Method and device for generating three-dimensional ultrasonic model and ultrasonic imaging system

Abstract

The invention relates to the technical field of ultrasonic imaging, and discloses a three-dimensional ultrasonic model generation method and device and an ultrasonic imaging system, and the method comprises the steps: obtaining a two-dimensional ultrasonic image corresponding to a target ultrasonic section of a target part; obtaining a first target contour corresponding to the structural feature of the target part in the two-dimensional ultrasonic image, and determining a plurality of first deformation reference points on the first target contour; obtaining a basic three-dimensional model corresponding to the target part, and determining a basic model section matched with the target ultrasonic section in the basic three-dimensional model; obtaining a second target contour corresponding to the structural features of the target part in the section of the basic model, and determining at least two first deformation control points on the second target contour; determining first model deformation information of the basic three-dimensional model according to the first deformation reference point and the first deformation control point; and deforming the basic three-dimensional model at least according to the first model deformation information to obtain a target three-dimensional model.

Description

Technical Field

[0001] The present application relates to the field of ultrasonic imaging technology, and in particular to a method and device for generating a three-dimensional ultrasonic model and an ultrasonic imaging system. Background Art

[0002] Ultrasound medicine has obvious advantages over other technologies. It is one of the indispensable imaging diagnostic methods in clinical medicine because it is non-invasive, harmless, painless, and intuitive to use. It has been widely used in clinical medicine. Traditional ultrasound imaging systems can only provide two-dimensional ultrasound images of the target area, making it difficult for patients who do not have ultrasound knowledge to understand ultrasound images. It is a big challenge for doctors to describe the condition to patients based on ultrasound images. At the same time, doctors with different qualifications and different departments have different understandings of ultrasound images, which causes unnecessary troubles in communication between doctors.

[0003] Three-dimensional images or three-dimensional models have the advantages of intuitive image display and are widely used in medical teaching and surgical planning. The traditional method of obtaining a three-dimensional model of a target part mainly uses an ultrasound probe dedicated to three-dimensional imaging to obtain three-dimensional ultrasound data of the target part, and obtains a three-dimensional model of the target part by processing the three-dimensional ultrasound data. However, the ultrasound probe used in this method is expensive and has a narrow imaging field of view, or the resolution of the three-dimensional ultrasound data obtained by the ultrasound probe is usually lower than that of the two-dimensional ultrasound data, resulting in insufficient resolution of the three-dimensional model synthesized by the imaging method, which ultimately limits the use of this method. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to provide a method and device for generating a three-dimensional ultrasound model and an ultrasound imaging system.

[0005] In a first aspect, an embodiment of the present application provides a method for generating a three-dimensional ultrasound model, comprising:

[0006] Acquire a two-dimensional ultrasound image corresponding to a target ultrasound section of a target part, wherein the two-dimensional ultrasound image includes structural features of the target part and lesion features of the target part;

[0007] Acquire a first target contour corresponding to the structural features of the target part and a first lesion contour corresponding to the lesion features of the target part in the two-dimensional ultrasound image, and determine a plurality of first deformation reference points on the first target contour and a plurality of second deformation reference points on the first lesion contour;

[0008] Acquire a basic three-dimensional model corresponding to the target part, and determine a basic model section that matches the target ultrasound section in the basic three-dimensional model, wherein the basic model section includes structural features of the target part and lesion features of the target part;

[0009] Acquire a second target contour corresponding to the structural features of the target part in the section of the base model, and determine at least two first deformation control points corresponding to at least two of the first deformation reference points on at least the second target contour, and acquire a second lesion contour corresponding to the lesion features of the target part in the section of the base model, and determine at least two second deformation control points corresponding to at least two of the second deformation reference points on at least the second lesion contour;

[0010] Determining first model deformation information of the basic three-dimensional model according to the first deformation reference point and the first deformation control point, and determining second model deformation information of the basic three-dimensional model according to the second deformation reference point and the second deformation control point;

[0011] The basic three-dimensional model is deformed into a target three-dimensional model at least according to the first model deformation information and the second model deformation information.

[0012] It can be seen from the technical solution provided by the present application that the method for generating a three-dimensional ultrasound model provided by the present application obtains a two-dimensional ultrasound image of the target part with an actual morphology, and obtains the first target contour corresponding to the structural features of the target part in the two-dimensional ultrasound image and the first lesion contour corresponding to the lesion features of the target part from the two-dimensional ultrasound image. Thus, the first target contour obtained can be used as a reference target for the second target contour of the structural features of the target part in the basic model section corresponding to the basic three-dimensional model, and the first lesion contour obtained can be used as a reference target for the second lesion contour of the lesion features of the target part in the basic model section corresponding to the basic three-dimensional model, and the structural features and lesion features of the target part in the basic three-dimensional model can be deformed and constrained, so that the deformed basic three-dimensional model is closer to the real model morphology of the target part, that is, the three-dimensional model of the target part finally obtained is more accurate and realistic.

[0013] In a second aspect, an embodiment of the present application further provides a method for generating a three-dimensional ultrasound model, comprising:

[0014] Acquire a two-dimensional ultrasonic image corresponding to a target ultrasonic section of a target part, wherein the two-dimensional ultrasonic image at least includes structural features of the target part;

[0015] Acquire a first target contour corresponding to the structural features of the target part in the two-dimensional ultrasound image, and determine a plurality of first deformation reference points on the first target contour;

[0016] Acquire a basic three-dimensional model corresponding to the target part, and determine a basic model section that matches the target ultrasound section in the basic three-dimensional model, wherein the basic model section includes structural features of the target part;

[0017] Acquire a second target contour corresponding to the structural features of the target part in the cross section of the base model, and determine at least two first deformation control points corresponding to at least two of the first deformation reference points on the second target contour;

[0018] Determining first model deformation information of the basic three-dimensional model according to the first deformation reference point and the first deformation control point;

[0019] The basic three-dimensional model is deformed into a target three-dimensional model at least according to the first model deformation information.

[0020] It can be seen from the technical solution provided by the present application that the method for generating a three-dimensional ultrasound model provided by the present application obtains a two-dimensional ultrasound image of the target part with an actual morphology, and obtains a first target contour corresponding to the structural features of the target part in the two-dimensional ultrasound image from the two-dimensional ultrasound image. Thus, the first target contour obtained can be used as a reference target for the second target contour of the structural features of the target part in the basic model section corresponding to the basic three-dimensional model, and the structural features of the target part in the basic three-dimensional model are deformed and constrained, so that the deformed basic three-dimensional model is closer to the real model morphology of the target part, that is, the three-dimensional model of the target part finally obtained is more accurate and realistic.

[0021] In a third aspect, an embodiment of the present application further provides a device for generating a three-dimensional ultrasound model, comprising:

[0022] Memory, used to store programs;

[0023] A processor is used to implement the steps of any of the aforementioned methods for generating a three-dimensional ultrasound model by executing the program stored in the memory.

[0024] In a fourth aspect, an embodiment of the present application further provides an ultrasonic imaging system, comprising:

[0025] An ultrasonic probe, wherein the ultrasonic probe comprises a plurality of array elements;

[0026] A transmitting circuit, used for stimulating the ultrasonic probe to transmit ultrasonic waves to a target site;

[0027] A receiving circuit, used for controlling the ultrasonic probe to receive the ultrasonic echo signal;

[0028] A memory, the memory being used to store a program;

[0029] a processor, the processor being used to generate a two-dimensional ultrasound image corresponding to a target ultrasound section of the target part according to the echo signal, the processor being further used to implement the steps of the method for generating a three-dimensional ultrasound model according to any one of claims 1 to 22 by executing a program stored in the memory;

[0030] The display is at least used to display the ultrasound image and / or the three-dimensional model generated by the processor.

[0031] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 A structural block diagram of an ultrasound imaging system according to an embodiment of the present application is shown;

[0034] Figure 2 A schematic flow chart showing a method for generating a three-dimensional ultrasound model according to an embodiment of the present application;

[0035] Figure 3 A frame of two-dimensional ultrasound image of the target part on the long axis section acquired by the ultrasound imaging system is shown;

[0036] Figure 4 A frame of two-dimensional ultrasound image of the target part on the short-axis section acquired by the ultrasound imaging system is shown;

[0037] Figure 5 A schematic diagram showing how to obtain a first target contour of a target part and a first deformation reference point on the first target contour from a two-dimensional ultrasonic image;

[0038] Figure 6 A schematic diagram showing how to obtain a second target contour of a target part and a first deformation control point on the second target contour from a section of a base model;

[0039] Figure 7 A schematic diagram showing a process of deforming a base three-dimensional model according to a first deformation amount to obtain a target three-dimensional model;

[0040] Figure 8 A schematic diagram showing how to obtain a first target contour, a first deformation reference point on the first target contour, a first lesion contour, and a second deformation reference point on the first lesion contour of a target part from a two-dimensional ultrasound image;

[0041] Fig. 9 A schematic diagram showing how to obtain a second target contour of a target part, a first deformation control point on the second target contour, a second lesion contour, and a second deformation control point on the second lesion contour from a section of a base model;

[0042] Fig.10 A schematic diagram showing a process of deforming a base three-dimensional model according to a first deformation amount and a second deformation amount to obtain a target three-dimensional model;

[0043] Fig.11 A schematic diagram showing the display of data obtained by measuring a two-dimensional ultrasonic image of a target part on a three-dimensional model of the target;

[0044] Fig.12 A schematic diagram showing the fusion display of a two-dimensional ultrasound image of a target site and a three-dimensional model of the target. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0047] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0048] Some embodiments of the present application are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0049] See also Figure 1 , Figure 1An ultrasound imaging system according to an embodiment of the present invention is described. Figure 1 A schematic structural block diagram of an ultrasound imaging system according to an embodiment of the present invention is shown.

