CN104182965A - Pectoralis segmentation method in breast image - Google Patents
Pectoralis segmentation method in breast image Download PDFInfo
- Publication number
- CN104182965A CN104182965A CN201410028053.4A CN201410028053A CN104182965A CN 104182965 A CN104182965 A CN 104182965A CN 201410028053 A CN201410028053 A CN 201410028053A CN 104182965 A CN104182965 A CN 104182965A
- Authority
- CN
- China
- Prior art keywords
- chest muscle
- image
- region
- galactophore image
- galactophore
- 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
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a pectoralis segmentation method in a breast image. The pectoralis segmentation method in the breast image comprises the following steps: carrying out morphological restriction region growing to a breast image to obtain a first pectoralis area; and carrying out first correction to the first pectoralis area to obtain the breast image of a pectoralis segmentation area. The pectoralis segmentation method provided by the invention has an automatic correction function, pectoralis parts can be quickly and effectively segmented and removed in a mediolateral oblique position mammogram, and the pectoralis segmentation method exhibits high accuracy and robustness. For multi-level greyscales, the pectoralis with fuzzy edges and irregular edges can be effectively segmented.
Description
Technical field
The present invention relates to field of medical image processing, relate in particular to a kind of cut apart chest muscle in galactophore image method.
Background technology
The human body chest muscle region of removing in inside and outside skew back (MLO) position is the basic steps in mammary X-ray image (Mammograms) computer-aided diagnosis (Computer-aided Diagnosis, CAD) system pre-service.In the galactophore image of MLO position, chest muscle region is usually located at the upper left corner or the upper right corner of image, and general edge is comparatively mild, presents triangle, has brightness high or the highest in entire image.Remove the chest muscle step of MLO bit image, can avoid bringing harmful effect to subsequent treatment, such as image regularization, the breast density estimation etc. in lesion segmentation, and can effectively suppress false positive for mammary gland CAD, thus improve focus verification and measurement ratio.
In prior art, the method for cutting apart chest muscle in the galactophore image of MLO position mainly contains following several: (1) method based on Threshold segmentation.First former figure is cut out to the area-of-interest that comprises chest muscle part, then carry out Threshold segmentation, finally image is carried out to threshold process.Because grey scale pixel value difference in dynamic range in chest muscle region in different galactophore images is very large, therefore cannot estimate threshold value, can only get empirical value, thereby cause the method applicability wideless, segmentation result degree of accuracy is low; (2) method based on region growing.First, former figure is carried out index mapping and quantizes to reduce gray level; Then carry out morphology processing; Be positioned under the prerequisite in the upper left corner at default chest muscle, Seed Points be located to the pixel in the upper left corner; Then carry out region growing by the method for iteration, in the process of growth, add dimensional constraints (Size Restriction), once outgrowth improves threshold value and regrows.The method can Fast Convergent, and can effectively control undue, but degree of accuracy is low, easily produces deviation; (3) dividing method based on Hough conversion.The method is a kind of widely used method of cutting apart chest muscle in prior art, is also each large manufacturer's patented technology.These class methods can only be suitable for the situation of chest muscle real border near linear, for the larger chest muscle border of curvature and there is the chest muscle of cortex stack inapplicable; (4) Hough conversion and Snake mixed method.First, obtain approaching the straight line of real border with aforesaid Hough transform method, then with Snake alternative manner, straight line is proofreaied and correct.The method is easily subject to the interference of noise and surrounding structure and causes accuracy to reduce in Snake step; (4) straight line is estimated and accurate adjustment (Refinement) method.First former figure is carried out to Threshold segmentation, obtain bianry image; Utilize the border of bianry image to estimate a straight line that approaches chest muscle real border; For each pixel on the straight line obtaining, get the gradation of image on its traverse, obtain an one dimension waveform, remove this waveform of matching with Sigmoid function, and find the most precipitous point (Cliff Detection) with parametric technique, this puts corresponding image coordinate and is the renewal to former frontier point.The shortcoming of the method is similar to the method for Hough conversion, once real border is more bending, it is far away that straight line differs with it, and Refinement can not go back edge correction.Because Refinement is only applicable to accurate adjustment among a small circle, will cause border not restrained once expand fine adjustment range.In addition, Sigmoid Function Fitting inapplicable with waveform complicated situation.
