CN119732703A

CN119732703A - Ultrasonic imaging device and method for generating cross-sectional images of pelvic floor

Info

Publication number: CN119732703A
Application number: CN202411828429.XA
Authority: CN
Inventors: 邹耀贤; 韩笑; 林穆清; 陈志杰; 龚闻达
Original assignee: Shenzhen Mindray Bio Medical Electronics Co Ltd
Current assignee: Shenzhen Mindray Bio Medical Electronics Co Ltd
Priority date: 2019-07-26
Filing date: 2019-07-26
Publication date: 2025-04-01
Also published as: CN112294361B; CN119732701A; CN119732702A; CN119732700A; CN112294361A

Abstract

The ultrasonic imaging device and the method for generating a cross-sectional image of the pelvic floor provided by the present invention first 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; 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 to obtain a 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.

Description

Ultrasonic imaging equipment and method for generating section image of basin bottom

Technical Field

The invention relates to the field of medical equipment, in particular to ultrasonic imaging equipment and a method for generating a tangential plane image of a basin bottom.

Background

In modern medical image inspection, the ultrasonic technology has become the inspection means which has the widest application and highest use frequency and the fastest popularization and application of the new technology due to the advantages of high reliability, rapidness, convenience, real-time imaging, repeated inspection and the like. Some new ultrasonic technologies, especially based on the development of artificial intelligence auxiliary technologies, further promote the application of the ultrasonic technologies in clinical diagnosis and treatment. Especially in China, due to the fact that the population is aged and the population base is large in recent years, the ultrasonic examination of hospitals faces the increasingly vigorous patient demands. The corresponding medical conditions are to be further improved, such as unbalanced distribution of medical resources among areas, great improvement of technical capability of basic doctors, and the like. The intelligent development of ultrasonic equipment can help doctors to improve the examination efficiency, balance the gap between hospitals in different regions and provide more accurate diagnosis and personalized treatment schemes for patients.

Pelvic floor dysfunction such as stress urinary incontinence and pelvic organ prolapse is one of the common chronic diseases affecting the physical and mental health of females, and severely affects the work and social activities of females. The pelvic floor ultrasonic examination plays an important role in diagnosing pelvic floor diseases, and by means of the ultrasonic technology at the present stage, an ultrasonic clinician can dynamically observe the changes of pelvic organs and levator ani muscle fissures by Valsalva action and anus contraction action. Under the conventional two-dimensional condition, the anatomical structure and prolapse condition of the pelvic floor viscera can be dynamically displayed in real time, meanwhile, an ultrasonic clinician can quantitatively evaluate the prolapse condition of the pelvic floor viscera by measuring, under the three-dimensional/four-dimensional condition, the minimum split Kong Qiemian coronal plane of the levator ani can be displayed, and in addition, a plurality of parallel section images of the split holes of the anal levani of the ultrasonic basin floor can be used for observing whether the levani is damaged layer by layer in the state of contracting the anus. The probe is rotated by 90 degrees and is inclined backwards and downwards, so that the cross section of the anal canal can be completely displayed, and whether the levator ani muscle is damaged or not and whether lesions exist around the levator ani muscle are observed. Meanwhile, the measurement of the levator ani muscle split hole area and the puborectalis muscle thickness under the three-dimensional/four-dimensional condition can help doctors to quantitatively evaluate the damage degree of the levani muscle at the pelvic floor.

However, when a doctor performs ultrasonic diagnosis on the basin bottom, the acquisition of a standard section and the imaging of a plurality of parallel sections are required to be completed manually by the doctor, and the process has high requirements on the experience and the manipulation of the doctor, is time-consuming and labor-consuming, and is extremely complicated in the measurement process of related measurement items. Meanwhile, valsalva and anus retraction actions are difficult to be completed and maintained in the examination process of a patient, and a doctor is required to complete a plurality of parallel section images more accurately and rapidly. After manually obtaining the minimum levator ani crack Kong Qiemian and the parallel section corresponding to the levator ani crack hole and the anal canal cross section, the ultrasonic clinician also needs to manually measure various data, so that the examination time and the examination efficiency of the doctor are greatly consumed.

Disclosure of Invention

The invention mainly provides ultrasonic imaging equipment and a method for generating a tangential plane image of a basin bottom so as to improve the working efficiency of an ultrasonic doctor.

In one embodiment, a method for generating a slice image of a basin bottom is provided, which is characterized by comprising:

acquiring three-dimensional volume data of the basin bottom;

identifying a pubic symphysis and an anorectal angle from the three-dimensional volume data, and obtaining spatial positions of the pubic symphysis and the anorectal angle in the three-dimensional volume data;

Determining a location of levator ani minimum crack Kong Qiemian in the three-dimensional volumetric data based on the spatial locations of the pubic symphysis and the anorectal angle in the three-dimensional volumetric data;

Based on the position of the minimum split Kong Qiemian of the levator ani, obtaining a section image of the minimum split hole of the levator ani according to the three-dimensional volume data.

In one embodiment, identifying a pubic symphysis and an anorectal angle from the three-dimensional volumetric data, and obtaining a spatial location of the pubic symphysis and the anorectal angle in the three-dimensional volumetric data comprises:

Identifying a pubic symphysis lower edge, two pubic ramus and an anorectal angle from the three-dimensional volume data, and obtaining spatial positions of the pubic symphysis lower edge, the two pubic ramus and the anorectal angle in the three-dimensional volume data;

Determining the location of levator ani minimum crack Kong Qiemian in the three-dimensional volumetric data based on the pubic symphysis and the spatial location of the anorectal angle in the three-dimensional volumetric data comprises:

And determining a tangent plane passing through at least one part of the pubic symphysis lower edge and the anorectal angle and parallel to a line formed by two points symmetrical on the two pubic branches relative to the pubic symphysis lower edge according to the spatial positions of the pubic symphysis lower edge, the two pubic branches and the anorectal angle in the three-dimensional volume data, wherein the position of the tangent plane is taken as the position of the minimum levator ani crack Kong Qiemian.

identifying a pubic symphysis lower edge and an anorectal angle from the three-dimensional volume data, and obtaining spatial positions of the pubic symphysis lower edge and the anorectal angle in the three-dimensional volume data;

determining a plurality of tangent planes passing through a preset point on the pubic symphysis lower edge and the anorectal angle according to the spatial positions of the pubic symphysis lower edge and the anorectal angle in the three-dimensional volume data, and obtaining tangent plane images of the plurality of tangent planes according to the three-dimensional volume data;

and determining symmetry of image areas positioned on two sides of a connecting line of the lower edge of the pubis symphysis and the preset point in each section image of the plurality of section images, and determining the position of the section image with symmetry meeting the preset condition as the position of the levator ani muscle minimum crack Kong Qiemian.

In one embodiment, the method further comprises measuring the area of the minimum split hole of the levator ani according to the obtained minimum split Kong Qiemian image of the levator ani, detecting levani muscles and a urethral orifice in the minimum split hole section image of the levator muscles, measuring the distance from the urethral orifice to the leftmost levani muscles and/or the distance from the urethral orifice to the rightmost levani muscles according to the detected levani muscles and urethral orifices, and/or extracting the outline of the levani muscles or the minimum split hole of the levani muscles in the minimum split hole section image of the levani muscles, and calculating the distance between the upper and lower radial lines of the levani muscles and/or the distance between the left and right radial lines of the levani muscles according to the outline.