[0050] 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.

[0051] The ultrasound probe 110 includes a plurality of transducer array elements, referred to as array elements, which may be arranged in a row to form a linear array, or arranged in a two-dimensional matrix to form a surface array, or may form a convex array. For example, a plurality of transducer array elements may be arranged in a single row along a preset direction, or a plurality of transducer array elements may be arranged in multiple rows along a preset direction.

[0052] 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. Therefore, each transducer array element can be used to realize the mutual conversion between the electrical pulse signal and the ultrasonic wave, so as to transmit the ultrasonic wave to the tissue of the target part 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, the transmission sequence and the receiving sequence can be used to control which transducer array elements are used to transmit ultrasonic waves and which transducer array elements are used to receive ultrasonic waves, or control the transducer array elements to transmit ultrasonic waves or receive ultrasonic wave echoes in time slots. The transducer array elements involved 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 involved 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.

[0053] 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 target part, receives the ultrasonic echo reflected from the target part 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. The beamforming module 122 performs focusing delay, weighting and channel summing on the ultrasonic echo data, and then sends it 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] 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.

[0059] 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, and the like. The memory may be a flash memory card, a solid-state memory, a hard disk, and the like. It may be a volatile memory and / or a non-volatile memory, a removable memory and / or a non-removable memory, and the like. For example, the memory 124 is a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like equipped on the ultrasound imaging system 100.

[0060] It should be understood that Figure 1 The components included in the ultrasonic imaging system 100 are merely exemplary, and the system may include more or fewer components, which is not limited to the present invention.

[0061] In some embodiments, an embodiment of the present application also provides an ultrasound imaging system 100 that is also used to execute the steps of a method for generating a three-dimensional ultrasound model, specifically: the transmitting circuit 112 of the ultrasound imaging system 100 is used to stimulate the ultrasound probe 110 to transmit ultrasound to the target part; the receiving circuit 114 of the ultrasound imaging system 100 is used to control the ultrasound probe 110 to receive the echo of the ultrasound to obtain the echo signal of the ultrasound; the processor 116 of the ultrasound imaging system 100 is used to generate a two-dimensional ultrasound image of the target part according to the echo signal, and is also used to execute the steps of the method for generating a three-dimensional ultrasound model described in any embodiment or example of the present application to obtain the corresponding target three-dimensional model; the display 118 is used to display the two-dimensional ultrasound image and / or the three-dimensional model.

[0062] The above only describes the main functions of the components of the ultrasound imaging system. For more details, please refer to the relevant description of the method for generating a three-dimensional ultrasound model below, which will not be repeated here.

[0063] In some embodiments, the embodiments of the present application also provide a device for generating a three-dimensional ultrasound model, which is used to implement the above-mentioned method for generating a three-dimensional ultrasound model. Exemplarily, the device for generating a three-dimensional ultrasound model includes a memory and a processor, wherein the memory is used to store a program, and the processor is used to execute the program stored in the memory to implement the steps of the method for generating a three-dimensional ultrasound model described in any embodiment or example of the present application specification.

[0064] It can be understood that the device for generating a three-dimensional ultrasound model can share a memory and / or a processor with the ultrasound imaging system 100, or the memory and processor of the device for generating a three-dimensional ultrasound model are independent of the ultrasound imaging system 100, that is, the device for generating a three-dimensional ultrasound model does not share a memory and a processor with the ultrasound imaging system 100, and the processor of the device for generating a three-dimensional ultrasound model is only required to execute the program stored in the memory to implement the steps of the method for generating a three-dimensional ultrasound model described in any embodiment or example of the specification of this application.

[0065] See also Figure 2 , Figure 2 It is a schematic flow chart of a method for generating a three-dimensional ultrasound model according to an embodiment of the present invention.

[0066] like Figure 2 As shown, the method for generating a three-dimensional ultrasound model can be applied to the aforementioned ultrasound imaging system 100 and executed by the processor of the ultrasound imaging system 100, or can be applied to the aforementioned device for generating a three-dimensional ultrasound model and executed by the processor of the device for generating a three-dimensional ultrasound model. The present application takes the application of the method for generating a three-dimensional ultrasound model to the ultrasound imaging system 100 as an example for explanation, and the method for generating a three-dimensional ultrasound model includes steps S101 to S106.

[0067] Step S101: acquiring a two-dimensional ultrasonic image corresponding to a target ultrasonic section of a target part, wherein the two-dimensional ultrasonic image at least includes structural features of the target part.

[0068] Exemplarily, the target part is the part corresponding to the target tissue corresponding to the two-dimensional ultrasound image to be generated, wherein the target part includes but is not limited to the patient's neck, chest, abdomen, pelvic organs and limb blood vessels. It can be understood that the target part can be the thyroid gland, parotid gland, submandibular gland, neck blood vessels and other neck organs. The target part can also be the pleura, lungs, heart and surrounding large blood vessels, mediastinal lymph nodes and other chest organs, and the target part can also be the liver, gallbladder, pancreas, spleen, kidney, ureter, bladder, uterus, ovary, fallopian tube, prostate and other abdominal organs.

[0069] In the process of obtaining a two-dimensional ultrasonic image corresponding to a target ultrasonic section of a target part of a patient, an ultrasonic wave can be emitted to a position corresponding to the target part through the ultrasonic probe 110, and at least one frame of a two-dimensional ultrasonic image corresponding to the target ultrasonic section of the target part can be obtained based on the ultrasonic echo signal of the received ultrasonic wave, and the two-dimensional ultrasonic image at least includes the structural features of the target part.

[0070] It can be understood that structural features are used to describe the structural properties of the target part and to distinguish the part category of the target part. In medicine, different target parts correspond to different structural features. For example, the heart has structural features unique to the heart, and the uterus has structural features unique to the uterus. The target parts can be distinguished by structural features.

[0071] Optionally, the method of obtaining the two-dimensional ultrasound image corresponding to the target ultrasound section of the target part can be to obtain at least two frames of two-dimensional ultrasound images corresponding to at least two different long-axis sections of the target part, wherein the two-dimensional ultrasound images contain structural features of the target part, wherein any two different long-axis sections are set at an angle. For example, the angle between any two different long-axis sections ranges from 30 to 90°, that is, the angle between any two different long-axis sections can be 30°, 40°, 50°, 60°, 70°, 80°, or 90°.

[0072] That is, ultrasonic waves are emitted to the target ultrasonic section of the target part on at least two different long-axis sections of the target part through the ultrasonic probe 110, and at least two frames of two-dimensional ultrasonic images corresponding to the target part on at least two different long-axis sections are obtained according to the ultrasonic echo signals of the received ultrasonic waves. The two different long-axis sections are set at an angle, for example, the angle between the two long-axis sections is 90°.

[0073] Optionally, a method for obtaining a two-dimensional ultrasound image corresponding to a target ultrasound section of a target part may also be to obtain at least one frame of two-dimensional ultrasound image corresponding to at least one long-axis section and at least one frame of two-dimensional ultrasound image corresponding to at least one short-axis section of the target part, wherein the two-dimensional ultrasound image contains structural features of the target part.

[0074] That is, ultrasonic waves are transmitted at a corresponding position of at least one long-axis section of the target part through the ultrasonic probe 110, and at least one frame of two-dimensional ultrasonic image corresponding to at least one long-axis section of the target part is obtained according to the ultrasonic echo signal of the received ultrasonic waves, and ultrasonic waves are transmitted at a corresponding position of at least one short-axis section of the target part, and at least one frame of two-dimensional ultrasonic image corresponding to at least one short-axis section is obtained according to the ultrasonic echo signal of the received ultrasonic waves.

[0075] like Figure 3 and Figure 4 As shown, Figure 3 is a frame of two-dimensional ultrasound image of the target part on the long axis section acquired by the ultrasound imaging system 100, and the two-dimensional ultrasound image includes the structural features of the target part. Figure 4 It is a frame of two-dimensional ultrasound image of the target part on the short-axis section acquired by the ultrasound imaging system 100, and the two-dimensional ultrasound image includes structural features of the target part.

[0076] Step S102: obtaining a first target contour corresponding to the structural features of the target part in the two-dimensional ultrasound image, and determining a plurality of first deformation reference points on the first target contour.

[0077] Exemplarily, the method for identifying the corresponding contour in the two-dimensional ultrasound image can be obtained by manually outlining the corresponding contour to be identified in the two-dimensional ultrasound image, or by using a pre-trained contour recognition model and taking the two-dimensional ultrasound image as the input of the contour recognition model to obtain the corresponding contour in the two-dimensional ultrasound image, or by identifying the corresponding contour in the two-dimensional ultrasound image through a preset contour recognition algorithm.

[0078] After obtaining the first target contour corresponding to the structural features of the target part, a plurality of first deformation reference points are determined on the first target contour, wherein the first deformation reference points can be determined by manual selection by a user, or can be automatically generated on the first target contour by a preset algorithm.

[0079] In some embodiments, a method for obtaining a first target contour corresponding to the structural features of the target part in the two-dimensional ultrasound image may be: in response to a user's first contour drawing operation on the two-dimensional ultrasound image, determining the first target contour corresponding to the structural features of the target part from the two-dimensional ultrasound image.

