Ultrasonic pelvic floor imaging method and ultrasonic imaging system
Through ultrasonic probes, transmit and receive waves, process signals, and use machine learning to identify levator anal tear, solving the problem that ultrasonic pelvic floor examinations are difficult to accurately identify levator anal tear in the existing technology, and achieving an efficient and accurate examination process .
Patent Information
- Application Number
- CN202110642554.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-06-09
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2041-06-09
AI Technical Summary
Existing ultrasound pelvic floor examination technology is difficult to accurately identify levator anal muscle tear, and users need to manually adjust the ultrasound probe, which is time-consuming and labor-intensive, and is prone to missed diagnosis and misdiagnosis.
By controlling the ultrasound probe to transmit ultrasound waves to the pelvic floor, receiving echo signals, performing signal processing to obtain ultrasound body data, extracting standard pelvic floor sagittal plane, determining the reference line to generate fault sections, and automatically identifying levator anal tear using machine learning models Cracking area, mark its location.
Significantly reduce user manual operations, improve the efficiency and accuracy of levator anal muscle tear examination, and reduce the occurrence of missed diagnosis and misdiagnosis.
Smart Images

Figure CN113229850B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of ultrasonic imaging, and more specifically to an ultrasonic pelvic floor imaging method and an ultrasonic imaging system. Background Art
[0002] In modern medical imaging, ultrasound technology has become the most widely used, most frequently used and fastest-growing new technology due to its high reliability, fast and convenient, real-time imaging and repeatable examination. The development of artificial intelligence-assisted technology has further promoted the application of ultrasound technology in clinical diagnosis and treatment. The intelligent development of ultrasound equipment can help doctors improve the efficiency of examinations, balance the gap between hospitals in different regions, and provide patients with more accurate diagnoses and personalized treatment plans.
[0003] Stress urinary incontinence and pelvic organ prolapse are common chronic diseases that affect women's physical and mental health, seriously affecting women's work and social activities as well as their physical and mental health. Among them, levator ani muscle tears are often one of the main causes of such diseases. Pelvic floor ultrasound examination plays an important role in the diagnosis of pelvic floor diseases. At present, it is mainly performed through tomographic imaging on 3D / 4D ultrasound in clinical practice. Users are usually required to manually align the pelvic floor ultrasound volume data, and then observe and mark the location of the tear and measure it one by one. However, the structure of the female pelvic floor is complex. In order to obtain a standard tomographic section, users usually need to repeatedly perform rotation and translation adjustments, which is time-consuming and laborious. At the same time, the identification of levator ani muscle tears is clinically difficult, and the confirmation of the tear location is highly dependent on the doctor's experience, which is prone to missed diagnosis and misdiagnosis. Summary of the invention
[0004] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.
[0005] An embodiment of the present invention provides, on one hand, a method for ultrasonic pelvic floor imaging, the method comprising:
[0006] Controlling the ultrasonic probe to transmit ultrasonic waves to the pelvic floor of the subject to be measured, and receiving echoes of the ultrasonic waves to obtain ultrasonic echo signals;
[0007] Performing signal processing on the ultrasonic echo signal to obtain ultrasonic volume data of the pelvic floor;
[0008] Extracting a standard pelvic floor sagittal plane based on the ultrasound volume data;
[0009] Determine a plurality of reference lines in the standard pelvic floor sagittal plane, and generate and display a plurality of corresponding standard pelvic floor fault sections according to the plurality of reference lines;
[0010] It is detected whether there is a levator ani muscle tear region in the plurality of standard pelvic floor tomographic sections, and the position of the levator ani muscle tear region is marked in the standard pelvic floor tomographic section where the levator ani muscle tear region exists.
[0011] In one embodiment, determining the target position based on the ultrasound volume data comprises:
[0012] Detecting a region of a target characteristic structure in the ultrasound volume data, wherein the target characteristic structure includes at least one of the following: anal levator hiatus, anorectal angle, pubic ramus structure, and anal canal structure;
[0013] The angle by which the ultrasound volume data needs to be rotated and / or the distance by which it needs to be translated is determined according to the position of at least one region of the target characteristic structure, or the angle by which the ultrasound volume data needs to be rotated and / or the distance by which it needs to be translated is determined according to the relative positional relationship between at least two regions of the target characteristic structure.
[0014] In one embodiment, determining the target orientation based on the ultrasound volume data includes: inputting the ultrasound volume data into a trained machine learning model, and outputting the angle at which the ultrasound volume data needs to be rotated and / or the distance at which it needs to be translated.
[0015] In one embodiment, the method further includes: extracting a standard pelvic floor coronal plane and a standard pelvic floor cross-section from the ultrasound volume data transformed to the target orientation; and displaying the standard pelvic floor sagittal plane, the standard pelvic floor coronal plane, and the standard pelvic floor cross-section.
[0016] In one embodiment, the determining of multiple reference lines in the standard pelvic floor sagittal plane includes: detecting an area of a pubic symphysis inferior edge point and an anorectal angle point in the standard pelvic floor sagittal plane; using a line connecting the area of a pubic symphysis inferior edge point and the area of anorectal angle point as a first reference line, generating multiple second reference lines at equal intervals on both sides of the first reference line, and using the first reference line and the second reference line as the multiple reference lines.
[0017] In one embodiment, determining multiple reference lines in the standard pelvic floor sagittal plane includes: using the horizontal center line of the standard pelvic floor sagittal plane as a first reference line, generating multiple second reference lines at equal intervals on both sides of the first reference line, and using the first reference line and the second reference line as the multiple reference lines.
[0018] In one embodiment, detecting whether there is a levator ani muscle tear area in the multiple standard pelvic floor tomographic sections includes: extracting image features of the standard pelvic floor tomographic sections; classifying the image features, and determining whether there is a levator ani muscle tear area in the standard pelvic floor tomographic sections based on the classification results.
[0019] In one embodiment, the detecting whether there is a levator ani muscle tear area in the multiple standard pelvic floor tomographic sections includes: detecting the area of the urethral orifice point and the area of the bilateral levator ani muscle attachment points in the standard pelvic floor tomographic section; obtaining the distance between the area of the urethral orifice point and the area of the levator ani muscle attachment points; if the distance exceeds a preset threshold, determining that there is a levator ani muscle tear area in the standard pelvic floor tomographic section.
[0020] In one embodiment, the method further comprises: when determining that there is a levator ani muscle tear region in the standard pelvic floor section, displaying the distance between the region of the urethral meatus point and the region of the bilateral levator ani muscle attachment points.
[0021] In one embodiment, the method further comprises: when it is determined that there is a levator ani muscle tear region in the standard pelvic floor tomographic section, generating and displaying a sagittal plane, a coronal plane and / or a cross-section of the levator ani muscle tear region.
[0022] In one embodiment, when it is determined that there is a levator ani muscle tear area in the standard pelvic floor tomographic section, the method also includes: determining a first target reference line corresponding to the standard pelvic floor tomographic section where the levator ani muscle tear area exists among the multiple reference lines; based on the first target reference line, generating multiple second target reference lines in the standard pelvic floor sagittal plane; based on the multiple second target reference lines, generating and displaying multiple tomographic sections.
[0023] In one embodiment, the method further comprises: adjusting the position of the mark of the levator ani tear area according to a received user instruction.
