CN101853376A - Computer aided detection method for microcalcification in mammograms - Google Patents
Computer aided detection method for microcalcification in mammograms Download PDFInfo
- Publication number
- CN101853376A CN101853376A CN201010111555A CN201010111555A CN101853376A CN 101853376 A CN101853376 A CN 101853376A CN 201010111555 A CN201010111555 A CN 201010111555A CN 201010111555 A CN201010111555 A CN 201010111555A CN 101853376 A CN101853376 A CN 101853376A
- Authority
- CN
- China
- Prior art keywords
- image
- microcalcifications
- target area
- goes out
- gray correction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a computer aided detection method for microcalcification in mammograms, which comprises the following steps of: performing grayscale correction and transformation on a mammogram image to obtain an image after grayscale correction; acquiring microcalcification enhanced mammogram image by adopting dual-structure element-based background superposition method, and simultaneously acquiring another background suppressed mammogram image by adopting a Top-hat transformation method in morphology; segmenting the two images by adopting double thresholds to acquire a preliminary microcalcification image, and performing postprocessing to form a coarse microcalcification detection image; and extracting characteristics from coarsely detected microcalcification destination area, classifying by using a support vector machine, removing false microcalcification destination areas, marking the rest microcalcification into the mammogram image for the reading of doctors. The method can free the doctors from trivial mammogram reading and classifying work, and assists the doctors in better understanding and judging the images so as to reduce error diagnosis and missed diagnosis and fulfill the aim of improving diagnostic accuracy.
Description
Technical field
The invention belongs to the automatic analyzing and processing technical field of medical image, be specifically related to a kind of computer aided detection method for microcalcification in mammograms.
Background technology
Breast cancer is one of modal malignant tumour of women all over the world, and women's health even life in serious threat.In developed countries such as Northern Europe, wests, breast cancer incidence occupies women's malignant tumour incidence of disease first place.In China, along with the change of people's living and diet custom, the incidence of disease of breast cancer also presents tangible ascendant trend, and wherein the female mammary gland cancer morbidity in 25-34 year also increases very fast.Nearly decades, along with the development of medical technology, the diagnosis of breast cancer and treatment technology have had bigger progress, and however, the mortality ratio of breast cancer does not obviously descend, and this mainly is because most breast cancer are later when being found, and is difficult to cure.Therefore, under the still uncertain situation of breast cancer causal prophylaxis, find it is the key that reduces mortality early.
At present, the main method that breast cancer diagnosis adopts is the inspection of molybdenum target grenz ray, and wherein microcalcifications and lump are the modal iconography features of breast cancer.But because the density of soft tissues such as body of gland, connective tissue, blood vessel, fat in the breast tissue is all very approaching with the density in focus zone, factors such as diagnosis person's visual fatigue, make early-stage cancer mistaken diagnosis and fail to pinpoint a disease in diagnosis still generation often.Along with the develop rapidly of computer technology and digital image processing techniques, make that utilizing computing machine to carry out mammary gland microcalcifications auxiliary detection becomes possibility.Utilize digital image processing techniques that the microcalcifications in the mammary X-ray image is carried out enhancement process, and the focus zone carried out mark, the doctor can be freed from loaded down with trivial details readding sheet, the classification work, the help doctor better understands image and judges, thereby reduce mistaken diagnosis and fail to pinpoint a disease in diagnosis, reach the purpose that improves accuracy of diagnosis.
But the method for using exists following some problem in the automatic context of detection of microcalcifications at present: at first, it is not ideal enough that conventional detection generally all exists the detection effect, the stability of detection algorithm is not high, particularly in the lower image of some breast tissue densifications, picture quality, the phenomenon that the microcalcifications target is difficult to detect is serious; Secondly, exist inadequately fully or shortcoming such as the focus of extracting zone is excessive, caused very big difficulty for follow-up feature extraction microcalcifications focus extracted region; At last, adopt which type of feature and sorter that the microcalcifications zone is described and classify, could make that the detection accuracy rate of positive sample is the highest, never be well solved.
Summary of the invention
The purpose of this invention is to provide a kind of computer aided detection method for microcalcification in mammograms, solved exist in the prior art to microcalcifications target in the fine and close mammary X-ray image is difficult to entirely truely to detect, the testing result false positive rate is too high problem.
