diode display, and / or any suitable one or more displays. The display system 134 can be operable to display information from the signal processor 132 and / or the archive 138, such as ultrasound images 610, 612, 614, 710, 712, 714, 810, 812, 814 extracted from the 3D ultrasound volume, volume renderings 616, 716, 816 of the segmented uterus 624, 724, 824, endometrium 634, 734, 834, and fibroids 744, 844, fibroid classification, measurements, reports, longitudinal analysis, probe orientation markings, and / or any suitable information.

[0056] The signal processor 132 may be one or more central processing units, microprocessors, microcontrollers, etc. For example, the signal processor 132 may be an integrated component, or may be distributed in various locations. The signal processor 132 includes a uterus segmentation processor 140, an endometrial segmentation processor 150, a fibroid segmentation processor 160, a fibroid classification processor 170, a mapping processor 180, and a measurement processor 190, as described above. Figure 1 As described, and may be capable of receiving input information from the user input device 130 and / or the archive 138, generating output that can be displayed by the display system 134, and manipulating the output in response to the input information from the user input device 130, etc. For example, the signal processor 132, the uterus segmentation processor 140, the endometrium segmentation processor 150, the fibroid segmentation processor 160, the fibroid classification processor 170, the mapping processor 180 and / or the measurement processor 190 may be capable of performing any of the methods and / or instruction sets discussed herein according to various embodiments.

[0057] The archive 138 may be one or more computer-readable memories, such as a picture archiving and communication system (PACS), a server, a hard disk, a floppy disk, a CD, a CD-ROM, a DVD, a compact memory, a flash memory, a random access memory, a read-only memory, an electrically erasable and programmable read-only memory, and / or any suitable memory, integrated with and / or communicatively coupled (e.g., via a network) to the medical workstation 300. The archive 138 may include, for example, a database, a library, a collection of information, or other memory accessed by and / or in conjunction with the signal processor 132. For example, the archive 138 may be capable of storing data temporarily or permanently. The archive 138 may be capable of storing medical image data, data generated by the signal processor 132, and / or instructions readable by the signal processor 132, etc. In various embodiments, the archive 138 stores, for example, ultrasound images 610, 612, 614, 710, 712, 714, 810, 812, 814, segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842, volume renderings 616, 716, 816 of segmented anatomical structures 624, 634, 724, 734, 744, 824, 834, 844, measurements of the segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842, reports generated related to the segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842, instructions for generating a drawing 624, 634, 724, 734, 744, 824, 834, 844 of the segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842, instructions for classifying the fibroids 740, 840, instructions for taking measurements of the segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842, instructions for generating a report, instructions for presenting a longitudinal analysis of the fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830 over time, and / or any suitable images, information, and / or instructions.

[0058] For example, the user input device 130 may include any device capable of transmitting information from a user and / or at the direction of a user to the signal processor 132 of the medical workstation 300. Figure 1As discussed, user input device 130 may include a touch panel, buttons, a mouse device, a keyboard, a rotary encoder, a trackball, a touchpad, a camera, voice recognition, and / or any other device capable of receiving user instructions.

[0059] Still see Figure 2 , the training system 200 may include a training engine 210 and a training database 220. The training engine 210 may include suitable logic, circuitry, interfaces, and / or code that may be operable to train neurons of a deep neural network (e.g., an artificial intelligence model) inferred (i.e., deployed) by the uterus segmentation processor 140, the endometrium segmentation processor 150, the fibroid segmentation processor 160, and / or the fibroid classification processor 170. For example, the artificial intelligence model inferred by the uterus segmentation processor 140, the endometrium segmentation processor 150, the fibroid segmentation processor 160 and / or the fibroid classification processor 170 can be trained to automatically identify and / or classify the uterus 620, 720, 820, the endometrium 630, 730, 830, and the fibroids 740, 840, or other anatomical objects of interest depicted in the ultrasound volume (or ultrasound slices 610, 612, 614, 710, 712, 714, 810, 812, 814 extracted from the ultrasound volume) using the database 220 of classified anatomical structures (e.g., the uterus 620, 720, 820, the endometrium 630, 730, 830, and the fibroids 740, 840).

[0060] In various embodiments, the database 220 of training images may be a picture archiving and communication system (PACS) or any suitable data storage medium. In certain embodiments, the training engine 210 and / or the training image database 220 may be a remote system communicatively coupled to the medical workstation 300 via a wired or wireless connection, such as Figure 2 Additionally and / or alternatively, components or all of the training system 200 may be integrated with the medical workstation 300 in various forms.

[0061] Figure 8 FIG. 9 is a flow chart 900 showing exemplary steps 902-918 that may be used to enhance visualization and documentation of a fibroid 740, 840 relative to a uterus 620, 720, 820 and endometrium 630, 730, 830 during ultrasound imaging, according to various embodiments. Figure 8, a flowchart 900 including exemplary steps 902 to 918 is shown. Certain embodiments may omit one or more steps, and / or perform steps in an order different from the order listed, and / or combine certain steps discussed below. For example, some steps may not be performed in certain embodiments. For another example, certain steps may be performed in a time sequence different from the time sequence listed below, including being performed simultaneously.