[0024] Another aspect of an embodiment of the present invention provides a method for ultrasonic pelvic floor imaging, the method comprising:
[0025] Controlling the ultrasonic probe to transmit ultrasonic waves to the pelvic floor of the subject to be measured, and receiving echoes of the ultrasonic waves to obtain ultrasonic echo signals;
[0026] Performing signal processing on the ultrasonic echo signal to obtain ultrasonic volume data of the pelvic floor;
[0027] Determine a target position based on the ultrasound volume data, and transform the ultrasound volume data to the target position;
[0028] extracting a standard pelvic floor sagittal plane from the ultrasound volume data transformed to the target orientation;
[0029] Determine a plurality of reference lines in the standard pelvic floor sagittal plane, and generate a plurality of corresponding standard pelvic floor fault sections according to the plurality of reference lines;
[0030] Detecting whether there is a levator ani muscle tear area in the multiple standard pelvic floor section planes;
[0031] The standard pelvic floor tomographic section showing the levator ani muscle tear area is displayed, and the position of the levator ani muscle tear area is marked in the standard pelvic floor tomographic section showing the levator ani muscle tear area.
[0032] In one embodiment, the method further comprises: when it is determined that there is a levator ani muscle tear region in the standard pelvic floor tomographic section, generating and displaying a sagittal plane, a coronal plane and / or a cross-section of the levator ani muscle tear region.
[0033] In one embodiment, when it is determined that there is a levator ani muscle tear area in the standard pelvic floor tomographic section, the method also includes: determining a first target reference line corresponding to the standard pelvic floor tomographic section where the levator ani muscle tear area exists among the multiple reference lines; based on the first target reference line, generating multiple second target reference lines in the standard pelvic floor sagittal plane; based on the multiple second target reference lines, generating and displaying multiple tomographic sections.
[0034] Another aspect of an embodiment of the present invention provides an ultrasound imaging system, comprising:
[0035] Ultrasound probe;
[0036] A transmitting circuit, used for stimulating the ultrasonic probe to transmit ultrasonic waves to the pelvic floor of the subject;
[0037] A receiving circuit, used for controlling the ultrasonic probe to receive the ultrasonic echo to obtain an ultrasonic echo signal;
[0038] A processor, configured to execute the steps of the ultrasonic pelvic floor imaging method as described above;
[0039] A display is used to display the ultrasound image obtained by the processor.
[0040] The ultrasonic imaging system and ultrasonic pelvic floor imaging method of the embodiments of the present invention can automatically generate multiple standard pelvic floor tomographic sections, automatically identify and display the levator ani muscle tear area based on the multiple standard pelvic floor tomographic sections, greatly reduce the user's manual operation, and improve the efficiency and accuracy of levator ani muscle tear inspection. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] The above and other purposes, features and advantages of the present application will become more apparent by describing the embodiments of the present invention in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.
[0042] Figure 1 A structural block diagram of an ultrasound imaging system according to an embodiment of the present invention is shown;
[0043] Figure 2 A schematic flow chart showing an ultrasonic pelvic floor imaging method according to an embodiment of the present invention;
[0044] Figure 3 A schematic diagram showing a standard pelvic floor sagittal plane, a standard pelvic floor coronal plane, and a standard pelvic floor cross section according to one embodiment of the present invention;
[0045] Figure 4 A schematic diagram showing a plurality of reference lines generated in a standard pelvic floor sagittal plane according to one embodiment of the present invention;
[0046] Figure 5 According to one embodiment of the present invention, Figure 4 Schematic diagram of multiple standard pelvic floor fault sections generated by the reference lines shown;
[0047] Figure 6 A schematic diagram showing marking of a levator ani muscle tear region according to one embodiment of the present invention;
[0048] Figure 7 A schematic diagram showing marking of a tear area of the levator ani muscle according to another embodiment of the present invention;
[0049] Figure 8 A schematic flow chart of an ultrasonic pelvic floor imaging method according to another embodiment of the present invention is shown. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solutions and advantages of the present application more obvious, the example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present invention described in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.
[0051] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present application. However, it is apparent to those skilled in the art that the present application can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present application, some technical features well known in the art are not described.
[0052] It should be understood that the present application can be implemented in different forms and should not be interpreted as being limited to the embodiments set forth herein. On the contrary, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the present application to those skilled in the art.
[0053] The purpose of the terms used herein is only to describe specific embodiments and is not intended to be limiting of the present application. When used herein, the singular forms "one", "an" and "said / the" are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "consisting of" and / or "comprising", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.
[0054] In order to thoroughly understand the present application, a detailed structure will be proposed in the following description to illustrate the technical solution proposed by the present application. The optional embodiments of the present application are described in detail as follows, but in addition to these detailed descriptions, the present application may also have other implementation methods.
[0055] Next, first refer to Figure 1 An ultrasound imaging system according to an embodiment of the present application is described. Figure 1 FIG. 1 is a schematic structural block diagram of an ultrasound imaging system 100 according to an embodiment of the present invention.
[0056] like Figure 1 As shown, the ultrasound imaging system 100 includes an ultrasound probe 110, a transmitting circuit 112, a receiving circuit 114, a processor 116, and a display 118. Further, the ultrasound imaging system may also include a transmit / receive selection switch 120 and a beamforming module 122, and the transmitting circuit 112 and the receiving circuit 114 may be connected to the ultrasound probe 110 through the transmit / receive selection switch 120.
[0057] The ultrasonic probe 110 includes a plurality of transducer array elements, which can be arranged in a row to form a linear array, or arranged in a two-dimensional matrix to form a surface array, or a plurality of transducer array elements can also form a convex array. The transducer array element is used to transmit ultrasonic waves according to the excitation electrical signal, or to convert the received ultrasonic waves into electrical signals, so each transducer array element can be used to realize the mutual conversion between the electrical pulse signal and the ultrasonic wave, so as to realize the transmission of ultrasonic waves to the tissue of the target area of the object to be tested, and can also be used to receive the ultrasonic wave echo reflected by the tissue. When performing ultrasonic testing, which transducer array elements are used to transmit ultrasonic waves and which transducer array elements are used to receive ultrasonic waves can be controlled by the transmission sequence and the reception sequence, or the transducer array elements can be controlled to transmit ultrasonic waves or receive ultrasonic wave echoes in time slots. The transducer array elements participating in ultrasonic wave transmission can be excited by electrical signals at the same time, so as to transmit ultrasonic waves at the same time; or, the transducer array elements participating in ultrasonic wave beam transmission can also be excited by several electrical signals with a certain time interval, so as to continuously transmit ultrasonic waves with a certain time interval.
[0058] During the ultrasonic imaging process, the processor 116 controls the transmitting circuit 112 to send the delayed focused transmitting pulse to the ultrasonic probe 110 through the transmitting / receiving selection switch 120. The ultrasonic probe 110 is stimulated by the transmitting pulse to transmit an ultrasonic beam to the tissue of the target area of the object to be measured, and receives the ultrasonic echo with tissue information reflected from the tissue of the target area after a certain delay, and reconverts the ultrasonic echo into an electrical signal. The receiving circuit 114 receives the electrical signal converted and generated by the ultrasonic probe 110, obtains the ultrasonic echo signal, and sends these ultrasonic echo signals to the beamforming module 122, which performs focusing delay, weighting and channel summing on the ultrasonic echo data, and then sends them to the processor 116. The processor 116 performs signal detection, signal enhancement, data conversion, logarithmic compression and other processing on the ultrasonic echo signal to form an ultrasonic image. The ultrasonic image obtained by the processor 116 can be displayed on the display 118 or stored in the memory 124.