[0080] For example, the acquired two-dimensional ultrasound image of the target part can be displayed on a display, and the user can identify the structural contour corresponding to the structural feature of the target part from the two-dimensional ultrasound image displayed on the display through experience, so that the first contour drawing operation can be performed on the two-dimensional ultrasound image by manipulating the input device, so as to draw the first target contour corresponding to the structural feature of the target part from the two-dimensional ultrasound image through the first contour drawing operation, so that the ultrasound imaging system 100 responds to the user's first contour drawing operation on the two-dimensional ultrasound image, and determines the first target contour corresponding to the structural feature of the target part from the two-dimensional ultrasound image. It can be understood that the input device includes but is not limited to at least one of a keyboard, a mouse, a touch panel, a stylus, and a button.

[0081] For example, the input device is a mouse or a stylus, and the user can identify the structural contour corresponding to the structural feature of the target part from the two-dimensional ultrasound image displayed on the monitor, and perform a contour drawing operation on the two-dimensional ultrasound image by manipulating the mouse or the stylus to draw a first target contour corresponding to the structural feature of the target part. The ultrasound imaging system 100 obtains the first target contour corresponding to the structural feature of the target part from the two-dimensional ultrasound image by identifying the contour drawing operation performed by the user manipulating the input device.

[0082] In some embodiments, a method for obtaining the first target contour corresponding to the structural features of the target part in the two-dimensional ultrasound image may also be: determining multiple first contour control points on the two-dimensional ultrasound image, and forming a first contour curve by interpolation (also called an interpolation algorithm) between each adjacent first contour control point, and using the first contour curve as the first target contour corresponding to the structural features of the target part.

[0083] Exemplarily, the acquired two-dimensional ultrasound image of the target part can be displayed on a display, and the user can identify the structural contour corresponding to the structural feature of the target part from the two-dimensional ultrasound image displayed on the display through experience, and determine multiple first contour control points in the structural contour corresponding to the structural feature of the target part through an input device. After identifying the multiple first contour control points determined by the user, the ultrasound imaging system 100 forms a first contour curve by interpolation between each adjacent first contour control point through a preset interpolation algorithm, and uses the first contour curve as the first target contour corresponding to the structural feature of the target part. It can be understood that the interpolation algorithm includes but is not limited to the B-spline interpolation algorithm, also known as the B-Spline interpolation method.

[0084] In some embodiments, the method for obtaining the first target contour corresponding to the structural feature of the target part in the two-dimensional ultrasound image may also be: obtaining the first target contour corresponding to the structural feature of the target part from the two-dimensional ultrasound image through a preset first contour recognition model.

[0085] Exemplarily, a pre-trained first contour recognition model is used to perform contour recognition on a two-dimensional ultrasound image to obtain a first target contour corresponding to the structural features of the target part. The first contour recognition model can be trained using a two-dimensional ultrasound image corresponding to the structural features of the target part as training data.

[0086] like Figure 5 As shown, the ultrasound imaging system 100 acquires a frame of two-dimensional ultrasound image of the target part on the long-axis section, and obtains a first target contour corresponding to the structural features of the target part in the two-dimensional ultrasound image based on the user's manual selection, preset algorithm or model recognition.

[0087] In some implementations, determining a plurality of first deformation reference points on the first object contour includes: determining a plurality of first deformation reference points on the first object contour based on a preset first rule or a user reference point selection operation.

[0088] Exemplarily, the first rule may be to set a random number or a preset number of first deformation reference points in the first target contour, and the spacing between two adjacent first deformation reference points is the same. Alternatively, the first rule may be to set a random number or a preset number of first deformation reference points in the first target contour, and the spacing between two adjacent first deformation reference points varies randomly. Alternatively, the first rule may be to set a preset number of first deformation reference points in the first target contour, and the spacing distribution between any two adjacent first deformation reference points is related to the type of the target part.

[0089] In some embodiments, multiple first deformation reference points are determined on the first target contour, including: determining multiple first key reference points on the first target contour, and determining a first key contour point on the contour between each adjacent two of the first key reference points based on a preset second rule, and using the first key contour point and the first key reference point as multiple first deformation reference points on the first target contour.

[0090] Exemplarily, the user sets a plurality of first key reference points on the first target contour based on experience, or the ultrasound imaging system 100 automatically generates a plurality of first key reference points using a preset deep learning algorithm or deep learning model, and then uses the first key reference points to segment the first target contour corresponding to the structural features of the target part, and divides the first target contour into a plurality of first sub-contours, and then sets a plurality of first key contour points on each first sub-contour, thereby using each first key contour point and each first key reference point as a plurality of first deformation reference points of the first target contour. Optionally, the spacing between two adjacent first key contour points on each first sub-contour is equal.

[0091] like Figure 5 As shown, a plurality of first deformation reference points are determined on a first target contour acquired from a corresponding two-dimensional ultrasound image on a long-axis section.

[0092] Step S103: Acquire the basic three-dimensional model corresponding to the target part, and determine the basic model section that matches the target ultrasound section in the basic three-dimensional model, wherein the basic model section contains the structural features of the target part. Exemplarily, there are multiple ways to acquire the basic three-dimensional model corresponding to the target part, for example, by collecting the three-dimensional ultrasound volume data of the target part of the patient, and converting the three-dimensional ultrasound volume data of the target part into a three-dimensional mesh model as a three-dimensional template model through a related algorithm; for another example, by collecting the CT data (CT, Computed Tomography, i.e., electronic computer tomography) of the target part of the patient, and converting the CT data of the target part into a three-dimensional mesh model as a three-dimensional template model through a related algorithm; for another example, by establishing a three-dimensional template model of the target part through three-dimensional modeling and other methods, these three-dimensional template models can be three-dimensional mesh models, and the mesh points on the model are evenly distributed; optionally, each mesh on the three-dimensional mesh model is filled with a patch, and the patch can be filled with texture information.

[0093] The basic three-dimensional model at least has structural features corresponding to the target part. The structural features of the target part corresponding to each patient are different. Therefore, the basic three-dimensional model can be adjusted to make the adjusted basic three-dimensional model closer to the target patient currently being tested, that is, the three-dimensional model corresponding to the acquired ultrasound image of the target part of the target patient is more accurate and realistic.

[0094] In this embodiment, after the basic three-dimensional model is acquired, a basic model section that matches the target ultrasonic section is determined in the basic three-dimensional model. For example, the target ultrasonic section is a section of the target part in the long axis direction at a preset angle. Then, a section in the long axis direction at the same angle as the preset angle is determined in the basic three-dimensional model corresponding to the target part. The basic model section obtained from the basic three-dimensional model and the target ultrasonic section are roughly the same section of the target part, thereby effectively improving the accuracy of subsequent deformation. In addition, the basic model section obtained from the basic three-dimensional model includes the structural features of the target part.

[0095] like Figure 6As shown, at a preset angle corresponding to the basic three-dimensional model, a basic model section of the target part in the long axis direction is obtained. Step S104: A second target contour corresponding to the structural features of the target part in the basic model section is obtained, and at least two first deformation control points corresponding to at least two of the first deformation reference points among the plurality of first deformation reference points are determined on the second target contour.

[0096] Exemplarily, the second target contour corresponding to the structural feature of the target part in the base model section can be obtained by manually outlining the contour to be identified corresponding to the base model section, or by using a pre-trained contour recognition model and taking the base model section as the input of the contour recognition model to obtain the corresponding contour in the base model section, or by identifying the corresponding contour in the base model section through a preset contour recognition algorithm, or by identifying the corresponding contour in the base model section through an edge recognition algorithm.

[0097] After obtaining the second target contour corresponding to the structural features of the target part, a plurality of first deformation control points are determined on the second target contour, wherein the first deformation control points can be determined by manual selection by a user, or can be automatically generated on the second target contour by a preset algorithm.

[0098] Optionally, the method of obtaining the second target contour corresponding to the structural features of the target part in the basic model section may be: in response to the user's third contour drawing operation on the basic model section, determining the second target contour corresponding to the structural features of the target part from the basic model section.

[0099] Exemplarily, the acquired basic model section of the target part can be displayed on a display, and the user can identify the structural contour corresponding to the structural feature of the target part from the basic model section displayed on the display through experience, so that the third contour drawing operation can be performed on the basic model section by manipulating the input device to draw the second target contour corresponding to the structural feature of the target part from the basic model section through the third contour drawing operation, so that the ultrasound imaging system 100 responds to the user's third contour drawing operation on the basic model section, and determines the second target contour corresponding to the structural feature of the target part from the basic model section. It can be understood that the input device includes but is not limited to at least one of a keyboard, a mouse, a touch panel, a stylus, and a button.

[0100] Optionally, a method for obtaining a second target contour corresponding to the structural features of a target part in a basic model section may be: determining a plurality of third contour control points on the basic model section, and forming a third contour curve by interpolation (also called an interpolation algorithm) between adjacent third contour control points, and using the third contour curve as the second target contour corresponding to the structural features of the target part.

[0101] Exemplarily, the acquired basic model section of the target part can be displayed on a display, and the user can identify the structural contour corresponding to the structural feature of the target part from the basic model section displayed on the display through experience, and determine multiple third contour control points in the structural contour corresponding to the structural feature of the target part through an input device. After identifying the multiple third contour control points determined by the user, the ultrasound imaging system 100 interpolates between each adjacent third contour control point through a preset interpolation algorithm to form a third contour curve, and uses the third contour curve as the second target contour corresponding to the structural feature of the target part. It can be understood that the interpolation algorithm includes but is not limited to the B-spline interpolation algorithm, also known as the B-Spline interpolation method.