In one embodiment, the identification of the pubic symphysis from the three-dimensional volume data comprises the steps of calculating at least one characteristic index of the three-dimensional volume data, inputting the characteristic index into a model function of a pre-established corresponding relation between the characteristic index of the three-dimensional volume data and the pubic symphysis to obtain a corresponding pubic symphysis, or carrying out target detection or image segmentation on the three-dimensional volume data, carrying out morphological feature detection on each region obtained after detection or segmentation to obtain a plurality of candidate regions, judging that the candidate region is the pubic symphysis according to the shape feature and/or gray level feature for each candidate region, and determining the candidate region with the highest probability as the pubic symphysis.

In one embodiment, identifying the anorectal angle from the three-dimensional volume data comprises calculating at least one characteristic index of the three-dimensional volume data, inputting the characteristic index into a model function of a corresponding relation between the characteristic index and the anorectal angle of the three-dimensional volume data, which is established in advance, 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 detection or segmentation to obtain a plurality of candidate regions, judging the probability that the candidate region is the anorectal angle according to the shape feature and/or gray level feature for each candidate region, and determining the candidate region with the highest probability as the anorectal angle.

In one embodiment, obtaining an levator ani minimum split hole tangent plane image according to the three-dimensional volume data based on the position of levator ani minimum split Kong Qiemian comprises obtaining image data containing levani minimum split Kong Qiemian from the three-dimensional volume data based on the position of levator ani minimum split Kong Qiemian, performing volume rendering on the image data containing minimum split Kong Qiemian to obtain a volume rendered image of minimum split Kong Qiemian, and/or obtaining a two-dimensional image of levani minimum split Kong Qiemian from the three-dimensional volume data based on the position of levani minimum split Kong Qiemian, and/or performing thick-layer imaging on levani minimum split Kong Qiemian according to a preset imaging thickness to obtain a thick-layer image of levani minimum split Kong Qiemian.

In one embodiment, a method for generating a slice image of a basin bottom is provided, including:

acquiring three-dimensional volume data of the basin bottom;

or generating at least one two-dimensional tangent plane according to the prior 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 in the two-dimensional tangent plane, and obtaining the spatial position of the key anatomical structure in the three-dimensional volume data;

and imaging the section of the target tissue according to the position of the key anatomical structure in the three-dimensional volume data to obtain a section image of the target tissue.

In one embodiment, the target tissue is levator ani, the method further comprising:

Detecting levator ani muscle based on the tangent plane image of levani muscle, and measuring the minimum split hole area of the detected levani muscle;

Or detecting levator ani and the urethral orifice based on the tangent plane image of levani, and measuring the distance from the urethral orifice to the leftmost levani and the distance from the urethral orifice to the rightmost levani.

In one embodiment, the target tissue is an anal canal, the tangential image of the target tissue is an anal canal cross section, and the method further comprises:

And detecting puborectal muscle based on the anal canal cross section, and measuring the thickness of the detected puborectal muscle.

In one embodiment, identifying at least one critical anatomical structure associated with the location of the target tissue from the three-dimensional volumetric data comprises:

And calculating at least one characteristic index of the three-dimensional volume data, and inputting the characteristic index into a model function of the corresponding relation between the characteristic index of the three-dimensional volume data and the key anatomical structure, so as to obtain the corresponding key anatomical structure.

and carrying out image segmentation on the three-dimensional volume data, carrying out morphological feature detection on each region obtained after segmentation to obtain a plurality of candidate regions, judging the probability that each candidate region is a key anatomical structure according to the shape features and/or the gray features, and determining the candidate region with the highest probability as the key anatomical structure.

In one embodiment, generating at least one two-dimensional tangent plane from the prior locations of the critical anatomical structures associated with the location of the target tissue in the three-dimensional volumetric data, identifying at least one critical anatomical structure associated with the location of the target tissue from the two-dimensional tangent plane comprises:

a most similar pair of two-dimensional cut planes is detected on both sides of a prior location of a critical anatomical structure associated with a location of a target tissue in the three-dimensional volumetric data, the critical anatomical structure being identified from a central plane of the pair of two-dimensional cut planes.

In one embodiment, imaging the section of the target tissue to obtain a section image of the target tissue includes:

performing volume rendering imaging on the tangential plane of the target tissue to obtain a volume rendering image of the tangential plane of the target tissue, and/or,

Gray imaging is carried out on the section of the target tissue to obtain a gray image of the section of the target tissue, and/or,

Determining a reference line according to an input instruction of a user, cutting and imaging the key anatomical structure through the reference line to obtain a section image of the target tissue, and/or,

Imaging a section of the target tissue to obtain images of a plurality of parallel sections of the target tissue, and/or,

And performing thick-layer imaging on the section of the target tissue according to the preset imaging thickness to obtain a thick-layer image of the section of the target tissue.

In one embodiment, the critical anatomical structure is a target tissue or a tissue capable of locating a target tissue.

In one embodiment, an ultrasound imaging apparatus is provided, comprising:

An ultrasonic probe for transmitting ultrasonic waves to an object to be imaged to scan the object to be imaged, and receiving ultrasonic echoes returned from the object to be imaged;

a transmitting/receiving circuit for controlling an ultrasonic probe to transmit ultrasonic waves to an object to be imaged and to receive echoes of the ultrasonic waves;

the processor is used for carrying out 3D reconstruction according to the echo of the ultrasonic wave to obtain three-dimensional volume data of the object to be imaged, wherein the object to be imaged comprises a basin bottom;

The processor is also used for identifying at least one key anatomical structure related to 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 tangent plane according to the prior position of the key anatomical structure related to the position of the target tissue in the three-dimensional volume data, identifying at least one key anatomical structure related to the position of the target tissue from the two-dimensional tangent plane and obtaining the spatial position of the key anatomical structure in the three-dimensional volume data;

And the display is used for displaying the section image of the target tissue.

In the ultrasound imaging apparatus of one embodiment, the target tissue is levator ani, and the processor is further configured to:

In the ultrasonic imaging device of one embodiment, the target tissue is an anal canal, the section image of the target tissue is an anal canal cross section, and the processor is further configured to:

In an ultrasound imaging device in one embodiment, the processor identifying from the three-dimensional volumetric data at least one critical anatomical structure associated with a location of a target tissue comprises:

In an ultrasound imaging device in one embodiment, the processor generates at least one two-dimensional tangent plane from a priori locations in the three-dimensional volumetric data of key anatomical structures associated with the location of the target tissue, identifying from the two-dimensional tangent plane the at least one key anatomical structure associated with the location of the target tissue comprises:

In an ultrasound imaging apparatus of one embodiment, the processor imaging a section of the target tissue, the obtaining a section image of the target tissue includes:

In the ultrasound imaging apparatus of one embodiment, the critical anatomical structure is a target tissue or a tissue capable of locating the target tissue.

In one embodiment, an ultrasound imaging apparatus is provided, comprising:

a memory for storing a program;

And a processor for executing the program stored in the memory to implement the method as described above.

In one embodiment, a computer readable storage medium is provided, comprising a program executable by a processor to implement a method as described above.

