CN110503642B

CN110503642B - Positioning method and system based on DSA image

Info

Publication number: CN110503642B
Application number: CN201910782193.3A
Authority: CN
Inventors: 王文智; 胡明辉; 马泽; 印胤; 杨光明; 秦岚
Original assignee: Union Strong Beijing Technology Co ltd
Current assignee: Union Strong Beijing Technology Co ltd
Priority date: 2019-08-23
Filing date: 2019-08-23
Publication date: 2021-10-29
Anticipated expiration: 2039-08-23
Also published as: CN110503642A

Abstract

The embodiment of the specification discloses a positioning method and a positioning system based on a DSA image, and belongs to the technical field of medical images and computers. The embodiment of the specification solves the problems that the macroscopic observation method is greatly influenced by subjective consciousness and takes much time by positioning the target region in the three-dimensional DSA image to be processed. The positioning method comprises the following steps: respectively obtaining two-dimensional images in a target direction from a three-dimensional DSA image to be processed by adopting a maximum density projection method; based on the two-dimensional image of the target direction, respectively obtaining the search results of the target area of the target direction by using a search model; and fusing the search results of the target region in the target direction to obtain a positioning region of the target region in the three-dimensional DSA image to be processed. The positioning method and system based on the DSA image provided by the embodiment of the specification can directly display the target region in the three-dimensional DSA image and shorten the time for artificial observation, thinking and judgment.

Description

Positioning method and system based on DSA image

Technical Field

The present disclosure relates to the field of medical imaging and computer technologies, and in particular, to a positioning method and system based on DSA images.

Background

Intracranial aneurysms are a common vascular disease, a neoplastic protrusion of the arterial wall resulting from local abnormal dilation of the intracranial arterial lumen. The prevalence of intracranial unbroken aneurysms in adults in our country is reported to be as high as 7%, which, after rupture, can lead to serious disability and even death. Therefore, the early discovery of intracranial aneurysms is of great significance.

DSA (Digital subtraction angiography) is widely used in clinical practice as a gold standard for the diagnosis of intracranial arterial vascular malformations and aneurysms. At present, the positioning of intracranial aneurysms is mainly judged by visual observation. The "macroscopic observation method" preliminarily judges whether intracranial aneurysm exists by reading a two-dimensional DSA image. The method is greatly influenced by the observation visual angle of the two-dimensional DSA image and the subjective consciousness of an observer, missed diagnosis is easy to occur, and in the observation process, the thinking of the observer is needed, and much time is spent.

Therefore, a new positioning method is needed, which can eliminate or reduce the diagnosis difference caused by the subjective factors and the imaging difference of the imaging device, reduce the time for artificial observation, thinking and judgment, and provide a basis for the subsequent diagnosis and teaching research by using the DSA image as a computer-aided method.

Disclosure of Invention

The embodiment of the specification provides a positioning method and a positioning system based on DSA images, which are used for solving the following technical problems: a new positioning method is needed, which can eliminate or reduce the diagnosis difference caused by the subjective factors and the imaging difference of the imaging device, reduce the time for artificial observation, thinking and judgment, and provide a basis for subsequent diagnosis and teaching research by using the DSA image as a computer-aided method.

An embodiment of the present specification provides a positioning method based on a DSA image, including the following steps:

respectively obtaining two-dimensional images of a target direction from a three-dimensional DSA image to be processed by adopting a maximum density projection method, wherein the target direction is the direction reserved by the maximum pixel value, and the target direction at least comprises three directions;

respectively obtaining search results of target areas in the target direction by using a search model based on the two-dimensional image in the target direction, wherein the search model is a model obtained in advance based on a deep learning method;

and fusing the search results of the target region in the target direction to obtain a positioning region of the target region in the three-dimensional DSA image to be processed.

Further, the method further comprises:

taking the point with the maximum gray scale in the three-dimensional DSA image to be processed as a seed point, and extracting a blood vessel region in the three-dimensional DSA image to be processed;

and taking the region where the extracted blood vessel region and the positioning region of the target region in the three-dimensional DSA image to be processed intersect as a new positioning region of the target region in the three-dimensional DSA image to be processed.

Further, the method further comprises:

performing surface reconstruction on a new positioning region of a target region in the three-dimensional DSA image to be processed by adopting a moving cube method;

and smoothing the positioning area subjected to surface reconstruction, and performing three-dimensional display on the image of the target area.