In sum, in prior art, mainly there is following problem for the method for cutting apart chest muscle in the galactophore image of inside and outside oblique side position (MLO is): applicability is low, and for multi-grey level, edge irregularity or fuzzy chest muscle can not be cut apart effectively; Threshold value can not be adjusted in real time, can only adopt empirical value, and the selection of parameter is subject to noise effect larger, causes segmentation result degree of accuracy to reduce.
Summary of the invention
The problem that the present invention solves is to provide a kind of cut apart chest muscle in galactophore image method, in the galactophore image of MLO position, cut apart effectively segmenting edge scrambling or fuzzy chest muscle of chest muscle method in order to solve, threshold value can not be adjusted in real time, can only adopt empirical value, the selection of parameter is subject to noise effect larger, segmentation result is accurately low, poor robustness.
In order to address the above problem, the invention provides a kind of cut apart chest muscle in galactophore image method, comprise the steps:
Galactophore image is carried out to the region growing of morphology restriction, obtain the first chest muscle region;
The first correction is carried out in described the first chest muscle region, obtain the galactophore image of cutting apart chest muscle region.
Further, the region growing of described morphology restriction comprises the steps:
(1) definition morphology restriction;
(2) carry out morphology restriction adaptive region increase, under the threshold value of described region growing, be limited to:
th
L=(1-t)*(T
max+T
min)／2
Wherein T
maxand T
minbe respectively maximal value and the minimum value of current growth district;
(3) judgement: if difference △ S≤a*S of the area S ' of growth district and the area S of morphology restricted area obtains described the first chest muscle region;
Otherwise, adjust parametric t=t*b, and repeating said steps (2) and (3);
Wherein a, b, t are the constant between (0,1).
Further, the method for described definition morphology restriction comprises the steps: on described two-dimentional galactophore image
Defining point p (1, y): the separation of getting chest muscle and breast in galactophore image the first row is a some p;
Defining point q (x, 1): get the line number m at peaked some place of the col width of breast in galactophore image, and it is capable to move down c, order point x=m+c that q is expert at;
The line pq that gets described some p and some q, image is divided into Part I and Part II by described line pq, and described Part I is the region of described morphology restriction.
Further, described the first correction comprises the steps:
(1) lofty structure operation is removed in described the first chest muscle region, obtain the second chest muscle region;
(2) accurate adjustment is carried out in described the second chest muscle region on the galactophore image of n kind yardstick, obtain the galactophore image of cutting apart chest muscle region;
Wherein, described n is more than or equal to 1 positive integer.
Further, the lofty structure operation of described removal comprises the steps:
Travel through all points in described the first chest muscle edges of regions, get any two terminal A and B, connect A, B two-end-point formation straight line AB, if straight line AB meets simultaneously:
Straight line AB distance
Straight line AB is positioned at described the first chest muscle intra-zone;
Straight line AB is apart from d
aB<d*C;
Remove lofty structure;
If not, do not deal with.
Wherein, described L is the overall length of described the first chest muscle region mesothorax flesh and mammary gland adjacent boundary; Described C is the chest muscle edge overall length that connects 2 of A B in described the first chest muscle region; Described d is greater than 1 constant.
Further, described accurate adjustment comprises the steps:
Get the frontier point of described the second chest muscle region mesothorax flesh, get any one frontier point, make the normal of described frontier point, get frontier point adjacent at least 2 pixels on normal;
The gray-scale value of at least 3 pixels described in calculating, the difference that defines the gray-scale value of adjacent 2 is gradient;
Determine gradient maximum point, the renewal coordinate that to define image coordinate that this point is corresponding be got frontier point;
Adopt the limit of Snake algorithm second chest muscle region accurate adjustment chest muscle in the galactophore image of n kind yardstick, cut apart the galactophore image in chest muscle region described in acquisition;
Wherein, the state equation of described Snake algorithm is:
State equation E
snake=E
int+ E
ext;
Described renewal coordinate is E in described Snake state equation
extfor external energy; The flatness on described chest muscle border is the internal energy E in described Snake state equation
int.
Further, described accurate adjustment is carried out iteration accurate adjustment from low to high successively according to the resolution of described galactophore image.
Further, before described accurate adjustment, edge-smoothing operation is carried out in described the second chest muscle region.
Further, obtain before described the first chest muscle region the direction of mammary gland in first described judgement image;
Further, the method for described judgement mammary gland direction comprises the steps:
Get any a line 1 and the middle column m that in described galactophore image, contain mammary gland part, it is Part III and Part IV that described the 1st row and m are listed as the first half symmetry division of described the first image;
Calculate the average gray T of described third and fourth two parts image
rightand T
left;
If T
right>T
left, mammary gland is positioned at the right side of described the first image;
If T
right<T
left, mammary gland is positioned at the left side of described the first image.
