CN104952044A - Mammary X-ray image enhancement method - Google Patents
Mammary X-ray image enhancement method Download PDFInfo
- Publication number
- CN104952044A CN104952044A CN201410124398.XA CN201410124398A CN104952044A CN 104952044 A CN104952044 A CN 104952044A CN 201410124398 A CN201410124398 A CN 201410124398A CN 104952044 A CN104952044 A CN 104952044A
- Authority
- CN
- China
- Prior art keywords
- mammography
- local
- normalization
- enhancement method
- full
- 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.)
- Pending
Links
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides a mammary X-ray image enhancement method comprising the steps that a mammary X-ray image is provided; and local normalization is performed on the local part in the mammary X-ray image so that image information corresponding to the local part can be enhanced. Local information is enhanced via local normalization so that implicit local information in the global image can be effectively enhanced, i.e. low intensity lesions can be effectively enhanced. Furthermore, local filtering is adopted after local normalization so that local contrast can be enhanced, adhesion between local objects can be suppressed and adhesion of the lesions and background tissues can be effectively suppressed.
Description
Technical field
The present invention relates to field of medical image processing, particularly relate to a kind of Enhancement Method of mammography X.
Background technology
Breast cancer is one of modal cancer of women, and is the second largest cancer killer causing women die.Evidence suggests, early stage Clinics and Practices can reduce mortality ratio effectively, and mammary X-ray figure (Mammograms) is the powerful carrying out breast cancer examination.Computer-aided diagnosis (CAD) based on mammography X can help doctor to locate suspicious lesions, effectively reduces and leaks false drop rate.In the pre-service of mammography X computer-aided diagnosis (CAD) system, it is very important for effectively strengthening lump focus.Lump focus presents various form in mammary X-ray figure, the wide density unevenness of range of size, and poor contrast, is often embedded in the background tissue that various characteristic differs and is difficult to distinguish.Effective enhancing lump focus can improve the susceptibility of CAD system greatly, has very important effect to the raising of CAD system overall performance.
Documents 1:Yin F F, Giger M L, Doi K, et al.Computerized detection of masses in digital mammograms:Analysis of bi lateral subtraction images [J] .Medical Physics, 1991, left and right mammography X is carried out registration by 18:955., then subtracts shadow, finally carries out binaryzation to detect highlighting suspicious lesions to subtraction image multilevel threshold.The limitation of the method is: 1) need registration, and registration is consuming time and likely make focus be out of shape, and there is the inaccurate risk of registration; 2) need left and right galactophore image simultaneously, inapplicable for the situation that only there is single image.
Documents 2:Zouras W K, Giger M L, Lu P, et al.Investigation of a temporal subtraction scheme for computerized detection of breast masses in mammograms [J] .Excerpta Medica, 1996,1119:411-415. will carry out after the mammography X registration of the different times of same people subtracting shadow to highlight suspicious lesions.The method has following limitation: 1) need registration, and registration is consuming time and likely make focus be out of shape, and there is the inaccurate risk of registration; 2) need the galactophore image of different times simultaneously, inapplicable for the situation that only there is single image.
Documents 3:Kobatake H, Murakami M, Takeo H, et al.Computerized detection of malignant tumors on digital mammograms [J] .Medical Imaging, IEEE Transactions on, 1999,18 (5): 369-378. provide and utilize iris wave filter (" iris filter ") to detect breast lump focus.The method based on thought be hypothesis breast lump be convex circle, it is bad that the limitation of described hypothesis makes to strengthen effect to other irregular focuses.
Documents 4:Petrick N, Chan H P, Sahiner B, et al.An adaptive density-weighted contrast enhancement fi lter for mammographic breast mass detection [J] .Medical Imaging, IEEE Transactions on, 1996,15 (1): the 59-67. boostfiltering devices (Adaptive density-weighted contrast-enhancement DWCE) providing a kind of adaptive Density Weighted contrast strengthen focus Background suppression.The basic thought of the method utilizes the density of each pixel as weight to strengthen the contrast of current pixel point, and limitation is the focus after strengthening and the serious adhesion of surrounding tissue, affects follow-up focus and detect.And the method for normalizing in this technology makes part focus strengthen rear center there is black hole problem.