[0102] Optionally, the method of obtaining the second target contour corresponding to the structural feature of the target part in the basic model section may be: obtaining the second target contour corresponding to the structural feature of the target part from the basic model section by using a preset third contour recognition model.

[0103] Exemplarily, a pre-trained third contour recognition model is used to perform contour recognition on a basic model section to obtain a second target contour corresponding to the structural features of the target part. The third contour recognition model can be trained using images corresponding to the structural features of the target part as training data.

[0104] Optionally, a method for obtaining a second target contour corresponding to the structural features of the target part in the basic model section may be: identifying the edges of the structural features of the target part in the basic model section by a preset edge recognition algorithm, thereby obtaining the second target contour corresponding to the structural features of the target part.

[0105] After obtaining a second target contour corresponding to the structural features of the target part in the cross section of the base model, at least two first deformation control points corresponding to at least two of the first deformation reference points are determined on the second target contour. Optionally, the first deformation control points of the second target contour correspond to the first deformation reference points on the first target contour one-to-one.

[0106] Exemplarily, based on the fact that the basic structural features of the same target parts are substantially the same, the corresponding first deformation control point can be determined according to the first position of the first deformation reference point on the first target contour and the second position on the second target contour corresponding to the first position.

[0107] Based on the fact that in the process of deforming the structural features of the basic three-dimensional model, only some of the first deformation control points may need to be deformed. Therefore, in order to ensure the deformation effect, it is necessary to determine at least two first deformation control points corresponding to at least two of the multiple first deformation reference points on the second target contour, so as to deform the second target contour according to the corresponding deformation control points and deformation reference points.

[0108] Step S105: determining first model deformation information of the basic three-dimensional model according to the first deformation reference point and the first deformation control point.

[0109] Optionally, the first model deformation information of the basic three-dimensional model is determined according to the first deformation reference point and the first deformation control point, including: determining a plurality of first deformation quantities corresponding to a plurality of the first deformation reference points on the first target contour and a plurality of the first deformation control points on the second target contour that match the first deformation reference point, and determining the first model deformation information of the basic three-dimensional model at least based on the plurality of the first deformation quantities.

[0110] Exemplarily, the first deformation control point on the second target contour can be matched one-to-one with the first deformation reference point on the first target contour, and the first mapping relationship (also called the first deformation amount) between the first deformation control point on the second target contour and the first deformation reference point on the first target contour can be obtained. Alternatively, a first deformation control point on the second target contour corresponds to several first deformation reference points on the first target contour, and the first mapping relationship (also called the first deformation amount) between the first deformation control point on the second target contour and the first deformation reference point on the first target contour can be obtained. Alternatively, several first deformation control points on the second target contour correspond to one first deformation reference point on the first target contour, and the first mapping relationship (also called the first deformation amount) between the first deformation control point on the second target contour and the first deformation reference point on the first target contour can be obtained. Thus, the first model deformation information of the basic three-dimensional model can be obtained according to the multiple first deformation amounts corresponding between the multiple first deformation reference points and the multiple first deformation control points.

[0111] like Figure 7As shown, for example, there are 18 first deformation reference points on the first target contour, numbered 1a-18a. There are 18 first deformation control points on the second target contour, numbered 1b-18b, where 1a-1b correspond to and have corresponding first deformation amounts, 2a-2b correspond to and have corresponding first deformation amounts, 3a-3b correspond to and have corresponding first deformation amounts, and so on, 17a-17b correspond to and have corresponding first deformation amounts, 18a-18b correspond to and have corresponding first deformation amounts, and the first deformation amounts corresponding to the 18 first deformation reference points are used as the first model deformation information of the basic three-dimensional model.

[0112] Optionally, the first model deformation information of the basic three-dimensional model is determined according to the first deformation reference point and the first deformation control point, including: determining a plurality of first deformation quantities corresponding to a plurality of the first deformation reference points on the first target contour and a plurality of the first deformation control points on the second target contour corresponding one-to-one to the first deformation reference points, and determining a first mesh deformation quantity corresponding to a first model mesh matching each of the first deformation control points in the basic three-dimensional model based on the first deformation quantity, the first model mesh being used to describe the structural features of the target part; and determining the first model deformation information of the basic three-dimensional model according to the first deformation quantity and the first mesh deformation quantity.

[0113] Exemplarily, the basic three-dimensional model includes a plurality of first model grids, that is, the plurality of first model grids can be constructed to form the basic three-dimensional model, each first deformation control point matches at least one first model grid on the basic three-dimensional model, and in the process of adjusting the position of the first deformation control point based on the first deformation amount, by controlling the first model grid of the basic three-dimensional model to deform based on the first grid deformation amount, the structural features of the target part in the section of the deformed basic model can be matched with the size of the structural features of the target part on the two-dimensional ultrasound image, and finally a more accurate and realistic target three-dimensional model of the target part of the patient can be obtained. Among them, the first grid deformation amount is the product of the corresponding first deformation amount and the preset weight.

[0114] Step S106: deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information.

[0115] Exemplarily, based on the first model deformation information and taking the first deformation reference point as a reference, multiple first deformation control points of the basic model section are deformed to the first deformation reference point on the first target contour of the two-dimensional ultrasound image, so that the first deformation control point and the corresponding first deformation reference point coincide with each other, thereby making the second target contour corresponding to the structural features of the target part on the basic model section and the first target contour corresponding to the structural features of the target part in the two-dimensional ultrasound image basically coincide with each other. By using the first target contour of at least one frame of the two-dimensional ultrasound image of the target part as the deformation reference of the basic three-dimensional model of the target part for deformation, a more accurate and realistic target three-dimensional model of the patient's target part can be obtained.

[0116] In some embodiments, deforming the basic three-dimensional model to obtain a target three-dimensional model at least according to the first model deformation information includes: determining according to the first model deformation information to positionally align the first deformation control point of the basic three-dimensional model with at least the first deformation reference point as a first alignment target until the first deformation control point coincides with the corresponding first deformation reference point, thereby obtaining a target three-dimensional model.

[0117] Exemplarily, taking the one-to-one correspondence between the first deformation reference point and the first deformation control point as an example, the first deformation reference point on the first target contour corresponding to the structural feature of the target part on a frame of two-dimensional ultrasound image and the first deformation control point on the second target contour corresponding to the structural feature of the target part in the basic model section in the basic three-dimensional model correspond one-to-one, and multiple first deformation quantities corresponding to the basic three-dimensional model on the corresponding basic model section are determined according to each first deformation reference point and a corresponding matching deformation control point, thereby obtaining the first model deformation information of the basic three-dimensional model.

[0118] After obtaining the first model deformation information of the basic three-dimensional model, the first deformation control point is aligned with the first deformation reference point as the alignment target. During the position alignment process, the position of the corresponding first deformation control point is adjusted by the first deformation amount to deform the basic model section in the basic three-dimensional model until the first deformation reference point and the corresponding first deformation control point coincide one by one, so that the structural features of the target part in the basic model section match the structural features of the target part on the two-dimensional ultrasound image, and finally a more accurate and realistic target three-dimensional model of the patient's target part can be obtained.

[0119] It can be understood that by using the first target contour corresponding to the structural features of the target part on a frame of two-dimensional ultrasound image, the cross-sectional contour of the target part on a section of the basic three-dimensional model can be adjusted more accurately. Therefore, by using the first target contour corresponding to the structural features of the target part on multiple frames of ultrasound images obtained at different angles, the cross-sectional contours of the target part on multiple sections of the basic three-dimensional model can be adjusted more accurately, so that the target three-dimensional model of the patient obtained is more accurate and closer to the three-dimensional model of the target part on the two-dimensional ultrasound image.

[0120] like Figure 7 As shown, there are 18 first deformation reference points on the first target contour, numbered 1a-18a. There are 18 first deformation control points on the second target contour, numbered 1b-18b, wherein 1a-1b correspond to and have corresponding first deformation amounts, 2a-2b correspond to and have corresponding first deformation amounts, 3a-3b correspond to and have corresponding first deformation amounts, and so on, 17a-17b correspond to and have corresponding first deformation amounts, and 18a-18b correspond to and have corresponding first deformation amounts.

[0121] After determining the corresponding first deformation amount, the position of the first deformation control point is adjusted based on the first deformation reference point, so that the first deformation control point undergoes the corresponding first deformation amount relative to the first deformation reference point, thereby making the first deformation reference point 1a coincide with the first deformation control point 1b, the first deformation reference point 2a coincide with the first deformation control point 2b, the first deformation reference point 3a coincide with the first deformation control point 3b, and so on, the first deformation reference point 17a coincides with the first deformation control point 17b, and the first deformation reference point 18a coincides with the first deformation control point 18b, so that the structural features of the target part in the cross-section of the basic model and the structural features of the target part on the two-dimensional ultrasound image match in size, and finally a more accurate and realistic target three-dimensional model of the patient's target part can be obtained.

[0122] Furthermore, by utilizing the first target contour corresponding to the structural features of the target part in the multi-frame two-dimensional ultrasound image, the second target contour corresponding to the structural features of the target part in the basic model section of the basic three-dimensional model can be adjusted, thereby further making the acquired target three-dimensional model of the patient's target part more accurate and realistic.