Compared with prior art, the present invention has the following advantages: (1) the invention provides a kind of cut apart chest muscle in galactophore image method, can in the process of region growing, regulate in real time threshold value by morphologic limiting adaptive ground, thereby effectively inhibition is overflowed on a large scale; (2) the present invention can effectively remove overflowing among a small circle by removing the method (method of Rolling Ball) of lofty structure, greatly improves the robustness of algorithm; (3) the present invention can carry out to chest muscle edge accurate adjustment on multiple dimensioned galactophore image, effectively ensures the flatness at chest muscle edge in accurate adjustment process, makes segmentation result more accurate; (4) the method applicability is wide, accuracy is high, can effectively cut apart multi-grey level, edge fog, the irregular chest muscle in edge.
Brief description of the drawings
Figure 1 shows that the method flow schematic diagram of cutting apart chest muscle in one embodiment of the invention in galactophore image;
Figure 2 shows that the method flow schematic diagram of determining mammary gland direction in one embodiment of the invention;
Figure 3 shows that the schematic diagram of Part III and Part IV in one embodiment of the invention;
Figure 4 shows that the area schematic of morphology restriction in one embodiment of the invention;
Figure 5 shows that the method flow schematic diagram of the region growing of morphology restriction in one embodiment of the invention;
Figure 6 shows that the method flow schematic diagram that defines morphology restriction in one embodiment of the invention;
Figure 7 shows that Part I in one embodiment of the invention and second 's schematic diagram;
Figure 8 shows that the first method flow schematic diagram of proofreading and correct in one embodiment of the invention;
Figure 9 shows that the schematic flow sheet of removing lofty structure operation in one embodiment of the invention;
Figure 10 shows that the schematic diagram of lofty structure in one embodiment of the invention;
Figure 11 shows that the local enlarged diagram of R part in Figure 10;
Figure 12 shows that the schematic flow sheet of accurate adjustment in one embodiment of the invention;
Figure 13 a～13e is each stage result schematic diagram of cutting apart chest muscle in one embodiment of the invention.
Embodiment
A lot of details are set forth in the following description so that fully understand the present invention.But the present invention can implement to be much different from alternate manner described here, and those skilled in the art can do similar popularization without prejudice to intension of the present invention in the situation that, and therefore the present invention is not subject to the restriction of following public concrete enforcement.
Secondly, the present invention utilizes schematic diagram to be described in detail, and in the time that the embodiment of the present invention is described in detail in detail, for ease of explanation, described schematic diagram is example, and it should not limit the scope of protection of the invention at this.
In order to solve the technical matters in background technology, the invention provides a kind of cut apart chest muscle in galactophore image method, first adopt the region growing method of morphology restriction, in the morphology restricted area of definition, automatically adjust threshold parameter, regulate in real time threshold value, effectively inhibition is overflowed on a large scale, avoid the shortcoming of available technology adopting empirical value method, improve applicability of the present invention and accuracy; Then adopt the method (Rolling Ball) of the lofty structure of removal and the method on Snake algorithm optimization chest muscle border to carry out the first correction to region growing structure, effectively cut apart multi-grey level, edge fog, the irregular chest muscle in edge.
Describe the present invention below in conjunction with accompanying drawing.As shown in cutting apart the method flow schematic diagram of chest muscle in the galactophore image of Fig. 1 one embodiment of the invention, described method comprises the steps:
First, execution step S10: determine mammary gland direction in described galactophore image, be convenient to follow-up unified operation; The method of described definite mammary gland direction is as shown in determining the method flow schematic diagram of mammary gland direction in Fig. 2 one embodiment of the invention, described method comprises the steps:
First, execution step S11: get any a line 1 of containing mammary gland part in described galactophore image and the middle column m of described galactophore image, described the 1st row and m are listed as described galactophore image is divided into Part III 3 and Part IV 4 as shown in Figure 3;
Then, execution step S12～S13: the average gray T that calculates respectively image in described Part III 3 and Part IV 4
rightand T
left, the relatively size of two values:
If T
right>T
left, mammary gland is positioned at the right side of described the first image;
If T
right< T
left, mammary gland is positioned at the left side of described the first image.
