CN112750120A - Medical image acquisition management method and system - Google Patents
Medical image acquisition management method and system Download PDFInfo
- Publication number
- CN112750120A CN112750120A CN202110073827.5A CN202110073827A CN112750120A CN 112750120 A CN112750120 A CN 112750120A CN 202110073827 A CN202110073827 A CN 202110073827A CN 112750120 A CN112750120 A CN 112750120A
- Authority
- CN
- China
- Prior art keywords
- image
- medical image
- medical
- gray
- images
- 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.)
- Withdrawn
Links
- 238000007726 management method Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 58
- 230000004927 fusion Effects 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 41
- 230000009467 reduction Effects 0.000 claims abstract description 31
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 30
- 238000003709 image segmentation Methods 0.000 claims abstract description 27
- 238000007500 overflow downdraw method Methods 0.000 claims abstract description 26
- 230000006835 compression Effects 0.000 claims abstract description 24
- 238000007906 compression Methods 0.000 claims abstract description 24
- 238000006243 chemical reaction Methods 0.000 claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims description 41
- 230000003044 adaptive effect Effects 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 10
- 230000000739 chaotic effect Effects 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 17
- 238000004891 communication Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 238000005481 NMR spectroscopy Methods 0.000 description 3
- 238000002059 diagnostic imaging Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000000926 separation method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000004872 soft tissue Anatomy 0.000 description 1
- 239000003826 tablet Substances 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Images
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
- G06T1/00—General purpose image data processing
- G06T1/0021—Image watermarking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- 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
- G06T2207/20004—Adaptive image processing
- G06T2207/20012—Locally adaptive
-
- 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
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
-
- 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
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- G06T2207/20024—Filtering details
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20052—Discrete cosine transform [DCT]
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, and discloses a medical image acquisition management method, which comprises the following steps: converting the medical image into a gray image by using a gray image conversion method, and performing noise reduction processing on the gray image by using a Gaussian filter; performing Laplacian pyramid decomposition on the medical image subjected to noise reduction; carrying out image segmentation processing on the medical image by using an image segmentation algorithm based on a self-adaptive region; fusing the approximate coefficients of the image by adopting a fusion method based on a self-adaptive image block, and fusing the detail coefficients of the image by adopting a fusion method based on an image gradient; adding medical image digital watermarks to the medical fusion images by using a medical image watermarking algorithm based on perceptual hash; and compressing the medical image by using an image compression method based on an image threshold value, and storing the compressed image in a medical image management system. The invention also provides a medical image acquisition management system. The invention realizes the management of medical images.
Description
Technical Field
The invention relates to the technical field of image management, in particular to a medical image acquisition management method and system.
Background
With the development of medical imaging technology, doctors begin to adopt medical imaging data as the basis of medical diagnosis and treatment in large quantities, and at present, all diagnostic imaging is computerized and can process digital data, which mainly includes X-ray, ultrasound, CT, etc., and the management of these medical images becomes a hot topic of current research.
Due to the limitation of image acquisition equipment, a single image cannot display medical image information in all directions, for example, a medical CT image mainly focuses on position information of human bones and implants, and a nuclear magnetic resonance image focuses on detail information of human soft tissues, so that different medical images need to be merged by adopting an image fusion strategy, more comprehensive information is presented in one image, the existing image fusion strategy does not consider information such as an imaging mechanism, inherent characteristics and the like of the image, but considers a source image as a common digital signal for processing, the purpose of pursuing numerical values of multiple objective evaluation indexes is the maximum, and the practical application field is not considered.
Meanwhile, the medical image digital watermarking technology can be used for protecting the privacy of patients, namely, the privacy information of the patients is hidden in the corresponding medical images as watermarks; however, the medical image is different from the ordinary image, and when the watermark embedding processing is carried out, the correctness and the accuracy of diagnosis by a doctor are not influenced.
In view of this, how to adopt a more efficient image fusion strategy to perform medical image fusion and add a digital watermark to a medical image becomes a problem to be solved urgently by those skilled in the art.
Disclosure of Invention
The invention provides a medical image acquisition management method, which fuses different medical images by using an image fusion strategy based on local self-adaptive difference, adds medical image digital watermarks to the medical images by using a medical image watermarking algorithm based on perceptual hash, compresses the medical images by using a compression algorithm, and realizes compression management of the medical images.
In order to achieve the above object, the present invention provides a medical image acquisition management method, including:
acquiring a medical image, converting the medical image into a gray image by using a gray image conversion method, and performing noise reduction processing on the gray image by using a Gaussian filter to obtain a noise-reduced medical image;
performing Laplacian pyramid decomposition on the medical image after noise reduction to obtain a detail coefficient and an approximate coefficient of the medical image;
carrying out image segmentation processing on the medical image by using an image segmentation algorithm based on the adaptive region to obtain an adaptive image block of the medical image;
fusing the approximate coefficients of the images by adopting a fusion method based on self-adaptive image blocks, and fusing the detail coefficients of the images by adopting a fusion method based on image gradient to obtain medical fusion images;
adding a medical image digital watermark to the medical fusion image by using a medical image watermark algorithm based on perceptual hash to obtain a medical image with the digital watermark;
and compressing the medical image with the digital watermark by using an image compression method based on an image threshold value, and storing the compressed image into a medical image management system.
Optionally, the converting the medical image into the gray scale map by using a gray scale map converting method, and performing noise reduction processing on the gray scale map by using a gaussian filter includes:
the medical images comprise CT images, nuclear magnetic resonance images and diagnosis report images of different patients; the invention utilizes a gray-scale image conversion method to convert a medical image into a gray-scale image, and the gray-scale image conversion formula of the image is as follows:
Gray(i,j)=R(i,j)×0.314+G(i,j)×0.591+B(i,j)×0.113
wherein:
R(i,j),G(i,j),B(i,j)the pixel value of the medical image pixel (i, j) in three color components of R, G and B;
Gray(i,j)is a pixel(ii) a grey scale value of (i, j);
and carrying out noise reduction processing on the gray-scale image by using a Gaussian filter, wherein the noise reduction formula based on the Gaussian filter is as follows:
wherein:
(i, j) representing a pixel point of a gray scale map;
omega represents the weight of the Gaussian template at the pixel point (i, j);
g (i, j) represents the pixel point (i, j) after noise reduction;
σ is a smoothing degree parameter, which is set as a standard deviation of the medical image pixels.