[0062] At step 902, one or more segmentation and / or classification networks are trained to segment and / or classify the uterus 620, 720, 820, endometrium 630, 730, 830, and / or fibroids 740, 840 in the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814. For example, the training engine 210 of the training system 200 uses the database 220 of classified anatomical structures (e.g., 620, 720, 820, endometrium 630, 730, 830, and fibroids 740, 840) to train the segmentation and / or classification network. The classified anatomical structures may include the input image and the ground truth binary image (e.g., mask) of the anatomical structure after manual segmentation. The training engine 210 may be configured to optimize the segmentation or classification network by adjusting the weights of the segmentation or classification network to minimize the loss function between the input ground truth mask and the output predicted mask.

[0063] At step 904, the ultrasound probe 104 of the ultrasound system 100 acquires an ultrasound image of the midsagittal plane 410, 510 of the uterus 420, 520, and the signal processor 132 of the ultrasound system 100 optionally receives a uterine trace 536. For example, before starting a three-dimensional (3D) ultrasound image acquisition at step 906, the ultrasound probe 104 may be navigated to identify the correct endometrial plane (i.e., the midsagittal plane of the uterus) 410, 510 via a two-dimensional (2D) ultrasound scan. The acquired ultrasound image 410, 510 may be presented at the display system 134 of the ultrasound system 100. In various embodiments, the signal processor 132 may optionally receive a uterine trace 536 passing through the endometrium 530 in the correct endometrial plane (i.e., the midsagittal plane) 510 via the user input device 130. The uterine trace 536 may be provided by an ultrasound operator via a user input device 130 (such as a mouse device or a touch screen display). The uterine trace 536 allows the ultrasound operator to confirm that the mid-sagittal plane has been acquired before switching to 3D image acquisition at step 906 .

[0064] At step 906, the ultrasound probe 104 of the ultrasound system 100 acquires an ultrasound volume including the region of interest of the uterus 620, 720, 820. For example, the ultrasound probe 104 may perform a 3D acquisition to acquire an ultrasound volume aligned with the ultrasound probe position at the mid-sagittal plane 410, 510, 610, 710, 810. The acquired ultrasound volume may be provided to a rendering processor 180 for rendering various views (e.g., A-plane 610, 710, 810, B-plane 612, 712, 812, C-plane 614, 714, 814, volume rendering 616, 716, 816, etc.) for presentation at a display system 134 of the ultrasound system 100 and / or the medical workstation 300, provided to a uterus segmentation processor 140, an endometrial segmentation processor 150, a fibroid segmentation processor 160, a fibroid classification processor 170, and / or a measurement processor 190 of a signal processor 132 of the ultrasound system 100 and / or the medical workstation 300, and / or stored in an archive 138 and / or any suitable data storage medium of the ultrasound system 100 and / or the medical workstation 300.

[0065] At step 908, the signal processor 132 of the ultrasound system 100 and / or the medical workstation 300 may automatically segment the uterus 620, 720, 820 and the endometrium 630, 730, 830 in the ultrasound volume. For example, the uterus segmentation processor 140 of the signal processor 132 may be configured to deploy the segmentation network trained at step 902 to automatically segment the uterus 620, 720, 820 in the ultrasound volume received from the ultrasound probe 104 or retrieved from the archive 138 and / or any suitable data storage medium. For another example, the endometrium segmentation processor 150 of the signal processor 132 may be configured to deploy the segmentation network trained at step 902 to automatically segment the endometrium 630, 730, 830 in the ultrasound volume. The segmented ultrasound volume may be provided to a rendering processor 180 for rendering various views (e.g., A-plane 610, 710, 810, B-plane 612, 712, 812, C-plane 614, 714, 814, volume rendering 616, 716, 816, etc.) for presentation at a display system 134, provided to a fibroid segmentation processor 160, a fibroid classification processor 170, and / or a measurement processor 190 of a signal processor 132, and / or stored at an archive 138 and / or any suitable data storage medium. In various embodiments, the signal processor 132 may be configured to receive, via the user input device 130, a probe and / or acquisition type (e.g., transvaginal, transabdominal, etc.), an ultrasound probe orientation (e.g., an angle in knob degrees), and a tilt (if applicable) from an ultrasound operator. The probe orientation information can be applied by the signal processor 132 to present markings (e.g., left, right, front, back, etc.) to the ultrasound image views (e.g., A plane 610, 710, 810, B plane 612, 712, 812, C plane 614, 714, 814, volume rendering 616, 716, 816) presented at the display system 134, thereby providing spatial context information to the ultrasound operator.

