CN110503642A - A kind of localization method and system based on DSA image - Google Patents
A kind of localization method and system based on DSA image Download PDFInfo
- Publication number
- CN110503642A CN110503642A CN201910782193.3A CN201910782193A CN110503642A CN 110503642 A CN110503642 A CN 110503642A CN 201910782193 A CN201910782193 A CN 201910782193A CN 110503642 A CN110503642 A CN 110503642A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- target area
- image
- target
- processed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Abstract
This specification embodiment discloses a kind of localization method and system based on DSA image, belongs to medical image and field of computer technology.This specification embodiment solves the problems, such as that " observation method of naked eye " is influenced by the subjective consciousness bigger, cost more time by the positioning to three-dimensional DSA objective area in image to be processed.The localization method includes:, using the method for maximum intensity projection, to obtain the two dimensional image of target direction respectively from three-dimensional DSA image to be processed；Two dimensional image based on target direction obtains the lookup result of the target area of target direction using model is searched respectively；The lookup result of the target area of target direction is merged, localization region of the target area in three-dimensional DSA image to be processed is obtained.The localization method and system based on DSA image that this specification embodiment provides can be realized the target area directly displayed in three-dimensional DSA image, reduce the time of artificial observation, thinking and judgement.
Description
Technical field
This specification is related to medical image and field of computer technology more particularly to a kind of positioning side based on DSA image
Method and system.
Background technique
Intracranial aneurysm is a kind of common vascular conditions, which is since the local anomaly of entocranial artery inner cavity expands
A kind of strumae of arterial wall caused by.It is reported that illness rate of the encephalic Unruptured aneurysm in China adult is high
Up to 7%, after encephalic Unruptured aneurysm ruptures, it is even dead to will lead to handicap.Therefore, entocranial artery is found early
Tumor is of great significance.
DSA (Digital subtraction angiography, digital subtraction angiography) is used as entocranial artery blood vessel
The goldstandard of deformity and Diagnosis of Aneurysm, is widely applied in clinic.It is seen currently, the positioning of intracranial aneurysm relies primarily on naked eyes
It examines and is judged." observation method of naked eye " is somebody's turn to do by reading two dimension DSA image, tentatively judges whether there is intracranial aneurysm.The party
Method is influenced bigger by the observation visual angle of two-dimentional DSA image and the subjective consciousness of observer, is easy to appear and is failed to pinpoint a disease in diagnosis, and observed
Cheng Zhong needs the thinking of observer, spends the more time.
Therefore, it is necessary to a kind of new localization methods, can exclude or reduce subjective factor and image documentation equipment imaging difference band
The diagnosis difference come reduces the time of artificial observation, thinking and judgement, as computer-aid method, schemes for later use DSA
Foundation is provided as carrying out diagnosis and teaching research.
Summary of the invention
This specification embodiment provides a kind of localization method and system based on DSA image, asks for solving following technology
Topic: needing a kind of new localization method, can exclude or reduce subjective factor and the diagnosis of image documentation equipment imaging difference bring is poor
It is different, reduce the time of artificial observation, thinking and judgement, as computer-aid method, is diagnosed for later use DSA image
And teaching research provides foundation.
This specification embodiment provides a kind of localization method based on DSA image, comprising the following steps:
From three-dimensional DSA image to be processed, using the method for maximum intensity projection, the two dimension of target direction is obtained respectively
Image, wherein the target direction is the direction for carrying out max pixel value retention, and the target direction includes at least three
Direction；
The target area of the target direction is obtained respectively using model is searched based on the two dimensional image of the target direction
The lookup result in domain, wherein the lookup model is the model being obtained ahead of time based on deep learning method；
The lookup result of the target area of the target direction is merged, obtains target area described to be processed
Localization region in three-dimensional DSA image.
Further, the method further includes:
It regard the maximum point of gray scale in the three-dimensional DSA image to be processed as seed point, extracts described to be processed three
Tie up the angiosomes in DSA image；
The localization region of target area in the angiosomes of the extraction and the three-dimensional DSA image to be processed is sent out
The region of raw intersection, the new localization region as the target area in the three-dimensional DSA image to be processed.
Further, the method further includes:
The new localization region of target area in the three-dimensional DSA image to be processed is used to the side of marching cube
Method carries out surface reconstruction；
The localization region for carrying out surface reconstruction is smoothed, the image where the target area is carried out
Three-dimensional Display.
