Ultrasonic imaging equipment and pelvic floor section image generation method

Abstract

According to the ultrasonic imaging equipment and the pelvic floor section image generation method, three-dimensional volume data of a pelvic floor are obtained; identifying at least one key anatomical structure associated with the location of the target tissue from the three-dimensional volumetric data; or generating at least one two-dimensional section according to the prior position of the key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, and identifying at least one key anatomical structure associated with the position of the target tissue from the two-dimensional section; the spatial position of the key anatomical structure in the three-dimensional volume data is obtained; and imaging the section of the target tissue on the basis of the position of the key anatomical structure in the three-dimensional volume data to obtain a section image of the target tissue. Therefore, an ultrasonic doctor can obtain the section image of the pelvic floor target tissue only by completing the three-dimensional volume data acquisition of the pelvic floor, the operation is simple and convenient, and the working efficiency of the ultrasonic doctor is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical devices, and in particular to an ultrasonic imaging device and a method for generating a cross-sectional image of a pelvic floor. Background Art

[0002] In modern medical imaging examinations, ultrasound technology has become the most widely used, most frequently used, and fastest-growing means of examination due to its advantages such as high reliability, fast and convenient, real-time imaging, and repeatable examinations. The development of some new ultrasound technologies, especially those based on artificial intelligence-assisted technologies, has further promoted the application of ultrasound technology in clinical diagnosis and treatment. However, the corresponding medical conditions need to be further improved, such as the imbalance in the distribution of medical resources between regions and the great room for improvement in the technical capabilities of grassroots doctors. The intelligent development of ultrasound equipment can help doctors improve the efficiency of examinations, balance the gaps between hospitals in different regions, and provide patients with more accurate diagnoses and personalized treatment plans.

[0003] Pelvic floor dysfunction, such as stress urinary incontinence and pelvic organ prolapse, is one of the common chronic diseases that affect women's physical and mental health, and seriously affects women's work and social activities. Pelvic floor ultrasound examination plays an important role in the diagnosis of pelvic floor diseases. With the help of current ultrasound technology, ultrasound clinicians can dynamically observe the changes in pelvic organs and levator ani hiatus during Valsalva maneuvers and anal contraction movements. Under conventional two-dimensional conditions, the anatomical structure and prolapse of the pelvic floor organs can be displayed dynamically and in real time. At the same time, by measuring ultrasound, clinicians can quantitatively evaluate their prolapse conditions; under three-dimensional and four-dimensional conditions, the coronal plane of the smallest hiatus section of the levator ani muscle can be displayed, and ultrasound imaging of the levator ani hiatus of the pelvic floor with multiple parallel sections can observe whether the levator ani muscle is damaged layer by layer under the anal contraction state. Rotating the probe 90° and tilting it backward and downward can fully display the cross-section of the anal canal and observe whether the levator ani muscle is damaged and whether there are lesions around it. At the same time, the measurement of the levator ani hiatus area and puborectalis muscle thickness under three-dimensional and four-dimensional conditions can help doctors quantitatively evaluate the degree of damage to the levator ani muscle of the pelvic floor.

[0004] However, when doctors perform pelvic floor ultrasound diagnosis, the acquisition of standard sections and the imaging of multiple parallel sections need to be completed manually by the doctor. This process requires a high level of experience and skills from the doctor, and is time-consuming and labor-intensive. At the same time, the measurement process of related measurement items is extremely complicated. At the same time, it is difficult for patients to complete and maintain Valsalva and anal contraction movements during the examination, requiring doctors to complete multiple parallel section imaging more accurately and quickly. After manually obtaining the section of the minimum hiatus of the levator ani muscle and the parallel sections corresponding to the hiatus of the levator ani muscle and the cross section of the anal canal, ultrasound clinicians also have to manually measure various data, which greatly consumes the doctor's examination time and efficiency. Summary of the invention

[0005] The present invention mainly provides an ultrasonic imaging device and a method for generating a section image of a pelvic floor, so as to improve the working efficiency of ultrasonic doctors.

[0006] In one embodiment, a method for generating a cross-sectional image of a pelvic floor is provided, characterized by comprising:

[0007] Obtain three-dimensional volume data of the pelvic floor;

[0008] Identifying the pubic symphysis and the anorectal angle from the three-dimensional volume data, and obtaining the spatial positions of the pubic symphysis and the anorectal angle in the three-dimensional volume data;

[0009] Determine the position of the minimum hiatus section of the levator ani muscle in the three-dimensional volume data based on the spatial positions of the pubic symphysis and the anorectal angle in the three-dimensional volume data;

[0010] Based on the position of the levator ani muscle minimum hiatus section, an image of the levator ani muscle minimum hiatus section is obtained according to the three-dimensional volume data.

[0011] In one embodiment, identifying the pubic symphysis and the anorectal angle from the three-dimensional volume data, and obtaining the spatial positions of the pubic symphysis and the anorectal angle in the three-dimensional volume data includes:

[0012] Identifying the lower edge of the pubic symphysis, two pubic branches, and the anorectal angle from the three-dimensional volume data, and obtaining the spatial positions of the lower edge of the pubic symphysis, the two pubic branches, and the anorectal angle in the three-dimensional volume data;

[0013] Determining the position of the minimum hiatus section of the levator ani muscle in the three-dimensional volume data based on the spatial positions of the pubic symphysis and the anorectal angle in the three-dimensional volume data includes:

[0014] According to the spatial positions of the lower edge of the pubic symphysis, the two pubic branches, and the anorectal angle in the three-dimensional volume data, a section plane passing through the lower edge of the pubic symphysis and at least a portion of the anorectal angle and parallel to a line connecting two points on the two pubic branches that are symmetrical relative to the lower edge of the pubic symphysis is determined, and the position of the section plane is taken as the position of the minimum hiatus section plane of the levator ani muscle.

[0015] In one embodiment, identifying the pubic symphysis and the anorectal angle from the three-dimensional volume data, and obtaining the spatial positions of the pubic symphysis and the anorectal angle in the three-dimensional volume data includes:

[0016] Identifying the lower edge of the pubic symphysis and the anorectal angle from the three-dimensional volume data, and obtaining the spatial positions of the lower edge of the pubic symphysis and the anorectal angle in the three-dimensional volume data;

[0017] Determining the position of the minimum hiatus section of the levator ani muscle in the three-dimensional volume data based on the spatial positions of the pubic symphysis and the anorectal angle in the three-dimensional volume data includes:

[0018] Determine, according to the spatial positions of the lower edge of the pubic symphysis and the anorectal angle in the three-dimensional volume data, a plurality of sections passing through the lower edge of the pubic symphysis and a predetermined point on the anorectal angle, and obtain section images of the plurality of sections according to the three-dimensional volume data;

[0019] Determine the symmetry of the image area located on both sides of the line connecting the lower edge of the pubic symphysis and the predetermined point in each of the multiple section images, and determine the position of the section image whose symmetry satisfies the predetermined condition as the position of the levator ani muscle minimum hiatus section.

[0020] In one embodiment, the method further includes: measuring the area of ​​the minimum hiatus of the levator ani muscle based on the obtained cross-sectional image of the minimum hiatus of the levator ani muscle; and / or, detecting the levator ani muscle and urethral opening in the cross-sectional image of the minimum hiatus of the levator ani muscle, and measuring the distance from the urethral opening to the leftmost levator ani muscle and / or the distance from the urethral opening to the rightmost levator ani muscle based on the detected levator ani muscle and urethral opening; and / or, extracting the contour of the levator ani muscle or the minimum hiatus of the levator ani muscle in the cross-sectional image of the minimum hiatus of the levator ani muscle, and calculating the distance between the upper and lower diameters of the levator ani muscle and / or the distance between the left and right diameters of the levator ani muscle based on the contour.

[0021] In one embodiment, identifying the pubic symphysis from the three-dimensional volume data includes: calculating at least one characteristic index of the three-dimensional volume data, inputting the characteristic index into a pre-established model function of the correspondence between the characteristic index of the three-dimensional volume data and the pubic symphysis, to obtain the corresponding pubic symphysis; or, performing target detection or image segmentation on the three-dimensional volume data, performing morphological feature detection on each region obtained after the detection or segmentation to obtain multiple candidate regions, judging for each candidate region whether the candidate region is the pubic symphysis based on shape features and / or grayscale features, and determining the candidate region with the highest probability as the pubic symphysis.

