CN109512547A - A kind of breast prosthesis construction method and device based on k-means - Google Patents
A kind of breast prosthesis construction method and device based on k-means Download PDFInfo
- Publication number
- CN109512547A CN109512547A CN201811466626.6A CN201811466626A CN109512547A CN 109512547 A CN109512547 A CN 109512547A CN 201811466626 A CN201811466626 A CN 201811466626A CN 109512547 A CN109512547 A CN 109512547A
- Authority
- CN
- China
- Prior art keywords
- breast
- user
- point cloud
- cloud chart
- chart picture
- 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
- 210000000481 breast Anatomy 0.000 title claims abstract description 264
- 238000010276 construction Methods 0.000 title claims abstract description 14
- 210000002445 nipple Anatomy 0.000 claims description 38
- 238000000034 method Methods 0.000 claims description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 239000006071 cream Substances 0.000 claims description 7
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 206010006187 Breast cancer Diseases 0.000 description 3
- 208000026310 Breast neoplasm Diseases 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 206010051131 Mastoptosis Diseases 0.000 description 1
- 208000035965 Postoperative Complications Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 210000005075 mammary gland Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
- A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
- A61F2/02—Prostheses implantable into the body
- A61F2/12—Mammary prostheses and implants
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
- A61F2240/00—Manufacturing or designing of prostheses classified in groups A61F2/00 - A61F2/26 or A61F2/82 or A61F9/00 or A61F11/00 or subgroups thereof
- A61F2240/001—Designing or manufacturing processes
- A61F2240/002—Designing or making customized prostheses
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Transplantation (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Artificial Intelligence (AREA)
- Vascular Medicine (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Cardiology (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of breast prosthesis construction method and device based on k-means, the point cloud chart picture including obtaining user's breast, the characteristic of user's breast is obtained according to the point cloud chart picture of user's breast;The corresponding cluster centre of characteristic of user's breast is matched, and using the breast shape of the cluster centre as the breast shape of user's breast;User's breast prosthesis is constructed according to user's breast shape;Wherein, the characteristic of the breast in the point cloud chart picture for the breast that the cluster centre is acquired according to history obtains;The present invention obtains cluster centre according to the breast point cloud chart picture that history acquires, it is contemplated that individual difference, the present invention obtain prosthese and more match with the breast grown naturally.
Description
Technical field
The present invention relates to medical prosthetic manufacturing fields, and in particular to a kind of breast prosthesis construction method based on k-means
And device.
Background technique
Breast cancer is the highest malignant tumour of women disease incidence, and breast modified radical mastectomy is the most widely used hand of China
Art method.But patient finishes that mammary cancer radical operation is postoperative to lose breast, bears physiology and psychological double blow, generates bad feelings
Thread influences the interpersonal relationships and family life of patient.So thus breast reconstruction generates and develops, and it is increasingly becoming breast cancer
The important component for the treatment of.
Chinese women breast volume is relatively small, and mammary gland shape is not good enough after traditional Breast-consering surgery;And latissimus dorsi myocutaneous flap and
TRAM Flap breast reconstruction operating difficulty is high, wound is big, postoperative complications are more, so silicone is implanted into breast weight
Building is presently preferred selection.
It is hemispherical that the prior art, which obtains prosthese, does not account for individual difference, so on the breast shape after prosthese reconstruction
It is mostly relatively round and unnatural, it is difficult to form the natural shape of mastoptosis, and the breast grown naturally has notable difference.
Summary of the invention
In view of the deficiencies of the prior art, in the purpose of the present invention is being clustered using the breast point cloud chart picture of history acquisition
The matched prosthese breast prosthesis of breast that the heart is constructed and grown naturally.
The purpose of the present invention is adopt the following technical solutions realization:
The present invention provides a kind of breast prosthesis construction method based on k-means, it is improved in that the method packet
It includes:
The point cloud chart picture for obtaining user's breast obtains the characteristic of user's breast according to the point cloud chart picture of user's breast
According to;
The corresponding cluster centre of characteristic of user's breast is matched, and using the breast shape of the cluster centre as use
The breast shape of family breast;
User's breast prosthesis is constructed according to user's breast shape;
Wherein, the characteristic of the breast in the point cloud chart picture for the breast that the cluster centre is acquired according to history obtains.