Further, the two dimensional image based on the target direction obtains the target using model is searched respectively
The lookup result of the target area in direction, specifically includes:
Using model is searched, when there are when target area, obtain target area to exist in the two dimensional image of the target direction
The two dimensional image of target direction, as the lookup result of the target area of the target direction.
Further, the lookup result of the target area by the target direction merges, and obtains target area
Localization region in the three-dimensional DSA image to be processed, specifically includes:
Using the lookup result of the target area of the target direction as template, extended along the target direction, it will be
The public domain that three-dimensional space intersects, the localization region as the target area in the three-dimensional DSA image to be processed.
Further, the method for the maximum intensity projection is using the method for retaining max pixel value, to obtain target side
To two dimensional image.
Further, the target direction is coronal-plane, sagittal plane and cross-sectional direction.
Further, the lookup model is according to preset target area, and based on deep learning method, training is obtained in advance
The model obtained.
A kind of positioning system based on DSA image that this specification embodiment provides, comprising:
Receiving unit receives three-dimensional DSA image to be processed；
Processing unit positions the three-dimensional DSA image to be processed；
Output unit shows the positioning result of the three-dimensional DSA image to be processed.
Further, described that the three-dimensional DSA image to be processed is positioned, it specifically includes:
From three-dimensional DSA image to be processed, using the method for maximum intensity projection, the two dimension of target direction is obtained respectively
Image, wherein the target direction is the direction for carrying out max pixel value retention, and the target direction includes at least three
Direction；
The target area of the target direction is obtained respectively using model is searched based on the two dimensional image of the target direction
The lookup result in domain, wherein the lookup model is the model being obtained ahead of time based on deep learning method；
The lookup result of the target area of the target direction is merged, obtains target area described to be processed
Localization region in three-dimensional DSA image.
Further, the method further includes:
It regard the maximum point of gray scale in the three-dimensional DSA image to be processed as seed point, extracts described to be processed three
Tie up the angiosomes in DSA image；
The localization region of target area in the angiosomes of the extraction and the three-dimensional DSA image to be processed is sent out
The region of raw intersection, the new localization region as the target area in the three-dimensional DSA image to be processed.
Further, the method further includes:
The new localization region of target area in the three-dimensional DSA image to be processed is used to the side of marching cube
Method carries out surface reconstruction；
The localization region for carrying out surface reconstruction is smoothed, the image where the target area is carried out
Three-dimensional Display.
Further, the two dimensional image based on the target direction obtains the target using model is searched respectively
The lookup result of the target area in direction, specifically includes:
Using model is searched, when there are when target area, obtain target area to exist in the two dimensional image of the target direction
The two dimensional image of target direction, as the lookup result of the target area of the target direction.
Further, the lookup result of the target area by the target direction merges, and obtains target area
Localization region in the three-dimensional DSA image to be processed, specifically includes:
Using the lookup result of the target area of the target direction as template, extended along the target direction, it will be
The public domain that three-dimensional space intersects, the localization region as the target area in the three-dimensional DSA image to be processed.
Further, the method for the maximum intensity projection is using the method for retaining max pixel value, to obtain target side
To two dimensional image.
Further, the target direction is coronal-plane, sagittal plane and cross-sectional direction.
Further, the lookup model is according to preset target area, and based on deep learning method, training is obtained in advance
The model obtained.
This specification embodiment use at least one above-mentioned technical solution can reach it is following the utility model has the advantages that
Method of this specification embodiment by using maximum intensity projection to three-dimensional DSA image to be processed, obtains mesh
The two dimensional image for marking direction carries out the fusion of target area, behind the target area for searching model acquisition target direction with reality
The positioning of existing three-dimensional DSA objective area in image, can be realized the target area directly displayed in three-dimensional DSA image, exclusion or
It reduces subjective factor and image documentation equipment imaging difference bring diagnoses difference, reduce the time of artificial observation, thinking and judgement.
Detailed description of the invention
In order to illustrate more clearly of this specification embodiment or technical solution in the prior art, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
The some embodiments recorded in this specification, for those of ordinary skill in the art, in not making the creative labor property
Under the premise of, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of schematic diagram for localization method based on DSA image that this specification embodiment provides；
Fig. 2 is the lookup flow chart for the target area that this specification embodiment provides；
Fig. 3 a is that this illustrates the schematic diagram for the target area that embodiment provides；
Fig. 3 b is that the three-dimensional space position for the target area that this specification embodiment provides intersects schematic diagram；
Fig. 4 is a kind of flow chart for localization method based on three-dimensional DSA image that this specification embodiment provides；
Fig. 5 is the flow diagram for extracting the angiosomes in three-dimensional DSA image that this specification embodiment provides；
Fig. 6 is a kind of positioning system based on DSA image that this specification embodiment provides.