[0022] In one embodiment, identifying the anorectal angle from the three-dimensional volume data includes: calculating at least one characteristic index of the three-dimensional volume data, inputting the characteristic index into a pre-established model function of the correspondence between the characteristic index of the three-dimensional volume data and the anorectal angle, to obtain the corresponding anorectal angle; or, performing target detection or image segmentation on the three-dimensional volume data, performing morphological feature detection on each region obtained after the detection or segmentation to obtain multiple candidate regions, judging the probability of each candidate region being the anorectal angle according to shape features and / or grayscale features, and determining the candidate region with the highest probability as the anorectal angle.

[0023] In one embodiment, based on the position of the minimum hiatus section of the levator ani muscle, obtaining the image of the minimum hiatus section of the levator ani muscle according to the three-dimensional volume data includes: based on the position of the minimum hiatus section of the levator ani muscle, obtaining image data containing the minimum hiatus section of the levator ani muscle from the three-dimensional volume data, and performing volume rendering on the image data containing the minimum hiatus section to obtain a volume rendering image of the minimum hiatus section; and / or, based on the position of the minimum hiatus section of the levator ani muscle, obtaining a two-dimensional image of the minimum hiatus section of the levator ani muscle from the three-dimensional volume data; and / or, according to a pre-set imaging thickness, performing thick-layer imaging on the minimum hiatus section of the levator ani muscle to obtain a thick-layer image of the minimum hiatus section of the levator ani muscle.

[0024] In one embodiment, a method for generating a cross-sectional image of a pelvic floor is provided, comprising:

[0025] Obtain three-dimensional volume data of the pelvic floor;

[0026] Identifying at least one key anatomical structure associated with the position of the target tissue from the three-dimensional volume data, and obtaining the spatial position of the key anatomical structure in the three-dimensional volume data; or, generating at least one two-dimensional section according to the a priori position of the key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, identifying at least one key anatomical structure associated with the position of the target tissue from the two-dimensional section, and obtaining the spatial position of the key anatomical structure in the three-dimensional volume data;

[0027] Based on the position of the key anatomical structure in the three-dimensional volume data, the section of the target tissue is imaged to obtain a section image of the target tissue.

[0028] In one embodiment, the target tissue is the levator ani muscle, and the method further comprises:

[0029] Detecting the levator ani muscle based on the cross-sectional image of the levator ani muscle, and measuring the minimum hiatus area of ​​the detected levator ani muscle;

[0030] Alternatively, the levator ani muscle and the urethral opening are detected based on the cross-sectional image of the levator ani muscle, and the distance from the urethral opening to the leftmost levator ani muscle and the distance from the urethral opening to the rightmost levator ani muscle are measured.

[0031] In one embodiment, the target tissue is an anal canal, and the cross-sectional image of the target tissue is a cross-section of the anal canal; the method further comprises:

[0032] The puborectalis muscle is detected based on the cross-section of the anal canal, and the thickness of the detected puborectalis muscle is measured.

[0033] In one embodiment, identifying at least one key anatomical structure associated with the location of the target tissue from the three-dimensional volume data comprises:

[0034] At least one characteristic index of the three-dimensional volume data is calculated, and the characteristic index is input into a pre-established model function of the correspondence between the characteristic index of the three-dimensional volume data and the key anatomical structure to obtain the corresponding key anatomical structure.

[0035] In one embodiment, identifying at least one key anatomical structure associated with the location of the target tissue from the three-dimensional volume data comprises:

[0036] The three-dimensional volume data is segmented, and morphological feature detection is performed on each region obtained after segmentation to obtain multiple candidate regions. For each candidate region, the probability of the candidate region being a key anatomical structure is determined based on shape features and / or grayscale features, and the candidate region with the highest probability is determined as the key anatomical structure.

[0037] In one embodiment, generating at least one two-dimensional slice according to a priori positions of key anatomical structures associated with the position of the target tissue in the three-dimensional volume data, and identifying at least one key anatomical structure associated with the position of the target tissue from the two-dimensional slice comprises:

[0038] According to the priori position of the key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, a pair of most similar two-dimensional slices are detected on both sides of the priori position, and the key anatomical structure is identified from the central plane of the pair of two-dimensional slices.

[0039] In one embodiment, imaging the cross-section of the target tissue to obtain the cross-section image of the target tissue includes:

[0040] Performing volume rendering imaging on the section of the target tissue to obtain a volume rendering image of the section of the target tissue; and / or,

[0041] Performing grayscale imaging on the cross-section of the target tissue to obtain a grayscale image of the cross-section of the target tissue; and / or,

[0042] Determine a reference line according to a user's input instruction, cut and image the key anatomical structure along the reference line, and obtain a cross-sectional image of the target tissue; and / or,

[0043] Imaging the cross-section of the target tissue to obtain images of multiple parallel cross-sections of the target tissue; and / or,

[0044] According to the preset imaging thickness, thick-layer imaging is performed on the section of the target tissue to obtain a thick-layer image of the section of the target tissue.

[0045] In one embodiment, the key anatomical structure is a target tissue or a tissue capable of locating a target tissue.

[0046] In one embodiment, an ultrasonic imaging device is provided, comprising:

[0047] An ultrasonic probe, used for transmitting ultrasonic waves to an object to be imaged so as to scan the object to be imaged, and receiving ultrasonic echoes returned from the object to be imaged;

[0048] A transmitting / receiving circuit, used for controlling the ultrasonic probe to transmit ultrasonic waves to the object to be imaged and to receive echoes of the ultrasonic waves;

[0049] A processor, configured to perform 3D reconstruction according to the ultrasonic echo to obtain three-dimensional volume data of the object to be imaged; the object to be imaged includes a pelvic floor;

[0050] The processor is further configured to identify at least one key anatomical structure associated with the position of the target tissue from the three-dimensional volume data, and obtain the spatial position of the key anatomical structure in the three-dimensional volume data; or, based on the prior position of the key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, generate at least one two-dimensional section, identify at least one key anatomical structure associated with the position of the target tissue from the two-dimensional section, and obtain the spatial position of the key anatomical structure in the three-dimensional volume data; based on the position of the key anatomical structure in the three-dimensional volume data, image the section of the target tissue to obtain a section image of the target tissue;

[0051] A display is used to display the cross-sectional image of the target tissue.

[0052] In an ultrasonic imaging device in one embodiment, the target tissue is the levator ani muscle, and the processor is further configured to:

[0053] Detecting the levator ani muscle based on the cross-sectional image of the levator ani muscle, and measuring the minimum hiatus area of ​​the detected levator ani muscle;

[0054] Alternatively, the levator ani muscle and the urethral opening are detected based on the cross-sectional image of the levator ani muscle, and the distance from the urethral opening to the leftmost levator ani muscle and the distance from the urethral opening to the rightmost levator ani muscle are measured.

[0055] In an ultrasonic imaging device in one embodiment, the target tissue is an anal canal, and the cross-sectional image of the target tissue is a cross-section of the anal canal; the processor is further configured to:

[0056] The puborectalis muscle is detected based on the cross-section of the anal canal, and the thickness of the detected puborectalis muscle is measured.

[0057] In an ultrasound imaging device in one embodiment, the processor identifying at least one key anatomical structure associated with the location of the target tissue from the three-dimensional volume data comprises:

[0058] At least one characteristic index of the three-dimensional volume data is calculated, and the characteristic index is input into a pre-established model function of the correspondence between the characteristic index of the three-dimensional volume data and the key anatomical structure to obtain the corresponding key anatomical structure.

[0059] In an ultrasound imaging device in one embodiment, the processor identifying at least one key anatomical structure associated with the location of the target tissue from the three-dimensional volume data comprises:

[0060] The three-dimensional volume data is segmented, and morphological feature detection is performed on each region obtained after segmentation to obtain multiple candidate regions. For each candidate region, the probability of the candidate region being a key anatomical structure is determined based on shape features and / or grayscale features, and the candidate region with the highest probability is determined as the key anatomical structure.

[0061] In an ultrasound imaging device in an embodiment, the processor generates at least one two-dimensional slice according to a priori positions of key anatomical structures associated with the position of the target tissue in the three-dimensional volume data, and identifying at least one key anatomical structure associated with the position of the target tissue from the two-dimensional slice comprises:

[0062] According to the priori position of the key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, a pair of most similar two-dimensional slices are detected on both sides of the priori position, and the key anatomical structure is identified from the central plane of the pair of two-dimensional slices.

