Vascular ultrasound image processing method, device, equipment and medium

Abstract

The embodiment of the invention discloses a blood vessel ultrasonic image processing method, device and equipment and a medium, and the method comprises the steps: obtaining a to-be-processed intravascular ultrasonic image, and detecting a shielded region in the to-be-processed intravascular ultrasonic image; performing target object detection in a non-occlusion region except the occluded region of the intravascular ultrasound image to be processed to obtain a first detection result of the target object; constructing a target implicit expression of the target object based on the first detection result; and determining a second detection result of the target object in the shielded area according to the target implicit expression, and completing target object recovery processing of the intravascular ultrasound image to be processed. According to the technical scheme of the embodiment, the problem that the process of restoring the occluded object in the image by constructing a deep learning model is complex and low in efficiency at present is solved, and the speed and accuracy of restoring the occluded object in the blood vessel image are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of image processing technology, and in particular to a method, device, equipment and medium for processing vascular ultrasound images. Background Art

[0002] Intravascular stent detection can be performed based on intravascular ultrasound (IVUS) images to assist doctors in evaluating the deployment and position of vascular stents. Due to the obstruction of high-density objects such as guidewires during IVUS imaging, stents in some areas cannot be observed, which in turn affects the above evaluation content. Therefore, image repair of the obscured vascular stents is required.

[0003] At present, vascular stent restoration is mostly performed through contour fitting or deep learning. Model training needs to be performed separately for stents with different structures. The process is relatively complicated and the efficiency of stent restoration needs to be improved. Summary of the invention

[0004] The embodiments of the present invention provide a vascular ultrasound image processing method, device, equipment and medium, which can realize the recovery processing of occluded objects in intravascular ultrasound images without relying on neural network training, avoid the cumbersome model training process, and improve the speed and accuracy of restoring occluded objects in vascular images.

[0005] In a first aspect, an embodiment of the present invention provides a method for processing a vascular ultrasound image, the method comprising:

[0006] Acquiring an intravascular ultrasound image to be processed, and detecting an obstructed area in the intravascular ultrasound image to be processed;

[0007] Performing target object detection in a non-blocked area of ​​the intravascular ultrasound image to be processed except the blocked area to obtain a first detection result of the target object;

[0008] Constructing a target implicit expression of the target object based on the first detection result;

[0009] A second detection result of the target object in the blocked area is determined according to the target implicit expression, and target object recovery processing of the intravascular ultrasound image to be processed is completed.

[0010] Optionally, constructing an implicit expression of the target object based on the first detection result includes:

[0011] Determining a constraint formula of an implicit expression of the target object according to structural attribute information of the target object;

[0012] Determining preset network parameters in the implicit expression of the target object according to the constraint formula and the pixel information in the first detection result;

[0013] The target object implicit expression is determined based on the preset network parameters.

[0014] Optionally, determining a constraint formula of an implicit expression of the target object according to structural attribute information of the target object includes:

[0015] Fitting the contour of the target object according to the coordinate information of each pixel point in the first detection result to obtain a target fitting result;

[0016] Establishing a constraint formula of the implicit expression of the target object based on the target fitting result and the structural attribute information;

[0017] The structural property information includes stress and strain information of the three-dimensional structure.

[0018] Optionally, determining a second detection result of the target object in the target occlusion area according to the target object implicit expression includes:

[0019] Inputting the coordinate information of each pixel point in the target occlusion area into the target object implicit expression respectively to obtain the implicit expression result of each pixel point;

[0020] Determining whether each of the pixel points belongs to a pixel point of the target object based on the implicit expression result;

[0021] A set of all pixel points belonging to the target object in the target occlusion area is taken as a second detection result.

[0022] Optionally, the method further includes:

[0023] Selecting an area containing a preset number of pixels in the non-blocked area as the area to be checked;

[0024] Constructing a verification implicit expression of the target object based on the second detection result and the pixel points in the non-occluded area except the area to be verified;

[0025] Input the coordinate information of each pixel point in the area to be verified into the verification implicit expression respectively, and obtain the verification implicit expression result of each pixel point in the area to be verified;

[0026] The accuracy of the second detection result is analyzed according to the verification implicit expression result.