Specific embodiment
In order to make those skilled in the art more fully understand the technical solution in this specification, below in conjunction with this explanation
Attached drawing in book embodiment is clearly and completely described the technical solution in this specification embodiment, it is clear that described
Embodiment be merely a part but not all of the embodiments of the present application.Based on this specification embodiment, this field
Those of ordinary skill's every other embodiment obtained without creative efforts, all should belong to the application
The range of protection.
Fig. 1 is the schematic diagram of a kind of localization method based on DSA image that this specification embodiment provides, specifically include with
Lower step:
Step S101: from three-dimensional DSA image to be processed, using the method for maximum intensity projection, target is obtained respectively
The two dimensional image in direction.
Three-dimensional DSA be with being constantly progressive of computer picture reconstruction technique, grow up on the basis of rotational DSA it is new
Technology.The method achieve from plane to three-dimensional leap, the three-dimensional configuration structure of blood vessel has been obtained using three-dimensional reconstruction,
And from being carried out from multi-angle.It is certain insufficient or scarce in cerebrovascular disease diagnosis that three-dimensional DSA can make up two-dimentional DSA
Fall into, extent of disease to entocranial artery blood vessel and it is in parallel with adjacent blood vessel can clearly show, therefore, can be used as two dimension
The optimization or supplement that DSA is checked.
This specification is process object with three-dimensional DSA image, using the method for maximum intensity projection, obtains target direction
Two dimensional image.In the specific implementation process, can be made using the method for retaining max pixel value with the direction of visual lines of target direction
For projection line, the max pixel value on the projection line is projected in the plane vertical with sight, to form target direction
Two dimensional image.Wherein, target direction includes at least three directions, and theoretically, any direction can be used as target direction, specific real
During applying, coronal-plane, sagittal plane and cross-sectional direction are preferentially selected.Wherein, coronal-plane is that body is divided into front and back two parts
Longitudal section；Sagittal plane is that body is divided into the two-part longitudal section in left and right；Cross section is to be divide into upper part and lower part body
Longitudal section.The method provided using this specification can obtain the two dimensional image of target direction, and each target direction is corresponding
One two dimensional image, the two dimensional image is consistent with used image when searching model training, searches model convenient for later use,
Target area is searched from two dimensional image.
Step S103: using model is searched, the lookup result of the target area of target direction is obtained.
After model is searched in the two dimensional image input for the target direction that abovementioned steps S101 is obtained, when the X-Y scheme of target direction
There are the lookup results for when target area, searching model output target area as in.The side provided using this specification embodiment
Method can obtain the lookup result of the target area of at least three target directions.The lookup result is also two dimensional image, can be anti-
Target area present in the two dimensional image of target direction is mirrored, is substantially binary map.
In the embodiment of this specification, target area be can be according to scene and/or preset need is preset, and be preassigned
Interested region.In practical applications, target area can include but is not limited to: intracranial aneurysm, arteriovenous malformation.
Lookup model in this specification embodiment is the model for first passing through the training of deep learning method in advance and obtaining, for more
It is readily appreciated that using the lookup for searching model progress target area, the lookup of target area is described in detail below, it is specific such as Fig. 2
It is shown.Fig. 2 is the lookup flow chart for the target area that this specification embodiment provides, and is specifically included:
Step S201: two dimension DSA image and data label are inputted to convolutional neural networks.
Sample for carrying out searching model training is two dimension DSA image, marks target area on two dimension DSA image
As data label.In order to guarantee that the accuracy of model is searched in training, the quantity of training sample should be sufficiently large.
Step S203: lookup model of the training based on convolutional neural networks.
After the two-dimentional DSA image and label data of abovementioned steps S201 is input to convolutional neural networks, convolutional Neural is calculated
The loss function of network output valve and target value, and convolutional neural networks model is optimized, loss function is minimized, is obtained
Model must be searched.It using the lookup model, may be implemented after inputting two-dimentional DSA image, directly export the lookup knot of target area
Fruit.It should be strongly noted that the essence for searching the lookup result of model output is a bianry image.
Step S205: model is searched into the two dimensional image input of target direction, searches target area.
The lookup model that step S203 is obtained, may be implemented the lookup of target area.The two dimensional image of target direction inputs
After searching model, the lookup result of target area can be exported.It should be strongly noted that input search model two dimensional image with
The format of two-dimentional DSA image for model training is consistent.