[0063] In an ultrasonic imaging device in one embodiment, the processor images a section of the target tissue, and obtaining the section image of the target tissue includes:

[0064] Performing volume rendering imaging on the section of the target tissue to obtain a volume rendering image of the section of the target tissue; and / or,

[0065] Performing grayscale imaging on the cross-section of the target tissue to obtain a grayscale image of the cross-section of the target tissue; and / or,

[0066] Determine a reference line according to a user's input instruction, cut and image the key anatomical structure along the reference line, and obtain a cross-sectional image of the target tissue; and / or,

[0067] Imaging the cross-section of the target tissue to obtain images of multiple parallel cross-sections of the target tissue; and / or,

[0068] According to the preset imaging thickness, thick-layer imaging is performed on the section of the target tissue to obtain a thick-layer image of the section of the target tissue.

[0069] In the ultrasound imaging device in one embodiment, the key anatomical structure is a target tissue or a tissue capable of locating the target tissue.

[0070] In one embodiment, an ultrasonic imaging device is provided, comprising:

[0071] Memory, used to store programs;

[0072] The processor is used to execute the program stored in the memory to implement the method as described above.

[0073] In one embodiment, a computer-readable storage medium is provided, including a program, wherein the program can be executed by a processor to implement the method described above.

[0074] According to the ultrasound imaging device and the method for generating a cross-sectional image of the pelvic floor of the above-mentioned embodiment, firstly obtain the three-dimensional volume data of the pelvic floor; identify at least one key anatomical structure associated with the position of the target tissue from the three-dimensional volume data, and obtain the spatial position of the key anatomical structure in the three-dimensional volume data; or, generate at least one two-dimensional cross section according to the prior position of the key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, identify at least one key anatomical structure associated with the position of the target tissue from the two-dimensional cross section, and obtain the spatial position of the key anatomical structure in the three-dimensional volume data; image the cross section of the target tissue based on the position of the key anatomical structure in the three-dimensional volume data, and obtain the cross-sectional image of the target tissue. It can be seen that the ultrasound doctor only needs to complete the three-dimensional volume data acquisition of the pelvic floor to obtain the cross-sectional image of the target tissue of the pelvic floor, which is simple and convenient to operate, and improves the work efficiency of the ultrasound doctor. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 is a structural block diagram of an ultrasonic imaging device in an embodiment;

[0076] Figure 2 is a flow chart of a method for generating a cross-sectional image of a pelvic floor in one embodiment;

[0077] Figure 3 This is an ultrasound image of the sagittal section of the basin;

[0078] Figure 4 This is the effect of volume rendering imaging of the smallest hiatus section of the levator ani muscle;

[0079] Figure 5 This is the effect of imaging any section of the smallest hiatus of the levator ani muscle;

[0080] Figure 6 This is the effect of imaging multiple parallel sections of the smallest hiatus section of the levator ani muscle;

[0081] Figure 7 It is a schematic diagram of a cross-sectional image of the smallest hiatus of the levator ani muscle in one embodiment. DETAILED DESCRIPTION

[0082] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present application better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present application are not shown or described in the specification, this is to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0083] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0084] The serial numbers of the components in this document, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. The "connection" and "coupling" mentioned in this application, unless otherwise specified, include direct and indirect connections (couplings).

[0085] The present invention obtains three-dimensional volume data of the pelvic floor; automatically detects and identifies key anatomical structures in the three-dimensional volume data of the pelvic floor; based on the key anatomical structures, realizes automatic imaging of the pelvic floor, and based on the automatic imaging results of the pelvic floor, performs measurements; and finally displays the imaging results and automatic measurement results on a display; thereby realizing automatic imaging and automatic measurement of the cross-sectional images of the pelvic floor, and improving the work efficiency of ultrasound doctors. The three-dimensional volume data can be three-dimensional volume data generated by acquisition through an ultrasound imaging device, or three-dimensional volume data generated by acquisition through a nuclear magnetic resonance device, and of course, can also be three-dimensional volume data generated by acquisition through electronic computer tomography (CT). Taking an ultrasound imaging device as an example, the ultrasound imaging device and its method for generating cross-sectional images of the pelvic floor are described in detail below.

[0086] like Figure 1 As shown, the ultrasonic imaging device provided by the present invention includes an ultrasonic probe 30, a transmitting / receiving circuit 40 (i.e., a transmitting circuit 410 and a receiving circuit 420), a beamforming module 50, an IQ demodulation module 60, a processor 20, a human-computer interaction device 70 and a memory 80.

[0087] The ultrasonic probe 30 includes a transducer (not shown in the figure) composed of a plurality of array elements arranged in an array, wherein the plurality of array elements are arranged in a row to form a linear array, or arranged in a two-dimensional matrix to form a surface array, or the plurality of array elements can also form a convex array. The array element is used to transmit an ultrasonic beam according to an excitation electrical signal, or to convert a received ultrasonic beam into an electrical signal. Therefore, each array element can be used to realize the mutual conversion between an electrical pulse signal and an ultrasonic beam, thereby realizing the transmission of ultrasonic waves to the object to be imaged (for example, the pelvic floor of the human body in this embodiment), and can also be used to receive the echo of the ultrasonic wave reflected back by the tissue. When performing ultrasonic detection, the transmitting circuit 410 and the receiving circuit 420 can be used to control which array elements are used to transmit ultrasonic beams and which array elements are used to receive ultrasonic beams, or control the array elements to transmit ultrasonic beams or receive the echo of ultrasonic beams in time slots. The array elements participating in ultrasonic emission can be excited by electrical signals at the same time, thereby transmitting ultrasonic waves at the same time; or the array elements participating in ultrasonic emission can also be excited by several electrical signals with a certain time interval, thereby continuously transmitting ultrasonic waves with a certain time interval.

[0088] The array element uses, for example, a piezoelectric crystal, and converts the electrical signal into an ultrasonic signal according to the transmission sequence transmitted by the transmitting circuit 410. Depending on the purpose, the ultrasonic signal may include one or more scanning pulses, one or more reference pulses, one or more push pulses and / or one or more Doppler pulses. According to the wave form, the ultrasonic signal includes a focused wave and a plane wave.

[0089] The user moves the ultrasonic probe 30 to select a suitable position and angle to transmit ultrasonic waves to the object to be imaged 10 and receive the echo of the ultrasonic waves returned by the object to be imaged 10, and outputs an ultrasonic echo signal. The ultrasonic echo signal is a channel analog electrical signal formed by the receiving array element as a channel, which carries amplitude information, frequency information and time information.

[0090] The transmitting circuit 410 is used to generate a transmitting sequence according to the control of the processor 20. The transmitting sequence is used to control some or all of the multiple array elements to transmit ultrasonic waves to biological tissues. The transmitting sequence parameters include the array element position, the number of array elements and the ultrasonic beam transmission parameters (such as amplitude, frequency, number of transmissions, transmission interval, transmission angle, waveform, focus position, etc.) used for transmission. In some cases, the transmitting circuit 410 is also used to phase delay the transmitted beam so that different transmitting array elements transmit ultrasonic waves at different times so that each transmitted ultrasonic beam can be focused on a predetermined area of ​​interest. Different working modes, such as B image mode, C image mode and D image mode (Doppler mode), may have different transmitting sequence parameters. After the echo signal is received by the receiving circuit 420 and processed by subsequent modules and corresponding algorithms, a B image reflecting the anatomical structure of the tissue, a C image reflecting the anatomical structure of the tissue and blood flow information, and a D image reflecting the Doppler spectrum image can be generated.

[0091] The receiving circuit 420 is used to receive the ultrasonic echo signal from the ultrasonic probe 30 and process the ultrasonic echo signal. The receiving circuit 420 may include one or more amplifiers, analog-to-digital converters (ADCs), etc. The amplifier is used to amplify the received echo signal after appropriate gain compensation, and the amplifier is used to sample the analog echo signal at a predetermined time interval to convert it into a digitized signal. The digitized echo signal still retains amplitude information, frequency information, and phase information. The data output by the receiving circuit 420 can be output to the beamforming module 50 for processing, or output to the memory 80 for storage.