According to the ultrasonic imaging device and the generating method of the tangential plane image of the basin bottom, three-dimensional volume data of the basin bottom are acquired firstly, at least one key anatomical structure related to the position of target tissue is identified from the three-dimensional volume data, the spatial position of the key anatomical structure in the three-dimensional volume data is obtained, or at least one two-dimensional tangential plane is generated according to the priori position of the key anatomical structure related to the position of the target tissue in the three-dimensional volume data, at least one key anatomical structure related to the position of the target tissue is identified from the two-dimensional tangential plane, the spatial position of the key anatomical structure in the three-dimensional volume data is obtained, and the tangential plane image of the target tissue is obtained by imaging the tangential plane of the target tissue according to the position of the key anatomical structure in the three-dimensional volume data. Therefore, the ultrasonic doctor only needs to complete three-dimensional volume data acquisition of the pelvic floor, so that the section image of the pelvic floor target tissue can be obtained, the operation is simple and convenient, and the working efficiency of the ultrasonic doctor is improved.

Drawings

FIG. 1 is a block diagram of an ultrasound imaging device in one embodiment;

FIG. 2 is a flow chart of a method of generating a slice image of a basin bottom in one embodiment;

FIG. 3 is an ultrasound image of a sagittal section of the basin;

FIG. 4 is an effect diagram of volume rendering imaging of levator ani minimal cleft Kong Qiemian;

FIG. 5 is a graph showing the effect of imaging an arbitrary section of levator ani minimal cleft Kong Qiemian;

FIG. 6 is a graph showing the effect of imaging multiple parallel sections of levator ani minimal cleft Kong Qiemian;

fig. 7 is a schematic view of an image of the levator ani minimum laceration cut in one embodiment.

Detailed Description

The application will be described in further detail below with reference to the drawings by means of specific embodiments. Wherein like elements in different embodiments are numbered alike in association. In the following embodiments, numerous specific details are set forth in order to provide a better understanding of the present application. However, one skilled in the art will readily recognize that some of the features may be omitted, or replaced by other elements, materials, or methods in different situations. In some instances, related operations of the present application have not been shown or described in the specification in order to avoid obscuring the core portions of the present application, and may be unnecessary to persons skilled in the art from a detailed description of the related operations, which may be presented in the description and general knowledge of one skilled in the art.

Furthermore, the described features, operations, or characteristics of the description may be combined in any suitable manner in various embodiments. Also, various steps or acts in the method descriptions may be interchanged or modified in a manner apparent to those of ordinary skill in the art. Thus, the various orders in the description and drawings are for clarity of description of only certain embodiments, and are not meant to be required orders unless otherwise indicated.

The numbering of the components itself, e.g. "first", "second", etc., is used herein merely to distinguish between the described objects and does not have any sequential or technical meaning. The term "coupled" as used herein includes both direct and indirect coupling (coupling), unless otherwise indicated.

The invention automatically detects and identifies key anatomical structures in the three-dimensional volume data of the basin bottom, realizes automatic imaging of the basin bottom based on the key anatomical structures, measures based on the automatic imaging result of the basin bottom, and finally displays the imaging result and the automatic measurement result through a display, thereby realizing automatic imaging and automatic measurement of the section image of the basin bottom and improving the working efficiency of an ultrasonic doctor. The three-dimensional volume data may be three-dimensional volume data acquired by an ultrasonic imaging apparatus, three-dimensional volume data acquired by a nuclear magnetic resonance apparatus, or three-dimensional volume data acquired by an electronic Computed Tomography (CT). The ultrasound imaging apparatus and the method for generating a slice image of the basin bottom thereof will be described in detail below using the ultrasound imaging apparatus as an example.

As shown in fig. 1, the ultrasonic imaging apparatus 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 beam forming module 50, an IQ demodulating module 60, a processor 20, a man-machine interaction device 70, and a memory 80.

The ultrasonic probe 30 includes a transducer (not shown in the figure) composed of a plurality of array elements arranged in an array, the plurality of array elements being arranged in a row to form a linear array, or being arranged in a two-dimensional matrix to form an area array, the plurality of array elements may also form a convex array. The array elements are used for transmitting ultrasonic beams according to the excitation electric signals or converting the received ultrasonic beams into electric signals. Each array element can thus be used to achieve a mutual conversion of the electrical pulse signal and the ultrasound beam, thus achieving an ultrasound transmission to the object to be imaged (e.g. the pelvic floor of the human body in this embodiment), and also to receive echoes of the ultrasound reflected back through the tissue. In performing ultrasonic detection, the transmit circuit 410 and the receive circuit 420 may control which elements are used to transmit ultrasonic beams and which elements are used to receive ultrasonic beams, or control element time slots are used to transmit ultrasonic beams or receive echoes of ultrasonic beams. The array elements participating in the ultrasonic wave transmission can be excited by the electric signals at the same time so as to simultaneously transmit the ultrasonic wave, or the array elements participating in the ultrasonic wave transmission can be excited by a plurality of electric signals with a certain time interval so as to continuously transmit the ultrasonic wave with a certain time interval.

The array elements, for example, employ piezoelectric crystals that convert electrical signals into ultrasound signals in accordance with a transmit sequence transmitted by the transmit circuit 410, which may include one or more scan pulses, one or more reference pulses, one or more push pulses, and/or one or more doppler pulses, depending on the application. Depending on the morphology of the wave, the ultrasonic signal includes a focused wave and a plane wave.

The user selects a proper position and angle by moving the ultrasonic probe 30 to transmit ultrasonic waves to the object to be imaged 10 and receive echoes of the ultrasonic waves returned by the object to be imaged 10, and outputs ultrasonic echo signals, which are analog electrical signals according to channels formed by taking receiving array elements as channels, carrying amplitude information, frequency information and time information.

The transmitting circuit 410 is configured to generate a transmitting sequence according to the control of the processor 20, where the transmitting sequence is configured to control some or all of the plurality of array elements to transmit ultrasonic waves to biological tissue, and the transmitting sequence parameters include an array element position for transmitting, an array element number, and an ultrasonic beam transmitting parameter (such as amplitude, frequency, number of transmitting times, transmitting interval, transmitting angle, waveform, focusing position, etc.). In some cases, the transmitting circuit 410 is further configured to delay the phases of the transmitted beams so that different transmitting elements transmit ultrasound waves at different times, so that each transmitting ultrasound beam can be focused at a predetermined region of interest. Different modes of operation, such as B-image mode, C-image mode, and D-image mode (doppler mode), the transmit sequence parameters may be different, and after the echo signals are received by the receive 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 and blood flow information, and a D-image reflecting the doppler spectrum image may be generated.

The receiving circuit 420 is used for receiving and processing the ultrasonic echo signals from the ultrasonic probe 30. The receive circuitry 420 may include one or more amplifiers, analog-to-digital converters (ADCs), and the like. The amplifier is used for amplifying the received echo signals after proper gain compensation, and the amplifier is used for sampling the analog echo signals at preset time intervals so as to convert the analog echo signals into digitized signals, and the digitized echo signals still retain amplitude information, frequency information and phase information. The data output by the receiving circuit 420 may be output to the beam forming module 50 for processing or output to the memory 80 for storage.

The beam forming module 50 is in signal connection with the receiving circuit 420, and is configured to perform corresponding beam forming processes such as delay and weighted summation on the echo signals, and because distances from the ultrasonic receiving points in the tissue to be measured to the receiving array elements are different, channel data of the same receiving point output by different receiving array elements have delay differences, delay processing is required to be performed, phases are aligned, and weighted summation is performed on different channel data of the same receiving point, so as to obtain beamformed ultrasonic image data, and the ultrasonic image data output by the beam forming module 50 is also referred to as radio frequency data (RF data). The beam forming module 50 outputs the radio frequency data to the IQ demodulation module 60. In some embodiments, the beam forming module 50 may also output the rf data to the memory 80 for buffering or saving, or directly output the rf data to the processor 20 for image processing.