Step S105: the lookup result of the target area of target direction is merged, and obtains target area to be processed
Three-dimensional DSA image in localization region.
Due to the lookup that the abovementioned steps S103 lookup result for obtaining the target area of target direction is each target direction
As a result, belonging to the lookup result of two dimensional image, in order to realize the positioning of the target area in three-dimensional DSA image, it is therefore desirable to
The lookup result further progress fusion that step S103 is obtained, to obtain target area in three-dimensional DSA image to be processed
Localization region.Specifically, using the lookup result of the target area of the abovementioned steps S103 target direction obtained as template, along mesh
Mark direction extended, and three-dimensional space intersect, using in the public domain that three-dimensional space intersects as three-dimensional DSA to be processed
The localization region of target area in image, it is specific as shown in Figure 3.
Using method provided in this embodiment, three-dimensional DSA image is positioned, may be implemented in three-dimensional DSA image
Target area is directly displayed, excludes or reduces subjective factor and image documentation equipment imaging difference bring diagnoses difference, reduction is artificial
The time of observation, thinking and judgement.
This specification embodiment in the specific implementation process, can be with the correction of further progress target area, three-dimensional table
Face is rebuild, with the localization region in the more accurate region that sets the goal really, more intuitive and accurate display positioning result.
In order to further illustrate the localization method based on three-dimensional DSA image, Fig. 4 is one kind that this specification embodiment provides
The flow chart of localization method based on three-dimensional DSA image, position fixing process is described in detail.
Step S401: from three-dimensional DSA image to be processed, using the method for maximum intensity projection, target is obtained respectively
The two dimensional image in direction.
Using coronal-plane, sagittal plane and cross-sectional direction as target direction, the direction of visual lines along target direction is as projection
Line projects to the max pixel value on the projection line in the plane vertical with sight, to form the X-Y scheme of target direction
Picture respectively obtains the two dimensional image, the two dimensional image in sagittal plane direction and the two dimensional image of cross-sectional direction in coronal-plane direction.
Step S403: using model is searched, the lookup result of the target area of target direction is obtained.
By the two dimensional image of the two dimensional image in coronal-plane direction, sagittal plane direction obtained in abovementioned steps S401 and cross-section
The two dimensional image in face direction inputs the lookup model being obtained ahead of time, and using model is searched, carries out the lookup of target area.Work as target
There are when target area in the two dimensional image in direction, lookup model exports target area, the target area as target direction
Lookup result respectively obtains the lookup of the lookup result in coronal-plane direction, the lookup result and cross-sectional direction in sagittal plane direction
As a result.Since the two dimensional image that the target direction of model is searched in input is obtained by retaining max pixel value, there is direction
Property, therefore the lookup result for searching model output also has directionality, is the directive bianry image of tool.Search model output
The lookup result of target area be used for subsequent lookup result as template of the target area in target direction two dimensional image
Fusion.
Step S405: the lookup result of the target area of target direction is merged, and obtains target area to be processed
Three-dimensional DSA image in localization region.
Using the lookup result of the target area of the abovementioned steps S403 target direction obtained as template, along looking into for target area
Target direction where looking for result is extended, by the public domain that three-dimensional space intersects, as three-dimensional to be processed
The localization region of target area in DSA image.Specifically, using the lookup result in coronal-plane direction as template, along coronal-plane
Direction is replicated, so that obtained image is replicated as the size of corresponding region in original three-dimensional DSA image, from
And the three-dimensional space position image of the target area in coronal-plane direction is obtained, which is similar to tubbiness.Using same
The method of sample handles sagittal plane direction and cross-sectional direction, obtains the three-dimensional space of the target area in sagittal plane direction
The three-dimensional space position image of the target area of location drawing picture and cross-sectional direction.Due to being carried out for the same target area
It searches, therefore in spatial position true intersection, the phase occur for the three-dimensional space position image of the target area of three target directions
Handing over region is the localization region of the target area in three-dimensional DSA image to be processed.
Step S407: the localization region of the target area in three-dimensional DSA image to be processed is corrected.
There may be errors for the localization region for the target area that abovementioned steps S405 is obtained, in order to more accurately position mesh
Region is marked, the localization region for the target area in three-dimensional DSA image to be processed for needing to obtain abovementioned steps S405 carries out
Correction.Specifically, it selects the maximum point of gray scale as seed point from three-dimensional DSA image to be processed, extracts to be processed three
Tie up the angiosomes in DSA image；By the positioning of the target area in the angiosomes of extraction and three-dimensional DSA image to be processed
The region that region is intersected, the new localization region as the target area in three-dimensional DSA image to be processed.