[0092] The beamforming module 50 is connected to the receiving circuit 420 signal, and is used to perform beamforming processing such as corresponding delay and weighted summation on the echo signal. Since the distances from the ultrasonic receiving point in the measured tissue to the receiving array element are different, the channel data of the same receiving point output by different receiving array elements have delay differences, and delay processing is required to align the phases and perform weighted summation on the different channel data of the same receiving point to obtain the ultrasound image data after beamforming. The ultrasound image data output by the beamforming module 50 is also called radio frequency data (RF data). The beamforming module 50 outputs the radio frequency data to the IQ demodulation module 60. In some embodiments, the beamforming module 50 may also output the radio frequency data to the memory 80 for caching or storage, or directly output the radio frequency data to the processor 20 for image processing.

[0093] The beamforming module 50 may perform the above functions in the form of hardware, firmware or software. For example, the beamforming module 50 may include a central controller circuit (CPU), one or more microprocessor chips or any other electronic components capable of processing input data according to specific logical instructions. When the beamforming module 50 is implemented in software, it may execute instructions stored on a tangible and non-transitory computer-readable medium (e.g., a memory) to perform beamforming calculations using any appropriate beamforming method.

[0094] The IQ demodulation module 60 removes the signal carrier through IQ demodulation, extracts the tissue structure information contained in the signal, and performs filtering to remove noise. The signal obtained at this time is called a baseband signal (IQ data pair). The IQ demodulation module 60 outputs the IQ data pair to the processor 20 for image processing.

[0095] In some embodiments, the IQ demodulation module 60 further outputs the IQ data pair to the memory 80 for caching or storage, so that the processor 20 reads the data from the memory 80 for subsequent image processing.

[0096] The IQ demodulation module 60 may also perform the above functions in the form of hardware, firmware or software. In some embodiments, the IQ demodulation module 60 may also be integrated with the beamforming module 50 in one chip.

[0097] The processor 20 is configured to be a central controller circuit (CPU), one or more microprocessors, a graphics controller circuit (GPU) or any other electronic component that can process input data according to specific logical instructions. It can control peripheral electronic components according to input instructions or predetermined instructions, or read and / or save data from the memory 80. It can also process the input data by executing the program in the memory 80, for example, performing one or more processing operations on the collected ultrasound data according to one or more working modes. The processing operations include but are not limited to adjusting or limiting the form of ultrasound waves emitted by the ultrasound probe 30, generating various image frames for subsequent display of the human-computer interaction device 70, or adjusting or limiting the content and form displayed on the display, or adjusting one or more image display settings displayed on the display (such as ultrasound images, interface components, and positioning areas of interest).

[0098] As echo signals are received, the acquired ultrasound data may be processed by the processor 20 in real time during scanning or treatment, or may be temporarily stored on the memory 80 and processed in quasi-real time in either on-line or off-line operation.

[0099] In this embodiment, the processor 20 controls the operation of the transmitting circuit 410 and the receiving circuit 420, for example, controls the transmitting circuit 410 and the receiving circuit 420 to work alternately or simultaneously. The processor 20 can also determine a suitable working mode according to the user's selection or the setting of the program, form a transmission sequence corresponding to the current working mode, and send the transmission sequence to the transmitting circuit 410, so that the transmitting circuit 410 uses the suitable transmission sequence to control the ultrasound probe 30 to transmit ultrasound waves.

[0100] The processor 20 is also used to process the ultrasound data to generate a grayscale image of signal strength changes within the scanning range, which reflects the anatomical structure inside the tissue, called a B image. The processor 20 can output the B image to the display of the human-computer interaction device 70 for display.

[0101] The human-computer interaction device 70 is used for human-computer interaction, that is, receiving user input and outputting visual information; it can receive user input using a keyboard, operation buttons, mouse, trackball, etc., or a touch screen integrated with a display; it can output visual information using a display.

[0102] based on Figure 1 The ultrasound imaging device shown in the figure, the process of generating the cross-sectional image of the pelvic floor is as follows Figure 2 As shown, the following steps are included:

[0103] Step 1, the processor 20 performs 3D reconstruction according to the ultrasound data stored in the memory 80, or performs 3D reconstruction according to the ultrasound data output by the beamforming module 50, or performs 3D reconstruction according to the ultrasound data output by the IQ demodulation module 60, to obtain three-dimensional volume data (three-dimensional volume data) of the pelvic floor, and outputs the three-dimensional volume data to the display of the human-machine interaction device 70 for display.

[0104] Step 2, the processor 20 identifies key anatomical structures from the three-dimensional volume data. In this embodiment, the target tissue is the levator ani muscle, and the key anatomical structure associated with it can be the target tissue itself, or it can be a tissue that can locate the target tissue. In this embodiment, there can be two key anatomical structures associated with it: the lower edge of the pubic symphysis (or its surrounding tissue) and the anorectal angle. For the identification of the key anatomical structures of the ultrasonic pelvic floor, for the posterior lower edge point of the pubic symphysis, it can be an independent coordinate point, or it can include\or the anatomical structures around the posterior lower edge point (such as the pubic branch structure of the posterior lower edge point of the pubic symphysis, etc. At the same time, the detection of key anatomical structures is not limited to the posterior lower edge point of the pubic symphysis and the anorectal angle. In this embodiment, for the sake of convenience, the key anatomical structures of the levator ani muscle mainly refer to the posterior lower edge point of the pubic symphysis and the anorectal angle. Step 2 specifically includes two methods: direct identification and indirect identification.

[0105] The direct identification method is shown in step 2.1, including:

[0106] The processor 20 identifies at least one key anatomical structure associated with the position of the target tissue from the three-dimensional volume data, and obtains the spatial position of the key anatomical structure in the three-dimensional volume data. Specifically, the key anatomical structure detection can be implemented based on machine learning or deep learning methods. For example, at least one characteristic index of the three-dimensional volume data is calculated, and the characteristic index is input into a pre-established model function of the correspondence between the characteristic index of the three-dimensional volume data and the key anatomical structure to obtain the corresponding key anatomical structure. The main steps are as follows:

[0107] Database construction steps: The database usually contains multiple sets of ultrasound pelvic floor three-dimensional volume data and calibration results of key anatomical structures. The calibration results can be set according to the actual task requirements, which can be a ROI (region of interest) box containing the target, or a Mask that accurately segments the posterior lower edge of the pubic symphysis (or\and its surrounding tissues) and the anorectal angle area.

[0108] Positioning and recognition steps: After the database is built, a machine learning algorithm is designed to learn the features or rules in the database that can distinguish the target area (key anatomical structure area) and the non-target area (background area) to achieve image positioning and recognition. This implementation step includes but is not limited to the following situations.

[0109] In the first case, the traditional sliding window-based method can be used. The common form is: first, feature extraction is performed on the area within the sliding window. The feature extraction method can be traditional PCA, LDA, Haar features, texture features, etc., or deep neural networks can be used for feature extraction. Then the extracted features are matched with the database, and classified using discriminators such as KNN, SVM, random forest, neural networks, etc. to determine whether the current sliding window is the area of ​​interest and obtain its corresponding category.

[0110] In the second case, the Bounding-Box method based on deep learning can be used for detection and recognition. The common form is: by stacking the basic convolutional layer and the fully connected layer to learn the features and regress the parameters of the constructed database. For an input image, the Bounding-Box of the corresponding area of ​​interest can be directly regressed through the network, and the category of the organizational structure in the area of ​​interest can be obtained. Common networks include R-CNN, Fast R-CNN, Faster-RCNN, SSD, YOLO, etc.

[0111] The third case is an end-to-end semantic segmentation network method based on deep learning. This method is similar to the second Bounding-Box method based on deep learning. The difference is that the fully connected layer is removed, and an upsampling or deconvolution layer is added to make the input and output sizes the same, so as to directly obtain the region of interest of the input image and its corresponding category. Common networks include FCN, U-Net, Mask R-CNN, etc.

[0112] The fourth case is to use only the method in the first case, the method in the second case, or the method in the third case to locate the target, and then design an additional classifier based on the positioning result to classify the target. Common classification judgment methods are: first extract features from the target ROI or Mask. The feature extraction method can be traditional PCA, LDA, Haar features, texture features, etc., or deep neural networks can be used for feature extraction. Then, the extracted features are matched with the database, and classified using discriminators such as KNN, SVM, random forest, neural network, etc.

[0113] The above machine learning or deep learning algorithm can automatically locate the positions of key anatomical structures such as the posterior inferior edge of the pubic symphysis and the anorectal angle in the three-dimensional volume data, thereby facilitating the subsequent positioning of the standard levator ani muscle minimum hiatus area section as the basis for subsequent imaging.