The beam forming module 50 may perform the above-described functions in hardware, firmware, or software, for example, the beam forming module 50 may include a central controller Circuit (CPU), one or more micro-processing chips, or any other electronic component capable of processing input data according to specific logic instructions, which when the beam forming module 50 is implemented in software, may execute instructions stored on tangible and non-transitory computer readable media (e.g., memory) to perform beam forming calculations using any suitable beam forming method.

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

In some embodiments, the IQ demodulation module 60 also outputs IQ data pairs to the memory 80 for buffering or saving so that the processor 20 reads the data from the memory 80 for subsequent image processing.

The IQ demodulation module 60 may also perform the above functions in hardware, firmware or software, and in some embodiments, the IQ demodulation module 60 may also be integrated with the beam forming module 50 in a single chip.

The processor 20 is configured to be a central controller Circuit (CPU), one or more microprocessors, graphics controller circuits (GPU) or any other electronic component capable of processing input data according to specific logic instructions, which may perform control of peripheral electronic components, or data reading and/or saving of memory 80, according to the input instructions or predetermined instructions, and may also perform processing of the input data by executing programs in the memory 80, such as one or more processing operations on the acquired ultrasound data according to one or more modes of operation, including but not limited to adjusting or defining the form of ultrasound emitted by the ultrasound probe 30, generating various image frames for display by a display of a subsequent human-machine interaction device 70, or adjusting or defining the content and form displayed on the display, or adjusting one or more image display settings (e.g., ultrasound images, interface components, locating regions of interest) displayed on the display.

The acquired ultrasound data may be processed by the processor 20 in real time during scanning or therapy as the echo signals are received, or may be temporarily stored on the memory 80 and processed in near real time in an on-line or off-line operation.

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 operate alternately or simultaneously. The processor 20 may also determine an appropriate operation mode according to a user's selection or a program setting, form a transmission sequence corresponding to the current operation mode, and send the transmission sequence to the transmission circuit 410, so that the transmission circuit 410 controls the ultrasound probe 30 to transmit ultrasound waves using the appropriate transmission sequence.

The processor 20 is also operative to process the ultrasound data to generate a gray scale image of the signal intensity variations over the scan range reflecting the anatomy inside the tissue, referred to as the B image. The processor 20 may output the B-image to a display of the human interaction device 70 for display.

The man-machine interaction device 70 is used for performing man-machine interaction, i.e. receiving input and output visual information of a user, wherein the input of the user can be a keyboard, an operation button, a mouse, a track ball, etc., a touch screen integrated with a display can be also adopted, and the output visual information can be a display.

Based on the ultrasonic imaging device shown in fig. 1, the flow of generating the sectional image of the basin bottom is shown in fig. 2, and the method comprises the following steps:

Step 1, the processor 20 performs 3D reconstruction according to the ultrasonic data stored in the memory 80, or performs 3D reconstruction according to the ultrasonic data output by the beam forming module 50, or performs 3D reconstruction according to the ultrasonic data output by the IQ demodulating module 60, so as to obtain three-dimensional volume data (three-dimensional volume data) of the basin bottom, and outputs the three-dimensional volume data to the display of the man-machine interaction device 70 for display.

Step 2, the processor 20 identifies key anatomical structures from the three-dimensional volumetric data. In this embodiment, the target tissue is levator ani, and the key anatomy associated with the target tissue may be the target tissue itself or a tissue capable of locating the target tissue, and in this embodiment, there may be two key anatomies associated with the target tissue, namely the pubic symphysis lower margin (or the surrounding tissue thereof) and the anorectal angle. The identification of the key anatomical structure of the ultrasonic pelvic floor can be an independent coordinate point for the pubic symphysis trailing edge point, and can also comprise/or anatomical structures around the trailing edge point (such as pubic ramus pubis structure of the pubic symphysis trailing edge point, and the like).

The direct identification mode is shown in step 2.1, and comprises the following steps:

The processor 20 identifies at least one critical anatomical structure associated with the location of the target tissue from the three-dimensional volumetric data and derives a spatial location of the critical anatomical structure in the three-dimensional volumetric data. Specifically, the detection of the key anatomical structure can be realized based on a machine learning or deep learning method. For example, at least one characteristic index of the three-dimensional volume data is calculated, the characteristic index is input into a model function of the corresponding relation between the characteristic index of the three-dimensional volume data and the key anatomical structure, and the corresponding key anatomical structure is obtained. The method mainly comprises the following steps:

The step of constructing a database, wherein the database generally comprises a plurality of three-dimensional volume data of ultrasonic basin bottoms and calibration results of key anatomical structures. The calibration result may be set according to the actual task, and may be an ROI (region of interest) frame containing the target, or may be a Mask for precisely dividing the pubic symphysis trailing edge (or/and its surrounding tissue) and the anorectal angle region.

And the positioning and identifying step is to design a machine learning algorithm to learn the characteristics or rules of the target area (key anatomical structure area) and the non-target area (background area) in the database after the database is built so as to realize the positioning and identifying of the image. This implementation step includes, but is not limited to, the following.

The first case can adopt a traditional sliding window-based method, and the common form is that firstly, the characteristic extraction is carried out on the region in the sliding window, the characteristic extraction method can be the traditional PCA, LDA, haar characteristics, texture characteristics and the like, or the characteristic extraction can be carried out by adopting a deep neural network, then the extracted characteristics are matched with a database, the classification is carried out by using a KNN, SVM, random forest, neural network and other discriminators, and whether the current sliding window is the region of interest or not is determined, and the corresponding classification is obtained.

In the second case, a Bounding-Box method based on deep learning can be adopted for detection and identification, and common forms are that characteristic learning and parameter regression are carried out on a constructed database by stacking a base layer convolution layer and a full connection layer, and for an input image, bounding-Box of a corresponding region of interest can be directly regressed through a network, and meanwhile, the category of an organization structure in the region of interest is obtained, wherein the common networks are R-CNN, fast-RCNN, SSD, YOLO and the like.

The third case is a deep learning-based end-to-end semantic segmentation network method, which is similar to the second deep learning-based Bounding-Box structure, and is different in that a full-connection layer is removed, an up-sampling or deconvolution layer is added to enable the input and output sizes to be the same, so that an interested region of an input image and the corresponding category of the interested region are directly obtained, and common networks include FCN, U-Net, mask R-CNN and the like.

The fourth case is to locate the target by adopting the method of the first case, the method of the second case or the method of the third case, and then additionally design a classifier according to the locating result to classify and judge the target. The common classification judging method comprises the steps of firstly extracting the characteristics of a target ROI or Mask, wherein the characteristic extracting method can be the traditional PCA, LDA, haar characteristics, texture characteristics and the like, or can also adopt a deep neural network to extract the characteristics, then matching the extracted characteristics with a database, and classifying the extracted characteristics by using discriminators such as KNN, SVM, random forest, neural network and the like.

The position of key anatomical structures such as the pubic symphysis trailing edge and the anorectal angle in the three-dimensional volume data can be automatically positioned by the machine learning or the deep learning algorithm, so that the standard levator ani muscle minimum split hole area section can be conveniently and subsequently positioned to serve as the basis for subsequent imaging.