Preferably, in the present embodiment, adopt mammary gland direction to be positioned at image left side, in the time that mammary gland is positioned at the right side of described galactophore image, make mammary gland be positioned at the left side of described galactophore image Image Reversal.
Then, execution step S20: galactophore image is carried out to region growing in the morphology restricted area as shown in the area schematic of morphology restriction in Fig. 4 one embodiment of the invention.
The method of the region growing of described morphology restriction is as shown in the method flow schematic diagram of the region growing of morphology restriction in Fig. 5 one embodiment of the invention, and described method comprises the steps:
First, execution step S21: definition morphology restriction; Be different from prior art, in the present embodiment, region growing is to carry out in the region of morphology restriction, and effectively large-scale overflow problem in the growth of control area, improves the accuracy that chest muscle is cut apart.The method of described definition morphology restriction is as shown in defining the method flow schematic diagram of morphology restriction in Fig. 6 one embodiment of the invention:
Execution step S211: defining point p and some q on described galactophore image;
Defining point p (1, y): the separation of getting chest muscle and breast in galactophore image the first row is a some p; Conventionally in the galactophore image of MLO position, chest muscle is triangular in shape, in entire image, there is high or the highest brightness, the boundary of general the first row chest muscle part and background or breast part is comparatively clear, and image below is due to the existence of body of gland, focus or other tissue, the boundary of chest muscle and other parts thickens, therefore be chosen at the separation of described galactophore image the first row chest muscle and breast in the present embodiment for a p, be convenient to anchor point p quickly and accurately.
Defining point q (x, 1): get the line number m at peaked some place of the col width of breast in galactophore image, and it is capable to move down c, order point x=m+c that q is expert at; Because breast shape is different, the separation of chest muscle lower end is not necessarily at the col width maximal value place of breast, so, the line number m at a peaked col width place is moved down to c capable, be expert at as a q, make to comprise as far as possible chest muscle region, improve the accuracy of cutting apart chest muscle.
Determine complete some p and put after q, execution step S212: the line pq that gets described some p and some q, described line pq is divided into image as shown in the schematic diagram of Part I 1 in Fig. 7 one embodiment of the invention and Part II 2, wherein said Part I 1 is the mammary gland parts of images near thoracic cavity one side, chooses the region of described Part I 1 for described morphology restriction.
Continue execution step S22: the adaptive region that described galactophore image is carried out to morphology restriction increases, and is limited to: th under the threshold value of described region growing
l=(1-t) * (T
max+ T
min)/2, wherein, T
maxand T
minbe respectively maximal value and the minimum value of current growth district.
Then perform step S23: the size of the area S ' of growth district and the difference △ S of the area S of described Part I 1 and the area S of described Part I more, if △ S≤a*S obtains described the first chest muscle region;
Otherwise, adjust parametric t=t*b, and repeating said steps S22 and S33; Wherein a, b, t are the constant between (0,1).
It should be noted that, in the present embodiment, the threshold value lower limit th of described region growing
lbe that passing threshold parametric t regulates in real time, effectively prevent overflowing in threshold value propagation process, the chest muscle that is applicable to the galactophore image of different gray scales is cut apart.In the present embodiment, preferably the size of a is 0.1, in the time that difference in areas △ S exceedes the region area 1/10 of described morphology restriction, adjust parametric t=t*b, in the present embodiment, the size of t is preferably 0.4, and the size of described b is preferably 0.9, brings the parameter after adjusting into th
l=(1-t) * (T
max+ T
minin)/2, re-start region growing, until meet morphology restriction.
In the present embodiment, adopt the region growing of morphology restriction, can be in the process of region growing, utilize morphology restriction automatically to adjust adaptive threshold parametric t, thereby regulate in real time threshold value th
l, effectively suppress to overflow on a large scale in propagation process, improve the accuracy of cutting apart chest muscle.
After described the first chest muscle region is determined, continue execution step S30: the first correction is carried out in described the first chest muscle region, increase for the adaptive region of optimizing, the above-mentioned morphology of accurate adjustment limits the chest muscle edges of regions obtaining, improve the accuracy that chest muscle is cut apart.The described first method of proofreading and correct is as shown in the first method flow schematic diagram of proofreading and correct in Fig. 8 one embodiment of the invention:
First perform step S31: lofty structure operation is removed in described the first chest muscle region, obtain the second chest muscle region; Described lofty structure refers in the region growing process of morphology restriction, at the irregular structure of described the first chest muscle edges of regions, may be some breast bodies of gland, or lesion tissue, or some overflowing among a small circle, cause the over-segmentation of chest muscle, in order to improve the accuracy of chest muscle dividing method in the present embodiment galactophore image, need to remove lofty structure.