The technical solution used in the present invention is that the method that a kind of mammary gland microcalcifications detects automatically comprises following operation steps:
Step 2, center details and fringe region details to doubtful microcalcifications target area in the image after the gray correction strengthen, doubtful microcalcifications target area after will strengthening then is added on the image after the gray correction, obtains the galactophore image F that microcalcifications strengthens
1(x, y);
Step 3 is selected the circular configuration element more bigger than calcification point target for use, and the image after the gray correction is carried out the Top-hat conversion, obtains the galactophore image F after background suppresses
2(x, y);
Step 4 is to the image F of above-mentioned steps 2 gained
1(x, y) and the image F of step 3 gained
2(x, y) associating threshold value T
1With threshold value T
2Carry out dual threshold and cut apart, wherein, threshold value T
1Be image F
1(x, y) 85% of maximum gray scale, threshold value T
2Be image F
2(x, y) 80% of maximum gray scale; The doubtful microcalcifications target area that the impact point that forms after dual threshold is cut apart goes out as Preliminary detection; Remove the false calcification point of part target area then, finish the Rough Inspection of calcification point target area;
Step 5, each microcalcifications target area that Rough Inspection goes out at step 4 extracts the circularity, contrast, average of each target area and 4 dimensional feature vectors that variance is formed in the position of original galactophore image correspondence;
Step 6 with 4 dimensional feature vectors that extract, is transferred to the svm classifier device and is judged, judges whether the microcalcifications that Rough Inspection goes out is real microcalcifications target area;
Step 7 is thought real microcalcifications target area to judgement, and its mark to original galactophore image, is promptly finished the automatic detection to the mammary gland microcalcifications.
The invention has the beneficial effects as follows, when 1. the present invention detects the microcalcifications in the galactophore image of low quality, can detect microcalcifications in the image and false positive zone accurately seldom, improved the precision that detects.2. the doctor can be freed from loaded down with trivial details readding sheet, the classification work, alleviate doctor's workload, improve the automaticity of detection and the speed of detection.
Description of drawings
Fig. 1 is the process flow diagram of detection method of the present invention;
Fig. 2 is the original galactophore image that a width of cloth has microcalcifications in the embodiment of the invention step 1;
Fig. 3 is the image after the Gamma conversion is proofreaied and correct in the embodiment of the invention step 1;
Fig. 4 adopts the double structure element in the embodiment of the invention step 2, carry out the image after microcalcifications strengthens;
Fig. 5 is through the image after the Top-hat conversion in the embodiment of the invention step 3;
Fig. 6 is the bianry image after dual threshold is cut apart in the embodiment of the invention step 4;
Fig. 7 is through the bianry image after the aftertreatment in the embodiment of the invention step 4;
Fig. 8 is the microcalcifications image that marks after the classification in the embodiment of the invention step 7.
Embodiment
The present invention is described in detail below by embodiment.
As shown in Figure 1, a kind of computer aided detection method for microcalcification in mammograms provided by the present invention comprises following operation steps:
The method of described Gamma gray correction is:
Wherein (x y) is the original galactophore image of input to I, and (x y) is image after the Gamma gray correction to F, and γ is the Gamma value;
Step 2, because microcalcifications presents subcircular, the less feature of area more in image, adopt the double structure element, by shade of gray computing in the morphology, strengthen image F after the gray correction (x, y) in the center details and the fringe region details of doubtful microcalcifications target area, the image F (x after the gray correction that is added to of the doubtful microcalcifications target area after will strengthening then, y) on, obtain the galactophore image F that microcalcifications strengthens
1(x y), is convenient to detect calcification point; Its concrete grammar is:
1) utilize the double structure element to be
And
Wherein, B
1Be interior centrosymmetric structure, be used to strengthen details near the target's center position; B
2Be outer centrosymmetric structure, be used to strengthen the details in object edge zone;
2) utilize structural element B
1, (x y) carries out the computing of gray scale morphology gradient and obtains image G to the image F after the Gamma gray correction
1(x, y), promptly
3) utilize structural element B
2, (x y) carries out the computing of gray scale morphology gradient and obtains image G to the image F after the Gamma gray correction
2(x, y), promptly
4) with the image G that forms
1(x, y) and G
2(x, y) be added to image F after the Gamma gray correction (x, y) on, form the galactophore image F after microcalcifications strengthens
1(x, y), that is: F
1(x, y)=F (x, y)+G
1(x, y)+G
2(x, y);