[0123] In some implementations, deforming the base three-dimensional model into a target three-dimensional model at least according to the first model deformation information includes:

[0124] According to the first model deformation information, it is determined that at least the first deformation control point of the basic three-dimensional model is aligned with the first deformation reference point as the first alignment target, and the first model mesh matching the first deformation control point is deformed according to the first mesh deformation amount until the first deformation control point and the corresponding first deformation reference point coincide with each other, thereby obtaining a target three-dimensional model.

[0125] like Figure 7 As shown, exemplarily, there are 18 first deformation reference points on the first target contour, numbered 1a-18a. There are 18 first deformation control points on the second target contour, numbered 1b-18b, wherein 1a-1b correspond to and have corresponding first deformation amounts, 2a-2b correspond to and have corresponding first deformation amounts, 3a-3b correspond to and have corresponding first deformation amounts, and so on, 17a-17b correspond to and have corresponding first deformation amounts, and 18a-18b correspond to and have corresponding first deformation amounts.

[0126] The basic three-dimensional model includes multiple first model grids, each of which corresponds to at least one first deformation control point. In this embodiment, for the convenience of explanation, each first model grid corresponds to one first deformation control point. For the purpose of explanation, the basic three-dimensional model includes 18 first model grids, namely 1c-18c. The first deformation control point 1b corresponds to the first model grid 1c, the first deformation control point 2b corresponds to the first model grid 2c, the first deformation control point 3b corresponds to the first model grid 3c, and so on. The first deformation control point 17b corresponds to the first model grid 17c, the first deformation control point 18b corresponds to the first model grid 18c, Figure 7 In the figure, only the first model grids 1c-9c on the front side of the basic three-dimensional model are shown, and the first model grids 10c-18c on the back side of the basic three-dimensional model are not shown.

[0127] After determining the first deformation amount corresponding to each first deformation control point, the first deformation control point is deformed according to the first deformation amount, so that the first deformation reference point 1a coincides with the first deformation control point 1b, the first deformation reference point 2a coincides with the first deformation control point 2b, the first deformation reference point 3a coincides with the first deformation control point 3b, and so on, the first deformation reference point 17a coincides with the first deformation control point 17b, and the first deformation reference point 18a coincides with the first deformation control point 18b.

[0128] At the same time, the first model mesh 1c of the basic three-dimensional model is controlled to deform based on the first mesh deformation amount following the first deformation control point 1b until the corresponding first deformation control point 1b coincides with the first deformation reference point 1a. The first mesh deformation amount is the product of the corresponding first deformation amount and the preset weight. After the deformation, the structural features of the target part in the cross-section of the basic model match the size of the structural features of the target part on the two-dimensional ultrasound image, and finally a more accurate and realistic target three-dimensional model of the patient's target part can be obtained.

[0129] See also Figures 8 to 10 In some embodiments, the two-dimensional ultrasound image at least includes the structural features of the target site and the lesion features of the target site, and the basic model section includes the structural features of the target site and the lesion features of the target site, wherein the lesion features are used to describe whether a lesion occurs in the target site, and if a lesion occurs, it can assist in diagnosing the type and / or location of the lesion.

[0130] At least before deforming the basic three-dimensional model into a target three-dimensional model according to the first model deformation information in step S106, the method further includes:

[0131] Acquire a first lesion contour corresponding to the lesion feature of the target part in the two-dimensional ultrasound image, and acquire a second lesion contour corresponding to the lesion feature of the target part in the basic model section;

[0132] Determine a plurality of second deformation reference points on the first lesion contour, and determine at least two second deformation control points corresponding to at least two of the plurality of second deformation reference points on at least the second lesion contour;

[0133] Determining second model deformation information of the basic three-dimensional model according to the second deformation reference point and the second deformation control point;

[0134] Wherein, step S106, deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information, includes:

[0135] The basic three-dimensional model is deformed according to the first model deformation information and the second model deformation information to obtain a target three-dimensional model.

[0136] In this implementation manner, the method for acquiring the first model deformation information may refer to the relevant description above and will not be elaborated here.

[0137] It can be understood that the first lesion contour corresponding to the lesion feature of the target part in the two-dimensional ultrasound image can be obtained by manual drawing or by identification through a model or algorithm.

[0138] like Figure 8 As shown, in some embodiments, obtaining a first lesion contour corresponding to the lesion feature of the target part in the two-dimensional ultrasound image includes: responding to a second contour drawing operation performed by a user on the two-dimensional ultrasound image, and determining a first lesion contour corresponding to the lesion feature of the target part from the two-dimensional ultrasound image.

[0139] Exemplarily, the acquired two-dimensional ultrasound image of the target part can be displayed on a display, and the user can identify the structural contour corresponding to the structural feature of the target part from the two-dimensional ultrasound image displayed on the display through experience, so that the second contour drawing operation can be performed on the two-dimensional ultrasound image by manipulating the input device, so as to draw the first lesion contour corresponding to the lesion feature of the target part from the two-dimensional ultrasound image through the second contour drawing operation, so that the ultrasound imaging system 100 responds to the user's second contour drawing operation on the two-dimensional ultrasound image, and determines the first lesion contour corresponding to the lesion feature of the target part from the two-dimensional ultrasound image. It can be understood that the input device includes but is not limited to at least one of a keyboard, a mouse, a touch panel, a stylus, and a button.

[0140] In some embodiments, obtaining a first lesion contour corresponding to the lesion feature of the target site in the two-dimensional ultrasound image includes: determining a plurality of second contour control points on the two-dimensional ultrasound image, and forming a second contour curve by interpolation between each adjacent second contour control point, and using the second contour curve as the first lesion contour corresponding to the lesion feature of the target site.

[0141] Exemplarily, the acquired two-dimensional ultrasound image of the target part can be displayed on a display, and the user can identify the lesion contour corresponding to the lesion feature of the target part from the two-dimensional ultrasound image displayed on the display through experience, and determine multiple second contour control points in the lesion contour corresponding to the lesion feature of the target part through an input device. After identifying the multiple second contour control points determined by the user, the ultrasound imaging system 100 interpolates between each adjacent second contour control point through a preset interpolation algorithm to form a second contour curve, and uses the second contour curve as the first lesion contour corresponding to the lesion feature of the target part. It can be understood that the interpolation algorithm includes but is not limited to the B-spline interpolation algorithm, also known as the B-Spline interpolation method.

[0142] In some embodiments, obtaining a first lesion contour corresponding to the lesion feature of the target site in the two-dimensional ultrasound image includes: obtaining the first lesion contour corresponding to the lesion feature of the target site from the two-dimensional ultrasound image through a preset second contour recognition model.

[0143] Exemplarily, a pre-trained second contour recognition model is used to perform contour recognition on a two-dimensional ultrasound image to obtain a first lesion contour corresponding to the lesion features of the target site. The second contour recognition model can be trained using a two-dimensional ultrasound image corresponding to the lesion features of the target site as training data.

[0144] In some embodiments, after acquiring the first lesion contour, a method of determining a plurality of second deformation reference points on the first lesion contour may be: determining a plurality of second deformation reference points on the first lesion contour based on a preset third rule.

[0145] Exemplarily, the third rule may be to set a random number or a preset number of second deformation reference points in the first lesion outline, and the spacing between two adjacent second deformation reference points is the same. Alternatively, the third rule may be to set a random number or a preset number of second deformation reference points in the first lesion outline, and the spacing between two adjacent second deformation reference points varies randomly. Alternatively, the third rule may be to set a preset number of second deformation reference points in the first lesion outline, and the spacing distribution between any two adjacent second deformation reference points is related to the type of target site and / or lesion.

[0146] In some embodiments, after obtaining the first lesion contour, multiple second deformation reference points are determined on the first lesion contour, including: determining multiple second key reference points on the first lesion contour, and determining key contour points on the contour between each adjacent two of the second key reference points based on a preset fourth rule, and using the second key contour points and the second key reference points as multiple second deformation reference points on the first lesion contour.

[0147] Exemplarily, the user sets a plurality of second key reference points on the first lesion contour based on experience, or the ultrasound imaging system 100 automatically generates a plurality of second key reference points using a preset deep learning algorithm or deep learning model, and then uses the second key reference points to segment the first lesion contour corresponding to the lesion feature of the target part, and divides the first lesion contour into a plurality of second sub-contours, and then sets a plurality of second key contour points on each second sub-contour, thereby using each second key contour point and each second key reference point as a plurality of second deformation reference points of the first lesion contour. Optionally, the spacing between two adjacent second key contour points on each second sub-contour is equal.

[0148] like Fig. 9 As shown, in some embodiments, a second lesion contour corresponding to the lesion feature of the target part in the section of the base model is obtained, and at least two second deformation control points corresponding to at least two of the second deformation reference points among the plurality of second deformation reference points are determined on at least the second lesion contour.

[0149] Exemplarily, the method of obtaining the second lesion contour corresponding to the lesion sign of the target part in the basic model section can be by manually outlining the contour to be identified (such as the lesion contour) corresponding to the basic model section, or by using a pre-trained contour recognition model and taking the basic model section as the input of the contour recognition model to obtain the corresponding contour in the basic model section, or by identifying the corresponding contour in the basic model section through a preset contour recognition algorithm, or by identifying the corresponding contour in the basic model section through an edge recognition algorithm.

[0150] After obtaining the second lesion contour corresponding to the lesion feature of the target part, a plurality of second deformation control points are determined on the second lesion contour, wherein the second deformation control points can be determined by manual selection by the user, or can be automatically generated on the second lesion contour by a preset algorithm.

[0151] Optionally, the method of obtaining the second lesion contour corresponding to the lesion characteristics of the target part in the basic model section may be: in response to the user's fourth contour drawing operation on the basic model section, determining the second lesion contour corresponding to the lesion characteristics of the target part from the basic model section.