Optionally, the performing laplacian pyramid decomposition on the noise-reduced medical image includes:
the Laplace pyramid is formed by subtracting a series of images of the images which are reduced and then amplified from the source image, and is the inverse operation of the Gaussian pyramid; the decomposition process of the Laplacian pyramid comprises the following steps:
1) mapping the medical image after noise reduction to a Laplacian pyramid, wherein the Laplacian pyramid is the ith layer LiIs expressed as:
wherein:
Gia medical image of the ith layer of the Laplacian pyramid is obtained;
the UP () operation is to map the pixel at the (x, y) position in the noise-reduced medical image to the (2x +1,2y +1) position of the target image, i.e., to perform UP-sampling;
g5×5represents a 5 × 5 gaussian kernel;
2) expanding the low-resolution image of the higher layer to make the sizes of the two layers of images consistent; the expansion method is that new pixels are inserted between the original pixels, and the value of the new pixels is the weighted average of the gray value in the area where the original pixels are located;
3) performing difference operation on the expanded low-resolution image of the higher layer and the high-resolution image of the lower layer, and forming a Laplacian pyramid decomposition image by the obtained result and the Gaussian pyramid decomposition result of the highest layer; generally, as the decomposition layer increases, the image becomes more and more blurred, the series of images obtained by applying the difference are approximate coefficients, and the images obtained by the decomposition of the top layer of the gaussian pyramid are detail coefficients.
Optionally, the image segmentation processing on the medical image by using the adaptive region-based image segmentation algorithm includes:
1) initializing the number of image blocks of a medical image, wherein an image block is denoted xi,j(g) I represents the number of the image block, j represents the dimension of the image block, and g represents the iteration number of the self-adaptive segmentation;
2) randomly selecting three different image blocks from the initialized medical image blocks, calculating the vector weighted sum of the differences of any two image blocks, and adding the vector weighted sum to the third image block to generate a new image block yi(g+1):
yi(g+1)=xi1(g)+F·(xi2(g)-xi3(g))
Wherein:
i, i1, i2, i3 denote different image block numbers;
f is a scaling factor, and in a specific embodiment of the present invention, the scaling factor is adjusted in an adaptive manner:
wherein:
Fmin0.1 is the lower limit of the scaling factor;
Fmax0.9 is shrinkageThe upper limit of the factor is released;
randiis [0, 1]]A random number in between;
tau is the adaptive algorithm threshold, which is set to 0.5 by the present invention;
3) calculating an objective function value f' of the added image block, wherein f is a minimization fitness function; and performing iterative computation for multiple times to obtain objective function values of different image blocks, and performing image segmentation processing on the medical image according to the image block number corresponding to the minimum objective function value to obtain a plurality of medical image blocks.
Optionally, the fusing the approximate coefficients of the image by using a fusion method based on a self-adaptive image block, and fusing the detail coefficients of the image by using a fusion method based on an image gradient, includes:
the method for fusing the approximate coefficients of the image by adopting a fusion method based on the self-adaptive image blocks comprises the following steps:
1) constructing an all-zero matrix D with the size equal to that of the medical image blocks, and determining Laplace energy of the two homologous medical image blocks; the homologous medical images represent two medical images from the same patient;
2) if the laplacian energies of the image blocks A and B in the homologous medical image are consistent, setting the corresponding positions of the medical image blocks in the all-zero matrix D as 1, otherwise, setting the corresponding positions of the medical image blocks in the all-zero matrix D as 0, and obtaining a laplacian-based medical image matrix;
3) for d in the matrixijIf the position is 1, selecting the approximation coefficient of the medical image block A as the approximation coefficient of the fused image, otherwise, selecting the approximation coefficient of the medical image block B as the approximation coefficient of the fused image; and optimizing the fused approximation coefficient by using a mode filtering algorithm, namely changing the approximation coefficient of the center into the approximation coefficient in the medical image B if the approximation coefficient of the center is derived from the medical image A and the approximation coefficients of the surrounding areas are derived from the medical image B.
The detail coefficient of the image is fused by adopting a fusion method based on image gradient, and the method comprises the following steps:
by setting different size windows, for a window with a window size of m × n, the image gradient energy with coordinates (x, y) is calculated:
wherein:
w (k, h) is the detail coefficient at coordinate (k, h);
according to the medical image matrix based on Laplace, for homologous medical images A and B, fusion based on image gradient energy is carried out on detail coefficients of the homologous medical images A and B:
wherein:
dxyis the value of the coordinate point (x, y) in the laplace-based medical image matrix;
wA(x,y),wB(x, y0 are detail coefficients for medical images A and B, respectively;
w (x, y) is a fused homologous medical image detail coefficient;
in one embodiment of the invention, fusion of detail coefficients and approximation coefficients is performed on all homologous medical images of a patient to merge different medical images, so that more comprehensive information is presented in one image.
Optionally, the adding a medical image digital watermark to the medical fusion image by using a medical image watermarking algorithm based on perceptual hash includes:
1) 2-level decomposition of contourlet transformation is carried out on the medical fusion image, the number of directions is set to be 4, medical approximate images are obtained after transformation, and 4 third-layer direction sub-bands with the size of 128x128 in the second-layer direction and the size of 256x256 in the 4 second-layer direction sub-bands are obtained;
2) obtaining a DCT coefficient matrix D with the same size as the medical approximate image by using global DCT, and calculating an average value M:
D(i,j)=DCT2(X(i,j))
wherein:
mxn is the size of the medical approximation image X;
x (i, j) is a sub-band pixel value to be measured of the medical approximate image;
d (i, j) is a value in a DCT coefficient matrix D;
3) reserving the lowest frequency part of the DCT coefficient matrix, namely a matrix D' with the size of 4 multiplied by 8 on the upper left corner;
4) comparing according to the retained 4 × 8 coefficient matrix, a value greater than or equal to the mean M is set to 1, and a value less than the mean M is set to 0, thereby constituting a 32-bit hash value H in order:
H=reshape(h(i,j))
wherein:
m is the mean value of a DCT coefficient matrix D;
5) converting patient information corresponding to the medical fusion image into a hash value W, converting the hash value W into a watermark W ' by using an encryption algorithm based on a chaotic sequence, and adding the watermark W ' into the medical fusion image as a medical image digital watermark, wherein the calculation method of the watermark W ' comprises the following steps:
wherein:
t (n) is a chaotic sequence;
w (i, j) is a patient information hash value;
6) and carrying out exclusive or operation on the 32-bit hash value H and each row of the watermark W' to obtain a logic key K:
and extracting an encrypted watermark W' by carrying out XOR calculation on the hash value H and the logic key, and obtaining the hash value W of the patient information through chaotic decryption reduction.