Further, the obtaining, by using a search model, search results of the target area in the target direction based on the two-dimensional image in the target direction includes:

and utilizing a search model to obtain a two-dimensional image of the target area in the target direction when the target area exists in the two-dimensional image in the target direction, and taking the two-dimensional image of the target area in the target direction as a search result of the target area in the target direction.

Further, the fusing the search results of the target region in the target direction to obtain a positioning region of the target region in the three-dimensional DSA image to be processed specifically includes:

and taking the search result of the target region in the target direction as a template, extending along the target direction, and taking a common region obtained by intersection in a three-dimensional space as a positioning region of the target region in the three-dimensional DSA image to be processed.

Further, the maximum intensity projection method adopts a method of reserving a maximum pixel value to obtain a two-dimensional image of the target direction.

Further, the target directions are coronal, sagittal, and transverse directions.

Further, the search model is a model obtained by pre-training based on a deep learning method according to a preset target region.

An embodiment of the present specification provides a positioning system based on DSA images, including:

the receiving unit is used for receiving a three-dimensional DSA image to be processed;

the processing unit is used for positioning the three-dimensional DSA image to be processed;

and the output unit is used for displaying the positioning result of the three-dimensional DSA image to be processed.

Further, the positioning the three-dimensional DSA image to be processed specifically includes:

Further, the method further comprises:

The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:

in the embodiment of the present specification, a two-dimensional image in a target direction is obtained by using a maximum density projection method for a three-dimensional DSA image to be processed, and after a target region in the target direction is obtained by using a search model, the target region is fused to realize the positioning of the target region in the three-dimensional DSA image, so that the target region in the three-dimensional DSA image can be directly displayed, diagnostic differences caused by subjective factors and imaging differences of imaging equipment are eliminated or reduced, and the time for artificial observation, thinking and judgment is shortened.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

Fig. 1 is a schematic diagram of a DSA image-based positioning method provided in an embodiment of the present disclosure;

fig. 2 is a flowchart of searching for a target area provided in an embodiment of the present disclosure;

FIG. 3a is a schematic view of a target area provided by an embodiment of the present description;

FIG. 3b is a schematic diagram of an intersection of three-dimensional spatial positions of a target region provided in an embodiment of the present disclosure;

fig. 4 is a flowchart of a positioning method based on three-dimensional DSA images provided by an embodiment of the present disclosure;

fig. 5 is a schematic flowchart of extracting a blood vessel region in a three-dimensional DSA image according to an embodiment of the present disclosure;

fig. 6 is a DSA image-based positioning system provided in an embodiment of the present disclosure.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.

Fig. 1 is a schematic view of a positioning method based on DSA images provided in an embodiment of the present disclosure, which specifically includes the following steps:

step S101: and respectively obtaining two-dimensional images in the target direction from the three-dimensional DSA images to be processed by adopting a maximum density projection method.

Three-dimensional DSA is a new technology developed on the basis of rotational DSA with continuous progress of computer image reconstruction technology. The method realizes the leap from plane to solid, obtains the three-dimensional morphological structure of the blood vessel by utilizing the three-dimensional reconstruction technology, and can observe from multiple angles. The three-dimensional DSA can make up for some defects or defects of the two-dimensional DSA in cerebrovascular disease diagnosis, can clearly display the disease range of intracranial arterial vessels and the parallel connection of adjacent vessels, and therefore, can be used as optimization or supplement of two-dimensional DSA examination.

The three-dimensional DSA image is taken as a processing object, and a maximum density projection method is adopted to obtain a two-dimensional image of a target direction. In the implementation process, a method of retaining the maximum pixel value may be adopted, the line-of-sight direction of the target direction is taken as a projection line, and the maximum pixel value on the projection line is projected onto a plane perpendicular to the line-of-sight, so as to form a two-dimensional image of the target direction. The target direction at least comprises three directions, theoretically, any direction can be used as the target direction, and in the specific implementation process, the directions of a coronal plane, a sagittal plane and a transverse plane are preferentially selected. Wherein, the coronal plane is a longitudinal section dividing the body into a front part and a rear part; the sagittal plane is a longitudinal section dividing the body into a left part and a right part; the cross section is a longitudinal section dividing the body into upper and lower parts. By adopting the method provided by the specification, the two-dimensional images of the target directions can be obtained, each target direction corresponds to one two-dimensional image, and the two-dimensional images are consistent with the images used in the search model training, so that the target area can be conveniently searched from the two-dimensional images by utilizing the search model subsequently.