[0066] In step 910, one or more fibroids 740, 840 may be segmented in the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814. For example, one or more fibroids 740, 840 may be automatically, semi-automatically, and / or manually segmented in the 3D ultrasound volume image and / or the 2D ultrasound image slices 610, 612, 614, 710, 712, 714, 810, 812, 814 extracted from the 3D ultrasound volume image. For example, the fibroid segmentation processor 160 may be configured to receive a manual trace provided by an ultrasound operator or other medical professional via the user input device 130. The ultrasound operator or other medical professional may scroll through the parallel A-plane ultrasound image slices 610, 710, 810 and manually trace the outline of the identified fibroids 740, 840 using a mouse device, a touch screen, and / or any suitable user input device 130. As another example, the fibroid segmentation processor 160 may automatically segment the fibroids 740, 840 from the 3D ultrasound volume image and / or the 2D ultrasound image slices 610, 612, 614, 710, 712, 714, 810, 812, 814 extracted from the 3D ultrasound volume image with the aid of the color Doppler ultrasound data. For example, the fibroid segmentation processor 160 may include an image analysis algorithm, an artificial intelligence algorithm, one or more deep neural networks (e.g., a convolutional neural network) and / or may utilize any suitable form of image analysis technology or machine learning processing functionality configured to automatically segment the fibroids 740, 840 from the ultrasound volume image and / or the 2D ultrasound image slices 610, 612, 614, 710, 712, 714, 810, 812, 814 extracted from the 3D volume image using the color Doppler ultrasound image data. As another example, additionally and / or alternatively, the fibroid segmentation processor 160 may be configured to semi-automatically segment the fibroids 740, 840 from the 3D ultrasound volume image and / or the 2D ultrasound image slices 610, 612, 614, 710, 712, 714, 810, 812, 814 extracted from the 3D ultrasound volume image with the assistance of a seed point for identifying the fibroids 740, 840 provided by a user. For example, the fibroid segmentation processor 160 may include an image analysis algorithm, an artificial intelligence algorithm, one or more deep neural networks (e.g., a convolutional neural network) and / or may utilize any appropriate form of image analysis technology or machine learning processing functionality, which is configured to semi-automatically segment fibroids 740, 840 based on user-selected points in the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814 of the fibroids 740, 840 to be segmented, from 2D ultrasound image slices 610, 612, 614, 710, 712, 714, 810, 812, 814 extracted from the 3D volumetric image.The fibroid segmentation processor 160 may provide the ultrasound volume having the segmented uterus 622, 722, 822, endometrium 632, 732, 832, and fibroids 742, 842 to the rendering processor 180 for presenting the ultrasound images 610, 612, 614, 710, 712, 714, 810, 812, 814 and the volume renderings 616, 716, 816 at the display system 134, and / or may store the ultrasound volume having the segmented uterus 622, 722, 822, endometrium 632, 732, 832, and fibroids 742, 842 at the archive 138 and / or any suitable data storage medium.

[0067] At step 912, the signal processor 132 of the ultrasound system 100 and / or the medical workstation 300 may classify each of the one or more fibroids 740, 840 based on the location of each of the fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830. For example, the fibroid classification processor 170 of the signal processor 132 may be configured to prompt the ultrasound operator or other medical professional to select a classification for each segmented fibroid 742, 842. For another example, the fibroid classification processor 170 may be configured to automatically classify each segmented fibroid 742, 842. For example, the fibroid classification processor 170 may include an image analysis algorithm, an artificial intelligence algorithm, one or more deep neural networks (e.g., a convolutional neural network), and / or may utilize any suitable form of image analysis technology or machine learning processing functionality configured to automatically classify the fibroids 742, 842 segmented from the ultrasound volume image and / or the 2D ultrasound image slices 610, 612, 614, 710, 712, 714, 810, 812, 814 extracted from the 3D volume image based on the spatial location of each of the segmented fibroids 740, 840 relative to the segmented uterus 622, 722, 822 and the segmented endometrium 632, 732, 832. The fibroid classification processor 170 may present the classification of the fibroids 740, 840 at the display system 134 and / or may store the classification of the fibroids 740, 840 at the archive 138 and / or any suitable data storage medium.