[0114] In the ultrasound pelvic floor data, if the pubic branches on both sides are parallel and symmetrical, the symmetry plane corresponding to the pubic branches is the standard midsagittal section, such as Figure 3 As shown. After determining the midsagittal section, the echo of the pubic symphysis and the anorectal angle is significantly different from the surrounding tissues: the pubic symphysis is a bright oval, the pubic branch outer edge fascia is a bright tissue wrapped around the outer edge of the fascia, and the posterior lower edge of the pubic symphysis is located at the intersection of the pubic branch midline and the fascia; when the examinee is in different action states (resting, anal contraction and valsalva), the anorectal angle presents a certain angle, and the angle is generally not greater than 180°. Therefore, traditional grayscale and / or morphological feature detection methods can be used to detect the posterior lower edge of the pubic symphysis and the anorectal angle. For example, firstly, the three-dimensional volume data is segmented, specifically binary segmentation, and the morphological feature detection is performed on each region obtained after the segmentation to obtain multiple candidate regions, and then the probability of each candidate region being a key anatomical structure (the lower edge of the pubic symphysis and the anorectal angle) is determined according to the shape feature and / or grayscale feature, and the candidate region with the highest probability is determined as the key anatomical structure. Of course, other traditional grayscale detection and segmentation methods may also be used, such as OTSU threshold, Level Set, Graph Cut, Snake, etc.

[0115] The indirect identification method is shown in step 2.2: the processor 20 generates at least one two-dimensional section according to the prior position of the key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, identifies at least one key anatomical structure associated with the position of the target tissue from the two-dimensional section, and obtains the spatial position of the key anatomical structure in the three-dimensional volume data. Specifically, the processor 20 detects the most similar pair of two-dimensional sections on both sides of the prior position according to the prior position of the key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, and identifies the key anatomical structure from the central plane of the pair of two-dimensional sections. Specifically in this embodiment, the processor 20 detects the most similar pair of two-dimensional sections on both sides of the sagittal section according to the sagittal section of the pelvic floor, and identifies the posterior inferior edge of the pubic symphysis and the anorectal angle from the central plane of the pair of two-dimensional sections. If the median sagittal section is directly identified, it is impossible to accurately find the ideal median sagittal section due to the problem of identification accuracy; however, the present invention can accurately identify the key anatomical structure through symmetric search without finding the median sagittal section.

[0116] The above-mentioned key anatomical structure recognition method is automatic, of course, it can also be performed manually. Manual acquisition of anatomical structures is that the user uses tools such as keyboards and mice to point, draw lines, etc. on specific anatomical structures in the three-dimensional volume data based on a certain workflow to inform the device of the type and location of key structures.

[0117] In one embodiment, when identifying key anatomical structures, the lower edge of the pubic symphysis, two pubic branches, and the anorectal angle can be directly identified from the three-dimensional volume data, thereby obtaining the spatial positions of the lower edge of the pubic symphysis, the two pubic branches, and the anorectal angle in the three-dimensional volume data. Then, based on the spatial positions of the lower edge of the pubic symphysis, the two pubic branches, and the anorectal angle in the three-dimensional volume data, a section passing through the lower edge of the pubic symphysis and at least a portion of the anorectal angle and parallel to a line connecting two points on the two pubic branches that are symmetrical relative to the lower edge of the pubic symphysis can be determined. The section can be considered as the section of the minimum hiatus of the levator ani muscle, and therefore the position of the section can be used as the position of the section of the minimum hiatus of the levator ani muscle.

[0118] In one embodiment, when identifying key anatomical structures, the lower edge of the pubic symphysis and the anorectal angle can be directly identified from the three-dimensional volume data, thereby obtaining the spatial positions of the lower edge of the pubic symphysis and the anorectal angle in the three-dimensional volume data. Then, according to the spatial positions of the lower edge of the pubic symphysis and the anorectal angle in the three-dimensional volume data, multiple sections passing through the line connecting the lower edge of the pubic symphysis and a predetermined point on the anorectal angle can be determined, and the section images of the multiple sections can be obtained according to the three-dimensional volume data. Thereafter, according to the image data of the section images of the multiple sections, the symmetry of the image area (all or part of the image area) located on both sides of the line connecting the lower edge of the pubic symphysis and the predetermined point in each of the section images can be determined, and the section of the section image whose symmetry meets the predetermined condition is considered to be the section of the minimum hiatus of the levator ani muscle, so the position of the section image whose symmetry meets the predetermined condition can be determined as the position of the section of the minimum hiatus of the levator ani muscle. Here, the "predetermined condition" can be set according to actual conditions. For example, in one embodiment, the predetermined condition may be set as "maximum symmetry". In another embodiment, the predetermined condition may be set as symmetry greater than a specific value, symmetry less than a specific value, or symmetry within a specific range, etc. The method for determining the symmetry of an image region may use conventional methods, which will not be described in detail herein.

[0119] Step 3: The processor 20 images the cross-section of the target tissue based on the position of the key anatomical structure in the three-dimensional volume data, obtains the cross-section image of the target tissue, and displays the cross-section image of the target tissue on a display. Figure 3 After identifying the lower edge of the pubic symphysis and the anorectal angle, a plane is used to slice the three-dimensional volume data, and the obtained section is the required minimum hiatus section of the anal levator muscle. Figure 3 The straight line where the planes intersect passes through the lower edge of the pubic symphysis and the anorectal angle, such as Figure 3 The cross-sectional image of the target tissue can be presented in the form of volume rendering imaging, cross-sectional imaging, arbitrary cross-sectional (plane or curved) imaging, multi-parallel plane imaging and cross-sectional imaging, arbitrary cross-sectional (plane or curved) imaging, and a combination of multiple parallel plane imaging and thick layer imaging.

[0120] Volume rendering imaging is based on the key anatomical structures detected in the three-dimensional volume data to adjust the position, size and curvature of the volume of interest (VOI) and the curvature of the imaging curve, so as to display the rendered image of the levator ani hiatus. Section imaging is based on the key anatomical structures detected in the three-dimensional volume data to adjust the position of the section in space to generate a levator ani hiatus section image. Arbitrary section (plane or curved surface) imaging is based on the key anatomical structures detected in the three-dimensional volume data to generate reference lines (straight lines or curves), and the minimum levator ani hiatus section is obtained through the reference lines; multi-parallel plane imaging is based on the key anatomical parts detected, with the minimum levator ani hiatus area section as the reference, and multiple parallel section imaging is achieved at equal intervals.

[0121] The effect of the processor 20 performing volume rendering imaging on the section with the smallest hiatus area of ​​the levator ani muscle is as follows: Figure 4 As shown. For three-dimensional stereoscopic imaging, volume rendering imaging is to display the three-dimensional volume data in the VOI box a through different imaging modes using algorithms such as ray tracing. In addition to adjusting the orientation of the volume data, obtaining a good volume rendering image also requires setting the size and position of the VOI box a. For ultrasonic pelvic floor three-dimensional volume data, after detecting anatomical structures such as the pubic symphysis and anorectal angle, the orientation of the volume data can be automatically adjusted according to the specific positions of the posterior inferior edge of the pubic symphysis and the anorectal angle, so that the posterior inferior edge of the pubic symphysis and the anorectal angle are at the same horizontal position, and the VOI imaging curve coincides with the straight line where the inferior edge of the pubic symphysis and the anorectal angle are located as much as possible. At the same time, adjust the VOI box a to an appropriate size (generally 2.5mm) to render the minimum hiatus section of the levator ani muscle, as shown Figure 5 As shown in the lower right corner of the picture.

[0122] The processor 20 performs grayscale imaging on the section of the minimum hiatus area of ​​the levator anus muscle: the section image refers to the section image at a specific position and direction in the three-dimensional volume data. By adjusting the rotation and translation, the section images at different positions and directions can be obtained. Based on the anatomical structures such as the lower edge of the pubic symphysis and the anorectal angle detected in the three-dimensional volume data, the standard section of the minimum hiatus area of ​​the levator anus muscle can be directly obtained through plane imaging. Usually, the section of the minimum hiatus area of ​​the levator anus muscle is a two-dimensional section through the lower edge of the pubic symphysis and the anorectal angle. Therefore, through the position of the key anatomical structure detected in the three-dimensional volume data in the previous step, a plane can be generated so that the plane passes through (or approximately passes through) the section where the lower edge of the pubic symphysis and the anorectal angle are located. The plane equation can be obtained by solving the equation or fitting. After obtaining the plane equation, the grayscale image corresponding to the plane can be taken out from the three-dimensional volume data, thereby obtaining the section of the minimum hiatus area of ​​the levator anus muscle. On the basis of automatic imaging, the user can also manually fine-tune the section position of the hiatus of the levator anus muscle based on the position of the lower edge of the pubic symphysis and the anorectal angle in the three-dimensional volume data.