Particularly, the lofty structure operation of described removal, as shown in removing the schematic flow sheet of lofty structure operation in Fig. 9 one embodiment of the invention, comprises the steps:
Execution step S311: first travel through all points in described the first chest muscle edges of regions, get any two terminal A and B, connect A, B two-end-point formation straight line AB, particularly choose two end points of any one lofty structure in described the first chest muscle edges of regions, as shown in Figure 10 and Figure 11; Then perform step S312～S313: if straight line AB meets following three conditions simultaneously: a) straight line AB distance
b) straight line AB is positioned at described the first chest muscle intra-zone; C) straight line AB is apart from d
aB<d*C; Remove lofty structure, be about to the straight line AB of connection A, B two-end-point as the border of described chest muscle; If not, do not deal with, retain this lofty structure.
Wherein, described L is the overall length of described the first chest muscle region mesothorax flesh and mammary gland adjacent boundary, and described condition is a) for controlling the bore width of lofty structure; For the lofty structure that meets bore width, conjugation condition judged result c) determines whether to remove lofty structure; Described condition b) is defined in described the first chest muscle intra-zone by the operation of removing lofty structure; Described C is the chest muscle edge overall length that connects 2 of A B in described the first chest muscle region, and described condition c), for controlling the lofty degree of lofty structure, is removed lofty structure in this case by conditional operation; Described d is greater than 1 constant, preferred d=2 in the present embodiment.
In the present embodiment, adopt Rolling Ball to remove lofty structure, can effectively optimize cutting apart of chest muscle to the condition of three groups of AND operations that arrange in Rolling Ball method, particularly in above-mentioned zone propagation process, overflow among a small circle part, for example elongated body of gland part, by the intersection operation of condition setting, for example, control the lofty degree of lofty structure and distinguish chest muscle and body of gland part, thereby obtain effectively cutting apart of chest muscle part.
Finally, execution step S40: accurate adjustment is carried out in described the second chest muscle region on the galactophore image of n kind yardstick, obtain the galactophore image of cutting apart chest muscle region;
Particularly, described accurate adjustment operation, as shown in the schematic flow sheet of accurate adjustment operation in Figure 12 one embodiment of the invention, comprises the steps:
First, execution step S41, carries out edge-smoothing operation to described the second chest muscle region obtaining; Then perform step S42～S43: all points on the border in described the second chest muscle region after traversal is level and smooth, get any one frontier point, make the normal of described frontier point; get frontier point and described frontier point adjacent at least 2 pixels in normal direction; the gray-scale value of at least 3 pixels described in calculating, the difference that defines the gray-scale value of adjacent 2 is gradient; Determine gradient maximum point, the mode of described gradient maximum point and gradient definition is relevant, if forward gradient before being exactly a bit, backward gradient after being exactly a bit, the renewal coordinate that to define image coordinate that described gradient maximum point is corresponding be described frontier point.Then, execution step S44: the renewal coordinate that above-mentioned steps is obtained is brought in the state equation of Snake algorithm, adopt Snake algorithm accurate adjustment chest muscle border in the second chest muscle region of the galactophore image of n kind yardstick, described in final acquisition, cut apart the galactophore image in chest muscle region, wherein, described n is more than or equal to 1 positive integer.
Wherein, the state equation of described Snake algorithm is: E
snake=E
int+ E
ext, described renewal coordinate is E in described Snake state equation
extexternal energy; The flatness on described chest muscle border is the internal energy E in described Snake state equation
int, for maintaining the flatness at chest muscle edge, restriction external energy E
extexcessive variation, the renewal coordinate that ought choose is abnormal, such as, in galactophore image, have the tissue of the high brightness such as body of gland because of frontier point, the greatest gradient value point calculating is not the boundary of chest muscle and breast, cause obtain renewal coordinate abnormal.