Documents 5:Pandey A, Yadav A, Bhateja V.Contrast Improvement of Mammographic Masses Using Adaptive Volterra Fi lter [C] //Proceedings of the Fourth International Conference on Signal and Image Processing2012 (ICSIP2012) .Springer India, 2013:583-593. provides a kind of adaptive Volterra wave filter, is used for improving the contrast of breast X-ray figure thus reaches the object strengthening breast lump.The limitation of this wave filter is the effect that can play suppression to the focus that gray-scale value itself is darker, is only applicable to the focus that brightness is higher.
Documents 6:Polakowski W E, Cournoyer D A, Rogers S K, et al.Computer-aided breast caneer detection and diagnosis of masses using difference of Gaussians and derivative-based feature saliency [J] .Medical Imaging, IEEE Transactions on, 1997,16 (6): 811-819. utilize Difference of Gaussian filter (difference of Gaussian (DOG) filter) to strengthen breast X-ray figure lump focus.The limitation of the method is to strengthen the size that effect is limited to lump self, therefore needs multiple yardstick to strengthen.
Summary of the invention
The problem that the present invention solves is to provide a kind of Enhancement Method of mammography X, to solve the enhancing problem of weak intensity focus in mammography X.
In order to solve the problem, the invention provides a kind of Enhancement Method of mammography X, comprise: mammography X is provided, focus in described mammography X is strengthened, also comprise: local normalization is carried out to the local in described mammography X, to strengthen the image information of described local correspondence.
Optionally, also comprise the connected region obtained in described mammography X, described local is normalized to carries out local normalization to described connected region.
Optionally, the normalization of described local comprises the gray-scale value I ' norm (x after obtaining local normalization, y), I ' norm (x, y)=(I ' (x, y)-I ' min)/(I ' max-I ' min), described I ' (x, y) be the gray-scale value before the local normalization of correspondence position, described I ' max and I ' min is respectively local maximum gradation value and local minimum gradation value.
Optionally, obtain described local maximum gradation value and minimum gradation value comprises: provide the grey level histogram of regional area and the highest gray scales C%, meet the gray-scale value of the pixel number of described C% as local maximum gradation value I ' max, in described regional area, minimum gradation value is as Local Minimum gray-scale value I ' min, and in described C% the most at high proportion, the span of C is 1<C<95.
Optionally, also comprise after the normalization of described local: part filter is carried out to the image after the normalization of described local, to strengthen local contrast, suppress adhesion between object locally.
Optionally, described part filter is one of nonlinear part filter or non-recursive part filter or combination.
Optionally, described part filter carries out part filter for adopting adaptive Volterra filter.
Optionally, also comprise the focus in the boostfiltering device enhancing mammography X adopting adaptive Density Weighted contrast, and suppress the background outside focus, utilize the density of each pixel as weight to strengthen the contrast of current pixel point; The boostfiltering device enhancing of the adaptive Density Weighted contrast of described employing comprises: adopt low-pass filter to obtain the density map of mammography X, in utilization, logical or Hi-pass filter obtains corresponding comparison diagram, or deduct low-pass filtering with the mammography X do not strengthened and obtain corresponding comparison diagram, the density map of described mammography X is finally adopted to carry out comparison diagram described in weighting as weight, realize preliminary enhancing, the image after being enhanced.
Optionally, also comprise before carrying out the normalization of described local and full figure normalization is carried out to described mammography X, obtain full figure Normalized Grey Level value Inorm (x, y), wherein Inorm (x, y)=(I (x, y)-Imin)/(Imax-Imin), the gray-scale value before the full figure normalization that described I (x, y) is correspondence position, Imin is full figure minimum gradation value, and Imax is full figure maximum gradation value.