[0059] Optionally, the processor 116 may be implemented as software, hardware, firmware or any combination thereof, and may use a single or multiple application specific integrated circuits (ASICs), a single or multiple general purpose integrated circuits, a single or multiple microprocessors, a single or multiple programmable logic devices, or any combination of the aforementioned circuits and / or devices, or other suitable circuits or devices. Furthermore, the processor 116 may control other components in the ultrasound imaging system 100 to perform the corresponding steps of the methods in various embodiments of the present specification.
[0060] The display 118 is connected to the processor 116, and the display 118 may be a touch screen, a liquid crystal display, etc.; or, the display 118 may be an independent display such as a liquid crystal display, a television, etc., which is independent of the ultrasound imaging system 100; or, the display 118 may be a display screen of an electronic device such as a smart phone or a tablet computer, etc. The number of the display 118 may be one or more.
[0061] The display 118 can display the ultrasound image obtained by the processor 116. In addition, while displaying the ultrasound image, the display 118 can also provide the user with a graphical interface for human-computer interaction. One or more controlled objects are set on the graphical interface, and the user is provided with a human-computer interaction device to input operation instructions to control these controlled objects, thereby performing corresponding control operations. For example, an icon is displayed on the graphical interface, and the icon can be operated by the human-computer interaction device to perform a specific function, such as drawing a region of interest box on the ultrasound image.
[0062] Optionally, the ultrasound imaging system 100 may further include other human-machine interaction devices in addition to the display 118, which are connected to the processor 116. For example, the processor 116 may be connected to the human-machine interaction device via an external input / output port, and the external input / output port may be a wireless communication module, or a wired communication module, or a combination of the two. The external input / output port may also be implemented based on USB, bus protocols such as CAN, and / or wired network protocols.
[0063] The human-computer interaction device may include an input device for detecting user input information, which may be, for example, a control instruction for ultrasonic transmission / reception timing, an operation input instruction for drawing points, lines or frames on an ultrasonic image, or other instruction types. The input device may include a keyboard, a mouse, a scroll wheel, a trackball, a mobile input device (such as a mobile device with a touch screen, a mobile phone, etc.), a multi-function knob, etc., or a combination of multiple thereof. The human-computer interaction device may also include an output device such as a printer.
[0064] The ultrasound imaging system 100 may further include a memory 124 for storing instructions executed by the processor, storing received ultrasound echoes, storing ultrasound images, etc. The memory may be a flash memory card, a solid-state memory, a hard disk, etc. It may be a volatile memory and / or a non-volatile memory, a removable memory and / or a non-removable memory, etc.
[0065] It should be understood that Figure 1 The components included in the ultrasonic imaging system 100 are only exemplary, and the ultrasonic imaging system 100 may include more or fewer components, and the present application is not limited thereto.
[0066] Next, we will refer to Figure 2 The ultrasonic pelvic floor imaging method according to an embodiment of the present application is described. Figure 2 It is a schematic flow chart of the ultrasonic pelvic floor imaging method 200 according to an embodiment of the present application.
[0067] like Figure 2 As shown, an ultrasonic pelvic floor imaging method 200 according to an embodiment of the present application includes the following steps:
[0068] In step S210, the ultrasonic probe is controlled to transmit ultrasonic waves to the pelvic floor of the subject, and an echo of the ultrasonic waves is received to obtain an ultrasonic echo signal;
[0069] In step S220, the ultrasonic echo signal is processed to obtain ultrasonic volume data of the pelvic floor;
[0070] In step S230, a standard pelvic floor sagittal plane is extracted based on the ultrasound volume data;
[0071] In step S240, a plurality of reference lines are determined in the standard pelvic floor sagittal plane, and a plurality of corresponding standard pelvic floor tomographic slices are generated and displayed according to the plurality of reference lines;
[0072] In step S250, it is detected whether there is a levator ani muscle tear region in the plurality of standard pelvic floor tomographic sections, and the position of the levator ani muscle tear region is marked in the standard pelvic floor tomographic section where the levator ani muscle tear region exists.
[0073] The ultrasonic pelvic floor imaging method 200 of the embodiment of the present application can automatically generate multiple standard pelvic floor tomographic sections, automatically identify and display the levator ani muscle tear area based on the multiple standard pelvic floor tomographic sections, greatly reduce the user's manual operation, and improve the efficiency and accuracy of levator ani muscle tear inspection.
[0074] For example, in step S210, based on Figure 1 The ultrasound imaging system 100 shown in the figure performs ultrasound scanning. Specifically, the clinician can move the ultrasound probe 110 to select a suitable position and angle, and use the volume probe to perform three-dimensional / four-dimensional ultrasound scanning on the labia of the female subject. During the scanning process, the transmitting circuit 112 sends a set of delayed and focused transmission pulses to the ultrasound probe 110 to stimulate the ultrasound probe 110 to transmit ultrasound waves to the pelvic floor of the subject along the two-dimensional scanning plane. The receiving circuit 114 controls the ultrasound probe 110 to receive the ultrasound echo reflected from the pelvic floor of the subject, and converts it into an electrical signal. The beamforming module 112 performs corresponding delay and weighted summation processing on the ultrasound echo signals obtained by multiple transmissions and receptions to realize beamforming, and then sends them to the processor 116 for subsequent signal processing.
[0075] In step S220, the processor 116 of the ultrasound imaging system may obtain ultrasound volume data of the pelvic floor of the subject based on the received ultrasound echo signal. The ultrasound volume data may include three-dimensional ultrasound data or four-dimensional ultrasound data. The four-dimensional ultrasound data is three-dimensional ultrasound video data composed of multiple volumes of continuous three-dimensional ultrasound data. Figure 1 The processor 116 can integrate the three-dimensional spatial relationship of the ultrasound echo signals obtained by the ultrasound probe 110 in a series of scanning planes, thereby realizing the scanning of the pelvic floor in three-dimensional space and the reconstruction of three-dimensional ultrasound data. Finally, after some or all of the image post-processing steps such as denoising, smoothing, and enhancement, the ultrasound volume data of the pelvic floor of the subject is obtained.
[0076] In step S230, a standard pelvic floor sagittal plane is extracted based on the ultrasound volume data. Specifically, the processor 116 of the ultrasound imaging system may extract the standard pelvic floor sagittal plane based on the ultrasound volume data, and the standard pelvic floor sagittal plane is the median sagittal plane of the pelvic floor.
[0077] In one embodiment, in order to obtain the standard pelvic floor sagittal plane, the ultrasound volume data is first automatically rectified, that is, the target orientation is determined based on the ultrasound volume data, and the ultrasound volume data is transformed to the target orientation. Afterwards, the standard pelvic floor sagittal plane is extracted from the ultrasound volume data transformed to the target orientation. The purpose of automatic alignment is to align the orientation of the ultrasound volume data with the extraction orientation of the section, so as to facilitate the extraction of the standard section from the ultrasound volume data, and also to display the user's interested parts such as the anal levator hiatus, pubic branch structure, anal canal structure, etc. to a position that is easy to observe, without the need for the user to manually rotate, thereby improving the efficiency and accuracy of pelvic floor ultrasound examination.
[0078] As an optional implementation, determining the target orientation based on ultrasound volume data may include: detecting a region of a target characteristic structure in the ultrasound volume data, and determining the angle by which the ultrasound volume data needs to be rotated and / or the distance by which it needs to be translated based on the position of at least one region of the target characteristic structure, or determining the angle by which the ultrasound volume data needs to be rotated and / or the distance by which it needs to be translated based on the relative positional relationship between regions of at least two of the target characteristic structures. Exemplarily, the target characteristic structure includes at least one of the following: anal levator hiatus, anorectal angle, pubic ramus structure, and anal canal structure. The target characteristic structure may also be other landmark characteristic structures of the pelvic floor.