Preferably, the point cloud chart picture for obtaining user's breast, comprising:
The point cloud chart picture of user's breast is obtained using laser scanner.
Preferably, the characteristic that user's breast is obtained according to the point cloud chart picture of user's breast, comprising:
The teat placement of the point cloud chart picture of user's breast is obtained using algorithm of region growing;
The point cloud chart picture of user's breast is projected into two-dimensional surface, obtains user's breast in the two-dimensional surface
Teat placement, and search for user's breast lower pleat coordinate in the two-dimensional surface;
According to teat placement and the lower pleat coordinate acquisition user cream of the user's breast in the two-dimensional surface
The characteristic in room;
Wherein, the characteristic includes: teat placement of user's breast in the two-dimensional surface to breast lower edge
Distance, teat placement to breast top edge distance, teat placement to breast left edge apart from, teat placement to breast right hand edge away from
From, teat placement away from length and breast height between lower pleat coordinate distance, submammary fold coordinate.
Further, the teat placement of the point cloud chart picture that user's breast is obtained using algorithm of region growing, packet
It includes:
S101. using the point cloud chart of user's breast as mean curvature is worth the smallest pixel is as the seed of algorithm of region growing
Point;
S102. the neighbor pixel point of the seed point is obtained, if the neighbor pixel point of the seed point and the seed point
Normal angle difference and the curvature value of neighbor pixel point be respectively less than corresponding cluster of preset threshold value and the seed point
Points are less than preset cluster maximum number of points, then the neighbor pixel point are added in corresponding cluster of the seed point;
S103. the pixel in described cluster is deleted from the point cloud chart picture of user's breast, if the user is newborn
Remaining pixel number is less than preset cluster minimal point in the point cloud chart picture in room, then goes to step S104, otherwise return to institute
State step S101;
S104. pixel is counted into position of the smallest cluster in point cloud chart picture as the point cloud chart of user's breast
The teat placement of picture.
Further, described search user breast lower pleat coordinate in the two-dimensional surface, comprising:
The two-dimensional surface is searched for using 3 × 3 regions of search, if the pixel points that 3 × 3 regions of search search are less than
Otherwise preset value then gives up any of second second column region of row pixel in 3 × 3 region of search as boundary point
The region searched is abandoned, until the whole region of the two-dimensional surface is searched;
The slope value of boundary point two boundary points adjacent thereto is obtained, if two slope value one is negative for positive number one
Number, then using the coordinate of the boundary point as the coordinate of lower pleat.
Preferably, the characteristic of the breast in the point cloud chart picture of the breast according to history acquisition obtains the cluster
The process at center includes:
Using the characteristic of the breast in the point cloud chart picture of the breast of history acquisition as the sample number of k-means algorithm
According to;
Classified using k-means algorithm to sample data, and obtains the corresponding cluster centre of each classification results.
Preferably, the corresponding cluster centre of characteristic of matching user's breast, and by the cream of the cluster centre
Breast shape of the room form as user's breast, comprising:
If the Euclidean distance in the characteristic and classification results of user's breast between the characteristic of cluster centre i is most short,
Then user's breast belongs to the i-th class, and i ∈ (1, k), k are classification sum in classification results;
It finds with cluster centre i in the i-th class data apart from shortest sample data, and by the breast shape of the sample data
Breast shape of the state as user's breast.
Further, the acquisition process of the breast shape of the sample data includes:
The corresponding point cloud chart picture of the sample data is handled using non-uniform rational B-spline method, obtains the sample number
According to breast shape.