[0027] Optionally, detecting the blocked area in the intravascular ultrasound image to be processed includes:

[0028] Inputting the intravascular ultrasound image to be processed into a pre-trained occlusion region recognition model;

[0029] The occluded area is determined based on an output result of the occluded area recognition model.

[0030] Optionally, performing target object detection in a non-occluded area of ​​the intravascular ultrasound image to be processed except the occluded area to obtain a first detection result of the target object includes:

[0031] Inputting the image in the non-occluded area into a pre-trained target object recognition model;

[0032] A first detection result of the target object is determined based on an output result of the target object recognition model.

[0033] Optionally, the target object is a vascular stent.

[0034] In a second aspect, an embodiment of the present invention provides a vascular ultrasonic image processing device, the device comprising:

[0035] An image region recognition module, used for acquiring an intravascular ultrasound image to be processed and detecting an obstructed region in the intravascular ultrasound image to be processed;

[0036] An image object recognition module, configured to detect a target object in a non-occluded area other than the occluded area of ​​the intravascular ultrasound image to be processed, and obtain a first detection result of the target object;

[0037] A target object description determination module, used to construct a target implicit expression of the target object based on the first detection result;

[0038] The target object determination module is used to determine the second detection result of the target object in the blocked area according to the target implicit expression, and complete the target object recovery processing of the intravascular ultrasound image to be processed.

[0039] Optionally, the target object description determination module is specifically used to:

[0040] Determining a constraint formula of an implicit expression of the target object according to structural attribute information of the target object;

[0041] Determining preset network parameters in the implicit expression of the target object according to the constraint formula and the pixel information in the first detection result;

[0042] The target object implicit expression is determined based on the preset network parameters.

[0043] Optionally, the target object description determination module is further used to:

[0044] Fitting the contour of the target object according to the coordinate information of each pixel point in the first detection result to obtain a target fitting result;

[0045] Establishing a constraint formula of the implicit expression of the target object based on the target fitting result and the structural attribute information;

[0046] The structural property information includes stress and strain information of the three-dimensional structure.

[0047] Optionally, the target object determination module is specifically used to:

[0048] Inputting the coordinate information of each pixel point in the target occlusion area into the target object implicit expression respectively to obtain the implicit expression result of each pixel point;

[0049] Determining whether each of the pixel points belongs to a pixel point of the target object based on the implicit expression result;

[0050] A set of all pixel points belonging to the target object in the target occlusion area is taken as a second detection result.

[0051] Optionally, the vascular ultrasonic image processing device further includes a target object recognition and analysis module for:

[0052] Selecting an area containing a preset number of pixels in the non-blocked area as the area to be checked;

[0053] Constructing a verification implicit expression of the target object based on the second detection result and the pixel points in the non-occluded area except the area to be verified;

[0054] Input the coordinate information of each pixel point in the area to be verified into the verification implicit expression respectively, and obtain the verification implicit expression result of each pixel point in the area to be verified;

[0055] The accuracy of the second detection result is analyzed according to the verification implicit expression result.

[0056] Optionally, the image region recognition module is specifically used for:

[0057] Inputting the intravascular ultrasound image to be processed into a pre-trained occlusion region recognition model;

[0058] The occluded area is determined based on an output result of the occluded area recognition model.

[0059] Optionally, the image object recognition module is specifically used to:

[0060] Inputting the image in the non-occluded area into a pre-trained target object recognition model;

[0061] A first detection result of the target object is determined based on an output result of the target object recognition model.

[0062] Optionally, the target object is a vascular stent.

[0063] In a third aspect, an embodiment of the present invention provides a computer device, the computer device comprising:

[0064] one or more processors;

[0065] A memory for storing one or more programs;

[0066] When the one or more programs are executed by the one or more processors, the one or more processors implement the vascular ultrasound image processing method described in any embodiment.

[0067] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vascular ultrasound image processing method described in any embodiment.