[0079] Among them, the target characteristic structure can be detected in the ultrasound volume data by using the traditional target detection method or the machine learning method. When detecting the target characteristic structure, the target characteristic structure can be detected in multiple two-dimensional sections of the ultrasound volume data, and the detection results of the target characteristic structure on multiple two-dimensional sections can be combined to obtain the three-dimensional detection result of the target characteristic structure in the ultrasound volume data. For example, the pubic area and the anorectal angle point structure on the sagittal plane, the pubic branch structure and the anal canal structure on the cross section, etc. can be checked. Alternatively, the ultrasound volume data can be directly subjected to three-dimensional detection to obtain the three-dimensional detection result of the target characteristic structure.
[0080] Exemplarily, traditional target detection methods may include three steps: region selection, feature extraction, and classification. Specifically, region selection refers to selecting candidate target regions based on methods such as sliding windows; feature extraction refers to feature extraction of candidate target regions, and the extracted features include SIFT (scale-invariant feature transform), HOG (histogram of oriented gradients), and other features. Classification refers to classifying candidate target regions using a classifier to determine whether the current candidate target region includes a target feature structure. The classifier may use KNN (K-nearest neighbor algorithm), SVM (support vector machine), random forest, and other types of classifiers. Traditional target detection methods may also include pixel clustering, edge segmentation, graph cutting, or threshold-based image segmentation algorithms.
[0081] Detecting target characteristic structures in ultrasound volume data based on machine learning methods requires pre-building an ultrasound volume database for each target characteristic structure, where each ultrasound volume data is marked with the position corresponding to the target characteristic structure, and then learning an optimal mapping function based on the ultrasound volume database to map from the ultrasound volume data to the target characteristic structure. Machine learning methods can include the following methods, which can be implemented separately or in combination with each other.
[0082] Among them, the first optional machine learning method is a sliding window-based method. Specifically, firstly, feature extraction is performed on the area within the sliding window. The extracted features can be traditional PCA (principal component analysis), LDA (linear discriminant analysis), Harr features, texture and other features, or deep neural networks can be used for feature extraction. Then, the trained classifier is used for classification to determine whether the target feature structure is included in the current window.
[0083] The second optional machine learning method is a deep learning method based on bounding boxes. First, a network is constructed by stacking convolutional layers and fully connected layers. The network is used to learn features and regress parameters based on the constructed ultrasound database. The training samples in the ultrasound database are sent to the pre-constructed network, and the network loss function is optimized for training until the network converges. During the training process, the network can learn how to identify the location of the target feature structure from the ultrasound data. The specific process of training the machine learning model can be to directly train the ultrasound data, or to decompose the ultrasound data into multiple two-dimensional slices, train the multiple two-dimensional slices separately, and then splice them into the training results of the ultrasound data.
[0084] After the network is trained, the network can directly regress the bounding box of the corresponding target feature structure for the ultrasound volume data input into the network, and obtain the category of the target feature structure contained in the bounding box. The network structure includes but is not limited to R-CNN, Fast R-CNN, Faster-RCNN, SSD, YOLO, etc.
[0085] The third optional machine learning method is an end-to-end semantic segmentation network method based on deep learning. This method is similar in structure to the above-mentioned deep learning method based on bounding boxes. The difference is that the semantic segmentation network removes the last fully connected layer of the network and adds an upsampling or deconvolution layer to make the input and output sizes the same, thereby directly obtaining the target feature structure and its corresponding category in the ultrasound volume data input to the network. Exemplarily, the network structure of the semantic segmentation network includes but is not limited to FCN, U-Net, Mask R-CNN, etc.
[0086] After detecting the target characteristic structure in the ultrasound volume data, the angle that the ultrasound volume data needs to be rotated can be indirectly calculated based on the target characteristic structure. Among them, the angle that the ultrasound volume data needs to be rotated and / or the distance that needs to be translated can be determined based on the position of the region of at least one target characteristic structure. For example, the rotation angle required to rotate the ultrasound volume data to the target orientation can be indirectly determined by calculating the rotation angle required to rotate the target characteristic structure from the current position to the target position, or the distance required to translate the ultrasound volume data to the target orientation can be determined. Alternatively, the angle that the ultrasound volume data needs to be rotated and / or the distance that needs to be translated can be determined based on the relative position relationship between the regions of at least two target characteristic structures. For example, the angle that the ultrasound volume data needs to be rotated and / or the distance that needs to be translated can be determined based on the symmetry between the target structures.
[0087] Afterwards, based on the angle that the ultrasound volume data needs to be rotated / or the distance that needs to be translated determined according to the target characteristic structure, the ultrasound volume data acquired in step S220 is transformed to the target orientation. The transformation of the ultrasound volume data may include at least one of rotation and translation. When the ultrasound volume data is rotated, the three dimensions correspond to a rotation angle, and the rotated ultrasound volume data can be obtained by rotating the three dimensions by the corresponding angles. Similarly, when the ultrasound volume data is translated, the three dimensions correspond to a translation amount, and the translated ultrasound volume data can be obtained by translating the three dimensions by the corresponding distances.
[0088] As another optional implementation method of transforming the ultrasound volume data to the target orientation, the ultrasound volume data can be directly input into a trained machine learning model, and the angle at which the ultrasound volume data needs to be rotated and / or the distance at which it needs to be translated can be output, and the ultrasound volume data can be rotated to the target orientation according to the angle and distance obtained by the machine learning model.
[0089] When a machine learning model is used to determine the angle that the ultrasound volume data needs to be rotated and the distance that needs to be translated, it is necessary to pre-build an ultrasound volume database of the pelvic floor for training the machine learning model. The ultrasound volume database of the pelvic floor contains calibration results corresponding to at least one ultrasound volume data of the pelvic floor. The calibration results are the angle that the ultrasound volume data needs to be rotated and the distance that needs to be translated. The rotation angle and translation amount can be directly regressed through the trained machine learning model. The machine learning model stacks convolutional layers and fully connected layers through a deep learning network, and directly regresses the angle and translation amount required for correction through the last fully connected layer. The deep learning network structure includes but is not limited to VGG, ResNet, DenseNet, DPN, etc.
[0090] For example, see Figure 3 After the ultrasound volume data is transformed to the target orientation, in addition to extracting the standard pelvic floor sagittal plane from the ultrasound volume data transformed to the target orientation, the standard pelvic floor coronal plane and standard pelvic floor cross section can also be extracted from the ultrasound volume data transformed to the target orientation, and the extracted standard pelvic floor sagittal plane, standard pelvic floor coronal plane and standard pelvic floor cross section are displayed. By straightening the ultrasound volume data, the pubic symphysis inferior edge point structure and the anorectal angle point structure on the standard pelvic floor sagittal plane extracted from the ultrasound volume data can be clearly displayed, and the two are on the same horizontal line. At the same time, the standard pelvic floor cross section displays the standard pelvic floor section imaging generated based on the section imaging reference line passing through the two points on the sagittal plane.
[0091] Furthermore, the rectified ultrasound volume data can also be rendered to obtain a VR image and display it. Since the ultrasound volume data has been rectified before, the VR image can better present the characteristic structure that the user is interested in. In some embodiments, the user can further adjust the orientation of the ultrasound volume data according to the currently displayed standard pelvic floor sagittal plane, standard pelvic floor coronal plane, standard pelvic floor cross section and VR image, and the processor transforms the orientation of the ultrasound volume data according to the received user instructions, and regenerates the standard pelvic floor sagittal plane, standard pelvic floor coronal plane and standard pelvic floor cross section.