Optionally, the compressing the medical image with the digital watermark by using an image compression method based on an image threshold includes:
1) for the medical image with the digital watermark, the medical image is converted into a two-dimensional gray image, the gray value range of the medical image is [0, 1, …, L-1], and the probability of each level of gray is as follows:
pi=ni/sum
wherein:
sum is the total pixel number of the two-dimensional gray level image;
nithe total number of pixels with the gray value of i;
2) setting the gray level k as a threshold, dividing the image pixels into C according to the threshold level k0And C1Two kinds, wherein C0Indicating gray scale levels at 0, 1, …, k]Set of pixels in (1), C1Indicating gray scale levels at [ k +1, k +2, …, L-1]In (2), the probability of occurrence of each of the two types is:
wherein:
ω (k) represents C0Representing the probability sum of the pixel number of each gray level in the total pixel number;
further, the invention calculates to obtain C0,C1Class mean μ of0,μ1:
μ0=μ(k)/ω(k)
Wherein:
and calculating to obtain C0,C1Inter-class variance of (c):
3) establishing an optimized objective function of a threshold k:
solving to obtain:
in one embodiment of the present invention, the present invention introduces an adjustable puncturing parameter T, T being the optimal separation threshold:
T=k′+t
when t is positive, a compact medical image salient region is represented, and the target region is guaranteed to have significance; when t is a negative number, a loose medical image salient region is represented, and the obtained region is ensured to better cover a plurality of salient objects under the condition of having significance;
4) carrying out salient region division on the medical image with the digital watermark through a threshold, carrying out lossless coding compression processing on the salient region, and carrying out lossy coding compression processing on the non-salient region; therefore, high-quality transmission or priority transmission management is carried out on the salient region, and the purpose of protecting important information in the medical image is achieved.
In addition, to achieve the above object, the present invention also provides a medical image acquisition management system, including:
the medical image acquisition device is used for acquiring a medical image, converting the medical image into a gray image by using a gray image conversion method, and simultaneously performing noise reduction processing on the gray image by using a Gaussian filter to obtain a noise-reduced medical image;
the medical image processor is used for carrying out Laplacian pyramid decomposition on the medical image subjected to noise reduction to obtain a detail coefficient and an approximate coefficient of the medical image; carrying out image segmentation processing on the medical image by using an image segmentation algorithm based on the adaptive region to obtain an adaptive image block of the medical image; fusing the approximate coefficients of the images by adopting a fusion method based on self-adaptive image blocks, and fusing the detail coefficients of the images by adopting a fusion method based on image gradient to obtain medical fusion images;
the medical image acquisition management device is used for adding a medical image digital watermark to the medical fusion image by using a medical image watermark algorithm based on perceptual hash to obtain a medical image with the digital watermark; and compressing the medical image with the digital watermark by using an image compression method based on an image threshold value, and storing the compressed image into a medical image management system.
Further, to achieve the above object, the present invention also provides a computer readable storage medium having stored thereon medical image acquisition management program instructions executable by one or more processors to implement the steps of the implementation method of medical image acquisition management as described above.
Compared with the prior art, the invention provides a medical image acquisition management method, which has the following advantages:
the invention provides an image fusion strategy based on local adaptive difference to fuse different medical images, wherein the medical images are decomposed based on a Laplace pyramid, a difference value operation is carried out on an expanded low-resolution image at a higher layer and a high-resolution image at a lower layer, the obtained result and a Gauss pyramid decomposition result at the highest layer jointly form a Laplace pyramid decomposition image, the images are more and more blurred along with the increase of decomposition layers, a series of images obtained by using the difference value are approximate coefficients, and the images obtained by decomposing the top layer of the Gauss pyramid are detail coefficients; and image segmentation processing is carried out on the medical image by using a self-adaptive regional map-based image segmentation algorithm, different three image blocks are randomly selected from the initialized medical image blocks, the vector weighted sum of the difference of any two image blocks is calculated and added to the third image block, and a new image block y is generatedi(g+1):
yi(g+1)=xi1(g)+F·(xi2(g)-xi3(g))
Wherein: i, i1, i2, i3 denote different image block numbers; f is a scaling factor, and the scaling factor is adjusted in a self-adaptive mode:
wherein: fmin0.1 is the lower limit of the scaling factor; fmax0.9 is the upper limit of the scaling factor; randiIs [0, 1]]A random number in between; tau is the adaptive algorithm threshold, which is set to 0.5 by the present invention; calculating an objective function value f' of the added image block, wherein f is a minimization fitness function; and performing iterative computation for multiple times to obtain objective function values of different image blocks, and performing image segmentation processing on the medical image according to the image block number corresponding to the minimum objective function value to obtain a plurality of medical image blocks. And the approximate coefficients of the image are fused by adopting a Laplace energy fusion method based on self-adaptive image blocks, and the image is subjected to image matchingThe detail coefficient of the image is fused by adopting a fusion method based on image gradient, and the method comprises the following steps:
by setting different size windows, for a window with a window size of m × n, the image gradient energy with coordinates (x, y) is calculated:
wherein: w (k, h) is the detail coefficient at coordinate (k, h); according to the medical image matrix based on Laplace, for homologous medical images A and B, fusion based on image gradient energy is carried out on detail coefficients of the homologous medical images A and B:
wherein: dxyIs the value of the coordinate point (x, y) in the laplace-based medical image matrix; w is aA(x,y),wB(x, y) are detail coefficients of the medical images A and B, respectively; w (x, y) is a fused homologous medical image detail coefficient; in one embodiment of the invention, fusion of detail coefficients and approximation coefficients is performed on all homologous medical images of a patient to fuse different medical images, so that more comprehensive information is presented in one image.