The present invention provides a kind of breast prosthesis construction device based on k-means, it is improved in that described device packet
It includes:
Characteristic obtains module, for obtaining the point cloud chart picture of user's breast, according to the point cloud chart of user's breast
Characteristic as obtaining user's breast;
Breast shape obtains module, the corresponding cluster centre of characteristic for matching user's breast, and described will gather
Breast shape of the breast shape at class center as user's breast;
Prosthese constructs module, for constructing user's breast prosthesis according to user's breast shape;
Wherein, the characteristic of the breast in the point cloud chart picture for the breast that the cluster centre is acquired according to history obtains.
Compared with the immediate prior art, the invention has the benefit that
The present invention provides a kind of breast prosthesis construction method and device based on k-means, obtains the point cloud of user's breast
Image obtains the characteristic of user's breast according to the point cloud chart picture of user's breast;Match the characteristic of user's breast
Corresponding cluster centre, and using the breast shape of the cluster centre as the breast shape of user's breast;According to the user
Breast shape constructs user's breast prosthesis;Wherein, the cream in the point cloud chart picture for the breast that the cluster centre is acquired according to history
The characteristic in room obtains;The present invention obtains cluster centre according to the breast point cloud chart picture that history acquires, it is contemplated that individual difference
It is different, it is more matched with the breast grown naturally.
Detailed description of the invention
Fig. 1 is breast prosthesis construction method flow chart of the present invention;
Fig. 2 is breast prosthesis construction device schematic diagram of the present invention.
Specific embodiment
Specific embodiments of the present invention will be described in further detail with reference to the accompanying drawing.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
All other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
The present invention provides a kind of breast prosthesis construction method based on k-means, as shown in Figure 1, which comprises
Step 1. obtains the point cloud chart picture of user's breast, according to the point cloud chart of user's breast as obtaining user's breast
Characteristic;
Step 2. matches the corresponding cluster centre of characteristic of user's breast, and by the breast shape of the cluster centre
Breast shape as user's breast;
Step 3. constructs user's breast prosthesis according to user's breast shape;
Wherein, the characteristic of the breast in the point cloud chart picture for the breast that the cluster centre is acquired according to history obtains.
The point cloud chart picture of user's breast is obtained in step 1, comprising:
The point cloud chart picture of user's breast is obtained using laser scanner.
The characteristic of user's breast is obtained in step 1 according to the point cloud chart picture of user's breast, comprising:
The teat placement of the point cloud chart picture of user's breast is obtained using algorithm of region growing;
The point cloud chart picture of user's breast is projected into two-dimensional surface, obtains user's breast in the two-dimensional surface
Teat placement, and search for user's breast lower pleat coordinate in the two-dimensional surface;
According to teat placement and the lower pleat coordinate acquisition user cream of the user's breast in the two-dimensional surface
The characteristic in room;
Wherein, the characteristic includes: teat placement of user's breast in the two-dimensional surface to breast lower edge
Distance, teat placement to breast top edge distance, teat placement to breast left edge apart from, teat placement to breast right hand edge away from
From, teat placement away from length and breast height between lower pleat coordinate distance, submammary fold coordinate.
Further, the teat placement of the point cloud chart picture that user's breast is obtained using algorithm of region growing, packet
It includes:
S101. using the point cloud chart of user's breast as mean curvature is worth the smallest pixel is as the seed of algorithm of region growing
Point;
S102. the neighbor pixel point of the seed point is obtained, if the neighbor pixel point of the seed point and the seed point
Normal angle difference and the curvature value of neighbor pixel point be respectively less than corresponding cluster of preset threshold value and the seed point
Points are less than preset cluster maximum number of points, then the neighbor pixel point are added in corresponding cluster of the seed point;
S103. the pixel in described cluster is deleted from the point cloud chart picture of user's breast, if the user is newborn
Remaining pixel number is less than preset cluster minimal point in the point cloud chart picture in room, then goes to step S104, otherwise return to institute
State step S101;
S104. pixel is counted into position of the smallest cluster in point cloud chart picture as the point cloud chart of user's breast
The teat placement of picture.
In a preferred embodiment, the neighbor pixel point for obtaining the seed point is to utilize kd-tree in point cloud chart picture
Search for adjacent pixels point.