[0068] The technical solution provided by the embodiment of the present invention is to obtain an intravascular ultrasound image to be processed and detect the occluded area in the intravascular ultrasound image to be processed; perform target object detection in the non-occluded area of ​​the intravascular ultrasound image to be processed except the occluded area to obtain a first detection result of the target object; construct a target implicit expression of the target object based on the first detection result; determine a second detection result of the target object in the occluded area according to the target implicit expression, and complete the target object recovery processing of the intravascular ultrasound image to be processed. The technical solution of this embodiment solves the problem that the current process of recovering occluded objects in images by constructing a deep learning model is complex and inefficient. It can realize the recovery processing of occluded objects in intravascular ultrasound images without relying on neural network training, avoid the cumbersome model training process, and improve the speed and accuracy of recovering occluded objects in vascular images. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 is a flow chart of a vascular ultrasound image processing method provided by an embodiment of the present invention;

[0070] Figure 2 It is a schematic diagram of an obstructed area in a blood vessel ultrasound image provided by an embodiment of the present invention;

[0071] Figure 3is a schematic diagram of a target object in a vascular ultrasound image provided by an embodiment of the present invention;

[0072] Figure 4 is a flow chart of a vascular ultrasound image processing method provided by an embodiment of the present invention;

[0073] Figure 5 is a structural schematic diagram of a vascular ultrasonic image processing device provided by an embodiment of the present invention;

[0074] Figure 6 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0076] Figure 1 This is a flow chart of a vascular ultrasound image processing method provided by an embodiment of the present invention. The embodiment of the present invention can be applied to the scenario of image restoration of occluded objects in intravascular ultrasound images, especially the detection and restoration of vascular stents. The method can be executed by a vascular ultrasound image processing device, which can be implemented by software and / or hardware and integrated in a computer device with application development function.

[0077] like Figure 1 As shown, the blood vessel ultrasound image processing method includes the following steps:

[0078] S110, acquiring an intravascular ultrasound image to be processed, and detecting an obstructed area in the intravascular ultrasound image to be processed.

[0079] In this embodiment, the goal of the image processing process is to restore the obscured objects in the image. Intravascular Ultrasound (IVUS) imaging is performed by introducing an ultrasound probe into a guidewire and placing an ultrasonic imaging device inside a coronary artery. Due to the obstruction of high-density objects such as the guidewire during IVUS imaging, the target object in the obscured area cannot be observed and analyzed, which will have a certain impact on the clinical application of intravascular ultrasound images. Therefore, in this embodiment, it is hoped that the obscured target object in the intravascular ultrasound image to be processed can be quickly restored in a simple manner.

[0080] The intravascular ultrasound image to be processed is an image having an occluded portion, and a target object in the occluded portion needs to be subjected to image restoration processing.

[0081] For detecting the occluded area in the intravascular ultrasound image to be processed, the occluded area and the non-occluded area can be distinguished based on the difference characteristics between the pixel information of the occluded area and the pixel information of the non-occluded area. For example, the occluded area and the non-occluded area can be distinguished by a pre-trained deep learning network, or by semantic segmentation and other methods.

[0082] In an optional embodiment, the size of the intravascular ultrasound image data is 512*512*N, where N is defined as the number of layers of the intravascular ultrasound image. For each layer, we define it as a cross-section, and its image size is 512*512. The intravascular ultrasound image to be processed can be input into a pre-trained occlusion area recognition model; the occluded area is determined based on the output result of the occlusion area recognition model. To facilitate image data processing, the image can be converted from a Cartesian coordinate system to a polar coordinate system, and then restored to a Cartesian coordinate system after the occluded area is located. The recognition result of the occluded area can be referred to. Figure 2 The area shown in .

[0083] S120 , performing target object detection in a non-occluded area of ​​the intravascular ultrasound image to be processed except the occluded area, to obtain a first detection result of the target object.

[0084] After determining the occluded area, the non-occluded area of ​​the intravascular ultrasound image to be processed can be determined, and the non-occluded area image can be input into a pre-trained target object recognition model; then, the first detection result of the target object is determined based on the output result of the target object recognition model.

[0085] The first detection result of the target object is the location information of the target object in the non-blocked area of ​​the intravascular ultrasound image to be processed.

[0086] The target object recognition model can be a deep learning network trained based on intravascular ultrasound image samples marked with target objects, and can recognize target objects in intravascular ultrasound images.