Meanwhile, the invention provides an image compression method based on image threshold, which is used for compressing medical images, converting the medical images with digital watermarks into two-dimensional gray images, wherein the gray value range of the two-dimensional gray images is [0, 1, …, L-1], and the probability of the gray levels is as follows:
pi=ni/sum
wherein: sum is the total pixel number of the two-dimensional gray level image; n isiThe total number of pixels with the gray value of i; by setting the gray level k as the threshold, the image pixels are divided into C according to the threshold level k0And C1Two kinds, wherein C0Indicating gray scale levels at 0, 1, …, k]Set of pixels in (1), C1Indicating gray scale levels at [ k +1, k +2, …, L-1]In (2), the probability of occurrence of each of the two types is:
wherein: ω (k) represents C0Representing the probability sum of the pixel number of each gray level in the total pixel number; and calculating to obtain C0,C1Class mean μ of0,μ1:
μ0=μ(k)/ω(k)
by establishing an optimized objective function for threshold k:
the above formula can be used, the denominator is not changed, and therefore, the maximum value of the function is required, namely, the maximum value of the numerator is equivalent to the maximum value of the numerator, so that the optimization of the objective function can be converted into the optimal solution of the numerator, and the solution is obtained:
in one embodiment of the present invention, the present invention introduces an adjustable puncturing parameter T, T being the optimal separation threshold:
T=k′+t
when t is positive, a compact medical image salient region is represented, and the target region is guaranteed to have significance; when t is a negative number, a loose medical image salient region is represented, and the obtained region is ensured to better cover a plurality of salient objects under the condition of having significance; carrying out salient region division on the medical image with the digital watermark through a threshold, carrying out lossless coding compression processing on the salient region, and carrying out lossy coding compression processing on the non-salient region; therefore, high-quality transmission or priority transmission management is carried out on the salient region, and the purpose of protecting important information in the medical image is achieved.
Drawings
Fig. 1 is a schematic flow chart of a medical image acquisition management method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a medical image acquisition management system according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The method comprises the steps of fusing different medical images by using an image fusion strategy based on local self-adaptive difference, adding medical image digital watermarks to the medical images by using a medical image watermarking algorithm based on perceptual hash, and compressing the medical images by using a compression algorithm to realize compression management of the medical images. Fig. 1 is a schematic view of a medical image acquisition management method according to an embodiment of the present invention.
In this embodiment, a medical image acquisition management method includes:
and S1, acquiring the medical image, converting the medical image into a gray image by using a gray image conversion method, and simultaneously performing noise reduction processing on the gray image by using a Gaussian filter to obtain the noise-reduced medical image.
Firstly, medical images are obtained, wherein the medical images comprise CT images, nuclear magnetic resonance images and diagnosis report images of different patients; further, the invention converts the medical image into the gray-scale image by using a gray-scale image conversion method, wherein the gray-scale image conversion formula of the image is as follows:
Gray(i,j)=R(i,j)×0.314+G(i,j)×0.591+B(i,j)×0.113
wherein:
R(i,j),G(i,j),B(i,j)the pixel value of the medical image pixel (i, j) in three color components of R, G and B;
Gray(i,j)is the gray value of pixel (i, j);
further, the invention utilizes a gaussian filter to perform noise reduction processing on the gray scale image, and the noise reduction formula based on the gaussian filter is as follows:
wherein:
(i, j) representing a pixel point of a gray scale map;
omega represents the weight of the Gaussian template at the pixel point (i, j);
g (i, j) represents the pixel point (i, j) after noise reduction;
σ is a smoothing degree parameter, which is set as a standard deviation of the medical image pixels.
And S2, performing Laplacian pyramid decomposition on the medical image subjected to noise reduction to obtain a detail coefficient and an approximate coefficient of the medical image.
Further, the medical image after noise reduction is subjected to Laplacian pyramid decomposition, wherein the Laplacian pyramid is formed by subtracting a series of images of the image which is reduced and then amplified from the source image and is the inverse operation of a Gaussian pyramid; the decomposition process of the Laplacian pyramid comprises the following steps:
1) mapping the medical image after noise reduction to a Laplacian pyramid, wherein the Laplacian pyramid is the ith layer LiIs expressed as:
wherein:
Gia medical image of the ith layer of the Laplacian pyramid is obtained;
the UP () operation is to map the pixel at the (x, y) position in the noise-reduced medical image to the (2x +1,2y +1) position of the target image, i.e., to perform UP-sampling;
g5×5represents a 5 × 5 gaussian kernel;
2) expanding the low-resolution image of the higher layer to make the sizes of the two layers of images consistent; the expansion method is that new pixels are inserted between the original pixels, and the value of the new pixels is the weighted average of the gray value in the area where the original pixels are located;
3) performing difference operation on the expanded low-resolution image of the higher layer and the high-resolution image of the lower layer, and forming a Laplacian pyramid decomposition image by the obtained result and the Gaussian pyramid decomposition result of the highest layer; generally, as the decomposition layer increases, the image becomes more and more blurred, the series of images obtained by applying the difference are approximate coefficients, and the images obtained by the decomposition of the top layer of the gaussian pyramid are detail coefficients.
S3, carrying out image segmentation processing on the medical image by using an image segmentation algorithm based on the adaptive region to obtain an adaptive image block of the medical image; and fusing the approximate coefficients of the images by adopting a fusion method based on self-adaptive image blocks, and fusing the detail coefficients of the images by adopting a fusion method based on image gradient to obtain medical fusion images.