[0152] Exemplarily, the acquired basic model section of the target part can be displayed on a display, and the user can identify the lesion contour corresponding to the lesion feature of the target part from the basic model section displayed on the display through experience, and thus can perform a fourth contour drawing operation on the basic model section by manipulating the input device to draw a second lesion contour corresponding to the lesion feature of the target part from the basic model section through the fourth contour drawing operation, so that the ultrasound imaging system 100 responds to the user's fourth contour drawing operation on the basic model section, and determines the second lesion contour corresponding to the lesion feature of the target part from the basic model section.

[0153] Optionally, the method for obtaining the second lesion contour corresponding to the lesion characteristics of the target part in the basic model section may be: determining multiple fourth contour control points on the basic model section, and forming a fourth contour curve by interpolation (also called interpolation algorithm) between each adjacent fourth contour control point, and using the fourth contour curve as the second lesion contour corresponding to the lesion characteristics of the target part.

[0154] Exemplarily, the acquired basic model section of the target part can be displayed on a display, and the user can identify the lesion contour corresponding to the lesion feature of the target part from the basic model section displayed on the display through experience, and determine multiple fourth contour control points in the structural contour corresponding to the structural feature of the target part through an input device. After identifying the multiple fourth contour control points determined by the user, the ultrasound imaging system 100 interpolates between each adjacent fourth contour control point through a preset interpolation algorithm to form a fourth contour curve, and uses the fourth contour curve as the second lesion contour corresponding to the lesion feature of the target part. It can be understood that the interpolation algorithm includes but is not limited to the B-spline interpolation algorithm, also known as the B-Spline interpolation method.

[0155] Optionally, the method of obtaining the second lesion contour corresponding to the lesion feature of the target part in the basic model section may be: obtaining the second lesion contour corresponding to the lesion feature of the target part from the basic model section through a preset fourth contour recognition model.

[0156] Exemplarily, a pre-trained fourth contour recognition model is used to perform contour recognition on the basic model section to obtain a second lesion contour corresponding to the lesion features of the target site. The fourth contour recognition model can be trained using images corresponding to the lesion features of the target site as training data.

[0157] Optionally, a method for obtaining a second lesion contour corresponding to the lesion features of the target part in the basic model section may be: identifying the edges of the lesion features of the target part in the basic model section by a preset edge recognition algorithm, thereby obtaining a second lesion contour corresponding to the lesion features of the target part.

[0158] After obtaining a second lesion contour corresponding to the lesion feature of the target part in the basic model section, at least two second deformation control points corresponding to at least two of the plurality of second deformation reference points are determined on the second lesion contour. Optionally, the second deformation control points of the second lesion contour correspond to the second deformation reference points on the first lesion contour one-to-one.

[0159] Based on the fact that in the process of deforming the lesion features of the basic three-dimensional model, only some of the second deformation control points may need to be deformed, therefore, in order to ensure the deformation effect, at least two second deformation control points corresponding to at least two of the multiple second deformation reference points are determined on the second lesion contour.

[0160] like Fig.10As shown, after determining the second deformation control point corresponding to the second deformation reference point on the second lesion contour, the second mapping relationship (also called the second deformation amount) between the second deformation control point on the second lesion contour and the second deformation reference point on the first lesion contour can be obtained. Alternatively, a second deformation control point on the second lesion contour corresponds to several second deformation reference points on the first lesion contour, and the second mapping relationship (also called the second deformation amount) between the second deformation control point on the second lesion contour and the second deformation reference point on the first lesion contour is obtained. Alternatively, several second deformation control points on the second lesion contour correspond to a second deformation reference point on the first lesion contour, and the second mapping relationship (also called the second deformation amount) between the second deformation control point on the second lesion contour and the second deformation reference point on the first lesion contour is obtained. Thus, the second model deformation information of the basic three-dimensional model can be obtained according to the multiple second deformation reference points and the multiple second deformation control points corresponding to the second deformation reference points.

[0161] In some implementations, after obtaining the first model deformation information and the second model deformation information, deforming the basic three-dimensional model according to the first model deformation information and the second model deformation information to obtain the target three-dimensional model includes:

[0162] The structural features of the target part in the basic three-dimensional model are deformed according to the first model deformation information, and the lesion features of the target part in the basic three-dimensional model are deformed according to the second model deformation information, so as to obtain the target three-dimensional model.

[0163] Exemplarily, according to the first model deformation information, it is determined that at least the first deformation control point of the basic three-dimensional model is aligned with the first deformation reference point as the first alignment target until the first deformation control point and the corresponding first deformation reference point coincide with each other; and according to the second model deformation information, it is determined that at least the second deformation control point of the basic three-dimensional model is aligned with the second deformation reference point as the second alignment target until the second deformation control point and the corresponding second deformation reference point coincide with each other, thereby obtaining the target three-dimensional model.

[0164] Alternatively, according to the first model deformation information, it is determined that at least the first deformation control point of the basic three-dimensional model is aligned with the first deformation reference point as the first alignment target, and the first model mesh matching the first deformation control point is deformed according to the first mesh deformation amount until the first deformation control point and the corresponding first deformation reference point coincide with each other; and according to the second model deformation information, it is determined that at least the second deformation control point of the basic three-dimensional model is aligned with the second deformation reference point as the second alignment target until the second deformation control point and the corresponding second deformation reference point coincide with each other, thereby obtaining the target three-dimensional model.

[0165] That is, in some embodiments, the method for generating a three-dimensional ultrasound model includes steps S101 to S106, and step S101: obtaining a two-dimensional ultrasound image corresponding to a target ultrasound section of the target part, wherein the two-dimensional ultrasound image at least includes structural features of the target part and lesion features of the target part.

[0166] Step S102: acquiring a first target contour corresponding to the structural features of the target part and a first lesion contour corresponding to the lesion features of the target part in the two-dimensional ultrasound image, and determining a plurality of first deformation reference points on the first target contour and a plurality of second deformation reference points on the first lesion contour;

[0167] Step S103: acquiring a basic three-dimensional model corresponding to the target part, and determining a basic model section that matches the target ultrasound section in the basic three-dimensional model, wherein the basic model section includes structural features of the target part and lesion features of the target part;

[0168] Step S104: obtaining a second target contour corresponding to the structural features of the target part in the section of the base model, and determining at least two first deformation control points corresponding to at least two of the first deformation reference points on at least the second target contour, and obtaining a second lesion contour corresponding to the lesion features of the target part in the section of the base model, and determining at least two second deformation control points corresponding to at least two of the second deformation reference points on at least the second lesion contour;

[0169] Step S105: determining first model deformation information of the basic three-dimensional model according to the first deformation reference point and the first deformation control point, and determining second model deformation information of the basic three-dimensional model according to the second deformation reference point and the second deformation control point;

[0170] Step S106: deforming the basic three-dimensional model according to the first model deformation information and the second model deformation information to obtain a target three-dimensional model.

[0171] In some embodiments, the two-dimensional ultrasound image further includes lesion features of the target site, and before deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information, the method further includes:

[0172] Acquiring the lesion characteristics of the target part in the two-dimensional ultrasound image;

[0173] Wherein, step S106, deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information, includes:

[0174] The basic three-dimensional model is deformed according to the first model deformation information, and the lesion is displayed on the deformed basic three-dimensional model according to the lesion characteristics to obtain a target three-dimensional model.

[0175] This embodiment is different from the aforementioned embodiment in that lesion data corresponding to lesion features are stored in a database, wherein the lesion data include but are not limited to lesion three-dimensional data, lesion pictures, etc. After the basic three-dimensional model is deformed using the first model deformation information, the corresponding lesion data can be obtained from the database according to the lesion features, and the lesion display position is determined in the deformed basic three-dimensional model according to the lesion features, and the lesion data is displayed at the lesion display position, such as filling the lesion picture on the model grid corresponding to the lesion display position in the deformed basic three-dimensional model, or displaying the lesion three-dimensional data (such as the lesion three-dimensional model) at the lesion display position in the deformed basic three-dimensional model.

[0176] Alternatively, the method of displaying the lesions on the deformed basic three-dimensional model according to the lesion characteristics to obtain a target three-dimensional model includes: determining, according to the lesion characteristics, a three-dimensional lesion morphology corresponding to the lesion area of ​​the target site and a lesion mapping position of the lesion area on the deformed basic three-dimensional model; and displaying the three-dimensional lesion morphology at the lesion mapping position of the deformed basic three-dimensional model to obtain a target three-dimensional model.

[0177] In some embodiments, the two-dimensional ultrasound image further includes lesion features of the target site, and before deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information, the method further includes:

[0178] Acquiring the lesion characteristics of the target part in the two-dimensional ultrasound image;

[0179] The step of deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information includes:

[0180] Deforming the structural features of the target part in the basic three-dimensional model according to the first model deformation information;

[0181] Determining, according to the lesion characteristics of the target part, a first lesion contour corresponding to the lesion region of the target part and a lesion mapping position of the lesion region on the deformed basic three-dimensional model;

[0182] The target three-dimensional model is obtained by interpolating the first lesion contour to generate a three-dimensional lesion shape corresponding to the lesion area, and displaying the three-dimensional lesion shape at the lesion mapping position of the deformed basic three-dimensional model.