[0068] At step 914, the signal processor 132 of the ultrasound system 100 and / or the medical workstation 300 may cause the display system 134 to present at least one rendering 610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816 of the segmented uterus 622, 624, 722, 724, 822, 824, the endometrium 632, 634, 732, 734, 832, 834, and one or more fibroids 742, 744, 842, 844. For example, the rendering processor 180 of the signal processor 132 may receive an ultrasound volume having a segmented uterus 622, 722, 822, endometrium 632, 732, 832 and / or fibroids 742, 842 from the uterus segmentation processor 160, the endometrium segmentation processor 150 and / or the fibroid segmentation processor 140, or may retrieve an ultrasound volume having a segmented uterus 622, 722, 822, endometrium 632, 732, 832 and / or fibroids 742, 842 from the archive 138 and / or any suitable data storage medium. The rendering processor 180 may be configured to generate volume renderings 616, 716, 816, cross-sectional images, A-planes (i.e., planes parallel to the acquisition plane) 610, 710, 810, B-planes (i.e., planes perpendicular to the A-plane but still parallel to the ultrasound beam) 612, 712, 812, C-planes (i.e., commonly referred to as coronal planes, or two-dimensional slices at different depths from the transducer face and parallel to the transducer face and perpendicular to the ultrasound beam) 614, 714, 814, curved slices (e.g., 2D image slices extracted from a 3D volume along a curved anatomical structure such as the endometrium of a uterus), and / or any suitable ultrasound image. The rendering processor 180 may be configured to cause the display system 134 to present the generated images 610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816 and / or store the generated images 610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816 at the archive 138 and / or any suitable data storage medium.

[0069] At step 916, the signal processor 132 of the ultrasound system 100 and / or the medical workstation 300 may automatically perform one or more measurements of the segmented uterus 622, 722, 822, the endometrium 632, 732, 832, and / or one or more fibroids 742, 842. For example, the measurement processor 190 of the signal processor 132 may be configured to perform measurements on the segmented uterus 622, 722, 822, the endometrium 632, 732, 832, and the fibroids 742, 842. For example, the measurement processor 190 may be configured to perform volume measurements, estimated diameter measurements, length measurements, width measurements, and / or any suitable measurements on the segmented anatomical structures 622, 632, 722, 732, 742, 822, 832, 842. The measurement processor 190 may be configured to cause the display system 134 to present the measurement results. The measurement processor 190 may be configured to store the measurement results at the archive 138 and / or any suitable data storage medium.

[0070] At step 918, the signal processor 132 of the ultrasound system 100 and / or the medical workstation 300 may generate and store a report including the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814, volume renderings 616, 716, 816, fibroid classifications, and measurements. For example, the signal processor 132 may be configured to generate a report including the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814, volume renderings 616, 716, 816, fibroid classifications, measurements, and the like. The ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814 and volume renderings 616, 716, 816 included in the report provide the precise location of the fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830, which can be used for treatment planning, treatment monitoring, and clinical follow-up. The generated report including the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814, volume renderings 616, 716, 816, fibroid classifications and / or measurements allows for longitudinal analysis with reference to subsequently acquired ultrasound image data, volume renderings, fibroid classifications and measurements. For example, the signal processor 132 may be configured to present at the display system 134 a comparison showing relative changes in the fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830. The generated reports and longitudinal analyses may be presented at the display system 134 and / or stored at the archive 138 and / or any suitable data storage medium.

[0071] Aspects of the present disclosure provide methods 900 and systems 100, 300 for enhancing visualization and documentation of the number, size, and location of fibroids 740, 840 relative to the uterus 620, 720, 820 and endometrium 630, 730, 830 during ultrasound imaging. According to various embodiments, the method 900 may include receiving 906, by at least one processor 132, an ultrasound volume of ultrasound image data including a region of interest, the region of interest including the uterus 620, 720, 820. The method 900 may include automatically segmenting 908, by at least one processor 132, 140, 150, the uterus 620, 720, 820 and endometrium 630, 730, 830 in the ultrasound volume. The method 900 may include segmenting 910 one or more fibroids 740, 840 in the ultrasound image data. The method 900 may include generating 912 a classification of each of the one or more fibroids 740, 840 based on a location of each of the one or more fibroids 740, 840 relative to the endometrium 630, 730, 830 and the uterus 620, 720, 820. The method 900 may include causing 914, by at least one processor 132, 180, a display system 134 to present at least one image 610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816 identifying the segmented uterus 622, 624, 722, 724, 822, 824, the endometrium 632, 634, 732, 734, 832, 834, and the one or more fibroids 742, 744, 842, 844.