Wherein, described accurate adjustment process is carried out accurate adjustment from low to high successively according to the resolution of described galactophore image, the galactophore image that for example former figure size is 100 × 100, by its down-sampled be 50 × 50 to resolution, further down-sampled is 25 × 25 to resolution.First chest muscle border is then adjusted in accurate adjustment chest muscle border in the second chest muscle region in adjusting galactophore image in 25 × 25 low resolution in 50 × 50 resolution, finally on former Figure 100 × 100, adjusts chest muscle border.By resolution galactophore image from low to high being carried out to the accurate adjustment chest muscle border operation of Snake algorithm, reduce noise and the interference of surrounding structure to Snake algorithm, improve the accuracy of optimizing border result.If Figure 13 a～13e is each stage result schematic diagram of cutting apart chest muscle in one embodiment of the invention.
In the present embodiment by the galactophore image of different scale, the edge in described the second chest muscle region being carried out to accurate adjustment, thereby effectively optimized for multi-grey level, edge fog or irregular chest muscle, improve chest muscle accuracy and the robustness cut apart.
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; can utilize method and the technology contents of above-mentioned announcement to make possible variation and amendment to technical solution of the present invention; therefore; every content that does not depart from technical solution of the present invention; any simple modification, equivalent variations and the modification above embodiment done according to technical spirit of the present invention, all belong to the protection domain of technical solution of the present invention.
Claims (10)
1. a method of cutting apart chest muscle in galactophore image, is characterized in that, comprises the steps:
Galactophore image is carried out to the region growing of morphology restriction, obtain the first chest muscle region;
The first correction is carried out in described the first chest muscle region, obtain the galactophore image of cutting apart chest muscle region.
2. the method for cutting apart chest muscle in galactophore image as claimed in claim 1, is characterized in that, the region growing of described morphology restriction comprises the steps:
(1) definition morphology restriction;
(2) carry out morphology restriction adaptive region increase, under the threshold value of described region growing, be limited to: th
l=(1-t) * (T
max+ T
min)/2
Wherein T
maxand T
minbe respectively maximal value and the minimum value of current growth district;
(3) judgement: if difference △ S≤a*S of the area S ' of growth district and the area S of morphology restricted area obtains described the first chest muscle region;
Otherwise, adjust parametric t=t*b, and repeating said steps (2) and (3);
Wherein a, b, t are the constant between (0,1).
3. the method for cutting apart chest muscle in galactophore image as claimed in claim 2, is characterized in that, described definition morphology restriction comprises the steps: on described galactophore image
(1) defining point p (1, y): the separation of getting chest muscle and breast in galactophore image the first row is a some p;
(2) defining point q (x, 1): get the line number m at peaked some place of the col width of breast in galactophore image, and it is capable to move down c, order point x=m+c that q is expert at;
(3) get described some p and the line pq that puts q, image is divided into Part I and Part II by described line pq, and described Part I is the region of described morphology restriction.
4. the method for cutting apart chest muscle in galactophore image as claimed in claim 1, is characterized in that, described the first correction comprises the steps:
(1) lofty structure operation is removed in described the first chest muscle region, obtain the second chest muscle region;
(2) accurate adjustment is carried out in described the second chest muscle region on the galactophore image of n kind yardstick, obtain the galactophore image of cutting apart chest muscle region;
Wherein, described n is more than or equal to 1 positive integer.
5. the method for cutting apart chest muscle in galactophore image as claimed in claim 4, is characterized in that, the lofty structure operation of described removal comprises the steps:
Travel through all points in described the first chest muscle edges of regions, get any two terminal A and B, connect A, B two-end-point formation straight line AB, if straight line AB meets simultaneously:
A) straight line AB distance
B) straight line AB is positioned at described the first chest muscle intra-zone;
C) straight line AB is apart from d
aB<d*C;
Remove lofty structure;
If not, do not deal with;
Wherein, described L is the overall length of described the first chest muscle region mesothorax flesh and mammary gland adjacent boundary; Described C is the chest muscle edge overall length that connects 2 of A, B in described the first chest muscle region; Described d is greater than 1 constant.
6. the method for cutting apart chest muscle in galactophore image as claimed in claim 4, is characterized in that, described accurate adjustment comprises the steps:
(1) get the frontier point of described the second chest muscle region mesothorax flesh, get any one frontier point, make the normal of described frontier point, get frontier point and frontier point adjacent at least 2 pixels in normal direction;
(2) gray-scale value of at least 3 pixels described in calculating, the difference that defines the gray-scale value of adjacent 2 is gradient;
(3) determine gradient maximum point, the renewal coordinate that to define image coordinate that this point is corresponding be described frontier point;
(4) in the second chest muscle region the border of accurate adjustment chest muscle in the galactophore image of n kind yardstick to adopt Snake algorithm, cuts apart the galactophore image in chest muscle region described in acquisition.