Further, the invention carries out image segmentation processing on the medical image by using an adaptive regional map-based image segmentation algorithm; the image segmentation algorithm based on the self-adaptive region comprises the following processes:
1) initializing the number of image blocks of a medical image, wherein an image block is denoted xi,j(g) I represents the number of the image block, j represents the dimension of the image block, and g represents the iteration number of the self-adaptive segmentation;
2) randomly selecting three different image blocks from the initialized medical image blocks, calculating the vector weighted sum of the differences of any two image blocks, and adding the vector weighted sum to the third image block to generate a new image block yi(g+1):
yi(g+1)=xi1(g)+F·(xi2(g)-xi3(g))
Wherein:
i, i1, i2, i3 denote different image block numbers;
f is a scaling factor, and in a specific embodiment of the present invention, the scaling factor is adjusted in an adaptive manner:
wherein:
Fmin0.1 is the lower limit of the scaling factor;
Fmax0.9 is the upper limit of the scaling factor;
randiis [0, 1]]A random number in between;
tau is the adaptive algorithm threshold, which is set to 0.5 by the present invention;
3) calculating an objective function value f' of the added image block, wherein f is a minimization fitness function; and performing iterative computation for multiple times to obtain objective function values of different image blocks, and performing image segmentation processing on the medical image according to the image block number corresponding to the minimum objective function value to obtain a plurality of medical image blocks.
Furthermore, the invention adopts a fusion method based on self-adaptive image blocks to fuse the approximate coefficients of the image, and the method comprises the following steps:
1) constructing an all-zero matrix D with the size equal to that of the medical image blocks, and determining Laplace energy of the two homologous medical image blocks; the homologous medical images represent two medical images from the same patient;
2) if the laplacian energies of the image blocks A and B in the homologous medical image are consistent, setting the corresponding positions of the medical image blocks in the all-zero matrix D as 1, otherwise, setting the corresponding positions of the medical image blocks in the all-zero matrix D as 0, and obtaining a laplacian-based medical image matrix;
3) for d in the matrixijIf the position is 1, selecting the approximation coefficient of the medical image block A as the approximation coefficient of the fused image, otherwise, selecting the approximation coefficient of the medical image block B as the approximation coefficient of the fused image; and optimizing the fused approximation coefficient by using a mode filtering algorithm, namely changing the approximation coefficient of the center into the approximation coefficient in the medical image B if the approximation coefficient of the center is derived from the medical image A and the approximation coefficients of the surrounding areas are derived from the medical image B.
Furthermore, the invention adopts an image gradient-based fusion method to fuse the detail coefficients of the image, and the steps are as follows:
by setting different size windows, for a window with a window size of m × n, the image gradient energy with coordinates (x, y) is calculated:
wherein:
w (k, h) is the detail coefficient at coordinate (k, h);
according to the medical image matrix based on Laplace, for homologous medical images A and B, fusion based on image gradient energy is carried out on detail coefficients of the homologous medical images A and B:
wherein:
dxyis the value of the coordinate point (x, y) in the laplace-based medical image matrix;
wA(x,y),wB(x, y) are detail coefficients of the medical images A and B, respectively;
w (x, y) is a fused homologous medical image detail coefficient;
in one embodiment of the invention, fusion of detail coefficients and approximation coefficients is performed on all homologous medical images of a patient to merge different medical images, so that more comprehensive information is presented in one image.
S4, adding medical image digital watermarks to the medical fusion images by using a medical image watermarking algorithm based on perceptual hash to obtain medical images with digital watermarks.
Further, the invention adds medical image digital watermark to the medical fusion image by using a medical image watermark algorithm based on perceptual hash, wherein the medical image watermark algorithm based on perceptual hash comprises the following steps:
1) 2-level decomposition of contourlet transformation is carried out on the medical fusion image, the number of directions is set to be 4, medical approximate images are obtained after transformation, and 4 third-layer direction sub-bands with the size of 128x128 in the second-layer direction and 256x256 in the second-layer direction are obtained;
2) obtaining a DCT coefficient matrix D with the same size as the medical approximate image by using global DCT, and calculating an average value M:
D(i,j)=DCT2(X(i,j))
wherein:
mxn is the size of the medical approximation image X;
x (i, j) is a sub-band pixel value to be measured of the medical approximate image;
d (i, j) is a value in a DCT coefficient matrix D;
3) reserving the lowest frequency part of the DCT coefficient matrix, namely a matrix D' with the size of 4x8 on the upper left corner;
4) comparing according to the retained 4x8 coefficient matrix, a value greater than or equal to the mean M is set to 1, and a value less than the mean M is set to 0, thereby composing a 32-bit hash value H in order:
H=reshape(h(i,j))
wherein:
m is the mean value of a DCT coefficient matrix D;
5) converting patient information corresponding to the medical fusion image into a hash value W, converting the hash value W into a watermark W ' by using an encryption algorithm based on a chaotic sequence, and adding the watermark W ' into the medical fusion image as a medical image digital watermark, wherein the calculation method of the watermark W ' comprises the following steps:
wherein:
t (n) is a chaotic sequence;
w (i, j) is a patient information hash value;
6) and carrying out exclusive or operation on the 32-bit hash value H and each row of the watermark W' to obtain a logic key K:
and extracting an encrypted watermark W' by carrying out XOR calculation on the hash value H and the logic key, and obtaining the hash value W of the patient information through chaotic decryption reduction.
And S5, compressing the medical image with the digital watermark by using an image compression method based on the image threshold value, and storing the compressed image in a medical image management system.