[0123] The processor 20 automatically performs arbitrary cross-sectional imaging on the section with the smallest hiatus area of ​​the levator ani muscle: In addition to displaying the section with the smallest hiatus area of ​​the levator ani muscle by three-dimensional reconstruction of the volume rendering image, it can also be displayed by arbitrary cross-sectional imaging, and the specific expression form is as follows: Figure 5 As shown. Arbitrary cross-sectional imaging is to take one or more reference lines (straight or curved lines, Figure 5 The reference line will form a section (plane or curved surface) with the three-dimensional data, and the section will be taken out and straightened into a plane for display. Usually, the formation of the minimum hiatus section of the levator ani muscle places the reference line at the straight line formed by the lower edge of the pubic symphysis and the anorectal angle. After obtaining the key anatomical structures such as the lower edge of the pubic symphysis and the anorectal angle through the automatic recognition method described above, the imaging straight line can be placed on the straight line formed by these two anatomical positions to achieve automated imaging of any section of the minimum hiatus of the levator ani muscle. Of course, the minimum hiatus area section of the levator ani muscle can also be obtained manually. For example, the reference line is determined according to the user's input command, and the key anatomical structure is cut and imaged through the reference line to obtain the minimum hiatus area section of the levator ani muscle.

[0124] The processor 20 automatically performs multi-parallel section imaging on the levator ani muscle minimum hiatus area section: During the process of ultrasound clinical examination, ultrasound clinicians usually need to observe the levator ani muscle hiatus area based on multiple parallel sections to obtain more comprehensive diagnostic information. Multi-parallel section imaging refers to an imaging method that displays multiple parallel sections at the same time. The distances between adjacent sections are equal, and the user can adjust the distance between parallel planes. After detecting key anatomical parts such as the pubic symphysis and anorectal angle, the levator ani muscle minimum hiatus section can be obtained by the above-mentioned method of automatic imaging of the levator ani muscle minimum hiatus area section, and then the levator ani muscle is imaged with multiple equally spaced sections in parallel based on this section, such as Figure 6 As shown. Users can change the position of the reference slice or reselect the reference slice according to the actual situation. At the same time, the spacing between frames can be fixed and equal, or it can be adjusted automatically or manually according to the actual situation.

[0125] The processor 20 combines the above-mentioned cross-sectional imaging, arbitrary cross-sectional imaging, and multiple parallel cross-sectional imaging with thick-layer imaging respectively: the imaging method of the levator ani hiatus section, in addition to the above four methods, can also combine the three imaging methods of cross-sectional imaging, arbitrary cross-sectional imaging, and multiple parallel cross-sectional imaging with thick-layer imaging. Thick-layer imaging refers to adding a certain thickness to the tomographic grayscale image and displaying it in a surface mode, an X-ray mode, or a fusion mode of the two. The thickness can be a pre-set imaging thickness. This mode can effectively improve the contrast resolution of the image and enhance the display of key anatomical structures and features, but attenuate the image details. At the same time, the image thickness of thick-layer imaging can be set to a fixed value (such as 2.5mm) according to actual clinical needs, or the thickness parameters can be adaptively adjusted according to the actual anatomical structure and features. Of course, the user can also manually set the parameter based on personal needs and operating habits.

[0126] During ultrasound scanning, after scanning the minimum hiatus area section of the levator anus muscle, the ultrasound probe is rotated 90° and tilted backward and downward to fully display the cross section of the anal canal. Therefore, after the processor 20 obtains the minimum hiatus area section of the levator anus muscle, a cross-sectional image of the anal canal cross section can be generated based on the positional relationship between the cross section of the anal canal and the minimum hiatus area section of the levator anus muscle. Of course, the target tissue can also be set as the anal canal, and the cross-sectional image of the anal canal cross section can be obtained by the above method. The process is similar to the process of obtaining the minimum hiatus area section of the levator anus muscle, so it will not be repeated. The imaging method of the puborectalis section is consistent with the imaging method of the levator ani minimum hiatus area section, that is, after detecting the key anatomical parts related to the anal sphincter, the puborectalis can be imaged in a variety of ways, namely, automatic imaging of puborectalis section volume rendering, section imaging, arbitrary section (plane or curved surface) imaging, section imaging of a multi-parallel plane imaging machine, arbitrary section (plane or curved surface) imaging, and a combination of multiple parallel plane imaging and thick layer imaging.

[0127] In the case of poor image quality and deviations in the positions of key anatomical structures detected by the algorithm, users can also use tools such as keyboard and mouse to move, scale, delete and recalibrate the VOI area in the detected section or any section imaging curve to achieve semi-automatic VOI imaging or imaging of any section; for pelvic floor corresponding to standard section plane imaging and multiple parallel section imaging, users can also adjust the section using the knob.

[0128] Step 4: Measure the cross-sectional image of the target tissue. After obtaining the cross-sectional view of the minimum hiatus of the levator ani muscle, doctors usually need to measure relevant measurement items on the corresponding cross-sectional view in order to quantitatively evaluate the prolapse and tearing of the pelvic floor organs. However, the relevant measurement items are often complicated, the measurement process is time-consuming and laborious, and the doctor's experience and skills are very high, making it difficult to ensure the robustness and accuracy of the measurement results. Therefore, it is very important to realize the intelligent measurement of the corresponding measurement items based on the pelvic floor cross-sectional view obtained above.

[0129] Based on the minimum hiatus section of the levator ani muscle, there are two items that ultrasound clinicians need to measure routinely at this stage, namely the minimum hiatus area of ​​the levator ani muscle and the distance from the urethral opening to the leftmost and rightmost levator ani muscles. For volume rendering imaging sections, section imaging sections and arbitrary section imaging sections, only the above two measurement items need to be intelligently measured on a single frame image; for multiple parallel section imaging, one or more frames of images need to be met for intelligent measurement, where the selection of measurement frames and frame numbers meets the user's needs and settings, and the default setting is Figure 6 The three consecutive frames in the middle.

[0130] Therefore, in this embodiment, step 4 includes: the processor 20 detects the levator ani muscle based on the cross-sectional image of the levator ani muscle (the minimum hiatus cross-sectional view of the levator ani muscle), performs area statistics on the detected levator ani muscle, and obtains the minimum hiatus area of ​​the levator ani muscle; detects the levator ani muscle and urethral opening based on the cross-sectional image of the levator ani muscle, and measures the distance from the urethral opening to the leftmost levator ani muscle and the distance from the urethral opening to the rightmost levator ani muscle.

[0131] Specifically, the processor 20 identifies the target to be measured, such as the levator ani muscle, based on the target segmentation methods such as traditional grayscale and / or morphology, and then performs the measurement: in the levator ani muscle hiatus section, the levator ani muscle presents a bright muscle fiber sound beam, and the ultrasonic imaging characteristics are significantly different from the surrounding anatomical structure. Therefore, similar to the idea of ​​key anatomical structure detection in the previous text, the processor 20 uses traditional grayscale and / or morphological feature detection and segmentation methods to achieve detection and segmentation of the levator ani muscle. For example, firstly, the levator ani muscle hiatus section image is binarized and segmented, and multiple candidate regions are obtained after some necessary morphological operations, and then the probability of each candidate region being the levator ani muscle is judged according to the shape, grayscale brightness and other features, and a region with the highest probability is selected as the target segmentation region. Of course, other traditional grayscale detection and segmentation methods can also be used, such as Otsu threshold (OTSU), level set (LevelSet), graph cut (Graph Cut), Snake, etc.