[0092] The above exemplarily describes several ways to straighten the ultrasound volume data. It is easier to straighten the ultrasound volume data first and then extract the standard pelvic floor sagittal plane from the straightened ultrasound volume data. The extracted section is more accurate and is conducive to the user to view the characteristic structure of interest in the VR image. In another embodiment, the ultrasound volume data may not be straightened, but the position of the standard pelvic floor sagittal plane may be first determined according to the ultrasound volume data, and then the standard pelvic floor sagittal plane may be extracted at this position. For example, at least one target characteristic structure on the standard pelvic floor sagittal plane may be identified in the ultrasound volume data, and the section intersecting with the at least one target characteristic structure may be used as the standard pelvic floor sagittal plane.
[0093] In order to facilitate the user to observe multiple cross sections of the pelvic floor ultrasound volume data, it is necessary to further generate multiple tomographic sections in the rectified volume data for display. Therefore, after obtaining the standard pelvic floor sagittal plane, step S240 is performed to determine multiple reference lines in the standard pelvic floor sagittal plane, and generate and display multiple corresponding standard pelvic floor tomographic sections according to the multiple reference lines, and each reference line generates a standard pelvic floor tomographic section. The reference line can also be called an imaging reference line, which is the intersection of the tomographic section and the standard pelvic floor sagittal plane.
[0094] For example, see Figure 4 When determining multiple reference lines, the center reference line 401 may be determined first, and then other reference lines 402 may be determined at equal intervals above and below the center reference line 401. As a specific implementation method, the area of the lower edge of the pubic symphysis and the area of the anorectal angle may be detected in the standard pelvic floor sagittal plane, and the line connecting the area of the lower edge of the pubic symphysis and the area of the anorectal angle may be used as the first reference line, and multiple second reference lines may be generated at equal intervals on both sides of the first reference line, and the first reference line and the second reference line may be used as multiple reference lines for generating a standard pelvic floor fault section. The first reference line is the center reference line mentioned above.
[0095] Among them, the area of the lower edge point of the pubic symphysis and the area of the anorectal angle point on the standard pelvic floor sagittal plane can be automatically detected by an image recognition algorithm, and the image recognition algorithm can include a traditional target detection method or a machine learning method, and the details can be seen above. After the area of the lower edge point of the pubic symphysis and the area of the anorectal angle point are identified, a first reference line can be automatically generated through these two points, and multiple second reference lines can be adaptively generated with the first reference line as the center and at equal intervals above and below the first reference line.
[0096] In another embodiment, since the horizontal center line of the standard pelvic floor sagittal plane passes through the lower edge of the pubic symphysis and the anorectal angle after the ultrasound volume data is straightened, the horizontal center line of the standard pelvic floor sagittal plane can also be directly used as the first reference line, and multiple second reference lines are generated at equal intervals on both sides of the first reference line, and the first reference line and the second reference line are used as multiple reference lines.
[0097] In some embodiments, the automatically determined multiple reference lines can be displayed in the standard pelvic floor sagittal plane for the user to view and adjust, and when the user receives an adjustment instruction for the reference line position, the position of the reference line can be adjusted according to the received user instruction. In some embodiments, the position of the center reference line can be adjusted according to the received user instruction, and the positions of other reference lines can be adaptively adjusted according to the adjusted center reference line.
[0098] After generating multiple reference lines on the standard pelvic floor sagittal plane, a standard pelvic floor tomographic section perpendicular to the standard pelvic floor sagittal plane is generated according to each reference line. The direction of the standard pelvic floor tomographic section is parallel to the direction of the standard pelvic floor cross section. Compared with the standard pelvic floor cross section, the standard pelvic floor tomographic section has a certain depth and can show the tissue structure of the pelvic floor more clearly. Figure 5 , multiple standard pelvic floor fault sections can be displayed in parallel in a matrix form on the same display interface, wherein the standard pelvic floor fault section corresponding to the first reference line is displayed at the center of the interface, and the distance between the section and the standard pelvic floor fault section corresponding to the first reference line is displayed in the upper right corner of each standard pelvic floor fault section.
[0099] Based on the multiple standard pelvic floor tomographic sections obtained in step S240, it is necessary to further determine whether there is a tear of the levator ani muscle on each section to reduce the user's manual operation and improve the inspection efficiency. Therefore, in step S250, the processor 116 of the ultrasound imaging system can automatically detect whether there is a tear area of the levator ani muscle in multiple standard pelvic floor tomographic sections, and control the display 118 to mark the position of the tear area of the levator ani muscle in the standard pelvic floor tomographic section where the tear area of the levator ani muscle exists. Exemplarily, the mark of the tear area of the levator ani muscle is adjustable, and the processor 116 can adjust the position of the mark of the tear area of the levator ani muscle according to the received user instruction.
[0100] In one embodiment, it is possible to detect whether there is a levator ani muscle tear region in multiple standard pelvic floor tomographic sections based on an image recognition algorithm. Specifically, the image features of the standard pelvic floor tomographic sections are extracted, the image features are classified, and it is determined whether there is a levator ani muscle tear region in the standard pelvic floor tomographic section according to the classification result, and the position of the levator ani muscle tear region is determined. Afterwards, the levator ani muscle tear region can be selected by a boundary box on the standard pelvic floor tomographic section where the levator ani muscle tear region exists, such as Figure 6 shown.
[0101] Exemplarily, the image recognition algorithm includes a template matching method based on traditional image processing and an image recognition algorithm based on deep learning. Among them, the template matching method based on traditional image processing includes: obtaining an ultrasound image database with a pre-established levator ani tear ROI (Region of Interest), traversing the standard pelvic floor tomographic section by means of a sliding window, and extracting image features within the sliding window. The feature extraction method includes extracting features such as PCA, Harr features or texture, and deep neural networks can also be used to extract features. The extracted image features are matched with the features in the database, and finally classified using a discriminator such as KNN, SVN, random forest or neural network to determine whether each standard pelvic floor tomographic section has a levator ani tear, and at the same time determine the location of the levator ani tear area.
[0102] The deep learning-based image recognition method is consistent with the detection network framework of the target feature structure in step S230, that is, a backbone network (Backbone) and a feature pyramid (FPN) are constructed by stacking convolutional layers to detect and mark the image features of the significant levator ani tear area on each standard pelvic floor section.
[0103] In another embodiment, the LUG (Levator Urethra Gap) index of the levator ani muscle can be automatically measured to determine whether there is a levator ani muscle tear on each standard pelvic floor section. Detect the area of the urethral orifice point and the area of the bilateral levator ani muscle attachment points in each standard pelvic floor section, and obtain the distance between the area of the urethral orifice point and the area of the levator ani muscle attachment points on each side. If the distance exceeds a preset threshold, it is determined that there is a levator ani muscle tear area in the standard pelvic floor section. Since levator ani muscle tears usually occur at the levator ani muscle attachment point, it can be determined that the levator ani muscle tear area is located at the location of the levator ani muscle attachment point where the distance between the urethral orifice point area and the levator ani muscle attachment point exceeds a preset threshold, and mark the area. Figure 7The cross at the center of the image represents the urethral orifice, and the crosses on both sides represent the levator ani muscle attachment point 1 and the levator ani muscle attachment point 2 respectively. The distance between the urethral orifice area and the levator ani muscle attachment point 1 is 1.97 cm, and the distance between the urethral orifice area and the levator ani muscle attachment point 2 is 3.50 cm. If the preset threshold is 2.5 cm, since the distance between the urethral orifice area and the levator ani muscle attachment point 2 exceeds the threshold, it is determined that there is a levator ani muscle tear area in the standard pelvic floor tomography section, and the area of the levator ani muscle attachment point 2 can be used as the levator ani muscle tear area.
