Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, the tumour Precise Position System for medical treatment that the present embodiment is provided includes that DDR tumor images gather mould
Block 1, DR tumor images acquisition module 2, image registration module 3, tumor-localizing module 4;The DDR tumor images acquisition module 1
DDR images for gathering the patient tumors region of the telltale mark point containing positioning patient tumors;The DR tumor images are adopted
Collection module 2 is used to gather the DR images in patient tumors region;Described image registration module 3 is used for the DDR images, DR images
Image registration is carried out, tumor-localizing parameter is obtained;The tumor-localizing module 4 is used for according to the tumor-localizing parameter to tumour
Reposition.
Preferably, the DDR images in the patient tumors region of telltale mark point of the collection containing positioning patient tumors, bag
Include:Gather the CT images of patient, DDR images are generated according to the CT image reconstructions of patient.
Preferably, the DR images in the collection patient tumors region, including:Patient tumors region is shot from different perspectives,
Obtain multiple DR images.
The above embodiment of the present invention uses image registration techniques, realizes the accurate positioning of tumour.
Preferably, referring to Fig. 2, the collection contains the patient tumors region of the telltale mark point of positioning patient tumors
DDR images, also include:Using customized screening function from multiple preferable CT images of CT optical sieving mass, for weight
Build generation DDR images:Wherein described customized screening function is:
Q={ Qi,Qi>0, i=1 ..., m }
Wherein
In formula, Q is the target image set after screening, ZiIt is i-th average gray value of image in multiple images, m is to adopt
The quantity of the image of collection, WiIt is i-th edge sharpness of image in multiple images, W is sharp according to the edge of actual conditions setting
Degree threshold value, whenWhen,When,
This preferred embodiment, the CT images after screening is used to rebuild generation DDR images, it is possible to increase the DDR figures of generation
The quality degree of picture, to realize tumour, accurately positioning lays the foundation.
Preferably, image registration is carried out to the DDR images, DR images, including:
(1) DDR images are chosen as reference picture S0, DR images calculate reference picture S as image S subject to registration respectively0
With the Arimoto entropys of the entropy diagram picture of image S subject to registrationVS, define Arimoto entropys computing formula be:
In formula, VS(x,y)Represent the Arimoto entropys of the entropy diagram picture of image S (x, y), U1、U2It is the regulation parameter of setting,
And U1>0,U1≠ 1, c (i, j) be centered on pixel (x, y), size as n × image block of n, wherein n is odd number,J [c (i, j)] represents the gray level of image block c (i, j), nkIt is
K-th frequency of gray level appearance, A is total pixel of image block c (i, j);
(2) based on differomorphism Demons algorithms, regard the registration of image as a gas diffusion process, give iteration
The initial value Ψ of displacement field0, displacement field is updated by following iterative formula:
In formula, GδIt is Gaussian filter, δ represents the mean square deviation of Gaussian filter kernel function, and * represents convolution operation, ΨkTable
Show displacement field during kth step iteration, Ψk-1Represent the displacement field during step iteration of kth -1, PSRepresent the gray scale of image S subject to registration
Value,The gray value of reference picture is represented,Represent the gradient of reference picture;
(3) constantly iteration updates displacement field, if meeting the stop condition of the object function of differomorphism Demons algorithms, jumps
Go out circulation and obtain final mean annual increment movement Ψ, otherwise continue to update displacement field, until reaching maximum iteration;
(4) using final mean annual increment movement Ψ as the optimal transformation between image subject to registration, reference picture S is completed0With figure subject to registration
The registration of picture.
In this preferred embodiment, brief biography of a deceased person DDR images, DR image registrations are entered using aforesaid way, reduce gray scale between image
The influence that difference is caused to registration result, improves the precision of image registration, so as to be advantageously implemented high-precision tumor-localizing.
Preferably, it is to realize the image registration effect that more optimizes, the object function to differomorphism Demons algorithms is carried out
Optimization, introduces regularization term and gradient distribution distance in object function, and the object function after definition optimization is:
The stop condition of objective function is:
In formula,It is the regularization term for introducing, B1、B2It is weight factor, ξ (Ψk) it is displacement field Ψk
Jacobian, M represents the number of pixels of lap between reference picture and image subject to registration,Represent and use
Displacement field ΨkEntropy diagram picture to image subject to registration carries out deformation;For introduce gradient distribution away from
From item, α is the sample point in image gradient,The gradient distribution of image S subject to registration is represented,Represent reference picture
Gradient distribution.
It is same to differential in this preferred embodiment, it is contemplated that the rough problem in spatial information and registration between pixel
The object function of embryo Demons algorithms is optimized, and regularization term and gradient distribution distance is introduced in object function, then
Optimal solution is asked for using the object function of the differomorphism Demons algorithms after optimization, relative to traditional differomorphism Demons
Algorithm, is obtained in that registration accuracy higher such that it is able to obtain the tumor-localizing effect of degree of precision.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of scope is protected, although being explained to the present invention with reference to preferred embodiment, one of ordinary skill in the art should
Work as understanding, technical scheme can be modified or equivalent, without deviating from the reality of technical solution of the present invention
Matter and scope.