Wherein, the state equation of described Snake algorithm is:
State equation E
snake=E
int+ E
ext;
Described renewal coordinate is E in described Snake state equation
extexternal energy; The flatness on described chest muscle border is the internal energy E in described Snake state equation
int.
7. the method for cutting apart chest muscle in the galactophore image as described in claim 4 or 6, is characterized in that, described accurate adjustment is carried out iteration accurate adjustment from low to high successively according to the resolution of described galactophore image.
8. the method for cutting apart chest muscle in galactophore image as claimed in claim 4, is characterized in that, before described accurate adjustment, edge-smoothing operation is carried out in described the second chest muscle region.
9. the method for cutting apart chest muscle in galactophore image as claimed in claim 1, is characterized in that, obtains before described the first chest muscle region the direction of mammary gland in first described judgement image.
10. the method for cutting apart chest muscle in galactophore image as claimed in claim 1, is characterized in that, the method for described judgement mammary gland direction comprises the steps:
Get any a line 1 and the middle column m that in described galactophore image, contain mammary gland part, it is Part III and Part IV that described the 1st row and m are listed as the first half symmetry division of described the first image;
Calculate the average gray T of described third and fourth two parts image
rightand T
left;
If T
right>T
left, mammary gland is positioned at the right side of described the first image;
If T
right<T
left, mammary gland is positioned at the left side of described the first image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410028053.4A CN104182965B (en) | 2014-01-22 | 2014-01-22 | The method of chest muscle is split in a kind of galactophore image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410028053.4A CN104182965B (en) | 2014-01-22 | 2014-01-22 | The method of chest muscle is split in a kind of galactophore image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104182965A true CN104182965A (en) | 2014-12-03 |
| CN104182965B CN104182965B (en) | 2016-03-30 |
Family
ID=51963983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410028053.4A Active CN104182965B (en) | 2014-01-22 | 2014-01-22 | The method of chest muscle is split in a kind of galactophore image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104182965B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447879A (en) * | 2015-12-15 | 2016-03-30 | 上海联影医疗科技有限公司 | Method and apparatus for detecting breast muscle in breast image |
| TWI587844B (en) * | 2016-01-28 | 2017-06-21 | 太豪生醫股份有限公司 | Medical image processing apparatus and breast image processing method thereof |
| US9959617B2 (en) | 2016-01-28 | 2018-05-01 | Taihao Medical Inc. | Medical image processing apparatus and breast image processing method thereof |
| US10297024B2 (en) | 2015-09-30 | 2019-05-21 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for determining a breast region in a medical image |
| CN113393475A (en) * | 2021-06-30 | 2021-09-14 | 神州医疗科技股份有限公司 | Mammary gland molybdenum target image segmentation device, electronic equipment, medical equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334895B (en) * | 2008-08-07 | 2011-09-14 | 清华大学 | Image division method aiming at dynamically intensified mammary gland magnetic resonance image sequence |
| CN101612047B (en) * | 2004-08-03 | 2013-03-06 | 株式会社东芝 | Image displaying apparatus |
| US20130223711A1 (en) * | 2012-02-24 | 2013-08-29 | Riverain Technologies, LLC | Maching Learning Techniques for Pectoral Muscle Equalization and Segmentation in Digital Mammograms |
| CN103473767A (en) * | 2013-09-05 | 2013-12-25 | 中国科学院深圳先进技术研究院 | Segmentation method and system for abdomen soft tissue nuclear magnetism image |
-
2014
- 2014-01-22 CN CN201410028053.4A patent/CN104182965B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101612047B (en) * | 2004-08-03 | 2013-03-06 | 株式会社东芝 | Image displaying apparatus |
| CN101334895B (en) * | 2008-08-07 | 2011-09-14 | 清华大学 | Image division method aiming at dynamically intensified mammary gland magnetic resonance image sequence |
| US20130223711A1 (en) * | 2012-02-24 | 2013-08-29 | Riverain Technologies, LLC | Maching Learning Techniques for Pectoral Muscle Equalization and Segmentation in Digital Mammograms |
| CN103473767A (en) * | 2013-09-05 | 2013-12-25 | 中国科学院深圳先进技术研究院 | Segmentation method and system for abdomen soft tissue nuclear magnetism image |
Non-Patent Citations (1)
| Title |
|---|