[0072] In an exemplary embodiment, the method 900 may include acquiring 904 a two-dimensional (2D) ultrasound image of a mid-sagittal plane 410, 510 of the uterus 420, 520. The step 900 may include presenting the 2D ultrasound image 410, 510 at the display system 134. Acquiring an ultrasound volume based on alignment with the mid-sagittal plane 410, 510. The method 900 may include receiving 904 a uterine trace 536 of the endometrium 530 on the 2D ultrasound image of the mid-sagittal plane 510 of the uterus 520. In a representative embodiment, segmenting 910 of one or more fibroids 740, 840 in the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814 is performed semi-automatically by first presenting ultrasound image slices 610, 710, 810 of the ultrasound volume separately at the display system 134. The ultrasound image slices 610, 710, 810 are parallel and extend from a first end of the ultrasound volume to a second end of the ultrasound volume. Secondly, the at least one processor 132, 160 receives a seed point for each of the one or more fibroids 740, 840 in the ultrasound image slices 610, 710, 810. Thirdly, the at least one processor 132, 160 segments each of the one or more fibroids 740, 840 based on the corresponding seed point. In various embodiments, the segmentation 910 of the one or more fibroids 740, 840 in the ultrasound image data is automatically performed by first receiving the color Doppler ultrasound image data by the at least one processor 132, 160. Secondly, the at least one processor 132, 160 segments each of the one or more fibroids 740, 840 based on the color Doppler ultrasound image data. In certain embodiments, the segmentation 910 of the one or more fibroids 740, 840 in the ultrasound image data is manually performed by receiving a manual trace of the contour of each of the one or more fibroids 740, 840 by the at least one processor 132, 160. In an exemplary embodiment, generating 912 a classification for each of the one or more fibroids 740, 840 includes automatically classifying, by the at least one processor 132, 170, each of the one or more fibroids 740, 840 based on a location of each of the one or more fibroids 740, 840 relative to the endometrium 630, 730, 830 and the uterus 620, 720, 820. In a representative embodiment, generating 912 a classification for each of the one or more fibroids 740, 840 includes presenting a prompt at the display system 134 for each of the one or more fibroids 740, 840, and receiving a user input selecting a classification that corresponds to the location relative to the endometrium 630, 730, 830 and the uterus 620, 720, 820.In various embodiments, the method 900 includes generating 916, by at least one processor 132, 190, measurement data including one or both of a volume measurement and an estimated diameter measurement of each of the one or more fibroids 740, 840, the uterus 620, 720, 820, and / or the endometrium 630, 730, 830. In certain embodiments, the method 900 includes generating 918, by at least one processor 132, a report including at least one image 610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816, a classification of each of the one or more fibroids, and the measurement data. In an exemplary embodiment, the method 900 includes causing a display system 134, by at least one processor, to present a comparison showing relative changes of the one or more fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830 over time.

[0073] Various embodiments provide a system 100 for enhancing visualization and recording of the number, size, and location of fibroids 740, 840 relative to the uterus 620, 720, 820 and endometrium 630, 730, 830 in ultrasound imaging. The system 100 may include an ultrasound probe 104, at least one processor 132, 140, 150, 160, 170, 180, 190, and a display system 134. The ultrasound probe 104 may be operable to acquire a two-dimensional (2D) ultrasound image of a mid-sagittal plane 410, 510 of the uterus 420, 520. The ultrasound probe 104 may be operable to acquire an ultrasound volume including ultrasound image data of a region of interest, the region of interest including the uterus 620, 720, 820. The ultrasound volume is acquired based on alignment with the mid-sagittal plane 410, 510. At least one processor 132, 140, 150 is configured to automatically segment the uterus 620, 720, 820 and the endometrium 630, 730, 830 in the ultrasound volume. At least one processor 132, 160 is configured to segment the one or more fibroids 740, 840 in the ultrasound image data. At least one processor 132, 170 is configured to generate a classification of each of the one or more fibroids 740, 840 based on the location of each of the one or more fibroids 740, 840 relative to the endometrium 630, 730, 830 and the uterus 620, 720, 820. The display system 134 is configured to present at least one image 610 , 612 , 614 , 616 , 710 , 712 , 714 , 716 , 810 , 812 , 814 , 816 identifying the segmented uterus 622 , 624 , 722 , 724 , 822 , 824 , the endometrium 632 , 634 , 732 , 734 , 832 , 834 , and one or more fibroids 742 , 744 , 842 , 844 .

[0074] In a representative embodiment, at least one processor 132, 160 is configured to semi-automatically segment one or more fibroids 740, 840 in ultrasound image data. At least one processor 132, 180 is configured to cause the display system 134 to individually present ultrasound image slices 610, 710, 810 of the ultrasound volume. The ultrasound image slices 610, 710, 810 are parallel and extend from a first end of the ultrasound volume to a second end of the ultrasound volume. At least one processor 132, 160 is configured to receive a seed point for each of the one or more fibroids 740, 840 in the ultrasound image slices 610, 710, 810. At least one processor 132, 160 is configured to segment each of the one or more fibroids 740, 840 based on the corresponding seed point. In various embodiments, at least one processor 132, 160 is configured to automatically segment one or more fibroids 740, 840 in ultrasound image data. The at least one processor 132, 160 is configured to receive color Doppler ultrasound image data. At least one processor 132, 160 is configured to segment each of the one or more fibroids 740, 840 based on the color Doppler ultrasound image data. In certain embodiments, at least one processor 132, 160 is configured to manually segment the one or more fibroids 740, 840 in the ultrasound image data. At least one processor 132, 160 is configured to receive a manual trace of the contour of each of the one or more fibroids 740, 840. In an exemplary embodiment, at least one processor 132, 170 is configured to automatically generate a classification of each of the one or more fibroids 740, 840 based on the location of each of the one or more fibroids 740, 840 relative to the endometrium 630, 730, 830 and the uterus 620, 720, 820. In a representative embodiment, the at least one processor 132, 170 is configured to receive a user input selecting a classification for each of the one or more fibroids 740, 840, the classification corresponding to a location relative to the endometrium 630, 730, 830 and the uterus 620, 720, 820, in response to the at least one processor 132, 170 causing the display system 134 to present a prompt selecting a classification for each of the one or more fibroids 740, 840. In various embodiments, the at least one processor 132, 190 is configured to generate measurement data including one or both of a volume measurement and an estimated diameter measurement for each of the one or more fibroids 740, 840, the uterus 620, 720, 820, and / or the endometrium 630, 730, 830.In certain embodiments, the at least one processor 132 is configured to generate a report that includes the at least one image 610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816, the classification of each of the one or more fibroids 740, 840, and the measurement data. In an exemplary embodiment, the at least one processor 132 is configured to cause the display system 134 to present a comparison showing relative changes in the one or more fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830 over time.