[0183] Optionally, the first deformation reference point corresponds to the first deformation control point one by one, and deforming the structural features of the target part in the basic three-dimensional model according to the first model deformation information includes:

[0184] According to the first model deformation information, determine to align the first deformation control point of the basic three-dimensional model with at least the first deformation reference point as a first alignment target until the first deformation control point coincides with the corresponding first deformation reference point.

[0185] In some embodiments, the method further includes: determining a first target position based on a target contour of the two-dimensional ultrasound image and generating a measurement mark, and measuring the first target position based on the measurement mark to obtain measurement data; determining a second target position matching the first target position on the target three-dimensional model, and displaying the measurement mark and measurement data in association with the second target position, the target contour including the first target contour and / or the first lesion contour.

[0186] Exemplarily, when it is necessary to measure the size (such as length and width) of a preset position on the first target contour in a two-dimensional ultrasound image, the user can generate a corresponding measurement mark at the position to be measured by operating the input device, and can easily measure the size of the preset position through the measurement mark to obtain the corresponding measurement data, and display the measurement data at the corresponding second position in the target three-dimensional model, wherein the first target position and the second target position are both used to represent the same corresponding position of the target part in two-dimensional and three-dimensional space.

[0187] like Fig.11As shown, the width of a preset position on a first target contour corresponding to the target part is measured using a measurement mark in a two-dimensional ultrasound image to obtain measurement data X. The measurement data X is displayed at a second position that is the same as the first position in a three-dimensional model corresponding to the target part, so that the user can more intuitively know the corresponding size of the target part from the three-dimensional model.

[0188] See also Fig.12 In some embodiments, the method further includes: simultaneously displaying or fusion displaying at least one frame of the two-dimensional ultrasound image of the target part and the three-dimensional model of the target in the same display interface.

[0189] Exemplarily, the display mode of the two-dimensional ultrasound image and the three-dimensional model corresponding to the target part can be to display the two-dimensional ultrasound image and the target three-dimensional model on different display screens respectively, or to display the two-dimensional ultrasound image and the target three-dimensional model together on different display interfaces of the same display, or to display the two-dimensional ultrasound image and the target three-dimensional model in different display windows under the same display interface of the same display, or to display the two-dimensional ultrasound image and the target three-dimensional model in different display areas under the same display interface of the same display. Alternatively, the two-dimensional ultrasound image and the target three-dimensional model are fused and displayed on the same display interface.

[0190] Optionally, the fusing and displaying at least one frame of the two-dimensional ultrasound image of the target part and the target three-dimensional model in the same display interface includes:

[0191] At least one frame of the two-dimensional ultrasound image of the target part and the target three-dimensional model are displayed in the same display interface, wherein the target three-dimensional model covers the target area where the structural features of the target part in the two-dimensional ultrasound image are located.

[0192] like Fig.12 As shown, the edge of the target three-dimensional model approximately coincides with the edge of the structural feature of the target part in the two-dimensional ultrasound image.

[0193] It should be understood that the use of colors to color some of the structures in the drawings corresponding to the specification of this application is only to facilitate the distinction between different structures in the drawings and to facilitate the understanding of the technical solutions to be protected in this application in combination with the text of the specification, and is not to protect the colors in the drawings. Moreover, the colors in the drawings can be changed as needed.

[0194] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0195] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for generating a three-dimensional ultrasound model, characterized in that: The method comprises: Acquire a two-dimensional ultrasound image corresponding to a target ultrasound section of a target part, wherein the two-dimensional ultrasound image includes structural features of the target part and lesion features of the target part; Acquire a first target contour corresponding to the structural features of the target part and a first lesion contour corresponding to the lesion features of the target part in the two-dimensional ultrasound image, and determine a plurality of first deformation reference points on the first target contour and a plurality of second deformation reference points on the first lesion contour; Acquire a basic three-dimensional model corresponding to the target part, and determine a basic model section that matches the target ultrasound section in the basic three-dimensional model, wherein the basic model section includes structural features of the target part and lesion features of the target part; Acquire a second target contour corresponding to the structural features of the target part in the section of the base model, and determine at least two first deformation control points corresponding to at least two of the first deformation reference points on at least the second target contour, and acquire a second lesion contour corresponding to the lesion features of the target part in the section of the base model, and determine at least two second deformation control points corresponding to at least two of the second deformation reference points on at least the second lesion contour; Determining first model deformation information of the basic three-dimensional model according to the first deformation reference point and the first deformation control point, and determining second model deformation information of the basic three-dimensional model according to the second deformation reference point and the second deformation control point; The basic three-dimensional model is deformed into a target three-dimensional model at least according to the first model deformation information and the second model deformation information.

2. The method for generating a three-dimensional ultrasound model according to claim 1, characterized in that: The obtaining of a first target contour corresponding to the structural feature of the target part in the two-dimensional ultrasonic image includes: In response to a first contour drawing operation performed by a user on the two-dimensional ultrasonic image, determining a first target contour corresponding to the structural feature of the target part from the two-dimensional ultrasonic image; Alternatively, a plurality of first contour control points are determined on the two-dimensional ultrasound image, and a first contour curve is formed by interpolation between adjacent first contour control points, and the first contour curve is used as a first target contour corresponding to the structural feature of the target part; Alternatively, a first target contour corresponding to the structural feature of the target part is acquired from the two-dimensional ultrasound image through a preset first contour recognition model.

3. The method for generating a three-dimensional ultrasound model according to claim 1, characterized in that: The obtaining of a first lesion contour corresponding to the lesion feature of the target part in the two-dimensional ultrasound image includes: In response to a second contour drawing operation performed by a user on the two-dimensional ultrasound image, determining a first lesion contour corresponding to a lesion feature of the target part from the two-dimensional ultrasound image; Alternatively, a plurality of second contour control points are determined on the two-dimensional ultrasound image, and a second contour curve is formed by interpolation between adjacent second contour control points, and the second contour curve is used as a first lesion contour corresponding to the lesion feature of the target part; Alternatively, a first lesion contour corresponding to the lesion feature of the target site is acquired from the two-dimensional ultrasound image through a preset second contour recognition model.

4. The method for generating a three-dimensional ultrasound model according to claim 1, characterized in that: The step of determining a plurality of first deformation reference points on the first target contour comprises: Based on a preset first rule, multiple first deformation reference points are determined on the first target contour; or, multiple first key reference points are determined on the first target contour, and based on a preset second rule, first key contour points are determined on the contour between each adjacent two of the first key reference points, and the first key contour points and the first key reference points are used as multiple first deformation reference points on the first target contour.

5. The method for generating a three-dimensional ultrasound model according to claim 1, characterized in that: The step of determining a plurality of second deformation reference points on the first lesion contour comprises: Based on a preset third rule, multiple second deformation reference points are determined on the first lesion contour; or, multiple second key reference points are determined on the first lesion contour, and based on a preset fourth rule, key contour points are determined on the contour between each adjacent two of the second key reference points, and the second key contour points and the second key reference points are used as multiple second deformation reference points on the first lesion contour.

6. The method for generating a three-dimensional ultrasound model according to claim 1, characterized in that: The step of obtaining a two-dimensional ultrasound image corresponding to a target ultrasound section of a target part includes: Acquire two-dimensional ultrasound images corresponding to the target part on at least two different long-axis sections, wherein any two different long-axis sections are arranged at an angle; Alternatively, a corresponding two-dimensional ultrasound image on at least one long-axis section and a corresponding two-dimensional ultrasound image on at least one short-axis section of the target part are obtained.

7. The method for generating a three-dimensional ultrasound model according to claim 1, characterized in that: The determining the first model deformation information of the basic three-dimensional model according to the first deformation reference point and the first deformation control point includes: Determine a plurality of first deformation amounts corresponding to a plurality of first deformation reference points on the first target contour and a plurality of first deformation control points on the second target contour that match the first deformation reference points, and determine first model deformation information of the basic three-dimensional model at least based on the plurality of first deformation amounts; Alternatively, determine a plurality of first deformation amounts corresponding to a plurality of first deformation reference points on the first target contour and a plurality of first deformation control points on the second target contour that correspond one-to-one to the first deformation reference points, and determine a first mesh deformation amount corresponding to a first model mesh matching each of the first deformation control points in the basic three-dimensional model based on the first deformation amounts, wherein the first model mesh is used to describe the structural features of the target part; and determine first model deformation information of the basic three-dimensional model based on the first deformation amounts and the first mesh deformation amounts.

8. The method for generating a three-dimensional ultrasound model according to claim 1, characterized in that: The determining the second model deformation information of the basic three-dimensional model according to the second deformation reference point and the second deformation control point includes: Determine a plurality of second deformation amounts corresponding to a plurality of second deformation reference points on the first lesion contour and a plurality of second deformation control points on the second lesion contour that match the second deformation reference points, and determine second model deformation information of the basic three-dimensional model according to the plurality of second deformation amounts; Alternatively, determine a plurality of second deformation amounts corresponding to a plurality of second deformation reference points on the first lesion contour and a plurality of second deformation control points on the second lesion contour that correspond one-to-one to the second deformation reference points, and determine a second mesh deformation amount corresponding to a second model mesh matching each second deformation control point in the basic three-dimensional model based on the second deformation amount, wherein the second model mesh is used to describe the lesion characteristics of the target site; and determine the second model deformation information of the basic three-dimensional model according to the second deformation amount and the second mesh deformation amount.

9. The method for generating a three-dimensional ultrasound model according to claim 1, characterized in that: The deforming the basic three-dimensional model into a target three-dimensional model according to the first model deformation information and the second model deformation information includes: The structural features of the target part in the basic three-dimensional model are deformed according to the first model deformation information, and the lesion features of the target part in the basic three-dimensional model are deformed according to the second model deformation information, so as to obtain the target three-dimensional model.