Further, described search user breast lower pleat coordinate in the two-dimensional surface, comprising:
The two-dimensional surface is searched for using 3 × 3 regions of search, if the pixel points that 3 × 3 regions of search search are less than
Otherwise preset value then gives up any of second second column region of row pixel in 3 × 3 region of search as boundary point
The region searched is abandoned, until the whole region of the two-dimensional surface is searched;
The slope value of boundary point two boundary points adjacent thereto is obtained, if two slope value one is negative for positive number one
Number, then using the coordinate of the boundary point as the coordinate of lower pleat.
Preferably, the characteristic of the breast in the point cloud chart picture of the breast according to history acquisition obtains the cluster
The process at center includes:
Using the characteristic of the breast in the point cloud chart picture of the breast of history acquisition as the sample number of k-means algorithm
According to;
Classified using k-means algorithm to sample data, and obtains the corresponding cluster centre of each classification results.
Preferably, the corresponding cluster centre of characteristic of matching user's breast, and by the cream of the cluster centre
Breast shape of the room form as user's breast, comprising:
If the Euclidean distance in the characteristic and classification results of user's breast between the characteristic of cluster centre i is most short,
Then user's breast belongs to the i-th class, and i ∈ (1, k), k are classification sum in classification results;
It finds with cluster centre i in the i-th class data apart from shortest sample data, and by the breast shape of the sample data
Breast shape of the state as user's breast.
Further, the acquisition process of the breast shape of the sample data includes:
The corresponding point cloud chart picture of the sample data is handled using non-uniform rational B-spline method, obtains the sample number
According to breast shape.
The present invention provides a kind of breast prosthesis construction device based on k-means, as shown in Fig. 2, described device includes:
Characteristic obtains module, for obtaining the point cloud chart picture of user's breast, according to the point cloud chart of user's breast
Characteristic as obtaining user's breast;
Breast shape obtains module, the corresponding cluster centre of characteristic for matching user's breast, and described will gather
Breast shape of the breast shape at class center as user's breast;
Prosthese constructs module, for constructing user's breast prosthesis according to user's breast shape;
Wherein, the characteristic of the breast in the point cloud chart picture for the breast that the cluster centre is acquired according to history obtains.
Preferably, the point cloud chart picture for obtaining user's breast, comprising:
The point cloud chart picture of user's breast is obtained using laser scanner.
Preferably, the characteristic acquisition module includes:
First acquisition unit, the nipple position of the point cloud chart picture for obtaining user's breast using algorithm of region growing
It sets;
Second acquisition unit obtains user's breast for the point cloud chart picture of user's breast to be projected to two-dimensional surface
Teat placement in the two-dimensional surface, and search for user's breast lower pleat coordinate in the two-dimensional surface;
Third acquiring unit, for the teat placement and lower pleat seat according to user's breast in the two-dimensional surface
Mark obtains the characteristic of user's breast;
Wherein, the characteristic includes: teat placement of user's breast in the two-dimensional surface to breast lower edge
Distance, teat placement to breast top edge distance, teat placement to breast left edge apart from, teat placement to breast right hand edge away from
From, teat placement away from length and breast height between lower pleat coordinate distance, submammary fold coordinate.
Further, the first acquisition unit is specifically used for:
S101. using the point cloud chart of user's breast as mean curvature is worth the smallest pixel is as the seed of algorithm of region growing
Point;
S102. the neighbor pixel point of the seed point is obtained, if the neighbor pixel point of the seed point and the seed point
Normal angle difference and the curvature value of neighbor pixel point be respectively less than corresponding cluster of preset threshold value and the seed point
Points are less than preset cluster maximum number of points, then the neighbor pixel point are added in corresponding cluster of the seed point;
S103. the pixel in described cluster is deleted from the point cloud chart picture of user's breast, if the user is newborn
Remaining pixel number is less than preset cluster minimal point in the point cloud chart picture in room, then goes to step S104, otherwise return to institute
State step S101;
S104. pixel is counted into position of the smallest cluster in point cloud chart picture as the point cloud chart of user's breast
The teat placement of picture.