[0087] S130. Construct a target implicit expression of the target object based on the first detection result.

[0088] Among them, the implicit expression of the target object can be based on This expression is determined as the objective function. This expression can be understood as a general expression for describing objects in space. After inputting the coordinate information of an object in the image into the formula, the corresponding probability value can be obtained.

[0089] Among them, f θ is the network parameter to be learned, γ is the given position encoding method, and n is the number of pixels in the non-occluded area. The first detection result is the pixel point that is determined to belong to the target object. The coordinate information of each pixel point corresponding to the first detection result can be input into the above objective function to solve the above network parameters to be learned to determine the target implicit expression. It can be understood that the above objective function can be determined based on the physical description characteristics of the target object.

[0090] S140. Determine a second detection result of the target object in the blocked area according to the target implicit expression, and complete target object recovery processing of the intravascular ultrasound image to be processed.

[0091] After determining the target implicit expression, the coordinate information of each pixel in the occluded area is input into the expression to obtain the probability value of each pixel belonging to the target object. When the probability value corresponding to each pixel is greater than a preset probability standard threshold, it can be determined whether each pixel is a target object pixel.

[0092] For each pixel in the blocked area, after the above analysis and judgment, all the pixels in the blocked area belonging to the target object can be determined to obtain a second detection result.

[0093] Correspondingly, the set of the first detection result and the second detection result is the entire target object, that is, the image restoration processing of the target object in the intravascular ultrasound image to be processed is realized. Figure 3 The target object may be any object that can be detected in a blood vessel, such as a vascular stent, a plaque, a calcification trace, etc., which may be determined according to actual image processing requirements.

[0094] The technical solution provided by the embodiment of the present invention is to obtain an intravascular ultrasound image to be processed and detect the occluded area in the intravascular ultrasound image to be processed; perform target object detection in the non-occluded area of ​​the intravascular ultrasound image to be processed except the occluded area to obtain a first detection result of the target object; construct a target implicit expression of the target object based on the first detection result; determine a second detection result of the target object in the occluded area according to the target implicit expression, and complete the target object recovery processing of the intravascular ultrasound image to be processed. The technical solution of this embodiment solves the problem that the current process of recovering occluded objects in images by constructing a deep learning model is complex and inefficient. It can realize the recovery processing of occluded objects in intravascular ultrasound images without relying on neural network training, avoid the cumbersome model training process, and improve the speed and accuracy of recovering occluded objects in vascular images.

[0095] Figure 4 It is a flow chart of a vascular ultrasound image processing method provided by an embodiment of the present invention. On the basis of the above embodiment, a process of further analyzing the image restoration accuracy based on the restoration result of the target object is provided. The method can be executed by a vascular ultrasound image processing device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0096] like Figure 4 As shown, the blood vessel ultrasound image processing method includes the following steps:

[0097] S210, acquiring an intravascular ultrasonic image to be processed, and detecting an obstructed area in the intravascular ultrasonic image to be processed.

[0098] S220 , performing target object detection in a non-occluded area of ​​the intravascular ultrasound image to be processed except the occluded area, to obtain a first detection result of the target object.

[0099] S230. Construct a target implicit expression of the target object based on the first detection result.

[0100] Specifically, the process of constructing the target implicit expression of the target object may be to first determine the constraint formula of the target object implicit expression based on the structural attribute information of the target object; then, determine the preset network parameters in the target object implicit expression based on the constraint formula and the pixel information in the first detection result; finally, determine the target object implicit expression based on the preset network parameters.

[0101] The structural attribute information of the target object can be information in a physical description feature of the target object. For example, when the target object is a vascular stent, since the stent design should not have obvious fractures, that is, the internal stress of the stent should be spatially continuous. Therefore, the Newton-Leibniz formula can be used to convert the internal stress of the stent into the form of displacement as a physical constraint of the neural network.

[0102]

[0103] Where Δ is a constant, and F can be calculated by the distance between the bracket of the unblocked area and the marked circle after ellipse fitting, combined with the assumption of Hooke's law, that is, the stress and strain of linear elastic materials are proportional. That is, the contour of the target object is fitted according to the coordinate information of each pixel point in the first detection result to obtain the target fitting result; based on the target fitting result and the structural attribute information, a constraint formula of the implicit expression of the target object is established.

[0104] Where E is the elastic modulus.

[0105] Therefore, combining the above two formulas, we can combine the decomposition of force to constrain in various directions, taking the x direction as an example:

[0106] The coordinate information of each pixel point corresponding to the first detection result is input into the above constraint function, and the above network parameters that need to be learned are solved to determine the target implicit expression.

[0107] S240. Determine a second detection result of the target object in the blocked area according to the target implicit expression, and complete target object recovery processing of the intravascular ultrasound image to be processed.

[0108] S250. Select an area containing a preset number of pixels in the non-occluded area as the area to be verified, and construct an implicit verification expression for the target object based on the second detection result and the pixel points in the non-occluded area except the area to be verified.

[0109] In this embodiment, the target object restoration result can be further evaluated to optimize the target implicit expression, that is, the second detection result is used as the determined known pixel point, and an area containing a preset number of pixels in the non-occluded area is selected as the area to be verified, that is, the area to be restored.

[0110] S260, input the coordinate information of each pixel point in the area to be verified into the verification implicit expression respectively, obtain the verification implicit expression result of each pixel point in the area to be verified, and analyze the accuracy of the second detection result according to the verification implicit expression result.

[0111] The restoration result corresponding to the area to be verified is compared with its original pixel attribute (whether it belongs to the target object), so that the image restoration accuracy of the area to be verified can be determined. In this embodiment, the calculated image restoration accuracy can be used to evaluate the accuracy of the second detection result as a reference. Furthermore, the parameters of the target implicit expression can also be optimized based on the evaluation results to express the target object more accurately. In actual application, the evaluation results can also be used as a reference to reduce the impact of erroneous restoration results on the doctor's evaluation process.

[0112] The technical solution provided by the embodiment of the present invention is as follows: acquiring an intravascular ultrasound image to be processed and detecting an occluded area in the intravascular ultrasound image to be processed; performing target object detection in a non-occluded area of ​​the intravascular ultrasound image to be processed except the occluded area to obtain a first detection result of the target object; constructing a target implicit expression of the target object based on the first detection result; determining a second detection result of the target object in the occluded area according to the target implicit expression to complete target object recovery processing of the intravascular ultrasound image to be processed; selecting an area containing a preset number of pixels in the non-occluded area as an area to be verified, and constructing a verification implicit expression of the target object based on the second detection result and the pixel points in the non-occluded area except the area to be verified; inputting the coordinate information of each pixel point in the area to be verified into the verification implicit expression respectively to obtain a verification implicit expression result of each pixel point in the area to be verified, and analyzing the accuracy of the second detection result according to the verification implicit expression result. The technical solution of this embodiment solves the problem that the current process of restoring occluded objects in images by building deep learning models is complex and inefficient. It can realize the restoration of occluded objects in intravascular ultrasound images without relying on neural network training, avoids the tedious model training process, and improves the speed and accuracy of restoring occluded objects in vascular images; it can also further evaluate the target object restoration results, thereby optimizing the target implicit expression.

[0113] Figure 5 It is a structural schematic diagram of a vascular ultrasound image processing device provided by an embodiment of the present invention. The embodiment of the present invention can be applied to the scenario of generating intravascular images based on intravascular ultrasound signals, especially the situation of suppressing artifact signals in the image. The device can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0114] like Figure 5As shown, the blood vessel ultrasound image processing device includes: an image region recognition module 310 , an image object recognition module 320 , a target object description determination module 330 and a target object determination module 340 .

[0115] Among them, the image area recognition module 310 is used to obtain the intravascular ultrasound image to be processed and detect the occluded area in the intravascular ultrasound image to be processed; the image object recognition module 320 is used to perform target object detection in the non-occluded area of ​​the intravascular ultrasound image to be processed except the occluded area, and obtain a first detection result of the target object; the target object description determination module 330 is used to construct a target implicit expression of the target object based on the first detection result; the target object determination module 340 is used to determine the second detection result of the target object in the occluded area according to the target implicit expression, and complete the target object recovery processing of the intravascular ultrasound image to be processed.

[0116] The technical solution provided by the embodiment of the present invention is to obtain an intravascular ultrasound image to be processed and detect the occluded area in the intravascular ultrasound image to be processed; perform target object detection in the non-occluded area of ​​the intravascular ultrasound image to be processed except the occluded area to obtain a first detection result of the target object; construct a target implicit expression of the target object based on the first detection result; determine a second detection result of the target object in the occluded area according to the target implicit expression, and complete the target object recovery processing of the intravascular ultrasound image to be processed. The technical solution of this embodiment solves the problem that the current process of recovering occluded objects in images by constructing a deep learning model is complex and inefficient. It can realize the recovery processing of occluded objects in intravascular ultrasound images without relying on neural network training, avoid the cumbersome model training process, and improve the speed and accuracy of recovering occluded objects in vascular images.

[0117] Optionally, the target object description determining module 330 is specifically used to:

[0118] Determining a constraint formula of an implicit expression of the target object according to structural attribute information of the target object;

[0119] Determining preset network parameters in the implicit expression of the target object according to the constraint formula and the pixel information in the first detection result;

[0120] The target object implicit expression is determined based on the preset network parameters.

[0121] Optionally, the target object description determination module 330 is further used to:

[0122] Fitting the contour of the target object according to the coordinate information of each pixel point in the first detection result to obtain a target fitting result;

[0123] Establishing a constraint formula of the implicit expression of the target object based on the target fitting result and the structural attribute information;

[0124] The structural property information includes stress and strain information of the three-dimensional structure.

[0125] Optionally, the target object determination module 340 is specifically used to:

[0126] Inputting the coordinate information of each pixel point in the target occlusion area into the target object implicit expression respectively to obtain the implicit expression result of each pixel point;

[0127] Determining whether each of the pixel points belongs to a pixel point of the target object based on the implicit expression result;

[0128] A set of all pixel points belonging to the target object in the target occlusion area is taken as a second detection result.

[0129] Optionally, the vascular ultrasonic image processing device further includes a target object recognition and analysis module for:

[0130] Selecting an area containing a preset number of pixels in the non-blocked area as the area to be checked;

[0131] Constructing a verification implicit expression of the target object based on the second detection result and the pixel points in the non-occluded area except the area to be verified;

[0132] Input the coordinate information of each pixel point in the area to be verified into the verification implicit expression respectively, and obtain the verification implicit expression result of each pixel point in the area to be verified;

[0133] The accuracy of the second detection result is analyzed according to the verification implicit expression result.

[0134] Optionally, the image region identification module 310 is specifically used for:

[0135] Inputting the intravascular ultrasound image to be processed into a pre-trained occlusion region recognition model;

[0136] The occluded area is determined based on an output result of the occluded area recognition model.

[0137] Optionally, the image object recognition module 320 is specifically used for:

[0138] Inputting the image in the non-occluded area into a pre-trained target object recognition model;

[0139] A first detection result of the target object is determined based on an output result of the target object recognition model.

[0140] Optionally, the target object is a vascular stent.

[0141] The vascular ultrasonic image processing device provided in the embodiment of the present invention can execute the vascular ultrasonic image processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0142] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Figure 6 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 6 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capability and can be configured in the angiography image display device.

[0143] like Figure 6 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0144] The bus 18 may be one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0145] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0146] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6not shown, usually called a "hard drive"). Although Figure 6 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0147] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0148] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0149] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing the vascular ultrasound image processing method provided in the embodiment of the present invention, which includes:

[0150] Acquiring an intravascular ultrasound image to be processed, and detecting an obstructed area in the intravascular ultrasound image to be processed;

[0151] Performing target object detection in a non-blocked area of ​​the intravascular ultrasound image to be processed except the blocked area to obtain a first detection result of the target object;

[0152] Constructing a target implicit expression of the target object based on the first detection result;

[0153] A second detection result of the target object in the blocked area is determined according to the target implicit expression, and target object recovery processing of the intravascular ultrasound image to be processed is completed.