[0075] Certain embodiments provide a system 300 for enhancing visualization and recording of the number, size, and location of fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830 in ultrasound imaging. The system 300 may include at least one processor 132, 140, 150, 160, 170, 180, 190 and a display system 134. At least one processor 132, 140, 150, 160, 170, 180, 190 may be configured to receive an ultrasound volume of ultrasound image data including a region of interest, the region of interest including the uterus 620, 720, 820. At least one processor 132, 140, 150 may be configured to automatically segment the uterus 620, 720, 820 and the endometrium 630, 730, 830 in the ultrasound volume. At least one processor 132, 160 may be configured to segment one or more fibroids 740, 840 in the ultrasound image data. The at least one processor 132, 170 may be configured to generate a classification of each of the one or more fibroids 740, 840 based on a location of each of the one or more fibroids 740, 840 relative to the endometrium 630, 730, 830 and the uterus 620, 720, 820. The display system 134 may be configured to present at least one image 610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816 identifying the segmented uterus 622, 624, 722, 724, 822, 824, the endometrium 632, 634, 732, 734, 832, 834, and the one or more fibroids 742, 744, 842, 844.

[0076] In various embodiments, at least one processor 132, 160 is configured to semi-automatically segment one or more fibroids 740, 840 in the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814. At least one processor 132, 180 is configured to cause the display system 134 to individually present ultrasound image slices 610, 710, 810 of the ultrasound volume. The ultrasound image slices 610, 710, 810 are parallel and extend from a first end of the ultrasound volume to a second end of the ultrasound volume. At least one processor 132, 160 is configured to receive a seed point for each of the one or more fibroids 740, 840 in the ultrasound image slices 610, 710, 810. At least one processor 132, 160 is configured to segment each of the one or more fibroids 740, 840 based on the corresponding seed point. In certain embodiments, at least one processor 132, 160 is configured to automatically segment one or more fibroids 740, 840 in the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814. The at least one processor 132, 160 is configured to receive color Doppler ultrasound image data. The at least one processor 132, 160 is configured to segment each of the one or more fibroids 740, 840 based on the color Doppler ultrasound image data. In an exemplary embodiment, the at least one processor 132, 160 is configured to manually segment one or more fibroids 740, 840 in the ultrasound image data 610, 612, 614, 710, 712, 714, 810, 812, 814. The at least one processor 132, 160 is configured to receive a manual trace of the contour of each of the one or more fibroids 740, 840. In a representative embodiment, the at least one processor 132, 170 is configured to automatically generate a classification for each of the one or more fibroids 740, 840 based on the location of each of the one or more fibroids 740, 840 relative to the endometrium 630, 730, 830 and the uterus 620, 720, 820. In various embodiments, the at least one processor 132, 170 is configured to receive user input selecting a classification for each of the one or more fibroids 740, 840 that corresponds to the location relative to the endometrium 630, 730, 830 and the uterus 620, 720, 820 in response to the at least one processor 132, 170 causing the display system 134 to present a prompt for selecting a classification for each of the one or more fibroids 740, 840.In certain embodiments, at least one processor 132, 190 is configured to generate measurement data including one or both of volume measurements and estimated diameter measurements of each of the one or more fibroids 740, 840, the uterus 620, 720, 820, and / or the endometrium 630, 730, 830. At least one processor 132 is configured to generate a report including at least one image 610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816, a classification of each of the one or more fibroids 740, 840, and the measurement data. In an exemplary embodiment, at least one processor 132 is configured to cause the display system 134 to present a comparison showing relative changes of the one or more fibroids 740, 840 relative to the uterus 620, 720, 820 and the endometrium 630, 730, 830 over time.