In the ultrasound pelvic floor volume data, if the pubic ramus is parallel and symmetrical on both sides, the symmetry plane corresponding to the pubic ramus is a standard median sagittal section, as shown in fig. 3. After the median sagittal section is determined, the echo and surrounding tissues of the pubic symphysis and the anorectal angle show obvious differences, namely the pubic symphysis shows a highlighted ellipse, the fascia at the outer edge of the pubic ramus is a highlighted tissue wrapped around the outer edge of the fascia, the lower edge of the pubic symphysis is positioned at the intersection point of the midline of the pubic ramus and the fascia, and the anorectal angle shows a certain angle when the inspected person is in different action states (rest, anus shrinkage and valsalva), and the angle is generally not more than 180 degrees. Therefore, the detection of the lower edge of the pubic symphysis and the anorectal angle can be realized by adopting the traditional gray level and/or morphology feature detection method. For example, firstly, image segmentation is performed on three-dimensional volume data, specifically binary segmentation is performed, morphological feature detection is performed on each region obtained after segmentation to obtain a plurality of candidate regions, then, each candidate region is judged to be the probability of a key anatomical structure (pubic symphysis lower edge and anorectal angle) according to the shape features and/or gray features, and the candidate region with the highest probability is determined to be the key anatomical structure. Of course, other conventional gray detection and segmentation methods may be used, such as, for example, otsu Threshold (OTSU), level set (LevelSet), graph Cut (Graph Cut), snake, and the like.

The manner of indirect identification is seen in step 2.2 in that the processor 20 generates at least one two-dimensional tangent plane from the a priori position in the three-dimensional volume data of the critical anatomical structure associated with the position of the target tissue, identifies at least one critical anatomical structure associated with the position of the target tissue from the two-dimensional tangent plane, and derives the spatial position of the critical anatomical structure in the three-dimensional volume data. In particular, the processor 20 detects a pair of two-dimensional cuts that are most similar on both sides of the anterior position based on an a priori position in the three-dimensional volumetric data of the critical anatomy associated with the location of the target tissue, and identifies the critical anatomy from a central plane of the pair of two-dimensional cuts. In particular to this embodiment, the processor 20 detects a pair of two-dimensional cuts that are most similar on either side of the sagittal cut from the sagittal cut of the pelvic floor, and identifies the pubic symphysis lower edge and anorectal angle from the central plane of the pair of two-dimensional cuts. If the median sagittal section is directly identified, the ideal median sagittal section cannot be accurately found due to the problem of identification accuracy, but the key anatomical structure can be accurately identified without finding the median sagittal section through symmetrical searching,

The above-described method of identifying key anatomical structures is automatic, but may of course also be performed manually. The manual acquisition of the anatomical structure is that a user informs the type and the position of the key structure of the device based on a certain workflow such as point points, line drawing and the like on a specific anatomical structure in the three-dimensional volume data through tools such as a keyboard, a mouse and the like.

In one embodiment, when identifying the critical anatomy, the pubic symphysis lower edge, two pubic ramus, and anorectal angle may be identified directly from the three-dimensional volumetric data, thereby obtaining the spatial locations of the pubic symphysis lower edge, two pubic ramus, and the anorectal angle in the three-dimensional volumetric data. A tangential plane passing through the lower pubic symphysis and at least a portion of the anorectal angle and parallel to a line passing through two points on the two pubic branches symmetrical with respect to the lower pubic symphysis can then be determined from the spatial locations of the lower pubic symphysis, the two pubic branches and the anorectal angle in the three-dimensional volumetric data, the tangential plane being considered as levator minima Kong Qiemian, and the location of the tangential plane can be taken as the location of the levator minima Kong Qiemian.

In one embodiment, the pubic symphysis inferior edge and anorectal angle may be identified directly from the three-dimensional volumetric data upon identification of the critical anatomy, thereby obtaining the spatial location of the pubic symphysis inferior edge and anorectal angle in the three-dimensional volumetric data. Then, a plurality of tangent planes passing through a connecting line of a preset point on the pubic symphysis lower edge and the anorectal angle can be determined according to the spatial positions of the pubic symphysis lower edge and the anorectal angle in the three-dimensional volume data, and a tangent plane image of the plurality of tangent planes is obtained according to the three-dimensional volume data. Then, according to the image data of the section images of the plurality of section images, symmetry of image areas (all or part of image areas) located on two sides of a connecting line of the pubic symphysis lower edge and the preset point in each section image can be determined, and the section of the section image with symmetry meeting the preset condition is regarded as levator ani minimum crack Kong Qiemian, so that the position of the section image with symmetry meeting the preset condition can be determined as the position of levani minimum crack Kong Qiemian. Here, the "predetermined condition" may be set according to actual conditions. For example, in one embodiment, the predetermined condition may be set to "symmetry is maximum". In another embodiment, the predetermined condition may be set such that the symmetry is greater than a specific value, the symmetry is less than a specific value, or the symmetry is within a specific range, and so on. The method for determining the symmetry of the image area may use a conventional method, and will not be described herein.

And 3, imaging the section of the target tissue by the processor 20 based on the position of the key anatomical structure in the three-dimensional volume data to obtain a section image of the target tissue, and displaying the section image of the target tissue through a display. For example, after identifying the inferior pubic symphysis and anorectal angle from fig. 3, the three-dimensional volumetric data is sectioned with a plane that intersects the plane of fig. 3 at a line that passes through the inferior pubic symphysis and anorectal angle to obtain the desired levator ani minimum crack Kong Qiemian, as shown by the line of fig. 3. The sectional image of the target tissue may be presented in a volume rendering imaging manner, a cross-sectional imaging manner, an arbitrary cross-sectional (planar or curved) imaging manner, multiple parallel plane imaging and cross-sectional imaging manner, an arbitrary cross-sectional (planar or curved) imaging manner, a combination of multiple parallel plane imaging and thick layer imaging manner.

Volume rendering imaging is based on the detection of critical anatomy in three-dimensional volume data to adjust the position, size, and curvature of the imaging curve of the volume of interest (Volume of Interest, VOI) to display an levator ani muscle split Kong Xuanran image. The profile imaging is to adjust the position of the profile in space based on the key anatomy detected in the three-dimensional volumetric data to generate an levator ani muscle split hole profile image. The imaging of any section (plane or curved surface) is to generate a reference line (straight line or curve) based on the key anatomical structure detected in the three-dimensional volume data, and obtain the minimum levator ani muscle crack Kong Qiemian through the reference line, and the imaging of multiple parallel planes is based on the key anatomical part detected, and realizes the imaging of multiple parallel sections at equal intervals by taking the section of the minimum levator muscle crack area as a reference.

The effect of processor 20 volume rendering the cut plane of minimum split area of levator ani is shown in fig. 4. For three-dimensional stereo imaging, the volume rendering imaging is to display three-dimensional volume data in the VOI frame a through different imaging modes by adopting algorithms such as ray tracing and the like. The acquisition of good volume rendered images requires the setting of the size and position of VOI box a in addition to the need to adjust the orientation of the volume data. For ultrasonic pelvic floor three-dimensional volume data, after anatomical structures such as pubic symphysis and anorectal angle are detected, the whole data azimuth can be automatically adjusted according to specific positions of the pubic symphysis lower edge and the anorectal angle, so that the pubic symphysis lower edge and the anorectal angle are positioned at the same horizontal position, and a VOI imaging curve is overlapped with the straight line of the pubic symphysis lower edge and the anorectal angle as far as possible. And meanwhile, the VOI frame a is adjusted to a proper size (generally 2.5 mm), so that the minimum split Kong Qiemian of levator ani can be rendered, as shown in the lower right corner diagram of fig. 5.