Optionally, after full figure normalization, also comprise the density map adopting low-pass filter to obtain mammography X, lead in utilization or the corresponding comparison diagram of image after the normalization of Hi-pass filter acquisition full figure, or deduct low-pass filtering with the mammography X do not strengthened and obtain corresponding comparison diagram, finally adopt the density map of described mammography X to carry out comparison diagram described in weighting as weight, realize tentatively strengthening, the image after being enhanced.
Compared with prior art, the present invention has the following advantages:
By local normalization, strengthen local message, to make unconspicuous local message in global image effectively be strengthened, the focus that namely intensity is weak can effectively strengthen.
Further, by adopting part filter again after the normalization of local, to strengthen local contrast, adhesion between the object of local is suppressed effectively to suppress the adhesion of focus and background tissues.
Further, strengthen described mammography X by the boostfiltering device of adaptive Density Weighted contrast, effectively to strengthen described image information and contrast.
Finally, described Enhancement Method, without the need to registration, without the need to several mammography X, and is not limited to the size and dimension of lump.
Accompanying drawing explanation
Figure 1 shows that the Enhancement Method schematic flow sheet of the mammography X of one embodiment of the invention.
The Enhancement Method effect schematic diagram of Fig. 2 ~ Figure 11 shows that mammography X of one embodiment of the invention.
Embodiment
Set forth a lot of detail in the following description so that fully understand the present invention.But the present invention can be much different from alternate manner described here to implement, those skilled in the art can when without prejudice to doing similar popularization when intension of the present invention, therefore the present invention is by the restriction of following public concrete enforcement.
Secondly, the present invention utilizes schematic diagram to be described in detail, and when describing the embodiment of the present invention in detail, for ease of illustrating, described schematic diagram is example, and it should not limit the scope of protection of the invention at this.
The problem that the present invention solves is to provide a kind of Enhancement Method of mammography X, to solve the enhancing problem of weak intensity focus in mammography X.
In order to solve the problem, the invention provides a kind of Enhancement Method of mammography X, comprising: mammography X is provided, local normalization is carried out to the local in described mammography X, to strengthen the image information of described local correspondence.
Further, described local is normalized to carries out local normalization to described connected region, comprises the connected region first obtained in described mammography X, then carries out local normalization to described connected region.
The normalization of described local comprises the gray-scale value I ' norm (x after obtaining local normalization, y), I ' norm (x, y)=(I ' (x, y)-I ' min)/(I ' max-I ' min), gray-scale value before the local normalization that described I ' (x, y) is correspondence position, described I ' max and I ' min is respectively local maximum gradation value and local minimum gradation value.
Particularly, described local maximum gradation value and minimum gradation value comprise: provide described connected region to ask grey level histogram and C% the most at high proportion, determine to meet retain the pixel number of C% the most at high proportion gray-scale value as local maximum gradation value I ' max, in described connected region, minimum gradation value is 1<C<95 as the span of Local Minimum gray-scale value I ' min, described C% the most at high proportion.
Further, also comprise after the normalization of described local: part filter is carried out to the image after the normalization of described local, to strengthen local contrast, suppress adhesion between object locally.Described part filter is nonlinear part filter, or is non-recursive part filter, further, can also be non-linear non-recursive part filter.
As an embodiment, described part filter adopts adaptive Volterra filter to carry out filtering.And after carrying out described part filter, also comprise and adopt binaryzation to strengthen described mammography X: threshold value d is provided, carry out binaryzation to the filtered image in local, remove the part that gray-scale value is less than described threshold value d, the span of described threshold value d is 0.5≤d≤1.
Particularly, also comprise the focus in the boostfiltering device enhancing mammography X adopting adaptive Density Weighted contrast, and suppress the background outside focus, utilize the density of each pixel as weight to strengthen the contrast of current pixel point.
Wherein, the boostfiltering device enhancing of described adaptive Density Weighted contrast comprises: adopt low-pass filter to obtain the density map of mammography X, in utilization, logical or Hi-pass filter obtains corresponding comparison diagram, or deduct low-pass filtering with former figure and obtain corresponding comparison diagram, the density map of described mammography X is finally adopted to carry out comparison diagram described in weighting as weight, realize preliminary enhancing, the image after being enhanced.