[0077] As used herein, the term "circuit" refers to physical electronic components (e.g., hardware) and any software and / or firmware ("code") that can configure hardware, is executed by hardware, and / or is otherwise associated with hardware. For example, as used herein, when executing one or more first codes, a specific processor and memory may include a first "circuit", and when executing one or more second codes, a specific processor and memory may include a second "circuit". As used herein, "and / or" represents any one or more of the items in the list connected by "and / or". For example, "x and / or y" represents any element in the three-element set {(x), (y), (x, y)}. As another example, "x, y and / or z" represents any element in the seven-element set {(x), (y), (z), (x, y), (x, z), (y, z), (x, y, z)}. As used herein, the term "exemplary" means used as a non-limiting example, instance, or illustration. As used herein, the terms "for example" and "such as" lead to a list of one or more non-limiting examples, instances, or illustrations. As used herein, a circuit is “operable to” and / or “configured to” perform a function whenever the circuit includes the necessary hardware and code (if necessary) to perform the function, regardless of whether execution of the function is disabled or not enabled by some user-configurable setting.

[0078] Other embodiments may provide a computer-readable device and / or a non-transitory computer-readable medium, and / or a machine-readable device and / or a non-transitory machine-readable medium having stored thereon machine code and / or a computer program having at least one code segment executable by a machine and / or a computer, so that the machine and / or the computer performs the steps as described herein for enhancing the visualization and recording of the number, size, and position of fibroids relative to the uterus and endometrium during ultrasound imaging.

[0079] Therefore, the present disclosure may be implemented in hardware, software, or a combination of hardware and software. The present disclosure may be implemented in a centralized manner in at least one computer system, or in a distributed manner, where different elements are distributed across several interconnected computer systems. Any type of computer system or other device suitable for executing the methods described herein is suitable.

[0080] The various embodiments may also be embedded in a computer program product, which comprises all the features enabling the implementation of the methods described herein and which, when loaded into a computer system, is capable of carrying out these methods. A computer program herein refers to any expression of a set of instructions in any language, code or notation, which is intended to cause a system with information processing capabilities to perform specific functions directly or after either or both of the following: a) conversion into another language, code or notation; b) reproduction in a different material form.

[0081] Although the present disclosure has been described with reference to certain embodiments, it will be appreciated by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the scope of the present disclosure. In addition, many modifications may be made to adapt specific circumstances or materials to the teachings of the present disclosure without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the specific embodiments disclosed, but the present disclosure will include all embodiments falling within the scope of the appended claims.

Claims

1. A method (900), comprising: receiving (906), by at least one processor (132), an ultrasound volume including ultrasound image data of a region of interest, the region of interest including a uterus (620, 720, 820); automatically segmenting (908) the uterus (620, 720, 820) and the endometrium (630, 730, 830) in the ultrasound volume by the at least one processor (132, 140, 150); Segmenting (910) one or more fibroids (740, 840) in the ultrasound image data; generating a classification (912) of each of the one or more fibroids (740, 840) based on a location of each of the one or more fibroids (740, 840) relative to the endometrium (630, 730, 830) and the uterus (620, 720, 820); as well as The at least one processor (132, 180) causes (914) a display system (134) to present at least one image (610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816) identifying the segmented uterus (622, 624, 722, 724, 822, 824), the endometrium (632, 634, 732, 734, 832, 834), and one or more fibroids (742, 744, 842, 844).

2. The method (900) according to claim 1, comprising: Acquiring (904) a two-dimensional (2D) ultrasound image of the midsagittal plane (410, 510) of the uterus (420, 520); presenting (904) the 2D ultrasound image (410, 510) at the display system (134), wherein the ultrasound volume is acquired based on alignment with the midsagittal plane (410, 510); as well as A uterine trace (536) of the endometrium (530) is received (904) on the 2D ultrasound image of the midsagittal plane (510) of the uterus (520).

3. The method (900) of claim 1, wherein the segmentation (910) of the one or more fibroids (740, 840) in the ultrasound image data (610, 612, 614, 710, 712, 714, 810, 812, 814) is performed semi-automatically by: separately presenting ultrasound image slices (610, 710, 810) of the ultrasound volume at the display system (134), wherein the ultrasound image slices (610, 710, 810) are parallel and extend from a first end of the ultrasound volume to a second end of the ultrasound volume; receiving, by the at least one processor (132, 160), a seed point for each of the one or more fibroids (740, 840) in the ultrasound image slice (610, 710, 810); and Each of the one or more fibroids (740, 840) is segmented by the at least one processor (132, 160) based on corresponding seed points.

4. The method (900) of claim 1, wherein segmenting (910) the one or more fibroids (740, 840) in the ultrasound image data is performed by one of: Automatically executed by: Receiving, by the at least one processor (132, 160), color Doppler ultrasound image data; and performing segmentation, by the at least one processor (132, 160), on each of the one or more fibroids (740, 840) based on the color Doppler ultrasound image data; or Manually via: A manual trace of the contour of each of the one or more fibroids (740, 840) is received by the at least one processor (132, 160).