Step 3, for further outstanding calcification point target area, suppress the influence of breast tissue background, select the circular configuration element more bigger for use than calcification point target, image after the Gamma correction is carried out the Top-hat conversion, obtain the galactophore image after background suppresses, microcalcifications target area wherein tentatively displays; Its concrete grammar is:
1) utilizes the circular configuration element
2) (x y) carries out morphology Top-hat conversion, forms the galactophore image F that background suppresses to the image F after the Gamma gray correction
2(x, y), i.e. F
2(x, y)=F (x, y)-(F (x, y) о B
3(x, y));
In the image that step 4, step 2 obtain, when the microcalcifications target area is strengthened, also, caused " noise zone " to strengthening with the approaching zone of microcalcifications target shape characteristic in the background; And in the image that step 3 obtains, background has then been suppressed well.For this reason, two width of cloth images that obtain in step 2 and the step 3 are adopted different threshold values respectively, unite and cut apart, the impact point of formation is as preliminary calcification point target area; Further, consider the size and the distribution range restriction of microcalcifications target, carry out aftertreatment then, remove the calcification point target area of part falseness, finish the Rough Inspection of calcification point target area; Its concrete grammar is;
1) obtains the image F that step 2 is obtained through the test of many times statistics
1(x, 85% of maximum gray scale y) is made as threshold value T
1, the image F that step 3 is obtained
2(x, 80% of maximum gray scale y) is made as threshold value T
2
2) again to image F
1(x is y) with image F
2(x, y) associating threshold value T
1With threshold value T
2Carry out dual threshold and cut apart, promptly to satisfying condition simultaneously: F
1(x, y)＞T
1And F
2(x, y)＞T
2Pixel promptly be confirmed as the doubtful microcalcifications target area that Preliminary detection is come out;
3) remove area at last less than 2 pixels or greater than 20 pixel target areas, be positioned at the target area of boundary vicinity up and down in the removal image, form the microcalcifications target area that Rough Inspection goes out;
Step 5 in the calcification point target image that Rough Inspection goes out in step 4, contains the calcification point target of many falsenesses, is called the false positive district.For further getting rid of these false positive districts, circularity, contrast, average and the variance of each calcification point target area that extraction step 4 Rough Inspections go out on original galactophore image with its characteristic feature as the calcification point target area, are formed 4 dimensional feature vectors; 4 dimensional feature vectors that extract are:
1) target area circularity: Y=P
2/ (4 π S), wherein, P is the girth of target area, S is the area of target area;
2) target area contrast:
Wherein f and b represent the average gray of target area and background area respectively, are specially:
N wherein
fThe number of pixels of the microcalcifications target area that the expression Rough Inspection goes out, Ω
fThe set that microcalcifications target area pixel is formed that the expression Rough Inspection goes out;
Ω wherein
bThe collection of pixels that non-microcalcifications is formed in the extraneous rectangular area of microcalcifications is surrounded in expression, and extraneous rectangular area by the minimum boundary rectangle that comprises a microcalcifications target area respectively up and down, the left and right zone that a pixel is formed, the N of respectively extending out
bExpression Ω
bIn number of pixels;
3) target area average:
N wherein
fThe number of pixels of the microcalcifications target area that the expression Rough Inspection goes out, Ω
fThe set that microcalcifications target area pixel is formed that the expression Rough Inspection goes out;
4) target area variance:
N wherein
fThe number of pixels of the microcalcifications target area that the expression Rough Inspection goes out, Ω
fThe set that microcalcifications target area pixel is formed that the expression Rough Inspection goes out;
Step 6 is utilized the proper vector that extracts in the step 5, adopts positive sample and negative sample, the training support vector machine; Whether will extract the proper vector of the calcification point target area that Rough Inspection goes out then, and be input in the vector machine that trains and go, and be classified in this target area, obtaining it is real calcification point target area;
With the method for support vector machine, the method for classifying in the microcalcifications target area that Rough Inspection is gone out is:
1) kernel function of using in the support vector machine is the radially basic kernel function of Gauss;
2) the true microcalcifications zone of contrast marker, the microcalcifications target area that Rough Inspection is detected is divided into positive sample and negative sample, and sample is divided into the subclass of 5 sizes at random, to each model parameter collection, training svm classifier device;
3) whether extract 4 dimensional feature vectors of the microcalcifications target area that Rough Inspection goes out, with the svm classifier device that trains, this target is classified, drawing it is real microcalcifications target area;
Step 7 is thought real microcalcifications target area to judgement, and its mark to original galactophore image, is promptly finished the automatic detection to the mammary gland microcalcifications.