For a further understanding of the present invention, the extraction process of angiosomes is described in detail, Fig. 5 is that this specification embodiment mentions
The flow diagram for extracting the angiosomes in three-dimensional DSA image of confession, specifically includes:
Step S501: the tonal range of three-dimensional DSA image is determined.
According to the codomain range of the imaging characteristics of three-dimensional DSA image and pixel value, about by simple maximum value and minimum value
Beam obtains a gray threshold, using the gray threshold as tonal range.
Specifically, the codomain for extracting three-dimensional DSA image, obtains maximum value and minimum value, then twice of minimum value and most
Big value carries out trisection, which then selects codomain maximum value as minimal gray range, maximum tonal range.
Since three-dimensional DSA image quality itself is preferable, tonal range can also be obtained using other methods.Extract three
The codomain for tieing up DSA image, obtains maximum value and minimum value, and then the three times of minimum value and maximum value carry out the quartering, this four etc.
Score value then selects codomain maximum value as minimal gray range, maximum tonal range.
Step S503: selection seed point.
Seed point definition in the present invention is the starting point of growth.The seed point is the subsequent starting for carrying out region growing
Point.
In one embodiment of this specification, three-dimensional DSA image is traversed, finds the maximum pixel of gray value, finally
The coordinate of the pixel is write down, the coordinate as seed point.
Step S505: using region growing, divides blood vessel.
Using the maximum point of above-mentioned gray scale as seed point, using region growing method, node-by-node algorithm and judgement carry out vessel graph
The segmentation of picture.This method can effectively reduce noise jamming, promote operation efficiency.
Step S409: the new localization region of the target area in three-dimensional DSA image to be processed is subjected to Three-dimensional Display.
Abovementioned steps S407 obtains the localization region of more accurate target area, for the ease of the exhibition of localization region
Show, needs to carry out Surface Creation to the new localization region that step S407 is obtained, then Three-dimensional Display.Specifically, it is calculated using MC
Method (MarchingCubes, marching cubes algorithm) realizes three-dimensional surface reconstruct.The basic thought of MC algorithm is exactly said three-dimensional body
The small cubes of data space tiered form rule, eight vertex of these small cubes are by four pixels each on adjacent layer
Composition, these small cubes are handled one by one, sort out the cube intersected with contour surface, and calculate using the method for interpolation
These are pressed one finally according to the relative position of contour surface and these intersection points by the intersection point of contour surface and these small cubes sides
That determines that mode is formed by connecting a contour surface approaches expression.Due to the three-dimensional surface using the reconstruct of MC algorithm, there are face joints
Place handles bad, the situations such as data inaccuracy, it is therefore desirable to be smoothed, can be realized by Windowing Sinc function
Smoothing processing can carry out three-dimensional display to realize the Surface Creation of new localization region.
A kind of localization method based on DSA image is described in detail in above content, corresponding, present invention also provides
A kind of positioning system based on DSA image, as shown in Figure 6.Fig. 6 is that one kind that this specification embodiment provides is based on DSA image
Positioning system, specifically include:
Receiving unit 601 receives three-dimensional DSA image to be processed；
Processing unit 603 positions three-dimensional DSA image to be processed；
Output unit 605 shows the positioning result of three-dimensional DSA image to be processed.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device,
For electronic equipment, nonvolatile computer storage media embodiment, since it is substantially similar to the method embodiment, so description
It is fairly simple, the relevent part can refer to the partial explaination of embodiments of method.
Device that this specification embodiment provides, electronic equipment, nonvolatile computer storage media with method are corresponding
, therefore, device, electronic equipment, nonvolatile computer storage media also have the Advantageous effect similar with corresponding method
Fruit, since the advantageous effects of method being described in detail above, which is not described herein again corresponding intrument,
The advantageous effects of electronic equipment, nonvolatile computer storage media.
In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker
Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " is patrolled
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed is most generally used at present
Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also answer
This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages,
The hardware circuit for realizing the logical method process can be readily available.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can
Read medium, logic gate, switch, specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and insertion microcontroller, the example of controller includes but is not limited to following microcontroller
Device: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320 are deposited
Memory controller is also implemented as a part of the control logic of memory.It is also known in the art that in addition to
Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic
Controller is obtained to come in fact in the form of logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and insertion microcontroller etc.
Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it
The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions
For either the software module of implementation method can be the structure in hardware component again.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
The combination of equipment.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when specification one or more embodiment.
It should be understood by those skilled in the art that, this specification embodiment can provide as method, system or computer program
Product.Therefore, this specification embodiment can be used complete hardware embodiment, complete software embodiment or combine software and hardware
The form of the embodiment of aspect.Moreover, it wherein includes that computer is available that this specification embodiment, which can be used in one or more,
It is real in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form for the computer program product applied.
This specification is referring to the method, equipment (system) and computer program product according to this specification embodiment
Flowchart and/or the block diagram describes.It should be understood that can be realized by computer program instructions every in flowchart and/or the block diagram
The combination of process and/or box in one process and/or box and flowchart and/or the block diagram.It can provide these computers
Processor of the program instruction to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices
To generate a machine, so that generating use by the instruction that computer or the processor of other programmable data processing devices execute
In the dress for realizing the function of specifying in one or more flows of the flowchart and/or one or more blocks of the block diagram
It sets.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
This specification can describe in the general context of computer-executable instructions executed by a computer, such as journey
Sequence module.Generally, program module include routines performing specific tasks or implementing specific abstract data types, programs, objects,
Component, data structure etc..Specification can also be practiced in a distributed computing environment, in these distributed computing environments,
By executing task by the connected remote processing devices of communication network.In a distributed computing environment, program module can
To be located in the local and remote computer storage media including storage equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The foregoing is merely this specification embodiments, are not intended to limit this application.For those skilled in the art
For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal
Replacement, improvement etc., should be included within the scope of the claims of this application.
Claims (17)
1. a kind of localization method based on DSA image, which is characterized in that the described method includes:
From three-dimensional DSA image to be processed, using the method for maximum intensity projection, the X-Y scheme of target direction is obtained respectively
Picture, wherein the target direction is the direction for carrying out max pixel value retention, and the target direction includes at least three sides
To；
The target area of the target direction is obtained respectively using model is searched based on the two dimensional image of the target direction
Lookup result, wherein the lookup model is the model being obtained ahead of time based on deep learning method；
The lookup result of the target area of the target direction is merged, obtains target area in the three-dimensional to be processed
Localization region in DSA image.
2. the method as described in claim 1, which is characterized in that the method further includes:
It regard the maximum point of gray scale in the three-dimensional DSA image to be processed as seed point, extracts the three-dimensional DSA to be processed
Angiosomes in image；
Phase is occurred into for the localization region of the target area in the angiosomes of the extraction and the three-dimensional DSA image to be processed
The region of friendship, the new localization region as the target area in the three-dimensional DSA image to be processed.
3. method according to claim 2, which is characterized in that the method further includes:
By the new localization region of the target area in the three-dimensional DSA image to be processed using marching cube method into
Row surface reconstruction；
The localization region for carrying out surface reconstruction is smoothed, the image where the target area is carried out three-dimensional
Display.
4. the method as described in claim 1, which is characterized in that the two dimensional image based on the target direction, using looking into
Model is looked for, the lookup result of the target area of the target direction is obtained respectively, specifically includes:
Using model is searched, when there are when target area, obtain target area in target in the two dimensional image of the target direction
The two dimensional image in direction, as the lookup result of the target area of the target direction.
5. the method as described in claim 1, which is characterized in that the lookup result of the target area by the target direction
It is merged, obtains localization region of the target area in the three-dimensional DSA image to be processed, specifically include:
Using the lookup result of the target area of the target direction as template, extended along the target direction, it will be in three-dimensional
The public domain that space intersection obtains, the localization region as the target area in the three-dimensional DSA image to be processed.
6. the method as described in claim 1, which is characterized in that the method for the maximum intensity projection is using reservation maximum pixel
The method of value, to obtain the two dimensional image of target direction.
7. the method as described in claim 1, which is characterized in that the target direction is coronal-plane, sagittal plane and cross section side
To.
8. the method as described in claim 1, which is characterized in that the lookup model is based on according to preset target area
The deep learning method model that training obtains in advance.
9. a kind of positioning system based on DSA image, which is characterized in that the system comprises:
Receiving unit receives three-dimensional DSA image to be processed；
Processing unit positions the three-dimensional DSA image to be processed；
Output unit shows the positioning result of the three-dimensional DSA image to be processed.