Further, the second acquisition unit is specifically used for:
The two-dimensional surface is searched for using 3 × 3 regions of search, if the pixel points that 3 × 3 regions of search search are less than
Otherwise preset value then gives up any of second second column region of row pixel in 3 × 3 region of search as boundary point
The region searched is abandoned, until the whole region of the two-dimensional surface is searched;
The slope value of boundary point two boundary points adjacent thereto is obtained, if two slope value one is negative for positive number one
Number, then using the coordinate of the boundary point as the coordinate of lower pleat.
Preferably, the characteristic of the breast in the point cloud chart picture of the breast according to history acquisition obtains the cluster
The process at center includes:
Using the characteristic of the breast in the point cloud chart picture of the breast of history acquisition as the sample number of k-means algorithm
According to;
Classified using k-means algorithm to sample data, and obtains the corresponding cluster centre of each classification results.
Preferably, the breast shape obtains module and is specifically used for:
If the Euclidean distance in the characteristic and classification results of user's breast between the characteristic of cluster centre i is most short,
Then user's breast belongs to the i-th class, and i ∈ (1, k), k are classification sum in classification results;
It finds with cluster centre i in the i-th class data apart from shortest sample data, and by the breast shape of the sample data
Breast shape of the state as user's breast.
Further, the acquisition process of the breast shape of the sample data includes:
The corresponding point cloud chart picture of the sample data is handled using non-uniform rational B-spline method, obtains the sample number
According to breast shape.
In conclusion a kind of breast prosthesis construction method and device based on k-means provided by the invention, obtains user
The point cloud chart picture of breast obtains the characteristic of user's breast according to the point cloud chart picture of user's breast;Match user's breast
The corresponding cluster centre of characteristic, and using the breast shape of the cluster centre as the breast shape of user's breast;Root
User's breast prosthesis is constructed according to user's breast shape;Wherein, the point cloud for the breast that the cluster centre is acquired according to history
The characteristic of breast in image obtains;The present invention obtains cluster centre according to the breast point cloud chart picture that history acquires, and considers
The difference of individual, especially determines the coordinate and length of submammary fold, the prosthese for utilizing the present invention to obtain with give birth to naturally
Long breast more matches.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Finally it should be noted that: the above embodiments are merely illustrative of the technical scheme of the present invention and are not intended to be limiting thereof, to the greatest extent
Invention is explained in detail referring to above-described embodiment for pipe, it should be understood by those ordinary skilled in the art that: still
It can be with modifications or equivalent substitutions are made to specific embodiments of the invention, and without departing from any of spirit and scope of the invention
Modification or equivalent replacement, should all cover within the scope of the claims of the present invention.
Claims (9)
1. a kind of breast prosthesis construction method based on k-means, which is characterized in that the described method includes:
The point cloud chart picture for obtaining user's breast obtains the characteristic of user's breast according to the point cloud chart picture of user's breast;
The corresponding cluster centre of characteristic of user's breast is matched, and using the breast shape of the cluster centre as user's cream
The breast shape in room;
User's breast prosthesis is constructed according to user's breast shape;
Wherein, the characteristic of the breast in the point cloud chart picture for the breast that the cluster centre is acquired according to history obtains.
2. the method as described in claim 1, which is characterized in that the point cloud chart picture for obtaining user's breast, comprising:
The point cloud chart picture of user's breast is obtained using laser scanner.
3. the method as described in claim 1, which is characterized in that described to obtain user according to the point cloud chart picture of user's breast
The characteristic of breast, comprising:
The teat placement of the point cloud chart picture of user's breast is obtained using algorithm of region growing;
The point cloud chart picture of user's breast is projected into two-dimensional surface, obtains nipple of the user's breast in the two-dimensional surface
Position, and search for user's breast lower pleat coordinate in the two-dimensional surface;
User's breast is obtained according to teat placement of the user's breast in the two-dimensional surface and lower pleat coordinate
Characteristic;
Wherein, the characteristic include: teat placement of user's breast in the two-dimensional surface to breast lower edge distance,
Teat placement to breast top edge distance, teat placement to breast left edge distance, teat placement to breast right hand edge apart from, it is newborn
Head position is away from length and breast height between lower pleat coordinate distance, submammary fold coordinate.