A kind of computer aided detection method for microcalcification in mammograms, carry out concrete enforcement by following steps:
The method of its Gamma gray correction is:
Wherein I (x y) is the input original image, F (x y) is image after the Gamma gray correction, and the value of γ is 3, obtain after the gray correction image as shown in Figure 3;
Step 2 adopts the background stacking method based on the double structure element, strengthens the center details and the fringe region details of doubtful microcalcifications target area among Fig. 3:
Utilization double structure element:
And
Fig. 3 is carried out following morphology handle, obtain image G
1(x, y) and G
2(x, y):
Then, with image G
1(x, y) and G
2(x y) is added on Fig. 3, forms the galactophore image F after microcalcifications strengthens
1(x, y), that is: F
1(x, y)=F (x, y)+G
1(x, y)+G
2(x, y), as shown in Figure 4;
Step 3, the Top-hat conversion in the utilization morphology forms the galactophore image after background suppresses: the utilization structural element
Fig. 3 is carried out the Top-hat conversion, obtain the galactophore image F after background suppresses as shown in Figure 5
2(x, y), i.e. F
2(x, y)=F (x, y)-(F (x, y) о B
3(x, y));
Step 4, the method for employing dual threshold and aftertreatment, Rough Inspection goes out the microcalcifications target area:
Select threshold value T
1Be 85% of the maximum gray scale of image shown in Figure 4, threshold value T
2Be 80% of the maximum gray scale of image shown in Figure 5, respectively to image shown in Figure 4 (image after microcalcifications strengthens) and image shown in Figure 5 (image after the Top-hat conversion) associating threshold value T
1With threshold value T
2Carry out dual threshold and cut apart, the bianry image after obtaining dual threshold and cutting apart as shown in Figure 6, is the doubtful microcalcifications target area that Preliminary detection goes out; At last, area among Fig. 6 less than 2 pixels or greater than 20 pixel target areas, and is positioned at the target area of boundary vicinity up and down, removes, form the microcalcifications target area that Rough Inspection goes out, as shown in Figure 7;
Step 5, at each microcalcifications target area that Rough Inspection among Fig. 7 goes out, extract circularity, contrast, histogram average and histogram variance 4 dimensional feature vectors of each target area in the position of Fig. 2 correspondence:
1) target area circularity: Y=P
2/ (4 π S), wherein P is the girth of target area, S is the area of target area;
2) target area contrast:
Wherein f and b represent the average gray of target area and background area respectively, are specially:
N wherein
fThe number of pixels of the microcalcifications target area that the expression Rough Inspection goes out, Ω
fThe set that microcalcifications target area pixel is formed that the expression Rough Inspection goes out;
Ω wherein
bThe collection of pixels that non-microcalcifications is formed in the extraneous rectangular area of microcalcifications is surrounded in expression, and extraneous rectangular area by the minimum boundary rectangle that comprises a microcalcifications target area respectively up and down, the left and right zone that a pixel is formed, the N of respectively extending out
bExpression Ω
bIn number of pixels;
3) target area average:
N wherein
fThe number of pixels of the microcalcifications target area that the expression Rough Inspection goes out, Ω
fThe set that microcalcifications target area pixel is formed that the expression Rough Inspection goes out;
4) target area variance:
N wherein
fThe number of pixels of the microcalcifications target area that the expression Rough Inspection goes out, Ω
fThe set that microcalcifications target area pixel is formed that the expression Rough Inspection goes out;
Step 6, adopt the method for support vector machine, classified in the microcalcifications target area that Rough Inspection goes out: whether to 4 dimensional feature vectors that each the microcalcifications target area among Fig. 7 extracts, transfer to the svm classifier device and judge, obtaining it is real microcalcifications target area;
Step 7 is thought real microcalcifications target area to judgement, and to original galactophore image Fig. 2, the result of mark promptly finishes the automatic detection to the mammary gland microcalcifications as shown in Figure 8 with its mark.