10. it is system as claimed in claim 9, described that the three-dimensional DSA image to be processed is positioned, it specifically includes:
From three-dimensional DSA image to be processed, using the method for maximum intensity projection, the X-Y scheme of target direction is obtained respectively
Picture, wherein the target direction is the direction for carrying out max pixel value retention, and the target direction includes at least three sides
To；
The target area of the target direction is obtained respectively using model is searched based on the two dimensional image of the target direction
Lookup result, wherein the lookup model is the model being obtained ahead of time based on deep learning method；
The lookup result of the target area of the target direction is merged, obtains target area in the three-dimensional to be processed
Localization region in DSA image.
11. system as claimed in claim 10, which is characterized in that the system further comprises:
It regard the maximum point of gray scale in the three-dimensional DSA image to be processed as seed point, extracts the three-dimensional DSA to be processed
Angiosomes in image；
Phase is occurred into for the localization region of the target area in the angiosomes of the extraction and the three-dimensional DSA image to be processed
The region of friendship, the new localization region as the target area in the three-dimensional DSA image to be processed.
12. system as claimed in claim 11, which is characterized in that the system further comprises:
By the new localization region of the target area in the three-dimensional DSA image to be processed using marching cube method into
Row surface reconstruction；
The localization region for carrying out surface reconstruction is smoothed, the image where the target area is carried out three-dimensional
Display.
13. system as claimed in claim 10, which is characterized in that the two dimensional image based on the target direction utilizes
Model is searched, the lookup result of the target area of the target direction is obtained respectively, specifically includes:
Using model is searched, when there are when target area, obtain target area in target in the two dimensional image of the target direction
The two dimensional image in direction, as the lookup result of the target area of the target direction.
14. system as claimed in claim 10, which is characterized in that the lookup knot of the target area by the target direction
Fruit is merged, and is obtained localization region of the target area in the three-dimensional DSA image to be processed, is specifically included:
Using the lookup result of the target area of the target direction as template, extended along the target direction, it will be in three-dimensional
The public domain that space intersection obtains, the localization region as the target area in the three-dimensional DSA image to be processed.
15. system as claimed in claim 10, which is characterized in that the method for the maximum intensity projection is using the maximum picture of reservation
The method of element value, to obtain the two dimensional image of target direction.
16. system as claimed in claim 10, which is characterized in that the target direction is coronal-plane, sagittal plane and cross section
Direction.
17. system as claimed in claim 10, which is characterized in that the lookup model is according to preset target area, base
In the deep learning method model that training obtains in advance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910782193.3A CN110503642B (en) | 2019-08-23 | 2019-08-23 | Positioning method and system based on DSA image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910782193.3A CN110503642B (en) | 2019-08-23 | 2019-08-23 | Positioning method and system based on DSA image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110503642A true CN110503642A (en) | 2019-11-26 |
| CN110503642B CN110503642B (en) | 2021-10-29 |
Family
ID=68588856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910782193.3A Active CN110503642B (en) | 2019-08-23 | 2019-08-23 | Positioning method and system based on DSA image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110503642B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507381A (en) * | 2020-03-31 | 2020-08-07 | 上海商汤智能科技有限公司 | Image recognition method and related device and equipment |
| CN111563876A (en) * | 2020-03-24 | 2020-08-21 | 上海依智医疗技术有限公司 | Medical image acquisition method and display method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103462696A (en) * | 2013-09-17 | 2013-12-25 | 浙江大学 | Integrated intravascular OCT (optical coherence tomography) image and DSA (digital subtraction angiography) integrating online real-time treatment device |
| CN103871036A (en) * | 2012-12-12 | 2014-06-18 | 上海联影医疗科技有限公司 | Rapid registering and splicing method used for three-dimensional digital subtraction angiography image |
| US20160143605A1 (en) * | 2014-11-21 | 2016-05-26 | Kabushiki Kaisha Toshiba | Image processing device and x-ray diagnostic apparatus |