The processor 20 performs gray level imaging on the section of the minimum split area of levator ani muscle, wherein the section image refers to the section image at a specific position and direction in the three-dimensional volume data, and the section images at different positions and directions can be obtained by adjusting rotation and translation. Based on the anatomical structures such as the pubic symphysis lower edge, the anorectal angle and the like detected in the three-dimensional volume data, the standard section of the minimum split hole area of the levator ani muscle can be directly obtained through plane imaging. Typically, levator ani minimal cleft Kong Qiemian is a two-dimensional cut through the inferior pubic symphysis margin and the anorectal angle, so that by detecting the critical anatomical location in the three-dimensional volume data from the previous step, a plane can be created that passes (or approximately passes) through the inferior pubic symphysis margin and the section where the anorectal angle is located. The plane equation can be obtained by solving or fitting the equation, and after the plane equation is obtained, a gray-scale image corresponding to the plane can be taken out from the three-dimensional volume data, so that the section with the minimum split hole area of levator ani muscle is obtained. Based on the automatic imaging, the user can also manually fine-tune the tangent plane position of the levator ani split hole based on the position of the pubic symphysis lower edge and the anorectal angle in the three-dimensional volumetric data.

The processor 20 automatically images any section of the area of the minimum split hole of the levator ani muscle, namely, the minimum split Kong Qiemian of the levani muscle can be displayed by using any section imaging besides the three-dimensional reconstruction of a volume rendering imaging chart, and the concrete expression form is shown in figure 5. Any section imaging is to take one or more reference lines (straight lines or curves, straight lines in fig. 5) from a certain section of the three-dimensional volume data, form a section (plane or curved surface) with the three-dimensional volume data by the reference lines, take the section out and straighten the section into a plane for display. Typically the formation of the levator ani minimum split cut places the reference line in a straight line formed by the inferior pubic symphysis and the anorectal angle. After the key anatomical structures such as the pubic symphysis lower edge and the anorectal angle are obtained through the automatic identification method, the imaging straight line can be placed on the straight line formed by the two anatomical positions, and automatic levator ani muscle minimal cleft Kong Renyi section imaging is achieved. Of course, the section of the minimum fracture area of the levator ani muscle can also be obtained manually, for example, a reference line is determined according to an input instruction of a user, and a key anatomical structure is dissected and imaged through the reference line to obtain the section of the minimum fracture area of the levani muscle.

Processor 20 automatically images the section of the levator ani muscle at the minimum split area multiple parallel sections, typically during the ultrasound clinical exam, the ultrasound clinician needs to view the levator ani muscle split area based on multiple parallel sections to obtain more comprehensive diagnostic information. The multi-parallel tangent plane imaging refers to an imaging mode of simultaneously displaying a plurality of parallel tangent planes, the distances between adjacent tangent planes are equal, and a user can adjust the distance between the parallel planes. After key anatomical parts such as pubic symphysis and anorectal angle are detected, the minimum split Kong Qiemian of levator ani can be obtained by the automatic imaging method of the section of the minimum split area of levator ani, and then equidistant multi-section parallel imaging is carried out on levani by taking the section as a reference, as shown in fig. 6. The user can change the position of the reference section or reselect the reference section according to the actual situation. Meanwhile, the spacing between frames can be fixed at equal intervals, and can be automatically or manually adjusted according to actual conditions.

The processor 20 combines the above-mentioned cross-section imaging, arbitrary cross-section imaging, and multiple parallel cross-section imaging with thick layer imaging, respectively, and the imaging mode of levator ani muscle split Kong Qiemian can also be used in combination with thick layer imaging in addition to the above-mentioned four methods. Thick layer imaging refers to adding a certain thickness to a tomographic gray-scale image and displaying the tomographic gray-scale image in a surface mode, an X-ray mode or a fusion mode of the tomographic gray-scale image and the tomographic gray-scale image. Wherein the thickness may be a preset imaging thickness. This mode can effectively enhance the contrast resolution of the image, enhancing the display for critical anatomy and features, but attenuating image details. Meanwhile, the thickness of the thick-layer imaging image can be set to a fixed value (such as 2.5 mm) according to actual clinical requirements, or the thickness parameter can be adjusted in a self-adaptive mode according to actual anatomical structures and characteristics, and a user can manually set the parameter based on personal requirements and operation habits.

During ultrasonic scanning, after the section with the smallest split hole area of levator ani muscle is scanned, the ultrasonic probe is rotated by 90 degrees and is inclined backwards and downwards, so that the cross section of the anal canal can be completely displayed. Thus, after the processor 20 obtains the levator ani minimum split area tangent plane, a tangent plane image of the anal canal cross section may be generated based on this positional relationship between the anal canal cross section and the levator ani minimum split area tangent plane. Of course, the target tissue can be set as the anal canal, and the process of obtaining the tangent plane image of the cross section of the anal canal by adopting the method is similar to the process of obtaining the tangent plane of the minimum split area of levator ani muscle, so that the description is omitted. The imaging method of the puborectal muscle section is consistent with the imaging method of the anal levator minimum laceration area section, namely after the critical anatomical part related to the anal sphincter is detected, puborectal muscle imaging can be carried out in various modes, namely, the puborectal muscle section volume rendering automatic imaging, section imaging, arbitrary section (plane or curved surface) imaging, multi-parallel plane imager section imaging, arbitrary section (plane or curved surface) imaging and the combination of a plurality of parallel plane imaging and thick layer imaging respectively.

The method has the advantages that under the condition that the image quality is poor and the position of a key anatomical structure detected through an algorithm is deviated, a user can also carry out modification operations such as moving, zooming, deleting and recalibrating on a VOI region or an arbitrary section imaging curve in the detected section through tools such as a keyboard, a mouse and the like, semi-automatic VOI imaging or arbitrary section imaging is realized, and for basin bottom corresponding standard section plane imaging and a plurality of parallel section imaging, the user can also adjust the section through a knob.

And 4, measuring the section image of the target tissue. After obtaining the minimum levator ani crack Kong Qiemian, the doctor typically needs to make a measurement of the relevant measurement on the corresponding section in order to quantitatively evaluate prolapse and tear of the pelvic floor organ. However, the measurement items are often complicated, the measurement process is time-consuming and labor-consuming, and meanwhile, the requirements on the experience and the manipulation of doctors are very high, so that the robustness and the accuracy of the measurement result are difficult to ensure. Therefore, based on the basin undercut surface obtained in the foregoing, it is important to realize intelligent measurement of the corresponding measurement items.

Based on the levator ani minimum laceration Kong Qiemian, two items are conventionally required to be measured by an ultrasonic clinician at the present stage, namely the minimum laceration hole area of levani and the distance from the urethral orifice to the leftmost levani and rightmost levani. For volume rendering imaging section, section imaging section and arbitrary section imaging section, intelligent measurement of the two measurement items is realized on a single frame image, and for multiple parallel section imaging, intelligent measurement of one or more frames of images is required, wherein the selection of the measurement frames and the frame numbers meets the requirement of a user, and the default setting is the middle continuous three-frame image of FIG. 6.