[0132] The processor 20 can also identify the target to be measured, such as the levator ani muscle, based on target segmentation methods such as machine learning or deep learning, and then measure it: in addition to the above-mentioned traditional image segmentation method, similar to the above-mentioned target detection method, the segmentation of the levator ani muscle can also be achieved based on target segmentation methods such as machine learning and deep learning. The segmentation method can refer to the third and fourth cases in the corresponding target detection method in the previous text. In other words, the levator ani muscle can be directly segmented based on the deep learning end-to-end semantic segmentation network; the target can also be located based on the end-to-end network segmentation, and then a classifier is additionally designed according to the positioning result to classify and interpret the target at the pixel level, and the levator ani muscle segmentation is achieved in two steps. These two ideas are similar to the ideas of the target detection method in the previous text, and will not be repeated here.

[0133] After segmenting the levator ani muscle, other measurement items can be calculated based on the levator ani muscle hiatus section, such as the distance from the urethral opening to the leftmost side of the levator ani muscle and the distance from the urethral opening to the rightmost side of the levator ani muscle. It should be noted that the automatic measurement of this measurement item requires the algorithm system to automatically detect the urethral opening. The automatic detection method is the same as the automatic detection method of key anatomical structures mentioned above, so it will not be repeated here.

[0134] In one embodiment, the contour of the levator ani muscle or the smallest levator ani muscle hiatus can be extracted from the levator ani muscle smallest hiatus section image, and the distance between the upper and lower diameters of the levator ani muscle and / or the distance between the left and right diameters of the levator ani muscle can be calculated based on the contour. Figure 7 As shown, A is the extracted contour of the levator ani muscle or the smallest hiatus of the levator ani muscle, B is the left and right diameter of the levator ani muscle, and C is the upper and lower diameter of the levator ani muscle. Here, the distance between the upper and lower diameters can be the length of the upper and lower diameters C, and the distance between the left and right diameters can be the length of the left and right diameters B.

[0135] In the embodiment where the target tissue is the anal canal, the cross-sectional image of the target tissue is the cross-section of the anal canal. The processor 20 detects the puborectalis muscle based on the cross-section of the anal canal and measures the thickness of the detected puborectalis muscle. Specifically, the processor 20 measures the thickness of the puborectalis muscle based on multiple parallel cross-sections of the puborectalis muscle. The thickness is measured three times in a row in the corresponding surrounding area of ​​the same frame image, and the measurement result is displayed correspondingly for each time, and the average value is calculated. The selection of the measurement frame, the number of frames, and the number of measurements satisfies the user's needs and is set, and the default is to take three measurement results for the intermediate frame. In the embodiment where the target tissue is the anal canal, the automatic measurement process is similar to the embodiment of the levator ani muscle, only the object of detection is different, so it will not be repeated.

[0136] The measurement of the above measurement items can be fully automatic or semi-automatic. Semi-automatic measurement allows users to set one or more input points on the corresponding interface and obtain corresponding measurement results based on the input points. At the same time, if the image quality is poor and the measurement results obtained by the intelligent algorithm are biased, users can also delete, modify, re-enter and other modification operations on the results through tools such as keyboards and mice.

[0137] Step 5: The processor 20 displays the cross-sectional image of the target tissue and its measurement results through the display of the human-computer interaction device 70. The doctor may need to measure different target tissues, so a certain workflow can be preset to integrate the doctor's selection function of the target tissue into the workflow for the doctor to freely select, and the image and measurement results corresponding to the selected function are displayed on the display.

[0138] In summary, the ultrasonic imaging device and the method for generating a cross-sectional image of the pelvic floor provided by the present invention can not only automatically generate a cross-sectional image of the target tissue of the pelvis, but also perform corresponding measurements, thereby greatly improving the work efficiency of ultrasound doctors.

[0139] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above-mentioned embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above-mentioned functions can be implemented. In addition, when all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and can be downloaded or copied and saved in the memory of the local device, or the system of the local device is updated, and when the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0140] This document is described with reference to various exemplary embodiments. However, those skilled in the art will recognize that changes and modifications may be made to the exemplary embodiments without departing from the scope of this document. For example, various operating steps and components for performing the operating steps may be implemented in different ways (e.g., one or more steps may be deleted, modified, or incorporated into other steps) depending on the specific application or considering any number of cost functions associated with the operation of the system.

[0141] In addition, as will be appreciated by those skilled in the art, the principles of the present invention may be reflected in a computer program product on a computer-readable storage medium, which is pre-installed with a computer-readable program code. Any tangible, non-temporary computer-readable storage medium may be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CD-ROMs, DVDs, Blu Ray disks, etc.), flash memory, and / or the like. These computer program instructions may be loaded onto a general-purpose computer, a special-purpose computer, or other programmable data processing device to form a machine, so that these instructions executed on a computer or other programmable data processing device may generate a device that implements a specified function. These computer program instructions may also be stored in a computer-readable memory, which may instruct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory may form a manufactured product, including an implementation device that implements a specified function. The computer program instructions may also be loaded onto a computer or other programmable data processing device, so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device may provide steps for implementing a specified function.

[0142] Although the principles of this invention have been shown in various embodiments, many modifications of structures, arrangements, proportions, elements, materials and components particularly suitable for specific environments and operational requirements can be used without departing from the principles and scope of this invention. The above modifications and other changes or amendments will be included in the scope of this invention.

[0143] The foregoing specific description has been described with reference to various embodiments. However, those skilled in the art will recognize that various modifications and changes can be made without departing from the scope of the present disclosure. Therefore, the consideration of the present disclosure will be illustrative rather than restrictive, and all these modifications will be included in its scope. Similarly, the advantages, other advantages and solutions to the problems of various embodiments have been described above. However, the benefits, advantages, solutions to the problems and any elements that can produce these, or make them more clear, should not be interpreted as critical, necessary or necessary. The term "include" and any other variants used in this article are all non-exclusive inclusions, so that the process, method, article or device including the list of elements not only includes these elements, but also includes other elements that are not explicitly listed or do not belong to the process, method, system, article or device. In addition, the term "coupled" and any other variants used in this article refer to physical connections, electrical connections, magnetic connections, optical connections, communication connections, functional connections and / or any other connections.

[0144] Those skilled in the art will appreciate that many changes may be made to the details of the above-described embodiments without departing from the basic principles of the invention. Therefore, the scope of the invention should be determined from the following claims.

Claims

1. A method for generating a cross-sectional image of a pelvic floor, characterized in that: include: Obtain three-dimensional volume data of the pelvic floor; Identifying the posterior lower edge of the pubic symphysis and at least a portion of the anorectal angle from the three-dimensional volume data, and obtaining the spatial positions of the posterior lower edge of the pubic symphysis and at least a portion of the anorectal angle in the three-dimensional volume data; Determine a volume region of interest in the three-dimensional volume data based on the spatial positions of the posterior inferior edge of the symphysis pubis and at least a portion of the anorectal angle in the three-dimensional volume data, wherein the volume region of interest includes the posterior inferior edge of the symphysis pubis and at least a portion of the anorectal angle; Volume rendering is performed on the volume region of interest to obtain an image of the smallest hiatus section of the levator ani muscle.

2. The method according to claim 1, characterized in that Identifying the posterior inferior edge of the pubic symphysis from the three-dimensional volume data includes: Calculating at least one characteristic index of the three-dimensional volume data, inputting the characteristic index into a pre-established model function of the correspondence between the characteristic index of the three-dimensional volume data and the posterior inferior edge of the pubic symphysis, and obtaining the corresponding posterior inferior edge of the pubic symphysis; or Perform target detection or image segmentation on the three-dimensional volume data, perform morphological feature detection on each region obtained after the detection or segmentation to obtain multiple candidate regions, judge for each candidate region whether the candidate region is the posterior inferior edge of the symphysis pubis based on shape features and / or grayscale features, and determine the candidate region with the highest probability as the posterior inferior edge of the symphysis pubis.

3. The method according to any one of claims 1, characterized in that Identifying at least a portion of the anorectal angle from the three-dimensional volumetric data includes: Calculating at least one characteristic index of the three-dimensional volume data, inputting the characteristic index into a pre-established model function of the correspondence between the characteristic index of the three-dimensional volume data and at least a portion of the anorectal angle, to obtain at least a portion of the corresponding anorectal angle; or Performing target detection or image segmentation on the three-dimensional volume data, performing morphological feature detection on each region obtained after the detection or segmentation to obtain multiple candidate regions, judging for each candidate region a probability that the candidate region is at least a part of the anorectal angle based on shape features and / or grayscale features, and determining the candidate region with the highest probability as at least a part of the anorectal angle.