Further, also comprise before carrying out the normalization of described local and full figure normalization is carried out to described mammography X, obtain full figure Normalized Grey Level value Inorm (x, y), wherein Inorm (x, y)=(I (x, y)-Imin)/(Imax-Imin), the gray-scale value before the full figure normalization that described I (x, y) is correspondence position, Imin is full figure minimum gradation value, and Imax is full figure maximum gradation value.
Particularly, described full figure normalization comprises: be first normalized by mammography X full figure, the part that pixel value is greater than threshold value a is mammary gland partial graph M1, then be normalized the part of pixel value non-zero and obtain figure M2, wherein the span of a is for being greater than 0<a≤0.4.
After obtaining above-mentioned figure M2, also comprise the density map adopting low-pass filter to obtain mammography X, in utilization, logical or Hi-pass filter obtains corresponding comparison diagram, or deduct low-pass filtering with former figure and obtain corresponding comparison diagram, the density map of described mammography X is finally adopted to carry out comparison diagram described in weighting as weight, realize preliminary enhancing, the image after being enhanced.
The present invention is by local normalization, and strengthen local message, to make unconspicuous local message in global image effectively be strengthened, the focus that namely intensity is weak can effectively strengthen; And by adopting part filter again after the normalization of local, to strengthen local contrast, suppress adhesion between the object of local effectively to suppress the adhesion of focus and background tissues.
Figure 1 shows that the Enhancement Method schematic flow sheet of the mammography X of one embodiment of the invention, below in conjunction with accompanying drawing, the Enhancement Method of the mammography X of one embodiment of the invention is described in detail.
First, obtain mammography X, Figure 2 shows that the mammography X of an embodiment.Then mammary gland segmentation is carried out to mammography X.
Comprise particularly: mammography X full figure is normalized, obtain full figure Normalized Grey Level value Inorm (x, y), wherein Inorm (x, y)=(I (x, y)-Imin)/(Imax-Imin), described I (x, y) be the gray-scale value before the full figure normalization of correspondence position, Imin is full figure minimum gradation value, and Imax is full figure maximum gradation value.
After mammography X full figure is normalized, threshold value a is provided, part pixel value being greater than threshold value a is defined as mammary gland partial graph M1, then the part of pixel value non-zero is normalized and obtains figure M2, wherein the span of a is for being greater than 0<a≤0.4,, wherein, figure M1 and figure M2 respectively as shown in Figures 2 and 3.
Continue with reference to figure 1, after obtaining described figure M2, adopt low-pass filter, low-pass filtering is carried out to described figure M2, and then obtains the density map M3 of mammography X as shown in Figure 4.Then logical in employing or Hi-pass filter obtains corresponding comparison diagram M4 as shown in Figure 5, further, can also deduct low-pass filter obtain corresponding comparison diagram M4 with former figure.
Finally, utilize described density map M3 as weight, described figure M4 is weighted, realize tentatively strengthening, obtain the image M5 after preliminary enhancing as shown in Figure 6.Namely adopt the boostfiltering device of adaptive Density Weighted contrast herein, in order to strengthen the focus in mammography X, and suppress the background outside focus, utilize the density of each pixel as weight to strengthen the contrast of current pixel point.
Further, described concrete weighting strengthens the technical method that can strengthen focus with reference to the boostfiltering device of the adaptive Density Weighted contrast in documents 4 (Adaptive density-weighted contrast-enhancement DWCE).
Then, also comprise and carry out Threshold segmentation to described image M5, the part of pixel value lower than b is set to zero and removes discrete point, obtains the image M6 after removal discrete point as shown in Figure 7, wherein the span of b is 0≤b≤0.8.
Then, adaptive normalization is carried out to each the block connected region in described preliminary enhancing image M6, comprise the connected region obtained in described mammography X, then local normalization is carried out to described connected region.Be illustrated in figure 8 the image M7 after carrying out local normalization.