4. method as claimed in claim 3, which is characterized in that described to obtain user's breast using algorithm of region growing
The teat placement of point cloud chart picture, comprising:
S101. using the point cloud chart of user's breast as mean curvature is worth the smallest pixel is as the seed point of algorithm of region growing;
S102. the neighbor pixel point of the seed point is obtained, if the method for the neighbor pixel point and the seed point of the seed point
The curvature value of line differential seat angle and neighbor pixel point is respectively less than the points of corresponding cluster of preset threshold value and the seed point
It is less than preset cluster maximum number of points, then the neighbor pixel point is added in corresponding cluster of the seed point;
S103. the pixel in described cluster is deleted from the point cloud chart picture of user's breast, if user's breast
Remaining pixel number is less than preset cluster minimal point in point cloud chart picture, then goes to step S104, otherwise return to the step
Rapid S101;
S104. using pixel count position of the smallest cluster in point cloud chart picture as the point cloud chart of user's breast as
Teat placement.
5. method as claimed in claim 3, which is characterized in that described search user breast lower pleat in the two-dimensional surface
Coordinate, comprising:
The two-dimensional surface is searched for using 3 × 3 regions of search, is preset if the pixel points that 3 × 3 regions of search search are less than
Otherwise value, then give up any of second second column region of row pixel in 3 × 3 region of search and search as boundary point
The region that rope arrives, until the whole region of the two-dimensional surface is searched;
The slope value for obtaining boundary point two boundary points adjacent thereto, if it is negative that two slope value one, which is positive number one,
Then using the coordinate of the boundary point as the coordinate of lower pleat.
6. the method as described in claim 1, which is characterized in that the cream in the point cloud chart picture of the breast according to history acquisition
The process that the characteristic in room obtains the cluster centre includes:
Using the characteristic of the breast in the point cloud chart picture of the breast of history acquisition as the sample data of k-means algorithm;
Classified using k-means algorithm to sample data, and obtains the corresponding cluster centre of each classification results.
7. the method as described in claim 1, which is characterized in that in the corresponding cluster of characteristic of matching user's breast
The heart, and using the breast shape of the cluster centre as the breast shape of user's breast, comprising:
If the Euclidean distance in the characteristic and classification results of user's breast between the characteristic of cluster centre i is most short, use
Family breast belongs to the i-th class, and i ∈ (1, k), k are classification sum in classification results;
It finds with cluster centre i in the i-th class data apart from shortest sample data, and the breast shape of the sample data is made
For the breast shape of user's breast.
8. the method for claim 7, which is characterized in that the acquisition process of the breast shape of the sample data includes:
The corresponding point cloud chart picture of the sample data is handled using non-uniform rational B-spline method, obtains the sample data
Breast shape.