[0104] Specifically, the key point regression network based on deep learning can directly regress the coordinates of the urethral orifice and the bilateral levator anus muscle attachment points on each standard pelvic floor section by stacking convolutional layers and fully connected layers, and automatically measure the LUG value based on the coordinates, and determine whether the tear exists by judging whether the LUG value exceeds the preset threshold. Alternatively, it is also possible to only stack convolutional layers to build a Gaussian point regression network with full convolutional layers, usually with a network structure of FCN or U-Net, and then take the position with the maximum probability based on the Gaussian heat map output by the network to obtain the coordinates of the urethral orifice and the bilateral levator anus muscle attachment points, and then automatically measure the LUG value to determine whether the levator anus muscle tear exists.
[0105] Further, when it is determined that there is a levator ani tear area in the standard pelvic floor section, the distance between the area of the urethral orifice and the area of the bilateral levator ani attachment points is displayed. Alternatively, only the distance between the area of the urethral orifice and the area of the levator ani attachment points exceeding the threshold may be displayed.
[0106] In order to facilitate users to observe the tear status of the levator ani muscle from all directions, after testing on various standard pelvic floor section planes, if the levator ani muscle tear area is detected, the tear position of the levator ani muscle can be further imaged.
[0107] For example, when it is determined that there is a levator ani muscle tear region in the standard pelvic floor tomographic section, at least one of the sagittal plane, coronal plane, and cross-section of the levator ani muscle tear region can be generated and displayed. That is, based on the levator ani muscle tear region, the sagittal plane, coronal plane, and cross-section at the levator ani muscle tear position are extracted from the ultrasound volume data and displayed.
[0108] Alternatively, when it is determined that there is a levator ani muscle tear region in the standard pelvic floor tomographic section, the reference line corresponding to the standard pelvic floor tomographic section with the levator ani muscle tear region in the multiple reference lines on the standard pelvic floor sagittal plane can be determined, which is recorded as the first target reference line, and the standard pelvic floor tomographic section with the levator ani muscle tear region is generated based on the first target reference line. Afterwards, based on the first target reference line, multiple second target reference lines are generated in the standard pelvic floor sagittal plane, and multiple tomographic sections are generated and displayed based on the multiple second target reference lines. Among them, the distance between two adjacent second target reference lines is less than the distance between two adjacent reference lines in the multiple reference lines generated in step S240, in order to make the tomographic section generated according to the second target reference line more likely to contain the levator ani muscle tear region, so that the user can observe the levator ani muscle tear state from multiple directions.
[0109] In summary, the ultrasonic pelvic floor imaging method 200 of the embodiment of the present application automatically realizes automatic imaging of the pelvic floor tomographic section based on the ultrasonic volume data of the pelvic floor, and fully automatically identifies and marks the levator ani muscle tears, greatly reducing the user's manual operation and improving the efficiency of pelvic floor ultrasonic examination.
[0110] The present application also provides an ultrasonic imaging system for implementing the ultrasonic pelvic floor imaging method 200. Figure 1 , the ultrasound imaging system can be implemented as follows Figure 1 The ultrasound imaging system 100 shown may include an ultrasound probe 110, a transmitting circuit 112, a receiving circuit 114, a processor 116 and a display 118. Optionally, the ultrasound imaging system 100 may also include a transmit / receive selection switch 120 and a beamforming module 122. The transmitting circuit 112 and the receiving circuit 114 may be connected to the ultrasound probe 110 via the transmit / receive selection switch 120. The relevant description of each component may refer to the relevant description above and will not be repeated here.
[0111] Among them, the transmitting circuit 112 is used to excite the ultrasonic probe 110 to transmit ultrasonic waves to the pelvic floor of the object under test; the transmitting circuit is used to control the ultrasonic probe to receive the echo of the ultrasonic wave to obtain an ultrasonic echo signal; the processor is used to execute the steps of the ultrasonic pelvic floor imaging method 200 as described above, specifically including: controlling the ultrasonic probe 110 to transmit ultrasonic waves to the pelvic floor of the object under test, and receiving the echo of the ultrasonic wave to obtain an ultrasonic echo signal; performing signal processing on the ultrasonic echo signal to obtain ultrasonic volume data of the pelvic floor; extracting a standard pelvic floor sagittal plane based on the ultrasonic volume data; determining multiple reference lines in the standard pelvic floor sagittal plane, and generating and displaying corresponding multiple standard pelvic floor tomographic sections according to the multiple reference lines; detecting whether there is a levator ani muscle tear area in the multiple standard pelvic floor tomographic sections, and marking the position of the levator ani muscle tear area in the standard pelvic floor tomographic section where the levator ani muscle tear area exists.
[0112] In one embodiment, extracting the standard pelvic floor sagittal plane based on the ultrasound volume data includes: determining a target orientation based on the ultrasound volume data, and transforming the ultrasound volume data to the target orientation; and extracting the standard pelvic floor sagittal plane from the ultrasound volume data transformed to the target orientation.
[0113] In one embodiment, determining the target orientation based on the ultrasound volume data includes: detecting an area of a target characteristic structure in the ultrasound volume data, the target characteristic structure including at least one of the following: anal levator hiatus, anorectal angle, pubic branch structure and anal canal structure; determining an angle to be rotated and / or a distance to be translated for the ultrasound volume data according to the position of at least one area of the target characteristic structure, or determining an angle to be rotated and / or a distance to be translated for the ultrasound volume data according to the relative position relationship between at least two areas of the target characteristic structure.
[0114] In one embodiment, determining the target orientation based on the ultrasound volume data includes: inputting the ultrasound volume data into a trained machine learning model, and outputting the angle at which the ultrasound volume data needs to be rotated and / or the distance at which it needs to be translated.
[0115] In one embodiment, the processor 116 is further used to: extract a standard pelvic floor coronal plane and a standard pelvic floor cross-section from the ultrasound volume data transformed to the target orientation; and control the display 118 to display the standard pelvic floor sagittal plane, the standard pelvic floor coronal plane and the standard pelvic floor cross-section.
[0116] In one embodiment, the determining of multiple reference lines in the standard pelvic floor sagittal plane includes: detecting an area of a pubic symphysis inferior edge point and an anorectal angle point in the standard pelvic floor sagittal plane; using a line connecting the area of a pubic symphysis inferior edge point and the area of anorectal angle point as a first reference line, generating multiple second reference lines at equal intervals on both sides of the first reference line, and using the first reference line and the second reference line as the multiple reference lines.
[0117] In one embodiment, determining multiple reference lines in the standard pelvic floor sagittal plane includes: using the horizontal center line of the standard pelvic floor sagittal plane as a first reference line, generating multiple second reference lines at equal intervals on both sides of the first reference line, and using the first reference line and the second reference line as the multiple reference lines.
[0118] In one embodiment, detecting whether there is a levator ani muscle tear area in the multiple standard pelvic floor tomographic sections includes: extracting image features of the standard pelvic floor tomographic sections; classifying the image features, and determining whether there is a levator ani muscle tear area in the standard pelvic floor tomographic sections based on the classification results.