Therefore, in the present embodiment, step 4 includes the processor 20 detecting levator ani based on the tangent plane image of levator ani (levator ani minimum split Kong Qiemian), performing area statistics on the detected levani to obtain the minimum split area of levani, detecting levani and urethral orifice based on the tangent plane image of levani, and measuring the distance from the urethral orifice to the leftmost levani and the distance from the urethral orifice to the rightmost levani.

Specifically, the processor 20 identifies the target to be measured, such as levator ani, based on a conventional gray scale and/or morphology target segmentation method, and further performs measurement, wherein the levator ani presents a high-brightness muscle fiber acoustic bundle at levator ani crack Kong Qiemian, and the ultrasonic imaging characteristics are obviously different from surrounding anatomical structures. So similar to the foregoing approach to critical anatomy detection, the processor 20 employs conventional gray scale and/or morphology feature detection and segmentation methods to achieve detection and segmentation of levator ani muscle. For example, firstly, performing binary segmentation on an levator ani split hole tangential plane image, obtaining a plurality of candidate areas through some necessary morphological operations, then judging the probability that the area is levani according to the characteristics of shape, gray brightness and the like for each candidate area, and selecting an area with the highest probability as a target segmentation area. Of course, other conventional gray detection and segmentation methods may be used, such as, for example, otsu Threshold (OTSU), level set (LevelSet), graph Cut (Graph Cut), snake, and the like.

The processor 20 may also identify the target to be measured, such as levator ani, based on a target segmentation method such as machine learning or deep learning, and further measure, in addition to the above-described conventional image segmentation method, the segmentation of levator ani may also be implemented based on a target segmentation method such as machine learning and deep learning, similar to the above-described target detection method. The segmentation method may refer to the third and fourth cases in the corresponding target detection methods. The method can directly segment levator ani muscles based on deep learning end-to-end semantic segmentation networks, can position targets based on end-to-end network segmentation, and can additionally design a classifier according to positioning results to classify and interpret the targets at pixel level, so that levani muscle segmentation is realized in two steps. These two ideas are similar to those of the foregoing target detection method, and are not described in detail herein.

After the levator ani is segmented, other measurements can be calculated based on levator ani split Kong Qiemian. Such as the distance from the urethral orifice to the leftmost side of the levator ani muscle, and the distance from the urethral orifice to the rightmost side of the levani muscle. It should be specifically noted that, the automatic measurement of the measurement item requires the algorithm system to automatically detect the urethral orifice, and the automatic detection method is consistent with the above automatic detection method of the key anatomical structure, and will not be described herein.

In one embodiment, the outline of the levator ani muscle or the minimum split hole of the levator ani muscle can be extracted from the image of the minimum split hole of the levani muscle, and the distance between the upper and lower radial lines of the levani muscle and/or the distance between the left and right radial lines of the levani muscle can be calculated according to the outline. As shown in fig. 7, a is the outline of the extracted levator ani or the minimal cleft hole of levator ani, B is the left and right radial line of levator ani, and C is the up and down radial line of levator ani. Here, the distance between the upper and lower radial lines may be the length of the upper and lower radial line C, and the distance between the left and right radial lines may be the length of the left and right radial line B.

In embodiments where the target tissue is the anal canal, the image of the tangential plane of the target tissue is the anal canal cross-section. The processor 20 detects puborectal muscle based on the anal canal cross-section and measures the thickness of the detected puborectal muscle. Specifically, processor 20 measures puborectal muscle thickness based on a plurality of parallel cuts of the puborectal muscle. The thickness measurement is to continuously measure three times in the corresponding peripheral area of the same frame image, correspondingly display each measurement result and average. The selection of the measurement frames, the frame numbers and the measurement times satisfies the requirement that the user sets based on the requirement, and the default is to take three measurement results for the intermediate frames. The target tissue is an anal canal embodiment, the automatic measurement process is similar to that of the levator ani embodiment, and only the detected objects are different, so that the description is omitted.

The measurement of the measurement items can be fully automatic or semi-automatic. Semi-automated measurement is a process that satisfies the requirement that a user can set one or more input points on a corresponding interface, and based on the input points, a corresponding measurement result is obtained. Meanwhile, under the condition that the image quality is poor and the measurement result obtained through the intelligent algorithm has deviation, a user can delete, modify, re-input and other modification operations on the result through a keyboard, a mouse and other tools.

Step 5, the processor 20 displays the section image of the target tissue and the measurement result thereof through the display of the man-machine interaction device 70. The doctor may need to measure different target tissues, so a certain workflow can be preset, the selection function of the doctor on the target tissues is integrated into the workflow, the doctor can select freely, and the image and the measurement result corresponding to the selected function are displayed in the display.

In summary, the ultrasonic imaging device and the method for generating the section image of the basin bottom thereof provided by the invention not only can automatically generate the section of the target tissue of the basin, but also can perform corresponding measurement, thereby greatly improving the working efficiency of an ultrasonic doctor.

Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments may be implemented by hardware, or may be implemented by a computer program. When all or part of the functions in the above embodiments are implemented by means of a computer program, the program may be stored in a computer-readable storage medium, which may include a read-only memory, a random access memory, a magnetic disk, an optical disk, a hard disk, etc., and the program is executed by a computer to implement the 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 functions described above can be realized. In addition, when all or part of the functions in the above embodiments are implemented by means of a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and the program in the above embodiments may be implemented by downloading or copying the program into a memory of a local device or updating a version of a system of the local device, and when the program in the memory is executed by a processor.

Reference is made to various exemplary embodiments herein. However, those skilled in the art will recognize that changes and modifications may be made to the exemplary embodiments without departing from the scope herein. For example, the various operational steps and components used to perform the operational steps may be implemented in different ways (e.g., one or more steps may be deleted, modified, or combined into other steps) depending on the particular application or taking into account any number of cost functions associated with the operation of the system.

Additionally, as will be appreciated by one of skill in the art, the principles herein may be reflected in a computer program product on a computer readable storage medium preloaded with computer readable program code. Any tangible, non-transitory 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, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions which execute on the computer or other programmable data processing apparatus create means for implementing the functions specified. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including means which implement the function specified. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified.

While the principles herein have been shown in various embodiments, many modifications of structure, arrangement, proportions, elements, materials, and components, which are particularly adapted to specific environments and operative requirements, may be used without departing from the principles and scope of the present disclosure. The above modifications and other changes or modifications are intended to be included within the scope of this document.

The foregoing detailed description has been described with reference to various embodiments. However, those skilled in the art will recognize that various modifications and changes may be made without departing from the scope of the present disclosure. Accordingly, the present disclosure is to be considered as illustrative and not restrictive in character, and all such modifications are intended to be included within the scope thereof. Also, advantages, other advantages, and solutions to problems have been described above with regard to various embodiments. The benefits, advantages, solutions to problems, and any element(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, system, article, or apparatus. Furthermore, the term "couple" and any other variants thereof are used herein to refer to physical connections, electrical connections, magnetic connections, optical connections, communication connections, functional connections, and/or any other connection.

Those skilled in the art will recognize that many changes may be made to the details of the above-described embodiments without departing from the underlying principles of the invention. Accordingly, the scope of the invention should be determined from the following claims.