5. The method (900) of claim 1, wherein generating (912) a classification for each of the one or more fibroids (740, 840) comprises one of: automatically classifying, by the at least one processor (132, 170), each of the one or more fibroids (740, 840) based on a location of each of the one or more fibroids (740, 840) relative to the endometrium (630, 730, 830) and the uterus (620, 720, 820); or For each of the one or more fibroids (740, 840), a prompt is presented at the display system (134) and a user input is received selecting the classification corresponding to a location relative to the endometrium (630, 730, 830) and the uterus (620, 720, 820).

6. The method (900) of claim 1, comprising generating (916), by the at least one processor (132, 190), measurement data comprising one or both of a volume measurement and an estimated diameter measurement of: Each of the one or more fibroids (740, 840), The uterus (620, 720, 820), and / or The endometrium (630, 730, 830).

7. The method (900) of claim 6, comprising generating (918) by the at least one processor (132) a report comprising the at least one image (610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816), a classification of each of the one or more fibroids (740, 840), and the measurement data.

8. The method (900) according to claim 1 includes causing the display system (134) to present a comparison result showing the relative changes of the one or more fibroids (740, 840) relative to the uterus (620, 720, 820) and the endometrium (630, 730, 830) over time by the at least one processor (132).

9. A system (100, 300), comprising: An ultrasound probe (104) operable to: Acquiring a two-dimensional (2D) ultrasound image of the midsagittal plane (410, 510) of the uterus (420, 520); acquiring an ultrasound volume including ultrasound image data of a region of interest, the region of interest including the uterus (620, 720, 820), wherein the ultrasound volume is acquired based on alignment with the midsagittal plane (410, 510); At least one processor (132, 140, 150, 160, 170, 180, 190), the at least one processor being configured to: automatically segmenting the uterus (620, 720, 820) and endometrium (630, 730, 830) in the ultrasound volume; Segmenting one or more fibroids in the ultrasound image data (740, 840); and generating a classification of each of the one or more fibroids (740, 840) based on a location of each of the one or more fibroids (740, 840) relative to the endometrium (630, 730, 830) and the uterus (620, 720, 820); and A display system (134) is configured to present at least one image (610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816) identifying the segmented uterus (622, 624, 722, 724, 822, 824), the endometrium (632, 634, 732, 734, 832, 834), and one or more fibroids (742, 744, 842, 844).

10. The system (100, 300) of claim 9, wherein the at least one processor (132, 160) is configured to semi-automatically segment the one or more fibroids (740, 840) in the ultrasound image data, wherein the at least one processor (132, 160, 180) is configured to: causing the display system (134) to individually present ultrasound image slices (610, 710, 810) of the ultrasound volume, wherein the ultrasound image slices (610, 710, 810) are parallel and extend from a first end of the ultrasound volume to a second end of the ultrasound volume; receiving a seed point for each of the one or more fibroids (740, 840) in the ultrasound image slice (610, 710, 810); and Each of the one or more fibroids (740, 840) is segmented based on corresponding seed points.

11. The system (100, 300) of claim 9, wherein the at least one processor (132, 160) is configured to segment the one or more fibroids (740, 840) in the ultrasound image data by one of: automatically segmenting, wherein the at least one processor (132, 160) is configured to: receiving color Doppler ultrasound image data; and Segmenting each of the one or more fibroids (740, 840) based on the color Doppler ultrasound image data; or manually segmenting, wherein the at least one processor (132, 160) is configured to: A manual trace of the contour of each of the one or more fibroids (740, 840) is received.

12. The system (100, 300) of claim 9, wherein the at least one processor (132, 170) is configured as one of: automatically generating a classification of each of the one or more fibroids (740, 840) based on a location of each of the one or more fibroids (740, 840) relative to the endometrium (630, 730, 830) and the uterus (620, 720, 820); or In response to the at least one processor (132, 170) causing the display system (134) to present a prompt selecting the classification for each of the one or more fibroids (740, 840), user input selecting the classification is received for each of the one or more fibroids (740, 840), the classification corresponding to a location relative to the endometrium (630, 730, 830) and the uterus (620, 720, 820).

13. The system (100, 300) of claim 9, wherein the at least one processor (132, 190) is configured to generate measurement data comprising one or both of a volume measurement and an estimated diameter measurement of: Each of the one or more fibroids (740, 840), The uterus (620, 720, 820), and / or The endometrium (630, 730, 830).

14. The system (100, 300) of claim 13, wherein the at least one processor (132) is configured to generate a report comprising the at least one image (610, 612, 614, 616, 710, 712, 714, 716, 810, 812, 814, 816), a classification of each of the one or more fibroids (740, 840).

15. The system (100, 300) of claim 9, wherein the at least one processor (132) is configured to cause the display system (134) to present a comparison showing relative changes of the one or more fibroids (740, 840) relative to the uterus (620, 720, 820) and the endometrium (630, 730, 830) over time.

Images