[0119] In one embodiment, the detecting whether there is a levator ani muscle tear area in the multiple standard pelvic floor tomographic sections includes: detecting the area of the urethral orifice point and the area of the bilateral levator ani muscle attachment points in the standard pelvic floor tomographic section; obtaining the distance between the area of the urethral orifice point and the area of the levator ani muscle attachment points; if the distance exceeds a preset threshold, determining that there is a levator ani muscle tear area in the standard pelvic floor tomographic section.
[0120] In one embodiment, the processor 116 is further configured to: when determining that there is a levator ani muscle tear area in the standard pelvic floor section, control the display 118 to display the distance between the area of the urethral opening point and the area of the bilateral levator ani muscle attachment points.
[0121] In one embodiment, the processor 116 is further configured to: when it is determined that there is a levator ani muscle tear region in the standard pelvic floor tomographic section, generate and display a sagittal plane, a coronal plane and / or a cross-section of the levator ani muscle tear region.
[0122] In one embodiment, when it is determined that there is a levator ani muscle tear area in the standard pelvic floor tomographic section, the processor 116 is also used to: determine the first target reference line corresponding to the standard pelvic floor tomographic section where the levator ani muscle tear area exists among the multiple reference lines; based on the first target reference line, generate multiple second target reference lines in the standard pelvic floor sagittal plane; based on the multiple second target reference lines, generate multiple tomographic sections, and control the display 118 to display the multiple tomographic sections.
[0123] In one embodiment, the processor 116 is further configured to adjust the position of the mark of the levator ani muscle tear area according to a received user instruction.
[0124] The above only describes the main functions of the components of the ultrasound imaging system. For more details, please refer to the related description of the ultrasound pelvic floor imaging method 200.
[0125] Next, we will refer to Figure 8 A method for ultrasonic pelvic floor imaging according to another embodiment of the present application is described. Figure 8 FIG. 8 is a schematic flow chart of an ultrasonic pelvic floor imaging method 800 according to an embodiment of the present application. Figure 8 As shown, the ultrasonic pelvic floor imaging method 800 includes the following steps:
[0126] In step S810, the ultrasonic probe is controlled to transmit ultrasonic waves to the pelvic floor of the subject, and an echo of the ultrasonic waves is received to obtain an ultrasonic echo signal;
[0127] In step S820, the ultrasonic echo signal is processed to obtain ultrasonic volume data of the pelvic floor;
[0128] In step S830, a standard pelvic floor sagittal plane is extracted based on the ultrasound volume data;
[0129] In step S840, a plurality of reference lines are determined in the standard pelvic floor sagittal plane, and a plurality of corresponding standard pelvic floor tomographic slices are generated according to the plurality of reference lines;
[0130] In step S850, detecting whether there is a levator ani muscle tear region in the plurality of standard pelvic floor section planes;
[0131] In step S860, a standard pelvic floor tomographic section with the levator ani muscle tear region is displayed, and the position of the levator ani muscle tear region is marked in the standard pelvic floor tomographic section with the levator ani muscle tear region.
[0132] like Figure 8 The difference between the ultrasonic pelvic floor imaging method 800 shown and the ultrasonic pelvic floor imaging method 200 described above is that in step S840 of the ultrasonic pelvic floor imaging method 800, a plurality of corresponding standard pelvic floor tomographic sections are generated according to a plurality of reference lines, but it is not necessary to display all the standard pelvic floor tomographic sections; when the presence of a levator ani muscle tear region is detected, the standard pelvic floor tomographic section with the levator ani muscle tear region is displayed and the levator ani muscle tear region is marked, thereby performing targeted display of the levator ani muscle tear region, thereby improving the inspection efficiency. In addition, the ultrasonic pelvic floor imaging method 800 is substantially similar to the ultrasonic pelvic floor imaging method 200.
[0133] Furthermore, in order to facilitate users to observe the tear state of the levator ani muscle from all directions, after detection on each standard pelvic floor section, if the levator ani muscle tear area is detected, the levator ani muscle tear position can be further imaged.
[0134] For example, when it is determined that there is a levator ani muscle tear region in the standard pelvic floor tomographic section, at least one of the standard pelvic floor sagittal plane, the standard pelvic floor coronal plane, and the standard pelvic floor cross section of the levator ani muscle tear region can also be generated and displayed. Alternatively, when it is determined that there is a levator ani muscle tear region in the standard pelvic floor tomographic section, the first target reference line corresponding to the standard pelvic floor tomographic section with the levator ani muscle tear region among multiple reference lines can be determined, and based on the first target reference line, multiple second target reference lines are generated in the standard pelvic floor sagittal plane; and multiple tomographic sections are generated and displayed based on the multiple second target reference lines.
[0135] In addition, the ultrasonic pelvic floor imaging method 800 has many identical or similar contents to the above-mentioned ultrasonic pelvic floor imaging method 200, which can be specifically referred to above and will not be described in detail here. The ultrasonic pelvic floor imaging method 200 according to the embodiment of the present application can automatically identify and mark the tear area of the levator ani muscle, greatly reducing the manual operation of the user and improving the efficiency of pelvic floor ultrasonic examination.
[0136] The present application also provides an ultrasonic imaging system for implementing the ultrasonic pelvic floor imaging method 800. Figure 1 , the ultrasound imaging system can be implemented as follows Figure 1 The ultrasound imaging system 100 shown may include an ultrasound probe 110, a transmitting circuit 112, a receiving circuit 114, a processor 116 and a display 118. Optionally, the ultrasound imaging system 100 may also include a transmit / receive selection switch 120 and a beamforming module 122. The transmitting circuit 112 and the receiving circuit 114 may be connected to the ultrasound probe 110 via the transmit / receive selection switch 120. The relevant description of each component may refer to the relevant description above and will not be repeated here.
[0137] Among them, the transmitting circuit 112 is used to excite the ultrasonic probe 110 to transmit ultrasonic waves to the pelvic floor of the object under test; the transmitting circuit is used to control the ultrasonic probe to receive the echo of the ultrasonic wave to obtain an ultrasonic echo signal; the processor is used to execute the steps of the ultrasonic pelvic floor imaging method 800 as described above, specifically including: controlling the ultrasonic probe 110 to transmit ultrasonic waves to the pelvic floor of the object under test, and receiving the echo of the ultrasonic wave to obtain an ultrasonic echo signal; performing signal processing on the ultrasonic echo signal to obtain ultrasonic volume data of the pelvic floor; extracting a standard pelvic floor sagittal plane based on the ultrasonic volume data; determining multiple reference lines in the standard pelvic floor sagittal plane, and generating corresponding multiple standard pelvic floor tomographic sections according to the multiple reference lines; detecting whether there is a levator ani muscle tear area in the multiple standard pelvic floor tomographic sections; displaying the standard pelvic floor tomographic section with the levator ani muscle tear area, and marking the position of the levator ani muscle tear area in the standard pelvic floor tomographic section with the levator ani muscle tear area.
[0138] In one embodiment, the processor 116 is further configured to: when it is determined that there is a levator ani muscle tear region in the standard pelvic floor tomographic section, generate and display a sagittal plane, a coronal plane and / or a cross-section of the levator ani muscle tear region.
[0139] In one embodiment, when it is determined that there is a levator ani muscle tear area in the standard pelvic floor tomographic section, the processor 116 is also used to: determine the first target reference line corresponding to the standard pelvic floor tomographic section where the levator ani muscle tear area exists among the multiple reference lines; based on the first target reference line, generate multiple second target reference lines in the standard pelvic floor sagittal plane; based on the multiple second target reference lines, generate multiple tomographic sections, and control the display 118 to display the multiple tomographic sections.