Particularly, the normalization of described local comprises the gray-scale value I ' norm (x after obtaining local normalization, y), I ' norm (x, y)=(I ' (x, y)-I ' min)/(I ' max-I ' min), described I ' (x, y) be the gray-scale value before the local normalization of correspondence position, described I ' max and I ' min is respectively local maximum gradation value and local minimum gradation value.Obtain described local maximum gradation value and minimum gradation value comprises: provide described connected region to ask grey level histogram and C% the most at high proportion, determine to meet retain the pixel number of C% the most at high proportion gray-scale value as local maximum gradation value I ' max, in described connected region, minimum gradation value is 1<C<95 as the span of Local Minimum gray-scale value I ' min, described C% the most at high proportion.
Also comprise after the normalization of described local: part filter is carried out to the image after the normalization of described local, to strengthen local contrast, suppress adhesion between object locally.In the present embodiment, described part filter adopts adaptive Volterra filter to carry out filtering.
Particularly, on figure M7 after described normalization, to each connected region, consider that the gray-scale value of himself and the information in surrounding field carry out filtering operation, make gray-scale value brighter, the part that comparison degree is higher is retained, and the more weak part of the darker contrast of gray-scale value is suppressed, the adaptive Volterra filter in the similar documents 5 of its principle.Thus reach the problem effectively suppressing adhesion between object, obtain figure M8 as shown in Figure 9.
Then, use a higher thresholds d to carry out binaryzation to figure M8, remove the part that gray-scale value is less than threshold value d, obtain final enhancing image M9 as shown in Figure 10.Wherein the span of d is (0.5=<d<=1).
Compared with prior art, the present invention has the following advantages:
By local normalization, strengthen local message, to make unconspicuous local message in global image effectively be strengthened, the focus that namely intensity is weak can effectively strengthen.
Further, by adopting part filter again after the normalization of local, to strengthen local contrast, adhesion between the object of local is suppressed effectively to suppress the adhesion of focus and background tissues.
Further, strengthen described mammography X by the boostfiltering device of adaptive Density Weighted contrast, effectively to strengthen described image information and contrast.
Finally, described Enhancement Method, without the need to registration, without the need to several mammography X, and is not limited to the size and dimension of lump.
Although the present invention with preferred embodiment openly as above; but it is not for limiting the present invention; any those skilled in the art without departing from the spirit and scope of the present invention; the Method and Technology content of above-mentioned announcement can be utilized to make possible variation and amendment to technical solution of the present invention; therefore; every content not departing from technical solution of the present invention; the any simple modification done above embodiment according to technical spirit of the present invention, equivalent variations and modification, all belong to the protection domain of technical solution of the present invention.
Claims (10)
1. the Enhancement Method of a mammography X, comprise: mammography X is provided, the focus in described mammography X is strengthened, it is characterized in that, also comprise: local normalization is carried out to the local in described mammography X, to strengthen the image information of described local correspondence.
2. the Enhancement Method of mammography X as claimed in claim 1, is characterized in that, also comprise the connected region obtained in described mammography X, described local is normalized to carries out local normalization to described connected region.
3. the Enhancement Method of mammography X as claimed in claim 1, it is characterized in that, the normalization of described local comprises the gray-scale value I ' norm (x after obtaining local normalization, y), I ' norm (x, y)=(I ' (x, y)-I ' min)/(I ' max-I ' min), described I ' (x, y) be the gray-scale value before the local normalization of correspondence position, described I ' max and I ' min is respectively local maximum gradation value and local minimum gradation value.
4. the Enhancement Method of mammography X as claimed in claim 3, it is characterized in that, obtain described local maximum gradation value and minimum gradation value comprises: provide the grey level histogram of regional area and the highest gray scales C%, meet the gray-scale value of the pixel number of described C% as local maximum gradation value I ' max, in described regional area, minimum gradation value is as Local Minimum gray-scale value I ' min, and in described C% the most at high proportion, the span of C is 1<C<95.