Claims (6)
1. the method that the mammary gland microcalcifications detects automatically is characterized in that, comprises following operation steps:
Step 1 is carried out gray correction to original galactophore image, to improve the overall contrast of image, obtain after the gray correction image F (x, y);
Step 2, center details and fringe region details to doubtful microcalcifications target area in the image after the gray correction strengthen, doubtful microcalcifications target area after will strengthening then is added on the image after the gray correction, obtains the galactophore image F that microcalcifications strengthens
1(x, y);
Step 3 is selected the circular configuration element more bigger than calcification point target for use, and the image after the gray correction is carried out the Top-hat conversion, obtains the galactophore image F after background suppresses
2(x, y);
Step 4 is to the image F of above-mentioned steps 2 gained
1(x, y) and the image F of step 3 gained
2(x, y) associating threshold value T
1With threshold value T
2Carry out dual threshold and cut apart, wherein, threshold value T
1Be image F
1(x, y) 85% of maximum gray scale, threshold value T
2Be image F
2(x, y) 80% of maximum gray scale; The doubtful microcalcifications target area that the impact point that forms after dual threshold is cut apart goes out as Preliminary detection; Remove the false calcification point of part target area then, finish the Rough Inspection of calcification point target area;
Step 5, each microcalcifications target area that Rough Inspection goes out at step 4 extracts the circularity, contrast, average of each target area and 4 dimensional feature vectors that variance is formed in the position of original galactophore image correspondence;
Step 6 with 4 dimensional feature vectors that extract, is transferred to the svm classifier device and is judged, judges whether the microcalcifications that Rough Inspection goes out is real microcalcifications target area;
Step 7 is thought real microcalcifications target area to judgement, and its mark to original galactophore image, is promptly finished the automatic detection to the mammary gland microcalcifications.
2. the method that a kind of mammary gland microcalcifications according to claim 1 detects automatically is characterized in that the concrete operations step of described step 1 is:
Adopt Gamma gray correction method that original galactophore image is carried out gray correction, to improve the overall contrast of image;
Described Gamma gray correction method is:
Wherein (x y) is the original galactophore image of input to I, and (x y) is the image after the gray correction to F, and γ is the Gamma value.
3. the method that a kind of mammary gland microcalcifications according to claim 1 detects automatically is characterized in that the concrete operations step of described step 2 is:
Adopt the double structure element, by shade of gray computing in the morphology, to the image F (x after the gray correction, y) the center details of doubtful microcalcifications target area and fringe region details strengthen in, doubtful microcalcifications target area after will strengthening the then image F (x after the gray correction that is added to, y) on, obtain the galactophore image F that microcalcifications strengthens
1(x, y); Its concrete grammar is:
1) adopts the double structure element
And
Wherein, B
1Be interior centrosymmetric structure, be used to strengthen details, B near the target's center position
2Be outer centrosymmetric structure, be used to strengthen the details in object edge zone;
2) utilize structural element B
1, (x y) carries out the computing of gray scale morphology gradient and obtains image G to the image F after the gray correction
1(x, y), promptly
3) utilize structural element B
2, (x y) carries out the computing of gray scale morphology gradient and obtains image G to the image F after the gray correction
2(x, y), promptly
4) with the image G that forms
1(x, y) and G
2(x, y) be added to image F after the gray correction (x, y) on, form the galactophore image F after microcalcifications strengthens
1(x, y), that is: F
1(x, y)=F (x, y)+G
1(x, y)+G
2(x, y).
4. the method that a kind of mammary gland microcalcifications according to claim 1 detects automatically is characterized in that the concrete operations step of described step 3:
The circular configuration element that utilization is more bigger than calcification point target carries out the Top-hat conversion to the image after the gray correction, obtains the galactophore image F after background suppresses
2(x, y), microcalcifications target area wherein tentatively displays; Its concrete grammar is:
1) selects the circular configuration element for use
2) (x y) carries out morphology Top-hat conversion, forms the galactophore image F that background suppresses to the image F after the gray correction
2(x, y), i.e. F
2(x, y)=F (x, y)-(F (x, y) о B
3(x, y)).
5. the method that a kind of mammary gland microcalcifications according to claim 1 detects automatically is characterized in that the concrete operations step of described step 4:
Two width of cloth images that obtain in step 2 and the step 3 are adopted different threshold values respectively, unite and cut apart, the impact point of formation removes the calcification point target area of part falseness then as preliminary calcification point target area, finishes the Rough Inspection of calcification point target area; Its concrete grammar is:
1) the image F that obtains for step 2
1(x, y), with image F
1(x y) 85% of maximum gray scale is made as threshold value T
1The image F that obtains for step 3
2(x, y), with image F
2(x y) 80% of maximum gray scale is made as threshold value T
2
2) again to image F
1(x is y) with image F
2(x, y) associating threshold value T
1With threshold value T
2Carry out dual threshold and cut apart, promptly satisfy T simultaneously
1(x, y)＞T
1And T
2(x, y)＞T
2The doubtful microcalcifications target area that goes out as Preliminary detection of pixel;
3) remove area at last less than 2 pixels or greater than 20 pixel target areas, be positioned at the target area of boundary vicinity up and down in the removal image, form the microcalcifications target area that Rough Inspection goes out.