4. The method as claimed in claim 1, characterized in that: Identifying the posterior lower edge of the pubic symphysis and at least a portion of the anorectal angle from the three-dimensional volume data, and obtaining the spatial positions of the posterior lower edge of the pubic symphysis and at least a portion of the anorectal angle in the three-dimensional volume data, comprising: Directly identifying the spatial positions of the posterior inferior edge of the pubic symphysis and at least a portion of the anorectal angle in the three-dimensional volume data from the three-dimensional volume data; or, At least one two-dimensional section is generated according to the prior positions of the posterior inferior edge of the pubic symphysis and at least a portion of the anorectal angle in the three-dimensional volume data, the posterior inferior edge of the pubic symphysis and at least a portion of the anorectal angle are identified from the two-dimensional section, and the spatial positions of the posterior inferior edge of the pubic symphysis and at least a portion of the anorectal angle in the three-dimensional volume data are obtained.

5. A method for generating a cross-sectional image of a pelvic floor, characterized in that: include: Obtain three-dimensional volume data of the pelvic floor; Identifying at least one key anatomical structure associated with the position of the target tissue from the three-dimensional volume data, and obtaining the spatial position of the at least one key anatomical structure in the three-dimensional volume data; or, generating at least one two-dimensional section according to the a priori position of the at least one key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, identifying at least one key anatomical structure associated with the position of the target tissue from the two-dimensional section, and obtaining the spatial position of the at least one key anatomical structure in the three-dimensional volume data; Determining a volume region of interest in the three-dimensional volume data based on a position of the at least one key anatomical structure in the three-dimensional volume data, wherein the volume region of interest includes the at least one key anatomical structure; Volume rendering is performed on the volume region of interest to obtain a volume rendering image of the target tissue.

6. The method according to claim 5, characterized in that The target tissue is the levator ani muscle, and the method further comprises: Detecting the levator ani muscle based on the cross-sectional image of the levator ani muscle, and measuring the minimum hiatus area of ​​the detected levator ani muscle; Alternatively, the levator ani muscle and the urethral opening are detected based on the cross-sectional image of the levator ani muscle, and the distance from the urethral opening to the leftmost levator ani muscle and the distance from the urethral opening to the rightmost levator ani muscle are measured; Alternatively, the contour of the levator ani muscle or the smallest hiatus of the levator ani muscle is extracted based on the cross-sectional image of the levator ani muscle, and the distance between the upper and lower diameters of the levator ani muscle and / or the distance between the left and right diameters of the levator ani muscle is calculated according to the contour.

7. The method according to claim 5, characterized in that: The target tissue is an anal canal, and the cross-sectional image of the target tissue is a cross section of the anal canal; the method further comprises: The puborectalis muscle is detected based on the cross-section of the anal canal, and the thickness of the detected puborectalis muscle is measured.

8. The method according to claim 5, characterized in that Identifying at least one key anatomical structure associated with the location of the target tissue from the three-dimensional volume data includes: At least one characteristic index of the three-dimensional volume data is calculated, and the characteristic index is input into a pre-established model function of the correspondence between the characteristic index of the three-dimensional volume data and the key anatomical structure to obtain the corresponding key anatomical structure.

9. The method according to claim 5, characterized in that Identifying at least one key anatomical structure associated with the location of the target tissue from the three-dimensional volume data includes: Performing target detection or image segmentation on the three-dimensional volume data, performing morphological feature detection on each region obtained after the detection or segmentation to obtain multiple candidate regions, judging the probability of each candidate region being a key anatomical structure based on shape features and / or grayscale features, and determining the candidate region with the highest probability as the key anatomical structure.

10. The method according to claim 5, characterized in that Identifying at least one key anatomical structure associated with the position of the target tissue from the three-dimensional volume data, and obtaining the spatial position of the at least one key anatomical structure in the three-dimensional volume data, comprising: Directly identifying at least one key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, and obtaining the spatial position of the at least one key anatomical structure associated with the position of the target tissue in the three-dimensional volume data; or, At least one two-dimensional section is generated based on the prior position of the key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, at least one key anatomical structure associated with the position of the target tissue is identified from the two-dimensional section, and the spatial position of the at least one key anatomical structure associated with the position of the target tissue in the three-dimensional volume data is obtained.

11. The method according to claim 6, characterized in that The key anatomical structure is the target tissue or a tissue capable of locating the target tissue.

12. An ultrasonic imaging device, characterized in that: include: An ultrasonic probe, used for transmitting ultrasonic waves to an object to be imaged so as to scan the object to be imaged, and receiving ultrasonic echoes returned from the object to be imaged; A transmitting / receiving circuit, used for controlling the ultrasonic probe to transmit ultrasonic waves to the object to be imaged and to receive echoes of the ultrasonic waves; A processor, configured to perform 3D reconstruction according to the ultrasonic echo to obtain three-dimensional volume data of the object to be imaged; the object to be imaged includes a pelvic floor; The processor is further configured to identify the posterior lower edge of the pubic symphysis and at least a portion of the anorectal angle from the three-dimensional volume data, and obtain the spatial position of the posterior lower edge of the pubic symphysis and at least a portion of the anorectal angle in the three-dimensional volume data; Determine a volume region of interest in the three-dimensional volume data based on the spatial positions of the posterior inferior edge of the symphysis pubis and at least a portion of the anorectal angle in the three-dimensional volume data, wherein the volume region of interest includes the posterior inferior edge of the symphysis pubis and at least a portion of the anorectal angle; Volume rendering is performed on the volume region of interest to obtain an image of the smallest hiatus section of the levator ani muscle.

13. An ultrasonic imaging device, characterized in that: include: An ultrasonic probe, used for transmitting ultrasonic waves to an object to be imaged so as to scan the object to be imaged, and receiving ultrasonic echoes returned from the object to be imaged; A transmitting / receiving circuit, used for controlling the ultrasonic probe to transmit ultrasonic waves to the object to be imaged and to receive echoes of the ultrasonic waves; A processor, configured to perform 3D reconstruction according to the ultrasonic echo to obtain three-dimensional volume data of the object to be imaged; the object to be imaged includes a pelvic floor; The processor is further configured to identify at least one key anatomical structure associated with the position of the target tissue from the three-dimensional volume data, and obtain the spatial position of the at least one key anatomical structure in the three-dimensional volume data; or, based on the a priori position of the at least one key anatomical structure associated with the position of the target tissue in the three-dimensional volume data, generate at least one two-dimensional section, identify at least one key anatomical structure associated with the position of the target tissue from the two-dimensional section, and obtain the spatial position of the at least one key anatomical structure in the three-dimensional volume data; Determining a volume region of interest in the three-dimensional volume data based on a position of the at least one key anatomical structure in the three-dimensional volume data, wherein the volume region of interest includes the at least one key anatomical structure; Volume rendering is performed on the volume region of interest to obtain a volume rendering image of the target tissue. A display is used to display the volume rendering image of the target tissue.

14. The ultrasonic imaging device according to claim 13, characterized in that: The target tissue is an anal canal, and the cross-sectional image of the target tissue is a cross-section of the anal canal; the processor is further used for: The puborectalis muscle is detected based on the cross-section of the anal canal, and the thickness of the detected puborectalis muscle is measured.

15. The ultrasonic imaging device according to claim 13, characterized in that: The processor identifies at least one key anatomical structure associated with the location of the target tissue from the three-dimensional volume data, including: At least one characteristic index of the three-dimensional volume data is calculated, and the characteristic index is input into a pre-established model function of the correspondence between the characteristic index of the three-dimensional volume data and the key anatomical structure to obtain the corresponding key anatomical structure.

16. The ultrasonic imaging device according to claim 13, characterized in that: The processor identifies at least one key anatomical structure associated with the location of the target tissue from the three-dimensional volume data, including: The three-dimensional volume data is segmented, and morphological feature detection is performed on each region obtained after segmentation to obtain multiple candidate regions. For each candidate region, the probability of the candidate region being a key anatomical structure is determined based on shape features and / or grayscale features, and the candidate region with the highest probability is determined as the key anatomical structure.

17. The ultrasonic imaging device according to claim 13, characterized in that: The key anatomical structure is the target tissue or a tissue capable of locating the target tissue.

18. An ultrasonic imaging device, characterized in that include: Memory, used to store programs; A processor, configured to execute the program stored in the memory to implement the method according to any one of claims 1 to 12.

19. A computer-readable storage medium, characterized in that: The method comprises a program which can be executed by a processor to implement the method according to any one of claims 1 to 12.

Images