10. The method for generating a three-dimensional ultrasound model according to claim 9, characterized in that: The first deformation reference point corresponds to the first deformation control point one by one, the second deformation reference point corresponds to the second deformation control point one by one, the structural features of the target part in the basic three-dimensional model are deformed according to the first model deformation information, and the lesion features of the target part in the basic three-dimensional model are deformed according to the second model deformation information, including: According to the first model deformation information, it is determined that at least the first deformation control point of the basic three-dimensional model is aligned with the first deformation reference point as the first alignment target until the first deformation control point and the corresponding first deformation reference point coincide with each other; and according to the second model deformation information, it is determined that at least the second deformation control point of the basic three-dimensional model is aligned with the second deformation reference point as the second alignment target until the second deformation control point and the corresponding second deformation reference point coincide with each other, thereby obtaining the target three-dimensional model.

11. The method for generating a three-dimensional ultrasound model according to claim 1, characterized in that: The method further comprises: Determine a first target position based on a target contour of the two-dimensional ultrasound image and generate a measurement mark, and measure the first target position based on the measurement mark to obtain measurement data; A second target position matching the first target position is determined on the target three-dimensional model, and the measurement mark and the measurement data are displayed in association at the second target position, wherein the target contour includes the first target contour and / or the first lesion contour.

12. The method for generating a three-dimensional ultrasound model according to any one of claims 1 to 11, characterized in that: The method further comprises: At least one frame of the two-dimensional ultrasound image of the target part and the target three-dimensional model are simultaneously displayed or fused in the same display interface.

13. The method for generating a three-dimensional ultrasound model according to claim 12, characterized in that: The method of fusing and displaying at least one frame of the two-dimensional ultrasound image of the target part and the three-dimensional model of the target in the same display interface includes: At least one frame of the two-dimensional ultrasound image of the target part and the target three-dimensional model are displayed in the same display interface, wherein the target three-dimensional model covers the target area where the structural features of the target part in the two-dimensional ultrasound image are located.

14. A method for generating a three-dimensional ultrasound model, characterized in that: The method comprises: Acquire a two-dimensional ultrasonic image corresponding to a target ultrasonic section of a target part, wherein the two-dimensional ultrasonic image at least includes structural features of the target part; Acquire a first target contour corresponding to the structural features of the target part in the two-dimensional ultrasound image, and determine a plurality of first deformation reference points on the first target contour; Acquire a basic three-dimensional model corresponding to the target part, and determine a basic model section that matches the target ultrasound section in the basic three-dimensional model, wherein the basic model section includes structural features of the target part; Acquire a second target contour corresponding to the structural features of the target part in the cross section of the base model, and determine at least two first deformation control points corresponding to at least two of the first deformation reference points on the second target contour; Determining first model deformation information of the basic three-dimensional model according to the first deformation reference point and the first deformation control point; The basic three-dimensional model is deformed into a target three-dimensional model at least according to the first model deformation information.

15. The method for generating a three-dimensional ultrasound model according to claim 14, characterized in that: The first deformation reference point corresponds to the first deformation control point one by one, and deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information includes: According to the first model deformation information, determine to align the first deformation control point of the basic three-dimensional model with at least the first deformation reference point as a first alignment target until the first deformation control point coincides with the corresponding first deformation reference point, thereby obtaining a target three-dimensional model.

16. The method for generating a three-dimensional ultrasound model according to claim 14, characterized in that: The step of obtaining a two-dimensional ultrasound image corresponding to a target ultrasound section of a target part includes: Acquire two-dimensional ultrasound images corresponding to the target part on at least two different long-axis sections, wherein any two different long-axis sections are arranged at an angle; Alternatively, a corresponding two-dimensional ultrasound image on at least one long-axis section and a corresponding two-dimensional ultrasound image on at least one short-axis section of the target part are obtained.

17. The method for generating a three-dimensional ultrasound model according to claim 14, characterized in that: The obtaining of a first target contour corresponding to the structural feature of the target part in the two-dimensional ultrasonic image includes: In response to a first contour drawing operation performed by a user on the two-dimensional ultrasonic image, determining a first target contour corresponding to the structural feature of the target part from the two-dimensional ultrasonic image; Alternatively, a plurality of first contour control points are determined on the two-dimensional ultrasound image, and a first contour curve is formed by interpolation between adjacent first contour control points, and the first contour curve is used as a first target contour corresponding to the structural feature of the target part; Alternatively, a first target contour corresponding to the structural feature of the target part is acquired from the two-dimensional ultrasound image through a preset first contour recognition model.

18. The method for generating a three-dimensional ultrasound model according to claim 14, characterized in that: The step of determining a plurality of first deformation reference points on the first target contour comprises: Determining a plurality of first deformation reference points on the first target contour based on a preset first rule; Alternatively, multiple first key reference points are determined on the first target contour, and first key contour points are determined on the contour between each adjacent two of the first key reference points based on a preset second rule, and the first key contour points and the first key reference points are used as multiple first deformation reference points on the first target contour.

19. The method for generating a three-dimensional ultrasound model according to claim 14, characterized in that: The two-dimensional ultrasound image also includes the lesion features of the target part. Before deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information, the method further includes: Acquiring the lesion characteristics of the target part in the two-dimensional ultrasound image; The step of deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information includes: The basic three-dimensional model is deformed according to the first model deformation information, and the lesion is displayed on the deformed basic three-dimensional model according to the lesion characteristics to obtain a target three-dimensional model.

20. The method for generating a three-dimensional ultrasound model according to claim 19, characterized in that: The step of displaying the lesion on the deformed basic three-dimensional model according to the lesion features to obtain a target three-dimensional model includes: Determine, according to the lesion characteristics, a three-dimensional lesion morphology corresponding to the lesion region of the target part and a lesion mapping position of the lesion region on the deformed basic three-dimensional model; The three-dimensional lesion morphology is displayed at the lesion mapping position of the deformed basic three-dimensional model to obtain a target three-dimensional model.

21. The method for generating a three-dimensional ultrasound model according to claim 14, characterized in that: The two-dimensional ultrasound image also includes the lesion features of the target part. Before deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information, the method further includes: Acquiring the lesion characteristics of the target part in the two-dimensional ultrasound image; The step of deforming the basic three-dimensional model into a target three-dimensional model at least according to the first model deformation information includes: Deforming the structural features of the target part in the basic three-dimensional model according to the first model deformation information; Determining, according to the lesion characteristics of the target part, a first lesion contour corresponding to the lesion region of the target part and a lesion mapping position of the lesion region on the deformed basic three-dimensional model; The target three-dimensional model is obtained by interpolating the first lesion contour to generate a three-dimensional lesion shape corresponding to the lesion area, and displaying the three-dimensional lesion shape at the lesion mapping position of the deformed basic three-dimensional model.

22. The method for generating a three-dimensional ultrasound model according to claim 21, characterized in that: The first deformation reference point corresponds to the first deformation control point one by one, and deforming the structural features of the target part in the basic three-dimensional model according to the first model deformation information includes: According to the first model deformation information, determine to align the first deformation control point of the basic three-dimensional model with at least the first deformation reference point as a first alignment target until the first deformation control point coincides with the corresponding first deformation reference point.

23. The method for generating a three-dimensional ultrasound model according to claim 14, characterized in that: The method further comprises: Determine a first target position based on a target contour of the two-dimensional ultrasound image and generate a measurement mark, and measure the first target position based on the measurement mark to obtain measurement data; A second target position matching the first target position is determined on the target three-dimensional model, and the measurement mark and the measurement data are displayed in association at the second target position, wherein the target contour includes the first target contour and / or the first lesion contour.

24. The method for generating a three-dimensional ultrasound model according to any one of claims 14 to 23, characterized in that: The method further comprises: At least one frame of the two-dimensional ultrasound image of the target part and the target three-dimensional model are simultaneously displayed or fused in the same display interface.

25. The method for generating a three-dimensional ultrasound model according to claim 24, characterized in that: The method of fusing and displaying at least one frame of the two-dimensional ultrasound image of the target part and the three-dimensional model of the target in the same display interface includes: At least one frame of the two-dimensional ultrasound image of the target part and the target three-dimensional model are displayed in the same display interface, wherein the target three-dimensional model covers the target area where the structural features of the target part in the two-dimensional ultrasound image are located.

26. A device for generating a three-dimensional ultrasound model, characterized in that: include: A memory, the memory being used to store a program; A processor, wherein the processor is used to generate a two-dimensional ultrasound image corresponding to a target ultrasound section of the target part according to the echo signal, and the processor is also used to implement the steps of the method for generating a three-dimensional ultrasound model as described in any one of claims 1 to 25 by executing the program stored in the memory.

27. An ultrasonic imaging system, characterized in that: include: An ultrasonic probe, wherein the ultrasonic probe comprises a plurality of array elements; A transmitting circuit, used for stimulating the ultrasonic probe to transmit ultrasonic waves to a target site; A receiving circuit, used for controlling the ultrasonic probe to receive the ultrasonic echo signal; A memory, the memory being used to store a program; a processor, the processor being used to generate a two-dimensional ultrasound image corresponding to a target ultrasound section of the target part according to the echo signal, the processor being further used to implement the steps of the method for generating a three-dimensional ultrasound model according to any one of claims 1 to 25 by executing a program stored in the memory; The display is at least used to display the ultrasound image and / or the three-dimensional model generated by the processor.

Images