5. the Enhancement Method of mammography X as claimed in claim 1, is characterized in that, also comprise after the normalization of described local: carry out part filter to the image after the normalization of described local, to strengthen local contrast, suppresses adhesion between object locally.
6. the Enhancement Method of mammography X as claimed in claim 5, is characterized in that, described part filter is one of nonlinear part filter or non-recursive part filter or combination.
7. the Enhancement Method of mammography X as claimed in claim 5, is characterized in that, described part filter carries out part filter for adopting adaptive Volterra filter.
8. the Enhancement Method of mammography X as claimed in claim 1, it is characterized in that, also comprise the focus in the boostfiltering device enhancing mammography X adopting adaptive Density Weighted contrast, and suppress the background outside focus, utilize the density of each pixel as weight to strengthen the contrast of current pixel point; The boostfiltering device enhancing of the adaptive Density Weighted contrast of described employing comprises: adopt low-pass filter to obtain the density map of mammography X, in utilization, logical or Hi-pass filter obtains corresponding comparison diagram, or deduct low-pass filtering with the mammography X do not strengthened and obtain corresponding comparison diagram, the density map of described mammography X is finally adopted to carry out comparison diagram described in weighting as weight, realize preliminary enhancing, the image after being enhanced.
9. the Enhancement Method of mammography X as claimed in claim 1, it is characterized in that, also comprise before carrying out the normalization of described local and full figure normalization is carried out to described mammography X, obtain full figure Normalized Grey Level value Inorm (x, y), wherein Inorm (x, y)=(I (x, y)-Imin)/(Imax-Imin), described I (x, y) be the gray-scale value before the full figure normalization of correspondence position, Imin is full figure minimum gradation value, and Imax is full figure maximum gradation value.
10. the Enhancement Method of mammography X as claimed in claim 9, it is characterized in that, after full figure normalization, also comprise the density map adopting low-pass filter to obtain mammography X, lead in utilization or the corresponding comparison diagram of image after the normalization of Hi-pass filter acquisition full figure, or deduct low-pass filtering with the mammography X do not strengthened and obtain corresponding comparison diagram, the density map of described mammography X is finally adopted to carry out comparison diagram described in weighting as weight, realize preliminary enhancing, the image after being enhanced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410124398.XA CN104952044A (en) | 2014-03-28 | 2014-03-28 | Mammary X-ray image enhancement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410124398.XA CN104952044A (en) | 2014-03-28 | 2014-03-28 | Mammary X-ray image enhancement method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104952044A true CN104952044A (en) | 2015-09-30 |
Family
ID=54166678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410124398.XA Pending CN104952044A (en) | 2014-03-28 | 2014-03-28 | Mammary X-ray image enhancement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104952044A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107316291A (en) * | 2017-06-14 | 2017-11-03 | 上海联影医疗科技有限公司 | Galactophore image processing method and breast imaging equipment |
| CN108182692A (en) * | 2018-01-05 | 2018-06-19 | 深圳蓝韵医学影像有限公司 | Mammary region recognition methods, device and storage medium in radioscopic image |
| CN108780508A (en) * | 2016-03-11 | 2018-11-09 | 高通股份有限公司 | System and method for normalized image |
| US10949950B2 (en) | 2017-06-14 | 2021-03-16 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for image processing |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096804A (en) * | 2010-12-08 | 2011-06-15 | 上海交通大学 | Method for recognizing image of carcinoma bone metastasis in bone scan |
| CN102332162A (en) * | 2011-09-19 | 2012-01-25 | 西安百利信息科技有限公司 | Method for automatic recognition and stage compression of medical image regions of interest based on artificial neural network |
-
2014