Step S103: and obtaining a search result of the target area in the target direction by using the search model.

After the two-dimensional image of the target direction obtained in step S101 is input into the search model, when the two-dimensional image of the target direction has the target area, the search model outputs a search result of the target area. By adopting the method provided by the embodiment of the specification, the search results of the target areas in at least three target directions can be obtained. The search result is also a two-dimensional image, which reflects the target area present in the two-dimensional image of the target direction, and is essentially a binary image.

In the embodiments of the present specification, the target area may be an area of interest that is designated in advance according to a preset scene and/or a preset requirement. In practical applications, the target area may include, but is not limited to: intracranial aneurysm, arteriovenous malformation.

The search model in the embodiment of the present specification is a model obtained by training in advance through a deep learning method, and in order to make it easier to understand the search of the target region by using the search model, the search of the target region will be described in detail below, which is specifically shown in fig. 2. Fig. 2 is a flowchart for searching a target area provided in an embodiment of the present specification, which specifically includes:

step S201: two-dimensional DSA images and data labels are input into a convolutional neural network.

The sample used for searching model training is a two-dimensional DSA image, and a target region is marked on the two-dimensional DSA image to be used as a data label. To ensure the accuracy of training the search model, the number of training samples should be large enough.

Step S203: a convolutional neural network based search model is trained.

After the two-dimensional DSA image and the label data of step S201 are input to the convolutional neural network, a loss function of the convolutional neural network output value and the target value is calculated, and the convolutional neural network model is optimized to minimize the loss function, thereby obtaining a search model. By using the search model, the search result of the target region can be directly output after the two-dimensional DSA image is input. It should be noted that the nature of the search result output by the search model is a binary image.

Step S205: and inputting the two-dimensional image of the target direction into a search model, and searching a target area.

The search model obtained in step S203 can realize the search of the target area. After the two-dimensional image in the target direction is input into the search model, a search result of the target area is output. It should be noted that the two-dimensional images input into the search model are in accordance with the format of the two-dimensional DSA images used for model training.

Step S105: and fusing the search results of the target region in the target direction to obtain a positioning region of the target region in the three-dimensional DSA image to be processed.

Since the search result of the target region in the target direction obtained in step S103 is the search result of each target direction, which belongs to the search result of the two-dimensional image, and in order to realize the positioning of the target region in the three-dimensional DSA image, the search results obtained in step S103 need to be further fused to obtain the positioning region of the target region in the three-dimensional DSA image to be processed. Specifically, the search result of the target region in the target direction obtained in the foregoing step S103 is used as a template, the template is extended along the target direction and intersected in the three-dimensional space, and the common region intersected in the three-dimensional space is used as a positioning region of the target region in the three-dimensional DSA image to be processed, which is specifically shown in fig. 3.

By adopting the method provided by the embodiment, the three-dimensional DSA image is positioned, the target region can be directly displayed in the three-dimensional DSA image, the diagnosis difference caused by subjective factors and imaging difference of imaging equipment is eliminated or reduced, and the time for artificial observation, thinking and judgment is shortened.

In the specific implementation process of the embodiment of the specification, the correction and the three-dimensional surface reconstruction of the target area can be further performed, so that the positioning area of the target area can be more accurately determined, and the positioning result can be more intuitively and accurately displayed.

To further illustrate the positioning method based on three-dimensional DSA images, fig. 4 is a flowchart of a positioning method based on three-dimensional DSA images provided in an embodiment of the present disclosure to describe the positioning process in detail.

Step S401: and respectively obtaining two-dimensional images in the target direction from the three-dimensional DSA images to be processed by adopting a maximum density projection method.

The coronal plane, the sagittal plane and the transverse plane are taken as target directions, the sight line direction along the target direction is taken as a projection line, the maximum pixel value on the projection line is projected on a plane vertical to the sight line, thereby forming a two-dimensional image of the target direction, and the two-dimensional image of the coronal plane direction, the two-dimensional image of the sagittal plane direction and the two-dimensional image of the transverse plane direction are respectively obtained.