9. a kind of breast prosthesis construction device based on k-means, which is characterized in that described device includes:
Characteristic obtains module and is obtained for obtaining the point cloud chart picture of user's breast according to the point cloud chart picture of user's breast
Take the characteristic of family breast;
Breast shape acquisition module, the corresponding cluster centre of characteristic for matching user's breast, and will be in the cluster
Breast shape of the breast shape of the heart as user's breast;
Prosthese constructs module, for constructing user's breast prosthesis according to user's breast shape;
Wherein, the characteristic of the breast in the point cloud chart picture for the breast that the cluster centre is acquired according to history obtains.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811466626.6A CN109512547B (en) | 2018-12-03 | 2018-12-03 | Breast prosthesis construction method and device based on k-means |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811466626.6A CN109512547B (en) | 2018-12-03 | 2018-12-03 | Breast prosthesis construction method and device based on k-means |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109512547A true CN109512547A (en) | 2019-03-26 |
CN109512547B CN109512547B (en) | 2024-07-12 |
Family
ID=65794034
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811466626.6A Active CN109512547B (en) | 2018-12-03 | 2018-12-03 | Breast prosthesis construction method and device based on k-means |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109512547B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080101678A1 (en) * | 2006-10-25 | 2008-05-01 | Agfa Healthcare Nv | Method for Segmenting Digital Medical Image |
CN104783924A (en) * | 2015-04-24 | 2015-07-22 | 杭州捷诺飞生物科技有限公司 | Breast prosthesis manufacturing method based on three-dimensional printing technology |
CN106919888A (en) * | 2015-12-25 | 2017-07-04 | 中国移动通信集团公司 | One kind is had a meal Activity recognition method, device and home gateway |
CN108510516A (en) * | 2018-03-30 | 2018-09-07 | 深圳积木易搭科技技术有限公司 | A kind of the three-dimensional line segment extracting method and system of dispersion point cloud |
-
2018
- 2018-12-03 CN CN201811466626.6A patent/CN109512547B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080101678A1 (en) * | 2006-10-25 | 2008-05-01 | Agfa Healthcare Nv | Method for Segmenting Digital Medical Image |
CN104783924A (en) * | 2015-04-24 | 2015-07-22 | 杭州捷诺飞生物科技有限公司 | Breast prosthesis manufacturing method based on three-dimensional printing technology |
CN106919888A (en) * | 2015-12-25 | 2017-07-04 | 中国移动通信集团公司 | One kind is had a meal Activity recognition method, device and home gateway |
CN108510516A (en) * | 2018-03-30 | 2018-09-07 | 深圳积木易搭科技技术有限公司 | A kind of the three-dimensional line segment extracting method and system of dispersion point cloud |
Also Published As
Publication number | Publication date |
---|---|
CN109512547B (en) | 2024-07-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107798682B (en) | Image segmentation system, method, apparatus and computer-readable storage medium | |
CN107808377B (en) | The positioning device of lesion in a kind of lobe of the lung | |
US20210153986A1 (en) | Method, system and computer readable storage media for creating three-dimensional dental restorations from two dimensional sketches | |
CN104156935B (en) | Image segmenting device, image partition method and medical image equipment | |
WO2023142956A1 (en) | Total hip replacement preoperative planning system based on deep learning | |
CN109215032A (en) | The method and system of image segmentation | |
Zanjani et al. | Mask-MCNet: Tooth instance segmentation in 3D point clouds of intra-oral scans | |
CN109903396A (en) | A kind of tooth three-dimensional model automatic division method based on surface parameterization | |
TWI597057B (en) | Systems and methods for creating hair transplantation procedure sites | |
CN110189352A (en) | A kind of root of the tooth extracting method based on oral cavity CBCT image | |
CN116982077A (en) | System and method for automatically segmenting patient-specific anatomy for pathology-specific measurements | |
CN107106117A (en) | The segmentation of tooth and alveolar bone and reconstructing method and device | |
CN108765483B (en) | Method and system for determining mid-sagittal plane from brain CT image | |
CN106420108A (en) | Manufacturing method for individual breast prosthesis based on breast digital image fusion technique | |
US20220301224A1 (en) | Systems and methods for image segmentation | |
EP4233782A1 (en) | Oral image processing device and oral image processing method | |
Kodym et al. | Skull shape reconstruction using cascaded convolutional networks | |
WO2012050830A1 (en) | Breast implant surgical decision support system and method | |
CN104899923B (en) | The construction method of face fake composite body Optimized model based on the modification of smile expression geometric properties | |
US20220361992A1 (en) | System and Method for Predicting a Crown and Implant Feature for Dental Implant Planning | |
CN115272585A (en) | Three-dimensional dentition model construction device and method | |
JP2013175006A (en) | Device, method, and program for generating mesh | |
WO2022232559A1 (en) | Neural network margin proposal | |
CN104915989B (en) | Blood vessel three-dimensional dividing method based on CT images | |
Ben-Hamadou et al. | 3DTeethSeg'22: 3D Teeth Scan Segmentation and Labeling Challenge |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |