CN105701777B - A kind of spiral-fault radiotherapy image quality improving method - Google Patents
A kind of spiral-fault radiotherapy image quality improving method Download PDFInfo
- Publication number
- CN105701777B CN105701777B CN201610012166.4A CN201610012166A CN105701777B CN 105701777 B CN105701777 B CN 105701777B CN 201610012166 A CN201610012166 A CN 201610012166A CN 105701777 B CN105701777 B CN 105701777B
- Authority
- CN
- China
- Prior art keywords
- mrow
- image
- matrix
- spiral
- msubsup
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000001959 radiotherapy Methods 0.000 title claims abstract description 40
- 238000001914 filtration Methods 0.000 claims abstract description 9
- 230000002146 bilateral effect Effects 0.000 claims abstract description 8
- 230000002708 enhancing effect Effects 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 51
- 230000006870 function Effects 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 10
- 238000003325 tomography Methods 0.000 claims description 6
- 238000002560 therapeutic procedure Methods 0.000 abstract description 2
- 210000003710 cerebral cortex Anatomy 0.000 abstract 2
- 210000001525 retina Anatomy 0.000 abstract 2
- 238000012545 processing Methods 0.000 description 7
- 230000001225 therapeutic effect Effects 0.000 description 5
- 206010028980 Neoplasm Diseases 0.000 description 4
- 238000002591 computed tomography Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000002721 intensity-modulated radiation therapy Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 230000003389 potentiating effect Effects 0.000 description 1
Classifications
-
- G06T5/73—
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/20028—Bilateral filtering
-
- 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
Abstract
A kind of spiral-fault radiotherapy image quality improving method, it is to be related to a kind of spiral-fault radiotherapy image quality improving method based on retina cerebral cortex theory, it has four big steps：Step 1：Computer reads spiral-fault radiotherapy image under MATLAB environment；Step 2：Bilateral filtering denoising is carried out to image；Step 3：The contrast lifting based on retina cerebral cortex theory is carried out to image；Step 4：Image border is strengthened using Gauss Sai Geer iterative methods.The present invention solves the problems, such as that more former spiral-fault radiotherapy picture noise, poor contrast and blur margin are clear, achieves preferable quality enhancing as a result, having broad application prospects in spiral-fault therapy field.
Description
(1) technical field：
The present invention provides a kind of spiral-fault radiotherapy image quality improving method, it is related to one kind and is based on retina-brain
The sheaf theoretic spiral-fault radiotherapy image quality improving method of skin, belongs to field of medical image processing.
(2) background technology：
With the development of information technology and medical image imaging technique, Medical Image Processing is sent out in clinical medicine and scientific research
More and more important effect is waved, effectively promotes the progress of medical scientific and clinical treatment.Wherein, for CT
The image processing techniques important role of (Computed Tomography, i.e. CT scan) image.And pin
To megavolt level CT (MVCT, Mega-Voltage Computed Tomography) of spiral-fault radiotherapy (Tomo therapy)
The research of the image procossing of image is at present still in initial stage.Spiral-fault radiotherapy be one kind rely on spiral-fault radiation control
The cancer radiation therapy method of equipment is treated, is current state-of-the-art tumour radiotherapy technology.Spiral-fault radiotherapy is that image is situated between
The three-dimensional intensity-modulated radiation therapy led, it by linear accelerator and it is spiral integrate, treatment plan, patient is put and position and was treated
Journey combines together, can treat different target areas, the tumour small from stereotactic irradiation to whole body therapeutic, by single spiral
Beam is completed, the MVCT images as obtained by treating every time, it is observed that tumor dose is distributed and swells over the course for the treatment of
The change of knurl, adjusts the treatment plan of target volume in time.There is the incomparable advantage of conventional accelerator radiotherapy, controlled for radiation
Treat doctor and open a new treatment platform, occupy critical role in intensity-modulated radiation therapy development history.However, use treatment
The imaging for the MVCT images that ray obtains has some limitations：Relative to common diagnosis CT scanner, MVCT needs applying
Traded off between dosage and imaging effect.That is, the noise of image, luminance proportion, contrast and resolution ratio can all be subject to agent
The influence of amount, so as to influence accurate judgement of the doctor to conditions of patients.
The method handled currently for spiral-fault radiotherapy image is relatively limited, mostly by the side in CT image procossings
Method is grafted directly in the processing of spiral-fault radiotherapy image.It common are the linear of Pixel-level, linear function operation, Nogata
Figure equalization algorithm, the mean filter with denoising effect, median filter method, more recent adaptive-filtering, wavelet shrinkage
Deng the methods of, the innovatory algorithm based on histogram equalization and the center based on background variance/surrounding method etc..These methods are all
It is for CT the images even universal method of normal image, it is difficult to which the characteristics of being directed to spiral-fault radiotherapy image is carried out at image
Reason.The present invention uses bilateral filtering method, and according to retina-cerebral cortex (Retinex) theory to spiral-fault radiotherapy figure
As being strengthened, while use the side of the Gauss-Seidel iteration method based on Poisson's equation (Poisson Image Editing)
Edge Enhancement Method, strengthens existing spiral-fault radiotherapy image, reaches desired effects.
(3) content of the invention：
1st, purpose：The object of the present invention is to provide a kind of spiral-fault radiotherapy figure based on retina-cerebral cortex theory
As quality enhancement method, this method utilizes bilateral filtering method, retina-cerebral cortex theory, Gauss-Seidel iteration method pair
Spiral-fault radiotherapy image carries out picture quality raising, solve spiral-fault radiotherapy image noise is more, contrast is low and side
The unsharp problem of edge.
2nd, technical solution：The present invention is achieved by the following technical solutions：
The present invention provides a kind of spiral-fault radiotherapy image quality improving method based on retina-cerebral cortex theory,
It is that one kind utilizes bilateral filtering method, retina-cerebral cortex theory and Gauss-Seidel iteration method to spiral-fault radiotherapy
The method that image carries out picture quality raising.This method comprises the following steps that：
Step 1：Computer digital image is exported by spiral-fault radiotherapy instrument first, then using Matlab language
In imread functions read the image, its information is switched into Matlab matrix forms, Matlab language is carried out it
Processing；
Spiral-fault radiotherapy image in the present invention is the digital picture of 512 pixel *, 512 pixel * c passages, that is, is read in
Matrix data is 512*512*c dimensions；Wherein symbol c represents the tomography quantity included in the image, and each tomography is width ash
Image is spent, the faultage image of c number of active lanes is stacked into complete spiral-fault radiotherapy image；This method is not used between passage
Related information, so following steps are completed on single width faultage image；For convenience of description, capital I used below
Represent image read in by Matlab after matrix data a certain passage (i.e. the matrix of 512*512 dimensions) therein；Subscript numeral
Show the intermediate image matrix data of different step in this method, such as I0Represent original image matrix data；Represented using subscript
A certain element (pixel on some coordinate in correspondence image), i.e. I in matrixX, yPositioned at coordinate (x, y) in representing matrix I
Element；
Step 2：In Matlab softwares, to matrix (the i.e. I of previous step reading0) carry out following computing：
Wherein, Ω represents the contiguous range of (x, y) coordinate, and coordinate (i, j) meets (i, j) ∈ Ω；The value of weight coefficient w
For codomain weightWith spatial domain weight's
Product；The step operates for the bilateral filtering of image, can have good denoising effect while image border is kept；
Step 3：In Matlab softwares, the matrix of previous step is proceeded as follows：
Wherein, a, b, c are hyper parameter, by manual setting, and are had：
Here, symbol * represents convolution, and symbol G represents Gaussian kernel, i.e. denominator is the image after molecule Gaussian kernel obscures；Should
Step is improved Retinex algorithm, it without using the logarithmic form used in common Retinex methods in the past, and
It is to have used new curvilinear function form；
Step 4：First, using the Sobel Operator function in Matlab, to matrix I2Operated, the edge of acquisition
Image array is labeled as Gra；
Then, edge image array Gra is traveled through pixel-by-pixel, finds the edge maximum in neighborhood, obtain matrix
GraMTo mark whether current location is neighborhood maximums in matrix Gra, then pass through：
Update matrix Gra, wherein fX, yFor one using the distance of the closest edge maximum point of current point (x, y) as independent variable
Custom function, which is more than 1 when in small distance with the edge maximum of points of arest neighbors；It is less than 1 when in larger distance,
New Gra can so be made1The distribution narrow at the edge in corresponding edge image, peak value become higher；
Finally, using Gauss-Saden that alternative manner, matrix Gra is utilized1The anti-image for releasing edge enhancing, step is such as
Under：
1. couple matrix Gra1Calculus of differences is carried out again, and the second order for obtaining target image leads image array Lap；
2. initialize matrix dst0=I2
3. following iteration is repeated, until iterations reaches 5 times, wherein n is iterations, n=0,1,2 ...：
1)
2)
By above step iteration, final image is obtained, completes the Quality advance to spiral-fault radiotherapy image.
3rd, advantage and effect：This method is at the same time by bilateral filtering, improved retina-cerebral cortex theory and Gauss-match
Dare iterative method strengthens spiral-fault radiotherapy image.From Figure 2 it can be seen that processing after image grey scale pixel value change frequency
Reduce, amplitude of variation increase, illustrates that this method both can effectively remove the noise in image, can also improve contrast, at the same time
Can become apparent from the edge in image.
(4) illustrate：
Fig. 1 the method for the invention flow charts.
Fig. 2 the method for the invention effect contrast figures.
(5) embodiment：
A kind of spiral-fault radiotherapy image quality improving method based on retina-cerebral cortex theory of the present invention, is shown in Fig. 1
Shown, its step is as follows：
Step 1：Computer digital image is exported by spiral-fault radiotherapy instrument first, then using Matlab language
In imread functions read the image, its information is switched into Matlab matrix forms, Matlab language is carried out it
Processing.
Spiral-fault radiotherapy image in the present invention is the digital picture of 512 pixel *, 512 pixel * c passages, that is, is read in
Matrix data is 512*512*c dimensions.Wherein symbol c represents the tomography quantity included in the image, and each tomography is width ash
Image is spent, the faultage image of c number of active lanes is stacked into complete spiral-fault radiotherapy image.This method is not used between passage
Related information, so following steps are completed on single width faultage image.For convenience of description, capital I used below
Represent image read in by Matlab after matrix data a certain passage (i.e. the matrix of 512*512 dimensions) therein；Subscript numeral
Show the intermediate image matrix data of different step in this method, such as I0Represent original image matrix data；Represented using subscript
A certain element (pixel on some coordinate in correspondence image), i.e. I in matrixX, yPositioned at coordinate (x, y) in representing matrix I
Element.
Step 2：In Matlab softwares, to matrix (the i.e. I of previous step reading0) carry out following computing：
Wherein, Ω represents the contiguous range of (x, y) coordinate, and coordinate (i, j) meets (i, j) ∈ Ω.The value of weight coefficient w
For codomain weightWith spatial domain weight's
Product.The step operates for the bilateral filtering of image, can have good denoising effect while image border is kept.
Step 3：In Matlab softwares, the matrix of previous step is proceeded as follows：
Wherein, a, b, c are hyper parameter, by manual setting, and are had：
Here, symbol * represents convolution, and symbol G represents Gaussian kernel, i.e. denominator is the image after molecule Gaussian kernel obscures.Should
Step is improved Retinex algorithm, it without using the logarithmic form used in common Retinex methods in the past, and
It is to have used new curvilinear function form.
Step 4：First, using the Sobel Operator function in Matlab, to matrix I2Operated, the edge of acquisition
Image array is labeled as Gra.
Then, edge image array Gra is traveled through pixel-by-pixel, finds the edge maximum in neighborhood, obtain matrix
GraMTo mark whether current location is neighborhood maximums in matrix Gra.Pass through again：
Update matrix Gra, wherein fX, yFor one using the distance of the closest edge maximum point of current point (x, y) as independent variable
Custom function, which is more than 1 when in small distance with the edge maximum of points of arest neighbors, 1 is less than when in larger distance,
New Gra can so be made1The distribution narrow at the edge in corresponding edge image, peak value become higher.
Finally, using Gauss-Saden that alternative manner, matrix Gra is utilized1The anti-image for releasing edge enhancing, step is such as
Under：
4. couple matrix Gra1Difference again, the second order for obtaining target image lead image array Lap；
5. initialize matrix dst0=I2
6. following iteration is repeated, until iterations reaches 5 times, wherein n is iterations, n=0,1,2 ...：
3)
4)
By above step iteration, final image is obtained, completes the Quality advance to spiral-fault radiotherapy image.
Beneficial effect：
Experimental result：In order to verify effectiveness of the invention, we are tested using this method, achieve preferable increasing
Potent fruit.Data used in present invention experiment are the image from the output of spiral-fault therapeutic equipment, and analysis chart 2 is as it can be seen that using being sent out
Bright method, has obtained more satisfactory picture quality enhancing as a result, not only effectively removes the noise in image, has also made figure
Image contrast improves, and edge also becomes apparent from clearly.
From the point of view of experimental result, the method that we invent solves the picture quality of spiral-fault therapeutic equipment output well
The problem of poor, this method is combined with spiral-fault therapeutic equipment, can effectively improve the effect that medical staff uses therapeutic equipment
Rate, has broad application prospects and is worth.
Claims (1)
1. a kind of spiral-fault radiotherapy image quality improving method, it is related to a kind of theoretical based on retina-cerebral cortex
Spiral-fault radiotherapy image quality improving method, it is characterised in that：This method comprises the following steps that：
Step 1：Computer digital image is exported by spiral-fault radiotherapy instrument first, then using in Matlab language
Imread functions read the image, its information is switched to Matlab matrix forms, it is handled using Matlab language；
Spiral-fault radiotherapy image is the digital picture of 512 pixel *, 512 pixel * R passages, that is, the matrix data read in is 512*
512*R dimensions；Wherein symbol R represents the tomography quantity included in the image, and each tomography is a width gray level image, R port numbers
Purpose faultage image is stacked into complete spiral-fault radiotherapy image；Capital I used below represents that image is read by Matlab
Matrix data a certain passage therein after entering, the i.e. matrix of 512*512 dimensions；Subscript numeral shows the middle graph of different step
As matrix data, such as I0Represent original image matrix data；Using a certain element in subscript representing matrix, i.e., in correspondence image
Pixel on some coordinate, i.e. Ix,yIt is located at the element of coordinate (x, y) in representing matrix I；
Step 2：In Matlab softwares, to the matrix of previous step reading, i.e. I0Carry out following computing：
<mrow>
<msubsup>
<mi>I</mi>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
<mn>1</mn>
</msubsup>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>&Sigma;</mi>
<mi>&Omega;</mi>
</msub>
<msubsup>
<mi>I</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
<mn>0</mn>
</msubsup>
<mi>w</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>,</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>&Sigma;</mi>
<mi>&Omega;</mi>
</msub>
<mi>w</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>,</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
</mrow>
Wherein, Ω represents the contiguous range of (x, y) coordinate, and coordinate (i, j) meets (i, j) ∈ Ω；The value of weight coefficient w is value
Domain weightWith spatial domain weightProduct；
The step operates for the bilateral filtering of image, has good denoising effect while image border is kept；
Step 3：In Matlab softwares, the matrix of previous step is proceeded as follows：
<mrow>
<msubsup>
<mi>I</mi>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
<mn>2</mn>
</msubsup>
<mo>=</mo>
<mfrac>
<mrow>
<mo>(</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mi>a</mi>
<mo>*</mo>
<msub>
<mi>R</mi>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
</msub>
<mo>+</mo>
<mi>b</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>+</mo>
<mi>c</mi>
<mo>)</mo>
</mrow>
<mrow>
<mi>c</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</mfrac>
</mrow>
Wherein, a, b, c are hyper parameter, by manual setting, and are had：
<mrow>
<msub>
<mi>R</mi>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<msubsup>
<mi>I</mi>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
<mn>1</mn>
</msubsup>
<mrow>
<msubsup>
<mi>I</mi>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
<mn>1</mn>
</msubsup>
<mo>*</mo>
<mi>G</mi>
</mrow>
</mfrac>
</mrow>
Here, symbol * represents convolution, and symbol G represents Gaussian kernel, i.e. denominator is the image after molecule Gaussian kernel obscures；The step
As improved Retinex algorithm, it makes without the logarithmic form used in the in the past common Retinex methods of use
With new curvilinear function form；
Step 4：First, using the Sobel Operator function in Matlab, to matrix I2Operated, the edge image square of acquisition
Battle array is labeled as Gra；
Then, edge image array Gra is traveled through pixel-by-pixel, finds the edge maximum in neighborhood, obtain matrix GraMCome
Mark whether each element is neighborhood maximums in matrix Gra, then pass through：
<mrow>
<msubsup>
<mi>Gra</mi>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
<mn>1</mn>
</msubsup>
<mo>=</mo>
<msub>
<mi>Gra</mi>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
</msub>
<mo>&CenterDot;</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
</msub>
</mrow>
Update matrix Gra, wherein fx,yFor one using the distance of the closest edge maximum of points of current point (x, y) as independent variable
Custom function, if when current point (x, y) and nearest edge maximum of points in small distance, which is more than 1；If current point
When (x, y) and nearest edge maximum of points in larger distance, which is less than 1；So make new Gra1Corresponding edge graph
The distribution narrow at the edge as in, peak value become higher；
Finally, using Gauss-Saden that alternative manner, matrix Gra is utilized1The anti-image for releasing edge enhancing, step are as follows：
Step 4.1：To matrix Gra1Calculus of differences is carried out again, and the second order for obtaining target image leads image array Lap；
Step 4.2：Initialize matrix dst0=I2
Step 4.3：Following iteration is repeated, until iterations reaches 5 times, wherein n is iterations, n=0,1,2 ...：
1)
2)
By above step iteration, final image is obtained, completes the Quality advance to spiral-fault radiotherapy image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610012166.4A CN105701777B (en) | 2016-01-08 | 2016-01-08 | A kind of spiral-fault radiotherapy image quality improving method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610012166.4A CN105701777B (en) | 2016-01-08 | 2016-01-08 | A kind of spiral-fault radiotherapy image quality improving method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105701777A CN105701777A (en) | 2016-06-22 |
| CN105701777B true CN105701777B (en) | 2018-04-27 |
Family
ID=56226984
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610012166.4A Expired - Fee Related CN105701777B (en) | 2016-01-08 | 2016-01-08 | A kind of spiral-fault radiotherapy image quality improving method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105701777B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102333B (en) * | 2020-09-02 | 2022-11-04 | 合肥工业大学 | Ultrasonic region segmentation method and system for B-ultrasonic DICOM (digital imaging and communications in medicine) image |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184403A (en) * | 2011-05-20 | 2011-09-14 | 北京理工大学 | Optimization-based intrinsic image extraction method |
| CN102682436A (en) * | 2012-05-14 | 2012-09-19 | 陈军 | Image enhancement method on basis of improved multi-scale Retinex theory |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2187620B1 (en) * | 2007-07-26 | 2014-12-24 | Omron Corporation | Digital image processing and enhancing system and method with function of removing noise |
-
2016
- 2016-01-08 CN CN201610012166.4A patent/CN105701777B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184403A (en) * | 2011-05-20 | 2011-09-14 | 北京理工大学 | Optimization-based intrinsic image extraction method |
| CN102682436A (en) * | 2012-05-14 | 2012-09-19 | 陈军 | Image enhancement method on basis of improved multi-scale Retinex theory |
Non-Patent Citations (2)
| Title |
|---|
| 一种改进的Retinex彩色图像增强方法;李小鹏 等;《兰州交通大学学报》;20150228;第34卷(第1期);第55-59、70页 * |
| 基于双边滤波的Retinex图像增强算法;胡韦伟;《工程图学学报》;20100630(第2期);第104-109页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105701777A (en) | 2016-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | Metal artifact reduction on cervical CT images by deep residual learning | |
| US11565130B2 (en) | System and method for diagnostic and treatment | |
| Jiang et al. | Augmentation of CBCT reconstructed from under-sampled projections using deep learning | |
| EP2652705B1 (en) | Contour guided deformable image registration | |
| Sheng et al. | Denoised and texture enhanced MVCT to improve soft tissue conspicuity | |
| Na et al. | Guided filter‐based images fusion algorithm for CT and MRI medical images | |
| CN111260703B (en) | Method, system, medium and storage medium for obtaining spinal straightening image set | |
| CN106780649A (en) | The artifact minimizing technology and device of image | |
| Amorim et al. | 3D Adaptive Histogram Equalization Method for Medical Volumes. | |
| Ganvir et al. | Filtering method for pre-processing mammogram images for breast cancer detection | |
| Li et al. | Metal artifact reduction in CT based on adaptive steering filter and nonlocal sinogram inpainting | |
| Deng et al. | Synthetic CT generation from CBCT using double-chain-CycleGAN | |
| CN105701777B (en) | A kind of spiral-fault radiotherapy image quality improving method | |
| Dawood et al. | The importance of contrast enhancement in medical images analysis and diagnosis | |
| CN110533667B (en) | Lung tumor CT image 3D segmentation method based on image pyramid fusion | |
| WO2023125683A1 (en) | Systems and methods for image reconstruction | |
| Liu et al. | A practical PET/CT data visualization method with dual-threshold PET colorization and image fusion | |
| Shi et al. | Fast shading correction for cone-beam CT via partitioned tissue classification | |
| CN116309647A (en) | Method for constructing craniocerebral lesion image segmentation model, image segmentation method and device | |
| CN108269263A (en) | A kind of liver vessel three-dimensional dividing method based on CT images | |
| Camps et al. | Various approaches for pseudo-CT scan creation based on ultrasound to ultrasound deformable image registration between different treatment time points for radiotherapy treatment plan adaptation in prostate cancer patients | |
| Cheong et al. | Enhancement of megavoltage electronic portal images for markerless tumor tracking | |
| Ben Gharsallah et al. | Phase congruency-based filtering approach combined with a convolutional network for lung CT image analysis | |
| CN113822796A (en) | Multi-modal brain image registration method based on improved image pyramid | |
| Wang et al. | Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180427 |