Step S403: and obtaining a search result of the target area in the target direction by using the search model.

The two-dimensional image in the coronal plane direction, the two-dimensional image in the sagittal plane direction, and the two-dimensional image in the transverse plane direction obtained in step S401 are input into a search model obtained in advance, and the search model is used to search for the target region. When the target area exists in the two-dimensional image in the target direction, the search model outputs the target area as a search result of the target area in the target direction, and a search result in the coronal plane direction, a search result in the sagittal plane direction and a search result in the transverse section direction are respectively obtained. Since the two-dimensional image of the target direction input to the search model is obtained by retaining the maximum pixel value and has directivity, the search result output from the search model also has directivity and is a binary image having directivity. And searching a searching result of the target area output by the searching model, wherein the searching result is used as a template of the target area in the two-dimensional image in the target direction and is used for fusing subsequent searching results.

Step S405: and fusing the search results of the target region in the target direction to obtain a positioning region of the target region in the three-dimensional DSA image to be processed.

Using the search result of the target region in the target direction obtained in step S403 as a template, extending along the target direction in which the search result of the target region is located, and using a common region obtained by intersection in the three-dimensional space as a positioning region of the target region in the three-dimensional DSA image to be processed. Specifically, the search result in the coronal plane direction is used as a template, and the image obtained by copying is copied along the coronal plane direction, so that the size of the corresponding region in the original three-dimensional DSA image is the same, and a three-dimensional spatial position image of the target region in the coronal plane direction is obtained, wherein the spatial position image is similar to a barrel shape. And processing the sagittal plane direction and the transverse plane direction by adopting the same method to obtain a three-dimensional space position image of the target area in the sagittal plane direction and a three-dimensional space position image of the target area in the transverse plane direction. Because the same target region is searched, the three-dimensional spatial position images of the target region in the three target directions are truly intersected at the spatial position, and the intersected region is a positioning region of the target region in the three-dimensional DSA image to be processed.

Step S407: and correcting the positioning area of the target area in the three-dimensional DSA image to be processed.

The positioning region of the target region obtained in step S405 may have an error, and in order to more accurately position the target region, the positioning region of the target region in the three-dimensional DSA image to be processed obtained in step S405 needs to be corrected. Specifically, a point with the maximum gray level is selected from the three-dimensional DSA image to be processed as a seed point, and a blood vessel region in the three-dimensional DSA image to be processed is extracted; and taking the region where the extracted blood vessel region and the positioning region of the target region in the three-dimensional DSA image to be processed intersect as a new positioning region of the target region in the three-dimensional DSA image to be processed.

To further understand the present invention and explain the process of extracting a blood vessel region in detail, fig. 5 is a schematic flow chart of extracting a blood vessel region in a three-dimensional DSA image according to an embodiment of the present disclosure, which specifically includes:

step S501: and determining the gray scale range of the three-dimensional DSA image.

And according to the imaging characteristics of the three-dimensional DSA image and the value range of the pixel value, obtaining a gray threshold value through simple maximum value and minimum value constraints, and taking the gray threshold value as a gray range.

Specifically, a value range of the three-dimensional DSA image is extracted to obtain a maximum value and a minimum value, then, trisection is carried out on twice of the minimum value and the maximum value, the trisection value is used as a minimum gray scale range, and the maximum gray scale range is selected as a value range maximum value.

Because the three-dimensional DSA image has good quality, other methods can be adopted to obtain the gray scale range. And extracting a value range of the three-dimensional DSA image to obtain a maximum value and a minimum value, then quartering three times of the minimum value and the maximum value, wherein the quartering value is used as a minimum gray scale range, and the maximum value of the value range is selected as a maximum gray scale range.

Step S503: a seed point is selected.

The seed point in the present invention is defined as the starting point of growth. The seed point is the starting point for subsequent region growing.

In an embodiment of the present specification, a three-dimensional DSA image is traversed, a pixel point with the maximum gray value is found, and finally, the coordinate of the pixel point is recorded as the coordinate of a seed point.

Step S505: and segmenting blood vessels by adopting region growing.

And taking the point with the maximum gray level as a seed point, and performing point-by-point calculation and judgment by adopting a region growing method to segment the blood vessel image. The method can effectively reduce noise interference and improve the operation efficiency.