[0154] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method for processing a vascular ultrasound image provided by any embodiment of the present invention is implemented, including:

[0155] Acquiring an intravascular ultrasound image to be processed, and detecting an obstructed area in the intravascular ultrasound image to be processed;

[0156] Performing target object detection in a non-blocked area of ​​the intravascular ultrasound image to be processed except the blocked area to obtain a first detection result of the target object;

[0157] Constructing a target implicit expression of the target object based on the first detection result;

[0158] A second detection result of the target object in the blocked area is determined according to the target implicit expression, and target object recovery processing of the intravascular ultrasound image to be processed is completed.

[0159] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0160] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0161] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0162] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0163] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0164] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for processing vascular ultrasound images, characterized in that: include: Acquire an intravascular ultrasound image to be processed, and detect an obstructed area in the intravascular ultrasound image to be processed; Performing target object detection in a non-blocked area of ​​the intravascular ultrasound image to be processed except the blocked area to obtain a first detection result of the target object; Constructing a target implicit expression of the target object based on the first detection result; A second detection result of the target object in the blocked area is determined according to the target implicit expression, and target object recovery processing of the intravascular ultrasound image to be processed is completed.

2. The method according to claim 1, characterized in that Constructing a target object implicit expression based on the first detection result includes: Determining a constraint formula of an implicit expression of the target object according to structural attribute information of the target object; Determining preset network parameters in the implicit expression of the target object according to the constraint formula and the pixel information in the first detection result; The target object implicit expression is determined based on the preset network parameters.

3. The method according to claim 2, characterized in that The step of determining the constraint formula of the implicit expression of the target object according to the structural attribute information of the target object includes: Fitting the contour of the target object according to the coordinate information of each pixel point in the first detection result to obtain a target fitting result; Establishing a constraint formula of the implicit expression of the target object based on the target fitting result and the structural attribute information; The structural property information includes stress and strain information of the three-dimensional structure.

4. The method according to claim 1, characterized in that Determining a second detection result of the target object in the target occlusion area according to the target object implicit expression includes: Inputting the coordinate information of each pixel point in the target occlusion area into the target object implicit expression respectively to obtain the implicit expression result of each pixel point; Determining whether each of the pixel points belongs to a pixel point of the target object based on the implicit expression result; A set of all pixel points belonging to the target object in the target occlusion area is taken as a second detection result.

5. The method according to claim 1, characterized in that The method also includes: Selecting an area containing a preset number of pixels in the non-blocked area as the area to be checked; Constructing a verification implicit expression of the target object based on the second detection result and the pixel points in the non-occluded area except the area to be verified; Input the coordinate information of each pixel point in the area to be verified into the verification implicit expression respectively, and obtain the verification implicit expression result of each pixel point in the area to be verified; The accuracy of the second detection result is analyzed according to the verification implicit expression result.

6. The method according to claim 1, characterized in that Detecting the blocked area in the intravascular ultrasound image to be processed includes: Inputting the intravascular ultrasound image to be processed into a pre-trained occlusion region recognition model; The occluded area is determined based on an output result of the occluded area recognition model.

7. The method according to claim 1, characterized in that Performing target object detection in a non-blocked area of ​​the intravascular ultrasound image to be processed except the blocked area to obtain a first detection result of the target object includes: Inputting the image in the non-occluded area into a pre-trained target object recognition model; A first detection result of the target object is determined based on an output result of the target object recognition model.

8. The method according to any one of claims 1 to 7, characterized in that: The target object is a vascular stent.

9. A blood vessel ultrasonic image processing device, characterized in that: include: An image region recognition module, used for acquiring an intravascular ultrasound image to be processed and detecting an obstructed region in the intravascular ultrasound image to be processed; An image object recognition module, configured to detect a target object in a non-occluded area other than the occluded area of ​​the intravascular ultrasound image to be processed, and obtain a first detection result of the target object; A target object description determination module, used to construct a target implicit expression of the target object based on the first detection result; The target object determination module is used to determine the second detection result of the target object in the blocked area according to the target implicit expression, and complete the target object recovery processing of the intravascular ultrasound image to be processed.

10. A computer device, characterized in that: The computer device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the vascular ultrasound image processing method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the vascular ultrasound image processing method as described in any one of claims 1 to 8 is implemented.

Images