Claims

1. A method for generating a tangential image of a basin bottom is characterized by comprising the following steps:

acquiring three-dimensional volume data of the basin bottom;

Obtaining a reference line in an levator ani tangent plane image from the three-dimensional volume data, wherein the reference line passes through at least a part of the lower edge of the pubic symphysis and the anorectal angle;

The reference line and the three-dimensional volume data form a tangent plane to acquire the minimum crack Kong Qiemian image of the levator ani muscle;

measuring the area of the minimum split hole of the levator ani according to the obtained minimum split Kong Qiemian image of the levator ani;

And/or

Detecting levator ani muscles and a urethral opening in the image of the minimum split hole tangential plane of levator ani muscles, and measuring the distance from the urethral opening to the leftmost levani muscles and/or the distance from the urethral opening to the rightmost levani muscles according to the detected levani muscles and the urethral opening;

And/or

Extracting the levator ani muscle or the outline of the minimum split hole of the levator ani muscle from the image of the section of the minimum split hole of the levator ani muscle, and calculating the distance between the upper and lower radial lines of the levator ani muscle and/or the distance between the left and right radial lines of the levani muscle according to the outline.

2. The method of claim 1, wherein obtaining a reference line in an image of an levator ani muscle cut from the three-dimensional volumetric data comprises:

Identifying from the three-dimensional volume data at least a portion of the pubic symphysis trailing edge and the anorectal angle, obtaining a spatial location of the pubic symphysis trailing edge and at least a portion of the anorectal angle in the three-dimensional volume data;

A reference line in the levator ani tangent plane image is acquired based on the spatial location of the pubic symphysis trailing edge and at least a portion of the anorectal angle in the three-dimensional volumetric data.

3. The method of claim 2, wherein identifying a pubic symphysis trailing edge from the three-dimensional volumetric data comprises:

Calculating at least one characteristic index of the three-dimensional volume data, inputting the characteristic index into a model function of the corresponding relation between the characteristic index of the three-dimensional volume data and the pubic symphysis trailing edge, and obtaining the corresponding pubic symphysis trailing edge, or

And performing target detection or image segmentation on the three-dimensional volume data, performing morphological feature detection on each region obtained after detection or segmentation to obtain a plurality of candidate regions, judging that each candidate region is the pubic symphysis lower edge according to the shape features and/or the gray features, and determining the candidate region with the highest probability as the pubic symphysis lower edge.

4. The method of claim 2, wherein identifying at least a portion of an anorectal angle from the three dimensional volumetric data comprises:

calculating at least one characteristic index of the three-dimensional volume data, inputting the characteristic index into a model function of the corresponding relation between the characteristic index of the three-dimensional volume data and at least one part of the anorectal angle, and obtaining at least one part of the corresponding anorectal angle, or

And carrying out target detection or image segmentation on the three-dimensional volume data, carrying out morphological feature detection on each region obtained after detection or segmentation to obtain a plurality of candidate regions, judging the probability that each candidate region is at least one part of the anorectal angle according to the shape features and/or the gray features, and determining the candidate region with the highest probability as at least one part of the anorectal angle.

5. A method as recited in claim 2, wherein identifying at least a portion of a pubic symphysis trailing edge and an anorectal angle from the three-dimensional volumetric data, obtaining a spatial location of the pubic symphysis trailing edge and at least a portion of the anorectal angle in the three-dimensional volumetric data, comprises:

directly identifying the spatial location of at least a portion of the pubic symphysis trailing edge and anorectal angle in the three-dimensional volumetric data from the three-dimensional volumetric data, or

Generating at least one two-dimensional tangent plane according to the priori positions of the pubic symphysis lower edge and at least one part of the anorectal angle in the three-dimensional volume data, identifying the pubic symphysis lower edge and at least one part of the anorectal angle from the two-dimensional tangent plane, and obtaining the spatial positions of the pubic symphysis lower edge and at least one part of the anorectal angle in the three-dimensional volume data.

6. The method of claim 1, wherein obtaining a reference line in an image of an levator ani muscle cut from the three-dimensional volumetric data comprises:

Acquiring an levator ani sagittal plane section image from the three-dimensional volume data, identifying the pubic symphysis trailing lower edge and at least a portion of the anorectal angle in the levator ani sagittal plane section image;

A reference line in the levator ani sagittal plane section image is acquired based on the identified pubic symphysis trailing edge and at least a portion of an anorectal angle.

7. The method of claim 6, wherein the acquiring a reference line in the levator ani sagittal plane section image based on the identified at least a portion of the pubic symphysis trailing edge and anorectal angle comprises:

responding to the operation instruction of the user on the identified pubic symphysis trailing edge and at least one part of anorectal angle, acquiring a reference line in the levator ani tangent plane image from the levator ani sagittal plane tangent plane image according to the operation instruction of the user, and/or

And automatically acquiring a reference line in an levator ani tangent plane image based on the identified pubic symphysis trailing edge and at least a portion of an anorectal angle.

8. An ultrasonic imaging apparatus, characterized by comprising:

The processor is also used for

And/or

Extracting the levator ani muscle or the outline of the minimum split hole of the levator ani muscle from the image of the section of the minimum split hole of the levator ani muscle, and calculating the distance between the upper and lower radial lines of the levator ani muscle and/or the distance between the left and right radial lines of the levani muscle according to the outline;

And the display is used for displaying the image of the minimum split hole section of the levator ani muscle.

9. The apparatus of claim 8, wherein the processor is configured to obtain a reference line in an levator ani tangent plane image from the three-dimensional volumetric data, comprising:

the processor identifies at least a portion of the pubic symphysis trailing edge and the anorectal angle from the three-dimensional volumetric data, and obtains a spatial location of the pubic symphysis trailing edge and at least a portion of the anorectal angle in the three-dimensional volumetric data;

10. The apparatus as recited in claim 9, wherein the processor is configured to identify at least a portion of a pubic symphysis trailing edge and an anorectal angle from the three-dimensional volumetric data, and to obtain a spatial location of the pubic symphysis trailing edge and at least a portion of the anorectal angle in the three-dimensional volumetric data, comprising:

The processor is used for directly identifying the spatial positions of the pubic symphysis lower edge and at least one part of the anorectal angle in the three-dimensional volume data or

The processing is configured to generate at least one two-dimensional tangent plane from prior locations of the pubic symphysis trailing edge and at least a portion of the anorectal angle in the three-dimensional volumetric data, identify the pubic symphysis and anorectal angle from the two-dimensional tangent plane, and obtain spatial locations of the pubic symphysis trailing edge and at least a portion of the anorectal angle in the three-dimensional volumetric data.

11. The identification of claim 10 wherein the processor is configured to obtain a reference line in an levator ani muscle cut plane image from the three-dimensional volumetric data, comprising:

the processor acquires an levator ani sagittal plane section image from the three-dimensional volume data, and identifies at least a part of the pubic symphysis trailing edge and the anorectal angle in the levator ani sagittal plane section image;

12. The apparatus of claim 11, wherein the processor is configured to obtain a reference line in the levator ani sagittal plane section image based on the identified pubic symphysis trailing edge and at least a portion of an anorectal angle, comprising:

the processor is used for responding to the operation instruction of a user on at least one part of the identified pubic symphysis trailing edge and anorectal angle, acquiring a reference line in the levator ani muscle section image from the levator ani muscle sagittal plane section image according to the operation instruction of the user, and/or

The processor automatically acquires a reference line in an levator ani tangent plane image based on the identified pubic symphysis trailing edge and at least a portion of an anorectal angle.

13. An ultrasonic imaging apparatus, characterized by comprising:

a memory for storing a program;

a processor for executing a program stored in the memory to implement the method of any one of claims 1-7.

14. A computer readable storage medium comprising a program executable by a processor to implement the method of any one of claims 1-7.