| 徐伟栋等: "基于模型的乳腺X线图像胸肌分割算法研究", 《浙江大学学报（工学版）》, vol. 39, no. 3, 31 March 2005 (2005-03-31), pages 427 - 432 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10297024B2 (en) | 2015-09-30 | 2019-05-21 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for determining a breast region in a medical image |
| US10636143B2 (en) | 2015-09-30 | 2020-04-28 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for determining a breast region in a medical image |
| US11250567B2 (en) | 2015-09-30 | 2022-02-15 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for determining a breast region in a medical image |
| CN105447879A (en) * | 2015-12-15 | 2016-03-30 | 上海联影医疗科技有限公司 | Method and apparatus for detecting breast muscle in breast image |
| CN105447879B (en) * | 2015-12-15 | 2018-04-03 | 上海联影医疗科技有限公司 | The method and device of chest muscle is detected in breast image |
| TWI587844B (en) * | 2016-01-28 | 2017-06-21 | 太豪生醫股份有限公司 | Medical image processing apparatus and breast image processing method thereof |
| US9959617B2 (en) | 2016-01-28 | 2018-05-01 | Taihao Medical Inc. | Medical image processing apparatus and breast image processing method thereof |
| CN113393475A (en) * | 2021-06-30 | 2021-09-14 | 神州医疗科技股份有限公司 | Mammary gland molybdenum target image segmentation device, electronic equipment, medical equipment and medium |
| CN113393475B (en) * | 2021-06-30 | 2024-02-20 | 神州医疗科技股份有限公司 | Mammary gland molybdenum target image segmentation device, electronic equipment, medical equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104182965B (en) | 2016-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101576997B (en) | Abdominal organ segmentation method based on secondary three-dimensional region growth | |
| CN104182965B (en) | The method of chest muscle is split in a kind of galactophore image | |
| CN109840913B (en) | Method and system for segmenting tumor in mammary X-ray image | |
| CN105654501B (en) | Self-adaptive image segmentation method based on fuzzy threshold | |
| CN103903254A (en) | X-ray image processing method and system and X-ray image processing equipment | |
| CN104376551A (en) | Color image segmentation method integrating region growth and edge detection | |
| CN103164855B (en) | A kind of Bayesian decision foreground extracting method in conjunction with reflected light photograph | |
| CN109753997B (en) | Automatic accurate robust segmentation method for liver tumor in CT image | |
| CN101714252A (en) | Method for extracting road in SAR image | |
| CN105389811A (en) | Multi-modality medical image processing method based on multilevel threshold segmentation | |
| KR102519515B1 (en) | Information processing device, information processing method, computer program | |
| CN104574327A (en) | Mammary gland image processing method and device | |
| Li et al. | Watershed algorithm based on morphology for dental X-ray images segmentation | |
| CN115147710A (en) | Sonar image target processing method based on heterogeneous filtering detection and level set segmentation | |
| CN103700085A (en) | Cutting method of pectoral muscle region in mammary gland X-ray image | |
| CN107154036A (en) | Blood vessel segmentation method and its segmenting system based on sub-pix | |
| Husain et al. | Image segmentation with improved watershed algorithm using radial bases function neural networks | |
| CN106447659B (en) | A kind of region growing detection method based on multiple decision | |
| CN117314793B (en) | Building construction data acquisition method based on BIM model | |
| CN103839244A (en) | Real-time image fusion method and device | |
| Ibánez et al. | Genetic approaches for topological active nets optimization | |
| CN110930330B (en) | Image segmentation and region growth based salt and pepper noise reduction algorithm | |
| CN107909610A (en) | A kind of gray scale target perimeter evaluation method based on image grain and sub-pix border detection | |
| Essaf et al. | An improved lung parenchyma segmentation using the maximum inter-class variance method (OTSU) | |
| CN107563992B (en) | Method and device for detecting breast skin line |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 201815 No. 1180 Xingxian Road, Jiading Industrial Zone, Jiading District, Shanghai Patentee after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201815 No. 1180 Xingxian Road, Jiading Industrial Zone, Jiading District, Shanghai Patentee before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 201807 2258 Chengbei Road, Jiading District, Shanghai Patentee after: Shanghai Lianying Medical Technology Co.,Ltd. Address before: 201815 No. 1180 Xingxian Road, Jiading Industrial Zone, Jiading District, Shanghai Patentee before: Shanghai Lianying Medical Technology Co.,Ltd. |