6. the method that a kind of mammary gland microcalcifications according to claim 1 detects automatically is characterized in that the concrete operations step of described step 5:
Each calcification point target area that Rough Inspection goes out at step 4 extracts circularity, contrast, average and the variance of each target area in the position of original galactophore image correspondence, with its characteristic feature as the calcification point target area, form 4 dimensional feature vectors; 4 dimensional feature vectors that extract are:
1) target area circularity: Y=P
2/ (4 π S), wherein, P is the girth of target area, S is the area of target area;
2) target area contrast:
Wherein f and b represent the average gray of target area and background area respectively; Be specially:
N wherein
fThe number of pixels of the microcalcifications target area that the expression Rough Inspection goes out, Ω
fThe set that microcalcifications target area pixel is formed that the expression Rough Inspection goes out;
Ω wherein
bThe collection of pixels that non-microcalcifications is formed in the extraneous rectangular area of microcalcifications is surrounded in expression, and extraneous rectangular area by the minimum boundary rectangle that comprises a microcalcifications target area respectively up and down, the left and right zone that a pixel is formed, the N of respectively extending out
bExpression Ω
bIn number of pixels;
3) target area average:
N wherein
fThe number of pixels of the microcalcifications target area that the expression Rough Inspection goes out, Ω
fThe set that microcalcifications target area pixel is formed that the expression Rough Inspection goes out;
4) target area variance:
N wherein
fThe number of pixels of the microcalcifications target area that the expression Rough Inspection goes out, Ω
fThe set that microcalcifications target area pixel is formed that the expression Rough Inspection goes out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101115555A CN101853376B (en) | 2010-02-10 | 2010-02-10 | Computer aided detection method for microcalcification in mammograms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101115555A CN101853376B (en) | 2010-02-10 | 2010-02-10 | Computer aided detection method for microcalcification in mammograms |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101853376A true CN101853376A (en) | 2010-10-06 |
| CN101853376B CN101853376B (en) | 2012-02-08 |
Family
ID=42804856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010101115555A Expired - Fee Related CN101853376B (en) | 2010-02-10 | 2010-02-10 | Computer aided detection method for microcalcification in mammograms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101853376B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034857A (en) * | 2012-12-18 | 2013-04-10 | 深圳市安健科技有限公司 | Method and system of automatic detection of exposure area in image picture |
| CN103337096A (en) * | 2013-07-19 | 2013-10-02 | 东南大学 | Coronary artery CT (computed tomography) contrastographic image calcification point detecting method |
| CN103679176A (en) * | 2013-12-30 | 2014-03-26 | 北京航空航天大学 | Linear feature extraction method utilizing multi-scale multi-constructing-element top-hat transformation |
| CN105096258A (en) * | 2014-05-05 | 2015-11-25 | 辽宁开普医疗系统有限公司 | Small part X ray image background suppression method and device thereof |
| CN105118030A (en) * | 2015-08-11 | 2015-12-02 | 上海联影医疗科技有限公司 | Medical image metal artifact correction method and device |
| CN107798679A (en) * | 2017-12-11 | 2018-03-13 | 福建师范大学 | Breast molybdenum target image breast area is split and tufa formation method |
| CN108491796A (en) * | 2018-03-22 | 2018-09-04 | 电子科技大学 | A kind of time domain period point target detecting method |
| CN108734705A (en) * | 2018-05-17 | 2018-11-02 | 杭州电子科技大学 | Digital galactophore fault image calcification clusters automatic testing method based on deep learning |
| CN109288536A (en) * | 2018-09-30 | 2019-02-01 | 数坤（北京）网络科技有限公司 | Obtain the method, apparatus and system of Coronary Calcification territorial classification |
| CN109389614A (en) * | 2018-10-24 | 2019-02-26 | 山东大学 | A kind of fast optical imaging data dividing method |
| CN109829896A (en) * | 2019-01-14 | 2019-05-31 | 中国科学院苏州生物医学工程技术研究所 | The micro-calcification clusters automatic testing method of digital galactophore tomography X image based on multi-domain characteristics |