Furthermore, the invention utilizes an image compression method based on an image threshold to compress the medical image with the digital watermark, and the image compression method based on the image threshold comprises the following processes:
1) for the medical image with the digital watermark, the medical image is converted into a two-dimensional gray image, the gray value range of the medical image is [0, 1, …, L-1], and the probability of each level of gray is as follows:
pi=ni/sum
wherein:
sum is the total pixel number of the two-dimensional gray level image;
nithe total number of pixels with the gray value of i;
2) setting the gray level k as a threshold, dividing the image pixels into C according to the threshold level k0And C1Two kinds, wherein C0Indicating gray scale levels at 0, 1, …, k]Set of pixels in (1), C1Indicating gray scale levels at [ k +1, k +2, …, L-1]In (2), the probability of occurrence of each of the two types is:
wherein:
ω (k) represents C0Representing the probability sum of the pixel number of each gray level in the total pixel number;
further, the invention calculates to obtain C0,C1Class mean μ of0,μ1:
μ0=μ(k)/ω(k)
Wherein:
and calculating to obtain C0,C1Inter-class variance of (c):
3) establishing an optimized objective function of a threshold k:
solving to obtain:
in one embodiment of the present invention, the present invention introduces an adjustable puncturing parameter T, T being the optimal separation threshold:
T=k′+t
when t is positive, a compact medical image salient region is represented, and the target region is guaranteed to have significance; when t is a negative number, a loose medical image salient region is represented, and the obtained region is ensured to better cover a plurality of salient objects under the condition of having significance;
4) carrying out salient region division on the medical image with the digital watermark through a threshold, carrying out lossless coding compression processing on the salient region, and carrying out lossy coding compression processing on the non-salient region; therefore, high-quality transmission or priority transmission management is carried out on the salient region, and the purpose of protecting important information in the medical image is achieved.
The following describes embodiments of the present invention through an algorithmic experiment and tests of the inventive treatment method. The hardware test environment of the algorithm of the invention is as follows: inter (R) core (TM) i7-6700K CPU, software python 3.5, test environment PyTorch 1.0; the contrast method is a medical image management method based on GF, a medical image management method based on Faster-rcnn and a medical image management method based on DE-LP.
In the algorithmic experiments described in the present invention, the data sets were medical images of 5000 different patients from three hospitals. In the experiment, medical image data is input into the medical image management method, and the accuracy of medical image fusion is used as an evaluation index of feasibility of the method.
According to the experimental result, the medical image fusion accuracy of the medical image management method based on GF is 73.63%, the medical image fusion accuracy of the medical image management method based on Faster-rcnn is 77.88%, the medical image fusion accuracy of the medical image management method based on DE-LP is 82.19%, and the medical image fusion accuracy of the method is 84.62%.
The invention also provides a medical image acquisition management system. Fig. 2 is a schematic diagram of an internal structure of a medical image acquisition management system according to an embodiment of the present invention.
In the present embodiment, the medical image acquisition management system 1 includes at least a medical image acquisition device 11, a medical image processor 12, a medical image acquisition management device 13, a communication bus 14, and a network interface 15.
The medical image acquiring apparatus 11 may be a PC (Personal Computer), a terminal device such as a smart phone, a tablet Computer, or a mobile Computer, or may be a server.
The medical image acquisition management device 13 may be, in some embodiments, a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor or other data Processing chip, and is used for executing program codes stored in the medical image processor 12 or Processing data, such as medical image acquisition management program instructions.
The communication bus 14 is used to enable connection communication between these components.
The network interface 15 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and is typically used to establish a communication link between the system 1 and other electronic devices.
Optionally, the system 1 may further comprise a user interface, which may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the medical image acquisition management system 1 and for displaying a visualized user interface.
Fig. 2 only shows the medical image acquisition management system 1 with the components 11-15, and it will be understood by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the medical image acquisition management system 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
In the embodiment of the apparatus 1 shown in fig. 2, medical image processor 12 stores therein medical image acquisition management program instructions; the procedure of executing the medical image acquisition management program instructions stored in the medical image processor 12 by the medical image acquisition management device 13 is the same as the implementation method of the medical image acquisition management method, and will not be described here.
Furthermore, an embodiment of the present invention also provides a computer-readable storage medium having stored thereon medical image acquisition management program instructions executable by one or more processors to implement the following operations:
acquiring a medical image, converting the medical image into a gray image by using a gray image conversion method, and performing noise reduction processing on the gray image by using a Gaussian filter to obtain a noise-reduced medical image;
performing Laplacian pyramid decomposition on the medical image after noise reduction to obtain a detail coefficient and an approximate coefficient of the medical image;
carrying out image segmentation processing on the medical image by using an image segmentation algorithm based on the adaptive region to obtain an adaptive image block of the medical image;
fusing the approximate coefficients of the images by adopting a fusion method based on self-adaptive image blocks, and fusing the detail coefficients of the images by adopting a fusion method based on image gradient to obtain medical fusion images;
adding a medical image digital watermark to the medical fusion image by using a medical image watermark algorithm based on perceptual hash to obtain a medical image with the digital watermark;
and compressing the medical image with the digital watermark by using an image compression method based on an image threshold value, and storing the compressed image into a medical image management system.
It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. A medical image acquisition management method, characterized in that the method comprises:
acquiring a medical image, converting the medical image into a gray image by using a gray image conversion method, and performing noise reduction processing on the gray image by using a Gaussian filter to obtain a noise-reduced medical image;
performing Laplacian pyramid decomposition on the medical image after noise reduction to obtain a detail coefficient and an approximate coefficient of the medical image;
carrying out image segmentation processing on the medical image by using an image segmentation algorithm based on the adaptive region to obtain an adaptive image block of the medical image;
fusing the approximate coefficients of the images by adopting a fusion method based on self-adaptive image blocks, and fusing the detail coefficients of the images by adopting a fusion method based on image gradient to obtain medical fusion images;
adding a medical image digital watermark to the medical fusion image by using a medical image watermark algorithm based on perceptual hash to obtain a medical image with the digital watermark;
and compressing the medical image with the digital watermark by using an image compression method based on an image threshold value, and storing the compressed image into a medical image management system.
2. The medical image acquisition management method according to claim 1, wherein the converting the medical image into the gray-scale image by using the gray-scale image conversion method and the denoising processing of the gray-scale image by using the gaussian filter comprises:
converting a medical image into a gray-scale image by using a gray-scale image conversion method, wherein the gray-scale image conversion formula of the image is as follows:
Gray(i,j)=R(i,j)×0.314+G(i,j)×0.591+B(i,j)×0.113
wherein:
R(i,j),G(i,j),B(i,j)for the pixel (i, j) of the medical image in three color components of R, G and BA pixel value;
Gray(i,j)is the gray value of pixel (i, j);
and carrying out noise reduction processing on the gray-scale image by using a Gaussian filter, wherein the noise reduction formula based on the Gaussian filter is as follows:
wherein:
(i, j) representing a pixel point of a gray scale map;
omega represents the weight of the Gaussian template at the pixel point (i, j);
g (i, j) represents the pixel point (i, j) after noise reduction;
σ is a smoothing degree parameter, which is set as a standard deviation of the medical image pixels.
3. The medical image acquisition management method according to claim 2, wherein the performing laplacian pyramid decomposition on the noise-reduced medical image includes:
the Laplace pyramid is formed by subtracting a series of images of the images which are reduced and then amplified from the source image, and is the inverse operation of the Gaussian pyramid; the decomposition process of the Laplacian pyramid comprises the following steps:
1) mapping the medical image after noise reduction to a Laplacian pyramid, wherein the Laplacian pyramid is the ith layer LiIs expressed as:
wherein:
Gia medical image of the ith layer of the Laplacian pyramid is obtained;
the UP () operation is to map the pixel at the (x, y) position in the noise-reduced medical image to the (2x +1,2y +1) position of the target image, i.e., to perform UP-sampling;
g5×5represents a 5 × 5 gaussian kernel;
2) expanding the low-resolution image of the higher layer to make the sizes of the two layers of images consistent; the expansion method is that new pixels are inserted between the original pixels, and the value of the new pixels is the weighted average of the gray value in the area where the original pixels are located;
3) performing difference operation on the expanded low-resolution image of the higher layer and the high-resolution image of the lower layer, and forming a Laplacian pyramid decomposition image by the obtained result and the Gaussian pyramid decomposition result of the highest layer; the series of images obtained by applying the difference are approximate coefficients, and the images obtained by Gaussian pyramid top-layer decomposition are detail coefficients.
4. The medical image acquisition management method according to claim 3, wherein the image segmentation processing for the medical image by using the adaptive region-based image segmentation algorithm includes:
1) initializing the number of image blocks of a medical image, wherein an image block is denoted xi,j(g) I represents the number of the image block, j represents the dimension of the image block, and g represents the iteration number of the self-adaptive segmentation;
2) randomly selecting three different image blocks from the initialized medical image blocks, calculating the vector weighted sum of the differences of any two image blocks, and adding the vector weighted sum to the third image block to generate a new image block yi(g+1):
yi(g+1)=xi1(g)+F·(xi2(g)-xi3(g))
Wherein:
i, i1, i2, i3 denote different image block numbers;
f is a scaling factor;
3) calculating an objective function value f' of the added image block, wherein f is a minimization fitness function; and performing iterative computation for multiple times to obtain objective function values of different image blocks, and performing image segmentation processing on the medical image according to the image block number corresponding to the minimum objective function value to obtain a plurality of medical image blocks.
5. The medical image acquisition management method according to claim 4, wherein the fusing of the approximate coefficients of the image by a fusion method based on adaptive image blocks and the fusing of the detail coefficients of the image by a fusion method based on image gradients comprises:
the method for fusing the approximate coefficients of the image by adopting a fusion method based on the self-adaptive image blocks comprises the following steps:
1) constructing an all-zero matrix D with the size equal to that of the medical image blocks, and determining Laplace energy of the two homologous medical image blocks;
2) if the laplacian energies of the image blocks A and B in the homologous medical image are consistent, setting the corresponding positions of the medical image blocks in the all-zero matrix D as 1, otherwise, setting the corresponding positions of the medical image blocks in the all-zero matrix D as 0, and obtaining a laplacian-based medical image matrix;
3) for d in the matrixijIf the position is 1, selecting the approximation coefficient of the medical image block A as the approximation coefficient of the fused image, otherwise, selecting the approximation coefficient of the medical image block B as the approximation coefficient of the fused image; and optimizing the fused approximation coefficient by using a mode filtering algorithm, namely changing the approximation coefficient of the center into the approximation coefficient in the medical image B if the approximation coefficient of the center is derived from the medical image A and the approximation coefficients of the surrounding areas are derived from the medical image B.
The detail coefficient of the image is fused by adopting a fusion method based on image gradient, and the method comprises the following steps:
by setting different size windows, for a window with a window size of m × n, the image gradient energy with coordinates (x, y) is calculated:
wherein:
w (k, h) is the detail coefficient at coordinate (k, h);
according to the medical image matrix based on Laplace, for homologous medical images A and B, fusion based on image gradient energy is carried out on detail coefficients of the homologous medical images A and B:
wherein:
dxyis the value of the coordinate point (x, y) in the laplace-based medical image matrix;
wA(x,y),wB(x, y) are detail coefficients of the medical images A and B, respectively;
and W (x, y) is the detail coefficient of the fused homologous medical image.
6. The medical image acquisition management method according to claim 5, wherein the adding of the medical image digital watermark to the medical fusion image by using the perceptual hash-based medical image watermarking algorithm comprises:
1) 2-level decomposition of contourlet transformation is carried out on the medical fusion image, the number of directions is set to be 4, medical approximate images are obtained after transformation, and 4 third-layer direction sub-bands with the size of 128x128 in the second-layer direction and the size of 256x256 in the 4 second-layer direction sub-bands are obtained;
2) obtaining a DCT coefficient matrix D with the same size as the medical approximate image by using global DCT, and calculating an average value M:
D(i,j)=DCT2(X(i,j))
wherein:
mxn is the size of the medical approximation image X;
x (i, j) is a sub-band pixel value to be measured of the medical approximate image;
d (i, j) is a value in a DCT coefficient matrix D;
3) reserving the lowest frequency part of the DCT coefficient matrix, namely a matrix D' with the size of 4 multiplied by 8 on the upper left corner;
4) comparing according to the retained 4 × 8 coefficient matrix, a value greater than or equal to the mean M is set to 1, and a value less than the mean M is set to 0, thereby constituting a 32-bit hash value H in order:
H=reshape(h(i,j))
wherein:
m is the mean value of a DCT coefficient matrix D;
5) converting patient information corresponding to the medical fusion image into a hash value W, converting the hash value W into a watermark W ' by using an encryption algorithm based on a chaotic sequence, and adding the watermark W ' into the medical fusion image as a medical image digital watermark, wherein the calculation method of the watermark W ' comprises the following steps:
wherein:
t (n) is a chaotic sequence;
w (i, j) is a patient information hash value;
6) and carrying out exclusive or operation on the 32-bit hash value H and each row of the watermark W' to obtain a logic key K:
and extracting an encrypted watermark W' by carrying out XOR calculation on the hash value H and the logic key, and obtaining the hash value W of the patient information through chaotic decryption reduction.