[0140] The above only describes the main functions of the components of the ultrasound imaging system. For more details, please refer to the related description of the ultrasound pelvic floor imaging method 800.
[0141] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application to this. Those of ordinary skill in the art may make various changes and modifications therein without departing from the scope and spirit of the present application. All these changes and modifications are intended to be included within the scope of the present application as required by the appended claims.
[0142] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0143] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.
[0144] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.
[0145] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present application should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with features less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby explicitly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.
[0146] It will be understood by those skilled in the art that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.
[0147] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.
[0148] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some modules according to embodiments of the present invention. The present application can also be implemented as a device program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.
[0149] It should be noted that the above embodiments illustrate rather than limit the present application, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.
[0150] The above is only a specific implementation or description of a specific implementation of the present application, and the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. The protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A method for ultrasonic pelvic floor imaging, characterized in that: The method comprises: Controlling the ultrasonic probe to transmit ultrasonic waves to the pelvic floor of the subject to be measured, and receiving echoes of the ultrasonic waves to obtain ultrasonic echo signals; Performing signal processing on the ultrasonic echo signal to obtain ultrasonic volume data of the pelvic floor; Automatically extracting a standard pelvic floor sagittal plane based on the ultrasonic volume data, comprising: determining a target orientation based on the ultrasonic volume data, transforming the ultrasonic volume data to the target orientation, and extracting the standard pelvic floor sagittal plane from the ultrasonic volume data transformed to the target orientation; Determine a plurality of reference lines in the standard pelvic floor sagittal plane, and generate and display a plurality of corresponding standard pelvic floor fault sections according to the plurality of reference lines; Detecting whether there is a levator ani muscle tear region in the multiple standard pelvic floor tomographic sections, and marking the position of the levator ani muscle tear region in the standard pelvic floor tomographic section where the levator ani muscle tear region exists, wherein detecting whether there is a levator ani muscle tear region in the multiple standard pelvic floor tomographic sections comprises: Extracting image features of the standard pelvic floor fault section; Classifying the image features, and determining whether there is a levator ani muscle tear area in the standard pelvic floor section according to the classification result; When it is determined that there is a levator ani muscle tear area in the standard pelvic floor tomographic section, the method also includes: determining a first target reference line corresponding to the standard pelvic floor tomographic section where the levator ani muscle tear area exists among the multiple reference lines; based on the first target reference line, generating multiple second target reference lines in the standard pelvic floor sagittal plane; based on the multiple second target reference lines, generating and displaying multiple tomographic sections; wherein the distance between two adjacent second target reference lines is less than the distance between two adjacent reference lines among the above multiple reference lines.
2. The method according to claim 1, characterized in that The determining the target position based on the ultrasound volume data comprises: Detecting a region of a target characteristic structure in the ultrasound volume data, wherein the target characteristic structure includes at least one of the following: anal levator hiatus, anorectal angle, pubic ramus structure, and anal canal structure; The angle by which the ultrasound volume data needs to be rotated and / or the distance by which it needs to be translated is determined according to the position of at least one region of the target characteristic structure, or the angle by which the ultrasound volume data needs to be rotated and / or the distance by which it needs to be translated is determined according to the relative positional relationship between at least two regions of the target characteristic structure.
3. The method according to claim 1, characterized in that The determining the target position based on the ultrasound volume data comprises: The ultrasound volume data is input into a trained machine learning model, and the angle by which the ultrasound volume data needs to be rotated and / or the distance by which it needs to be translated is output.
4. The method according to claim 1, characterized in that: Also includes: Extracting a standard pelvic floor coronal plane and a standard pelvic floor cross section from the ultrasound volume data transformed to the target orientation; The standard pelvic floor sagittal plane, the standard pelvic floor coronal plane and the standard pelvic floor cross-section are displayed.
5. The method according to claim 1, characterized in that Determining multiple reference lines in the standard pelvic floor sagittal plane includes: Detecting the area of the lower edge of the pubic symphysis and the area of the anorectal angle in the standard pelvic floor sagittal plane; A line connecting the area of the lower edge point of the pubic symphysis and the area of the anorectal angle point is used as a first reference line, a plurality of second reference lines are generated at equal intervals on both sides of the first reference line, and the first reference line and the second reference line are used as the plurality of reference lines.
6. The method according to claim 1, characterized in that Determining multiple reference lines in the standard pelvic floor sagittal plane includes: The horizontal center line of the standard pelvic floor sagittal plane is used as a first reference line, a plurality of second reference lines are generated at equal intervals on both sides of the first reference line, and the first reference line and the second reference line are used as the plurality of reference lines.
7. The method according to claim 1, characterized in that Also includes: When it is determined that there is a levator ani muscle tear region in the standard pelvic floor tomographic section, a sagittal plane, a coronal plane and / or a cross-section of the levator ani muscle tear region is generated and displayed.
8. The method according to claim 1, characterized in that Also includes: The position of the mark of the levator ani tear area is adjusted according to the received user instruction.
9. A method for ultrasonic pelvic floor imaging, characterized in that: The method comprises: Controlling the ultrasonic probe to transmit ultrasonic waves to the pelvic floor of the subject to be measured, and receiving echoes of the ultrasonic waves to obtain ultrasonic echo signals; Performing signal processing on the ultrasonic echo signal to obtain ultrasonic volume data of the pelvic floor; Automatically extracting a standard pelvic floor sagittal plane based on the ultrasonic volume data, comprising: determining a target orientation based on the ultrasonic volume data, transforming the ultrasonic volume data to the target orientation, and extracting the standard pelvic floor sagittal plane from the ultrasonic volume data transformed to the target orientation; Determine a plurality of reference lines in the standard pelvic floor sagittal plane, and generate a plurality of corresponding standard pelvic floor fault sections according to the plurality of reference lines; Detecting whether there is a levator ani muscle tear region in the plurality of standard pelvic floor tomographic sections, comprising: extracting image features of the standard pelvic floor tomographic sections; classifying the image features, and determining whether there is a levator ani muscle tear region in the standard pelvic floor tomographic sections according to the classification result; Displaying a standard pelvic floor tomographic section with a levator ani muscle tear area, and marking the position of the levator ani muscle tear area in the standard pelvic floor tomographic section with a levator ani muscle tear area; When it is determined that there is a levator ani muscle tear area in the standard pelvic floor tomographic section, the method also includes: determining a first target reference line corresponding to the standard pelvic floor tomographic section where the levator ani muscle tear area exists among the multiple reference lines; based on the first target reference line, generating multiple second target reference lines in the standard pelvic floor sagittal plane; based on the multiple second target reference lines, generating and displaying multiple tomographic sections; wherein the distance between two adjacent second target reference lines is less than the distance between two adjacent reference lines among the above multiple reference lines.
10. The method according to claim 9, characterized in that Also includes: When it is determined that there is a levator ani muscle tear region in the standard pelvic floor tomographic section, a sagittal plane, a coronal plane and / or a cross-section of the levator ani muscle tear region is generated and displayed.
11. An ultrasonic imaging system, characterized in that: include: Ultrasound probe; A transmitting circuit, used for stimulating the ultrasonic probe to transmit ultrasonic waves to the pelvic floor of the subject; A receiving circuit, used for controlling the ultrasonic probe to receive the ultrasonic echo to obtain an ultrasonic echo signal; A processor, configured to execute the steps of the ultrasonic pelvic floor imaging method according to any one of claims 1 to 10; A display is used to display the ultrasound image obtained by the processor.