| CN110021015A (en) * | 2019-04-01 | 2019-07-16 | 数坤（北京）网络科技有限公司 | Punctate clacification method for detecting area and system based on brightness and gradient |
| CN110021016A (en) * | 2019-04-01 | 2019-07-16 | 数坤（北京）网络科技有限公司 | A kind of calcification detection method |
| CN110264461A (en) * | 2019-06-25 | 2019-09-20 | 南京工程学院 | Microcalciffcation point automatic testing method based on ultrasonic tumor of breast image |
| CN110782451A (en) * | 2019-11-04 | 2020-02-11 | 哈尔滨理工大学 | Suspected microcalcification area automatic positioning method based on discriminant depth confidence network |
| CN111145160A (en) * | 2019-12-28 | 2020-05-12 | 上海联影医疗科技有限公司 | Method, device, server and medium for determining coronary artery branch where calcified area is located |
| CN113822864A (en) * | 2021-09-16 | 2021-12-21 | 什维新智医疗科技(上海)有限公司 | Mammary nodule calcification detection device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6434261B1 (en) * | 1998-02-23 | 2002-08-13 | Board Of Regents, The University Of Texas System | Method for automatic detection of targets within a digital image |
| CN101234026A (en) * | 2008-03-07 | 2008-08-06 | 李立 | Mammary gland affection quantification image evaluation system and using method thereof |
-
2010
- 2010-02-10 CN CN2010101115555A patent/CN101853376B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6434261B1 (en) * | 1998-02-23 | 2002-08-13 | Board Of Regents, The University Of Texas System | Method for automatic detection of targets within a digital image |
| CN101234026A (en) * | 2008-03-07 | 2008-08-06 | 李立 | Mammary gland affection quantification image evaluation system and using method thereof |
Non-Patent Citations (3)
| Title |
|---|
| 《CT理论与应用研究》 20061231 文浩; 马金盛; 王玉慧; 庄达民; 《基于形态学灰度重构的乳腺微钙化点提取》 33－37 1－6 , 第2期 2 * |
| 《中国图象图形学报》 20061231 董妍 等 《一种基于Top-hat的乳腺图像中钙化点的检测方法》 1839－1843 1－6 第11卷, 第12期 2 * |
| 《医疗卫生装备》 20051231 李宁 等 《基于支持向量机的乳腺病变检测》 12－14 1－6 , 2 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034857B (en) * | 2012-12-18 | 2016-02-17 | 深圳市安健科技有限公司 | The method and system of exposure area in automatic detected image |
| CN103034857A (en) * | 2012-12-18 | 2013-04-10 | 深圳市安健科技有限公司 | Method and system of automatic detection of exposure area in image picture |
| CN103337096B (en) * | 2013-07-19 | 2015-09-09 | 东南大学 | A kind of coronary artery CT contrastographic picture tufa formation method |
| CN103337096A (en) * | 2013-07-19 | 2013-10-02 | 东南大学 | Coronary artery CT (computed tomography) contrastographic image calcification point detecting method |
| CN103679176A (en) * | 2013-12-30 | 2014-03-26 | 北京航空航天大学 | Linear feature extraction method utilizing multi-scale multi-constructing-element top-hat transformation |
| CN105096258A (en) * | 2014-05-05 | 2015-11-25 | 辽宁开普医疗系统有限公司 | Small part X ray image background suppression method and device thereof |
| CN105096258B (en) * | 2014-05-05 | 2017-12-05 | 辽宁开普医疗系统有限公司 | A kind of small position X-ray image background suppression method and its device |
| CN105118030A (en) * | 2015-08-11 | 2015-12-02 | 上海联影医疗科技有限公司 | Medical image metal artifact correction method and device |
| CN105118030B (en) * | 2015-08-11 | 2018-08-03 | 上海联影医疗科技有限公司 | The bearing calibration of medical image metal artifacts and device |
| CN107798679B (en) * | 2017-12-11 | 2021-04-27 | 福建师范大学 | Breast region segmentation and calcification detection method for mammary gland molybdenum target image |
| CN107798679A (en) * | 2017-12-11 | 2018-03-13 | 福建师范大学 | Breast molybdenum target image breast area is split and tufa formation method |
| CN108491796A (en) * | 2018-03-22 | 2018-09-04 | 电子科技大学 | A kind of time domain period point target detecting method |
| CN108491796B (en) * | 2018-03-22 | 2021-10-22 | 电子科技大学 | Time domain periodic point target detection method |
| CN108734705A (en) * | 2018-05-17 | 2018-11-02 | 杭州电子科技大学 | Digital galactophore fault image calcification clusters automatic testing method based on deep learning |
| CN109288536A (en) * | 2018-09-30 | 2019-02-01 | 数坤（北京）网络科技有限公司 | Obtain the method, apparatus and system of Coronary Calcification territorial classification |
| CN109389614A (en) * | 2018-10-24 | 2019-02-26 | 山东大学 | A kind of fast optical imaging data dividing method |