- 2014-03-28 CN CN201410124398.XA patent/CN104952044A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096804A (en) * | 2010-12-08 | 2011-06-15 | 上海交通大学 | Method for recognizing image of carcinoma bone metastasis in bone scan |
| CN102332162A (en) * | 2011-09-19 | 2012-01-25 | 西安百利信息科技有限公司 | Method for automatic recognition and stage compression of medical image regions of interest based on artificial neural network |
Non-Patent Citations (4)
| Title |
|---|
| CONTRAST IMPROVEMENT OF MAMMOGRAPHIC MASSES USING ADAPTIVE VOLTE: "Contrast Improvement of Mammographic Masses Using Adaptive Volterra Filter", 《PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING 2012》 * |
| NICHOLAS PETRICK等: "An Adaptive Density-Weighted Contrast Enhancement Filter for MammoEraDhic Breast Mass Detection", 《IEEE TRANSACTIONS ON MEDICAL IMAGING》 * |
| 张英涛等: "一种基于模糊逻辑的乳腺 X光片增强方法", 《哈尔滨工业大学学报》 * |
| 石宝刚: "乳腺微钙化点增强与检测的研究", 《万方数据知识服务平台》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108780508A (en) * | 2016-03-11 | 2018-11-09 | 高通股份有限公司 | System and method for normalized image |
| CN107316291A (en) * | 2017-06-14 | 2017-11-03 | 上海联影医疗科技有限公司 | Galactophore image processing method and breast imaging equipment |
| US10949950B2 (en) | 2017-06-14 | 2021-03-16 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for image processing |
| US11562469B2 (en) | 2017-06-14 | 2023-01-24 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for image processing |
| CN108182692A (en) * | 2018-01-05 | 2018-06-19 | 深圳蓝韵医学影像有限公司 | Mammary region recognition methods, device and storage medium in radioscopic image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104952044A (en) | Mammary X-ray image enhancement method | |
| CN107578374B (en) | Stretching method of X-ray image and computer readable storage medium | |
| Mohan et al. | Optimized histogram based contrast limited enhancement for mammogram images | |
| Suryavamsi et al. | Comparative analysis of various enhancement methods for astrocytoma MRI images | |
| Alankrita et al. | Contrast improvement of cerebral MRI features using combination of non-linear enhancement operator and morphological filter | |
| Liu et al. | Enhancement of low illumination images based on an optimal hyperbolic tangent profile | |
| Renukalatha et al. | AUTOMATIC ROI EXTRACTION IN NOISY MEDICAL IMAGES. | |
| Soliman et al. | An Efficient Breast Cancer Detection Framework for Medical Diagnosis Applications. | |
| Abdel-massieh et al. | Automatic liver tumor segmentation from CT scans with knowledge-based constraints | |
| Amutha et al. | Mammographic image enhancement using modified mathematical morphology and Bi-orthogonal wavelet | |
| Ayed et al. | New developments in the diagnostic procedures to reduce prospective biopsies breast | |
| Aldoury et al. | A new X-ray images enhancement method using a class of fractional differential equation | |
| Prakoso et al. | Enhancement methods of brain MRI images: A Review | |
| Sreeja et al. | Detection of tumours in digital mammograms using wavelet based adaptive windowing method | |
| Spandana et al. | Novel image processing techniques for early detection of breast cancer, mat lab and lab view implementation | |
| Kaur et al. | Region of interest based contrast enhancement techniques for CT images | |
| Arpana et al. | Feature extraction values for digital mammograms | |
| Sharma et al. | Contrast Enhancement and Noise Reduction of chest X-ray images | |
| Tie-Rui et al. | The research of X-ray bone fracture image enhancement algorithms | |
| Ziyad et al. | Performance evaluation of contrast enhancement techniques in computed tomography of lung images | |
| Aimi Salihah et al. | Improving blast segmentation of acute myelogenous leukemia (AML) images using bright stretching technique | |
| Zhang et al. | A LDCT image contrast enhancement algorithm based on single-scale retinex theory | |
| Lala et al. | Implementation on K-means Clustering and Fuzzy C-means Algorithm For Brain Tumor Segmentation | |
| Hou et al. | Research on tumor image segmentation in medical imaging based on extremum adaptive median filtering | |
| Seong et al. | Segmentation of abnormal liver using adaptive threshold in abdominal CT images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150930 |
|
| WD01 | Invention patent application deemed withdrawn after publication |