7. The medical image acquisition management method according to claim 6, wherein the compressing the medical image with the digital watermark by using the image compression method based on the image threshold comprises:
1) for the medical image with the digital watermark, the medical image is converted into a two-dimensional gray image, the gray value range of the medical image is [0, 1., L-1], and the probability of each level of gray is as follows:
pi=ni/sum
wherein:
sum is the total pixel number of the two-dimensional gray level image;
nithe total number of pixels with the gray value of i;
2) setting the gray level k as a threshold, dividing the image pixels into C according to the threshold level k0And C1Two kinds, wherein C0Indicating a gray value level of [0, 1.,. k ]]Set of pixels in (1), C1Indicating gray scale values at [ k +1, k +2]In (2), the probability of occurrence of each of the two types is:
wherein:
ω (k) represents C0Representing the probability sum of the pixel number of each gray level in the total pixel number;
calculating to obtain C0,C1Class mean μ of0,μ1:
μ0=μ(k)/ω(k)
Wherein:
and calculating to obtain C0,C1Inter-class variance of (c):
3) establishing an optimized objective function of a threshold k:
solving to obtain:
4) carrying out salient region division on the medical image with the digital watermark through a threshold, carrying out lossless coding compression processing on the salient region, and carrying out lossy coding compression processing on the non-salient region; and performs high-quality transmission or priority transmission management for the salient region.
8. A medical image acquisition management system, characterized in that the system comprises:
the medical image acquisition device is used for acquiring a medical image, converting the medical image into a gray image by using a gray image conversion method, and simultaneously performing noise reduction processing on the gray image by using a Gaussian filter to obtain a noise-reduced medical image;
the medical image processor is used for carrying out Laplacian pyramid decomposition on the medical image subjected to noise reduction to obtain a detail coefficient and an approximate coefficient of the medical image; carrying out image segmentation processing on the medical image by using an image segmentation algorithm based on the adaptive region to obtain an adaptive image block of the medical image; fusing the approximate coefficients of the images by adopting a fusion method based on self-adaptive image blocks, and fusing the detail coefficients of the images by adopting a fusion method based on image gradient to obtain medical fusion images;
the medical image acquisition management device is used for adding a medical image digital watermark to the medical fusion image by using a medical image watermark algorithm based on perceptual hash to obtain a medical image with the digital watermark; and compressing the medical image with the digital watermark by using an image compression method based on an image threshold value, and storing the compressed image into a medical image management system.
9. A computer readable storage medium having stored thereon medical image acquisition management program instructions executable by one or more processors to perform the steps of a method of implementing medical image acquisition management as claimed in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110073827.5A CN112750120A (en) | 2021-01-20 | 2021-01-20 | Medical image acquisition management method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110073827.5A CN112750120A (en) | 2021-01-20 | 2021-01-20 | Medical image acquisition management method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112750120A true CN112750120A (en) | 2021-05-04 |
Family
ID=75652620
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110073827.5A Withdrawn CN112750120A (en) | 2021-01-20 | 2021-01-20 | Medical image acquisition management method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112750120A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113077464A (en) * | 2021-05-06 | 2021-07-06 | 吴国军 | Medical image processing method, medical image identification method and device |
-
2021
- 2021-01-20 CN CN202110073827.5A patent/CN112750120A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113077464A (en) * | 2021-05-06 | 2021-07-06 | 吴国军 | Medical image processing method, medical image identification method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Swaraja | Medical image region based watermarking for secured telemedicine | |
Eswaraiah et al. | Robust medical image watermarking technique for accurate detection of tampers inside region of interest and recovering original region of interest | |
Luo et al. | Image fusion with contextual statistical similarity and nonsubsampled shearlet transform | |
Memon et al. | Hybrid watermarking of medical images for ROI authentication and recovery | |
CN111696084B (en) | Cell image segmentation method, device, electronic equipment and readable storage medium | |
CN107004042B (en) | Image fingerprint identification | |
Rai et al. | SVM based robust watermarking for enhanced medical image security | |
Nyeem et al. | Utilizing least significant bit-planes of RONI pixels for medical image watermarking | |
Arumugham et al. | Tamper-resistant secure medical image carrier: an IWT–SVD–Chaos–FPGA combination | |
CN115272250B (en) | Method, apparatus, computer device and storage medium for determining focus position | |
US20180365876A1 (en) | Method, apparatus and system for spine labeling | |
Mousavi et al. | A heuristic automatic and robust ROI detection method for medical image warermarking | |
CN114926382A (en) | Generation countermeasure network for fused images, image fusion method and terminal equipment | |
Chen et al. | Bone suppression of chest radiographs with cascaded convolutional networks in wavelet domain | |
CN115510488A (en) | Medical image sensitive information processing method, device, computer equipment and medium | |
CN112750120A (en) | Medical image acquisition management method and system | |
Singh et al. | Intelligent Data Security Solutions for e-Health Applications | |
Abdulazeez et al. | Wavelet applications in medical images: A review | |
CN112950506A (en) | Image data establishing method and system by utilizing nuclear magnetic resonance | |
Yamni et al. | Copyright protection of multiple CT images using Octonion Krawtchouk moments and grey Wolf optimizer | |
Palkar et al. | Fusion of multi‐modal lumbar spine images using Kekre's hybrid wavelet transform | |
Rezaee et al. | A wavelet-based robust medical image watermarking technique using whale optimization algorithm for data exchange through internet of medical things | |
CN116563539A (en) | Tumor image segmentation method, device, equipment and computer readable storage medium | |
CN115809954A (en) | Medical image watermarking method, device and medium | |
CN115375971B (en) | Multi-mode medical image registration model training method, registration method, system and equipment |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210504 |
|
WW01 | Invention patent application withdrawn after publication |