Step S409: and displaying the new positioning region of the target region in the three-dimensional DSA image to be processed in a three-dimensional mode.

The foregoing step S407 obtains a more accurate positioning region of the target region, and in order to facilitate displaying the positioning region, the new positioning region obtained in step S407 needs to be surface-generated and then three-dimensionally displayed. Specifically, the MC algorithm (marching cubes algorithm) is used to realize the three-dimensional surface reconstruction. The MC algorithm has the basic idea that small cubes with regular hierarchical shapes in a three-dimensional data space are processed one by one, eight vertexes of the small cubes are composed of four pixel points on adjacent layers, the small cubes are classified to be intersected with an isosurface, intersection points of the isosurface and the edges of the small cubes are calculated by adopting an interpolation method, and finally the points are connected in a certain mode to form an approximate representation of the isosurface according to the relative positions of the isosurface and the intersection points. Due to the fact that the three-dimensional surface reconstructed by the MC algorithm has the situations of poor surface seam processing, inaccurate data and the like, smoothing processing is needed, smoothing processing can be achieved through a windowed Sinc function, surface generation of a new positioning area is achieved, and three-dimensional display can be conducted.

The above details a positioning method based on DSA images, and accordingly, the present application also provides a positioning system based on DSA images, as shown in fig. 6. Fig. 6 is a DSA image-based positioning system provided in an embodiment of the present disclosure, which specifically includes:

a receiving unit 601, which receives a three-dimensional DSA image to be processed;

the processing unit 603 is used for positioning the three-dimensional DSA image to be processed;

the output unit 605 displays the positioning result of the three-dimensional DSA image to be processed.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the electronic device, and the nonvolatile computer storage medium, since they are substantially similar to the embodiments of the method, the description is simple, and the relevant points can be referred to the partial description of the embodiments of the method.

The apparatus, the electronic device, the nonvolatile computer storage medium and the method provided in the embodiments of the present description correspond to each other, and therefore, the apparatus, the electronic device, and the nonvolatile computer storage medium also have similar advantageous technical effects to the corresponding method.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the various elements may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.

As will be appreciated by one skilled in the art, the present specification embodiments may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A positioning method based on DSA images, characterized in that the method comprises:

respectively obtaining two-dimensional images of a target direction by adopting a maximum density projection method from a three-dimensional DSA image to be processed, wherein the target direction is a direction in which a maximum pixel value is retained, and the target direction at least comprises three directions;

2. The method of claim 1, wherein the method further comprises:

3. The method of claim 2, wherein the method further comprises:

4. The method according to claim 1, wherein the obtaining the search results of the target area in the target direction by using the search model based on the two-dimensional image in the target direction comprises:

5. The method according to claim 1, wherein the fusing the search results of the target region in the target direction to obtain a positioning region of the target region in the three-dimensional DSA image to be processed specifically comprises:

6. The method of claim 1, wherein the maximum intensity projection method employs a method of preserving maximum pixel values to obtain a two-dimensional image of the target direction.

7. The method of claim 1, wherein the target directions are coronal, sagittal, and transverse directions.

8. The method of claim 1, wherein the search model is a model obtained by pre-training based on a deep learning method according to a preset target region.

9. A DSA image based localization system, the system comprising:

the processing unit is used for positioning the three-dimensional DSA image to be processed, and specifically comprises the following steps:

fusing the search results of the target area in the target direction to obtain a positioning area of the target area in the three-dimensional DSA image to be processed;

10. The system of claim 9, wherein the system further comprises:

11. The system of claim 10, wherein the system further comprises:

12. The system according to claim 9, wherein the obtaining the search results of the target area in the target direction by using the search model based on the two-dimensional image in the target direction respectively comprises:

13. The system according to claim 9, wherein the fusing the search results of the target region in the target direction to obtain a positioning region of the target region in the three-dimensional DSA image to be processed specifically comprises:

14. The system of claim 9, wherein the maximum intensity projection method employs a method that preserves maximum pixel values to obtain a two-dimensional image of the target direction.

15. The system of claim 9, wherein the target directions are coronal, sagittal, and transverse directions.

16. The system of claim 9, wherein the search model is a model obtained by pre-training based on a deep learning method according to a preset target region.