| CN109829896A (en) * | 2019-01-14 | 2019-05-31 | 中国科学院苏州生物医学工程技术研究所 | The micro-calcification clusters automatic testing method of digital galactophore tomography X image based on multi-domain characteristics |
| CN110021015A (en) * | 2019-04-01 | 2019-07-16 | 数坤（北京）网络科技有限公司 | Punctate clacification method for detecting area and system based on brightness and gradient |
| CN110021016A (en) * | 2019-04-01 | 2019-07-16 | 数坤（北京）网络科技有限公司 | A kind of calcification detection method |
| CN110264461A (en) * | 2019-06-25 | 2019-09-20 | 南京工程学院 | Microcalciffcation point automatic testing method based on ultrasonic tumor of breast image |
| CN110782451A (en) * | 2019-11-04 | 2020-02-11 | 哈尔滨理工大学 | Suspected microcalcification area automatic positioning method based on discriminant depth confidence network |
| CN111145160A (en) * | 2019-12-28 | 2020-05-12 | 上海联影医疗科技有限公司 | Method, device, server and medium for determining coronary artery branch where calcified area is located |
| CN111145160B (en) * | 2019-12-28 | 2023-06-30 | 上海联影医疗科技股份有限公司 | Method, device, server and medium for determining coronary artery branches where calcified regions are located |
| CN113822864A (en) * | 2021-09-16 | 2021-12-21 | 什维新智医疗科技(上海)有限公司 | Mammary nodule calcification detection device |
| CN113822864B (en) * | 2021-09-16 | 2023-10-31 | 什维新智医疗科技(上海)有限公司 | Breast nodule calcification detection device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101853376B (en) | 2012-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101853376B (en) | Computer aided detection method for microcalcification in mammograms | |
| Jin et al. | Pulmonary nodule detection based on CT images using convolution neural network | |
| Nagi et al. | Automated breast profile segmentation for ROI detection using digital mammograms | |
| US9959617B2 (en) | Medical image processing apparatus and breast image processing method thereof | |
| Kharel et al. | Early diagnosis of breast cancer using contrast limited adaptive histogram equalization (CLAHE) and Morphology methods | |
| TWI482102B (en) | Methods for processing enhancement of target pattern, method for generating classification system of target patterns and classifying detected target patterns | |
| CN103700085A (en) | Cutting method of pectoral muscle region in mammary gland X-ray image | |
| Lewis et al. | Detection of breast tumor candidates using marker-controlled watershed segmentation and morphological analysis | |
| Palma et al. | Detection of masses and architectural distortions in digital breast tomosynthesis images using fuzzy and a contrario approaches | |
| Maitra et al. | Automated digital mammogram segmentation for detection of abnormal masses using binary homogeneity enhancement algorithm | |
| Al-Shamlan et al. | Feature extraction values for breast cancer mammography images | |
| He et al. | Breast image pre-processing for mammographic tissue segmentation | |
| Wirth et al. | Segmentation of the breast region in mammograms using snakes | |
| CN110782451B (en) | Suspected microcalcification area automatic positioning method based on discriminant depth confidence network | |
| TW201726064A (en) | Medical image processing apparatus and breast image processing method thereof | |
| CN101404062A (en) | Automatic screening method for digital galactophore image based on decision tree | |
| El Abbadi et al. | Breast cancer diagnosis by CAD | |
| Ayed et al. | New developments in the diagnostic procedures to reduce prospective biopsies breast | |
| Kim et al. | Breast mass detection using slice conspicuity in 3D reconstructed digital breast volumes | |
| Ameer et al. | Using Morphological Operation and Watershed Techniques for Breast Cancer Detection. | |
| Widodo et al. | Sample K-means clustering method for determining the stage of breast cancer malignancy based on cancer size on mammogram image basis | |
| Feudjio et al. | Automatic extraction of pectoral muscle in the MLO view of mammograms | |
| CN111062909A (en) | Method and equipment for judging benign and malignant breast tumor | |
| Marrocco et al. | Detection of cluster of microcalcifications based on watershed segmentation algorithm | |
| Hemalatha et al. | Computerized breast cancer detection system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120208 Termination date: 20150210 |
|
| EXPY | Termination of patent right or utility model |