| CN107019522A (en) * | 2015-12-04 | 2017-08-08 | 西门子保健有限责任公司 | Method, X-ray apparatus and computer program that image is supported are provided operator |
| CN109447966A (en) * | 2018-10-26 | 2019-03-08 | 科大讯飞股份有限公司 | Lesion localization recognition methods, device, equipment and the storage medium of medical image |
| CN109472803A (en) * | 2018-10-26 | 2019-03-15 | 强联智创（北京）科技有限公司 | A kind of entocranial artery blood vessel segmentation method and system |
| CN109816650A (en) * | 2019-01-24 | 2019-05-28 | 强联智创（北京）科技有限公司 | A kind of target area recognition methods and its system based on two-dimentional DSA image |
-
2019
- 2019-08-23 CN CN201910782193.3A patent/CN110503642B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871036A (en) * | 2012-12-12 | 2014-06-18 | 上海联影医疗科技有限公司 | Rapid registering and splicing method used for three-dimensional digital subtraction angiography image |
| CN103462696A (en) * | 2013-09-17 | 2013-12-25 | 浙江大学 | Integrated intravascular OCT (optical coherence tomography) image and DSA (digital subtraction angiography) integrating online real-time treatment device |
| US20160143605A1 (en) * | 2014-11-21 | 2016-05-26 | Kabushiki Kaisha Toshiba | Image processing device and x-ray diagnostic apparatus |
| CN107019522A (en) * | 2015-12-04 | 2017-08-08 | 西门子保健有限责任公司 | Method, X-ray apparatus and computer program that image is supported are provided operator |
| CN109447966A (en) * | 2018-10-26 | 2019-03-08 | 科大讯飞股份有限公司 | Lesion localization recognition methods, device, equipment and the storage medium of medical image |
| CN109472803A (en) * | 2018-10-26 | 2019-03-15 | 强联智创（北京）科技有限公司 | A kind of entocranial artery blood vessel segmentation method and system |
| CN109816650A (en) * | 2019-01-24 | 2019-05-28 | 强联智创（北京）科技有限公司 | A kind of target area recognition methods and its system based on two-dimentional DSA image |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563876A (en) * | 2020-03-24 | 2020-08-21 | 上海依智医疗技术有限公司 | Medical image acquisition method and display method |
| CN111563876B (en) * | 2020-03-24 | 2023-08-25 | 北京深睿博联科技有限责任公司 | Medical image acquisition method and medical image display method |
| CN111507381A (en) * | 2020-03-31 | 2020-08-07 | 上海商汤智能科技有限公司 | Image recognition method and related device and equipment |
| CN111507381B (en) * | 2020-03-31 | 2024-04-02 | 上海商汤智能科技有限公司 | Image recognition method, related device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110503642B (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109493348B (en) | Method and system for measuring morphological parameters of intracranial aneurysm image | |
| CN109345585B (en) | Method and system for measuring morphological parameters of intracranial aneurysm image | |
| CN109523526A (en) | Organize nodule detection and its model training method, device, equipment and system | |
| US7773791B2 (en) | Analyzing lesions in a medical digital image | |
| CN109389637A (en) | A kind of measurement method and system of the Morphologic Parameters of intracranial aneurysm image | |
| US10950338B2 (en) | Method and apparatus for generating an artificial intelligence 3D dataset and performing interactive manipulation and rendering of the dataset | |
| CN110517780A (en) | A kind of aneurysm rupture methods of risk assessment and system | |
| CN109584997A (en) | A kind of measurement method and system of the Morphologic Parameters of intracranial aneurysm image | |
| CN109448003A (en) | A kind of entocranial artery blood-vessel image dividing method and system | |
| CN109472823B (en) | Method and system for measuring morphological parameters of intracranial aneurysm image | |
| CN110517242A (en) | A kind of aneurysmal analysis method and device | |
| CN109448004B (en) | Centerline-based intracranial blood vessel image interception method and system | |
| WO2021098768A1 (en) | Method and system for assessing aneurysm rupture risk | |
| CN109584169A (en) | A kind of intercept method and system of the intracranial vessel image based on center line | |
| WO2020118618A1 (en) | Mammary gland mass image recognition method and device | |
| CN110534193A (en) | A kind of aneurysm rupture methods of risk assessment and system | |
| US20150104090A1 (en) | Modification of a hollow organ representation | |
| CN110189258A (en) | Arteria carotis lumen and tube wall automatic division method based on the multi-modal sequence of MRI | |
| CN110503642A (en) | A kind of localization method and system based on DSA image | |
| CN109816650A (en) | A kind of target area recognition methods and its system based on two-dimentional DSA image | |
| CN109671066A (en) | A kind of method and system of the cerebral infarction judgement based on head CT images | |
| CN106952264B (en) | Method and device for cutting three-dimensional medical target | |
| CN109447967A (en) | A kind of dividing method and system of intracranial aneurysm image | |
| CN105513055A (en) | Method and apparatus for segmenting tissue in CTA image | |
| CN106469445A (en) | A kind of calibration steps of 3-D view, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |