CN106355586A - Automatic extraction method of human chest organ tissue - Google Patents
Automatic extraction method of human chest organ tissue Download PDFInfo
- Publication number
- CN106355586A CN106355586A CN201610793714.1A CN201610793714A CN106355586A CN 106355586 A CN106355586 A CN 106355586A CN 201610793714 A CN201610793714 A CN 201610793714A CN 106355586 A CN106355586 A CN 106355586A
- Authority
- CN
- China
- Prior art keywords
- extraction method
- tissue
- human chest
- dimensional
- breastbone
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 16
- 210000000056 organ Anatomy 0.000 title abstract 3
- 238000000034 method Methods 0.000 claims abstract description 26
- 210000001562 sternum Anatomy 0.000 claims abstract description 21
- 230000011218 segmentation Effects 0.000 claims abstract description 16
- 210000000038 chest Anatomy 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 15
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 7
- 210000003437 trachea Anatomy 0.000 claims abstract description 4
- 210000004872 soft tissue Anatomy 0.000 claims abstract 2
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 230000009977 dual effect Effects 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 abstract description 9
- 238000005516 engineering process Methods 0.000 abstract description 4
- 210000001519 tissue Anatomy 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 238000009472 formulation Methods 0.000 abstract description 2
- 239000000203 mixture Substances 0.000 abstract description 2
- 238000012800 visualization Methods 0.000 abstract description 2
- 238000009877 rendering Methods 0.000 abstract 2
- 238000003745 diagnosis Methods 0.000 abstract 1
- 238000003325 tomography Methods 0.000 abstract 1
- 206010028980 Neoplasm Diseases 0.000 description 5
- 210000004072 lung Anatomy 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000001356 surgical procedure Methods 0.000 description 3
- 238000002591 computed tomography Methods 0.000 description 2
- 208000037841 lung tumor Diseases 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000004195 computer-aided diagnosis Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 210000004247 hand Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000002324 minimally invasive surgery Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000002271 resection Methods 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/08—Volume rendering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/41—Medical
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses an automatic extraction method of human chest organ tissue, belongs to the technical field of medical image processing, and aims to solve the problems that boundaries of organ tissue are unsmooth and observation by researchers and clinicians is affected due to the fact that an existing image segmentation technology is not clear enough. The automatic extraction method is characterized by comprising steps as follows: reading three-dimensional tomography images; performing fitting and primary segmentation processing on each image in a sequence with a least square ellipse fitting algorithm, parts outside sternums are removed, and parts inside the sternums are reserved; image noise of the parts inside the sternums is removed, segmentation processing is performed again to remove unnecessary soft tissue, and regions of interest, including trachea and blood vessels, inside the sternums are obtained; volume rendering and surface rendering are performed. Medical image segmentation has great significance in three-dimensional visualization, three-dimensional positioning, operation planning formulation and computer assisted diagnosis. With the adoption of the automatic segmentation method, the effect of subjective factors of an observer is completely avoided, the data processing speed is increased, and the repeatability is good.
Description
Technical field
The present invention relates to a kind of extraction method of human chest organ-tissue, belong to Medical Image Processing neck
Domain.
Background technology
Nearly 20 years, medical imaging device fast development, each medical institutions will produce the medical image data of magnanimity daily,
Computed tomography (computed tomography, ct), nuclear magnetic resonance (magnetic resonance imaging,
) etc. mri imaging technique has become the important means observing organ-tissue.The result of Medical Image Processing makes scientific research personnel and clinic
The visual and clear observation inside of human body of doctor is normal and lesion locations.Therefore, domestic and international associated specialist pays much attention to medical science always
Image processing techniquess, and medical image segmentation is the classic problem in image processing techniquess.Existing image Segmentation Technology exists
Not clear, cause the border of organ-tissue unsmooth, the observation of impact scientific research personnel and clinician.
Content of the invention
The present invention is not clear for the existing image Segmentation Technology solving, and causes the border of organ-tissue unsmooth,
The problem of the observation of impact scientific research personnel and clinician, and then provide a kind of side of automatically extracting of human chest organ-tissue
Method.
The present invention is to solve above-mentioned technical problem to adopt the technical scheme that:
A kind of extraction method of human chest organ-tissue, the process of realizing of methods described is:
Step one, the three-dimensional tomographic image of one sequence of reading;
Step 2, using least square ellipse fitting algorithm, primary segmentation is fitted to every image in sequence and processes,
Remove breastbone with outer portion, retain breastbone with interior part;
Step 3, remove breastbone and with the picture noise of interior part and again carry out dividing processing, remove unnecessary soft group
Knit, obtain including trachea, the area-of-interest of blood vessel within breastbone;
Step 4, carry out volume drawing, obtain three-dimensional reconstruction result;
Step 5, iso-surface patch is carried out according to volume drawing result;
Step 6, iso-surface patch result is saved as 3d model format file, print for 3d.
In step 2, using least square ellipse fitting algorithm, every image in sequence is fitted at primary segmentation
Reason, detailed process is as follows:
1) survey, in input breastbone, the coordinate that the two-dimensional discrete point of matching is treated at edge, bring formula (3) into and obtain coefficient matrix b;
2) coefficient matrix b is decomposed using qr and obtain comprising r11, the matrix of r12, r22;
3) singular value decomposition r is adopted to matrix r 2222=u ∑ vt;
4) according to r11, r12 and the ellipse being determined last matching by the v of singular value decomposition;
In step 3, apply 3d tv-l1 model removal breastbone with the picture noise of interior part and carry out segmentation portion again
Reason, its process is as follows:
1) input three-dimensional ct volume data f, initialize v0=f, ξ0=0, and u0=0,
2) beginning iteration, k=0,1,2,3 ...;
3) adoptCalculate dual variable ξ;
4) adoptCalculate master variable uu;
5) adopt uk+1=uk+1+α(uk+1-uk) calculating difference variable u;
6) broad sense soft-threshold formula is adopted to calculate v;
7) until meeting the condition of convergence.
After carrying out volume drawing in step 4, can manual interactive segmentation, choose manually unwanted region and carry out at deletion
Reason.
In step 5, application mc (marching cube) algorithm carries out iso-surface patch, obtains three-dimensional reconstruction result.
In step 6, iso-surface patch result is saved as the 3d model format file of stl form, print for 3d.
Three-dimensional tomographic image described in step one adopts ct or closes the acquisition of magnetic resonance (mri) equipment.
The form of the three-dimensional tomographic image described in step one is dicom, bmp or jpg.
Invention has the advantages that
The present invention, according to medical image, rebuilds organizational structure threedimensional model, realizes the rotation to model, scaling, cutting etc.
Basic interactive operation.Solve the inadequate clearly problem of image segmentation, by the tv-l1 model of improvement come smoothed image.This
After bright use ellipse fitting method matching ct data, part interested is carried out primary segmentation, then apply 3d tv-l1 model
Carry out secondary splitting after carrying out denoising smooth, reach the effect of smooth volume, finally provide a clearly three-dimensional volume drawing knot
Really, substantial amounts of experiment show the inventive method image segmentation is clear, the performance of edge smoothing.
The present invention is used for medical image segmentation, the anatomical structure in image or area-of-interest is delineated out, medical science
Image segmentation has great importance to three-dimensional visualization, three-dimensional localization, formulation surgical planning and computer-aided diagnosises.Automatically
Dividing method completely avoid the impact of observer's subjective factorss, improves the speed of processing data, favorable repeatability.
Brief description
Fig. 1 is the flow chart of the extraction method of the present invention;Fig. 2 to Fig. 5 is to automatically extract procedure chart;
A, b, c, d in Fig. 2 is the four Zhang San's dimension tomoscan images reading flanking sequence;
A, b, c, d in Fig. 3 is that four Zhang San's dimension tomoscan images in Fig. 2 are carried out after primary segmentation denoising respectively
Four Zhang San dimension tomoscan images;
A, b, c, d in Fig. 4 is to apply 3d tv-l1 model to carry out respectively four Zhang San's dimension tomoscan images in Fig. 3
Four Zhang San's dimension tomoscan images after denoising;
A, b, c, d in Fig. 5 is to apply 3d tv-l1 model to carry out respectively four Zhang San's dimension tomoscan images in Fig. 4
Four Zhang San's dimension tomoscan images after secondary splitting;
A, b, c in Fig. 6 be by volume drawing after three different angles axonometric chart;
A, b, c in Fig. 7 be by iso-surface patch after three different angles axonometric chart.
Fig. 8 is the accompanying drawing in the embodiment of the present invention 1, in figure, and a is ct datagram, and b is three-dimensional reconstruction result figure.
Fig. 9 is the accompanying drawing in the embodiment of the present invention 2, in figure, and a is ct datagram, and b is three-dimensional reconstruction result figure, and c beats for 3d
Print result figure.
Specific embodiment
Specific embodiment one: referring to Fig. 1, Fig. 2 to Fig. 7, present embodiment is described, as shown in Figures 2 to 7: Fig. 2 is former
Beginning ct image;Fig. 3 is the result after application least square ellipse fitting algorithm segmentation;Fig. 4 is application 3d tv-l1 algorithm denoising
Smooth result;Fig. 5 is the result of application 3d tv-l1 algorithm secondary splitting;Fig. 6 is said three-dimensional body drawing result;Fig. 7 is three-dimensional
Iso-surface patch result.The process of realizing of the extraction method of human chest organ-tissue described in present embodiment is:
Step one, the three-dimensional tomographic image of one sequence of reading;
Step 2, using least square ellipse fitting algorithm, primary segmentation is fitted to every image in sequence and processes,
Remove breastbone with outer portion, retain breastbone with interior part;The method of ellipse fitting is applied in two-dimensional sequence, can be effective
It is partitioned into the position wanted;
Step 3, remove breastbone and with the picture noise of interior part and again carry out dividing processing, remove unnecessary soft group
Knit, obtain including trachea, the area-of-interest of blood vessel within breastbone;
Step 4, carry out volume drawing, obtain three-dimensional reconstruction result;
Step 5, iso-surface patch is carried out according to volume drawing result;
Step 6, iso-surface patch result is saved as 3d model format file, print for 3d.
Carry out image denoising and recovery using 3d tv-l1, obtain clearly said three-dimensional body drawing result.
The method of ellipse fitting described in step 2 for the present embodiment, has three elements, i.e. conic section, ginseng
Number, and focal length.The description of the expression formula of one conic section to be expressed by following implicit expression second order polynomial:
F (x, y)=a11x2+2a12xy+a22y2+b1x+b2Y+c=0 (1)
Equation (1) is converted into following quadratic form
xtax+btx+c≈0 (2)
X=(x, y) heret,B=(b1,b2)t.
In order to ensure formula (2) be an ellipse it is desirable to
V=(b1,b2,c)t
Constraint | | w | |=1, additionally, we define following coefficient matrix b
The decomposition qr obligating | | w | |=1, b completes, and result in following equivalent system afterwards
Solve following two equations
r22w≈0
W | |=1
Decompose r22, obtain
r22=u ∑ vt
W is substituted for (4), remaining variables in v are solved by equation below
V=-r11 -1r12w
Determine that v and w is assured that an accurately ellipse.
In step 3, apply 3d tv-l1 model removal breastbone with the picture noise of interior part and carry out segmentation portion again
Reason, its process is as follows:
1) input three-dimensional ct volume data f, initialize v0=f, ξ0=0, and u0=0,
2) beginning iteration, k=0,1,2,3 ...;
3) adoptCalculate dual variable ξ;
4) adoptCalculate master variable uu;
5) adopt uk+1=uk+1+α(uk+1-uk) calculating difference variable u;
6) broad sense soft-threshold formula is adopted to calculate v;
7) until meeting the condition of convergence.
The algorithm adopting in step 2 and three in present embodiment is algorithm of the prior art, and its corresponding parameter contains
Justice is common knowledge.
Specific embodiment two: present embodiment, after carrying out volume drawing in step 4, can manual interactive segmentation, manually
Choose unwanted region and carry out delete processing.Other steps are identical with specific embodiment one.
Specific embodiment three: present embodiment, in step 5, application mc (marching cube) algorithm carries out face
Draw, obtain three-dimensional reconstruction result.Other steps are identical with specific embodiment one or two.
Specific embodiment four: present embodiment, in step 6, iso-surface patch result is saved as the 3d mould of stl form
Type formatted file, prints for 3d.Other steps and specific embodiment one, two or three are identical.
Specific embodiment five: present embodiment, the three-dimensional tomographic image described in step one adopts ct or conjunction
Magnetic resonance (mri) equipment obtains.Other steps and specific embodiment one, two, three or four are identical.
Specific embodiment six: present embodiment, the form of the three-dimensional tomographic image described in step one is
Dicom, bmp or jpg.Other steps and specific embodiment one, two, three, four or five are identical.
The embodiment of the inventive method:
Embodiment 1: lung tumors-domestic are the first to complete complicated hilus pulumonis tumor operation using 3d printing technique:
Case introduces the (deadline: on July 16th, 2015;Cooperation unit: breathe out the forth academy of medical university thoracic surgery): hilus pulumonis tumor position
In the root of lung, conventional ct is difficult to distinguish the relation of hilus pulumonis tumor and peripheral vesselses, and operation risk is high, it is more to lose blood.Print 3d
After lung model, can clear and definite tumor actual position and tumor and the relation of peripheral vesselses, can more accurately perform the operation.From
The 3d model traditional Chinese medical science survive find aunt Liu blood vessel be lopsided.This root blood vessel common people do not have, and aunt Liu is exactly in left side
A thick blood vessel that arterial branch goes out from left collarbone is there is in thoracic cavity, if do not noted, may be by mistake in operation
Wound.As shown in Figure 8.
Embodiment 2: lung tumors-lung section local precisely resection operation:
Case introduces the (deadline: in July, 2015;Cooperation unit: breathe out the forth academy of medical university thoracic surgery): this case is big by one
Open chest surgery becomes a Minimally Invasive Surgery, prints in 3d and has carried out lung section local precisely excision handss under the guidance of physical model
Art.Shorten operating time, reduce operation risk, as much as possible remain the lung tissue of patient.As shown in Figure 9.
Claims (8)
1. a kind of extraction method of human chest organ-tissue is it is characterised in that the process of realizing of methods described is:
Step one, the three-dimensional tomographic image of one sequence of reading;
Step 2, using least square ellipse fitting algorithm, primary segmentation is fitted to every image in sequence and processes, remove
Breastbone, with outer portion, retains breastbone with interior part;
Step 3, remove breastbone and with the picture noise of interior part and again carry out dividing processing, remove unnecessary soft tissue, obtain
Inclusion trachea within breastbone, the area-of-interest of blood vessel;
Step 4, carry out volume drawing, obtain three-dimensional reconstruction result;
Step 5, iso-surface patch is carried out according to volume drawing result;
Step 6, iso-surface patch result is saved as 3d model format file, print for 3d.
2. according to claim 1 a kind of extraction method of human chest organ-tissue it is characterised in that in step 2
In, using least square ellipse fitting algorithm, primary segmentation is fitted to every image in sequence and processes, detailed process is as follows:
1) survey, in input breastbone, the coordinate that the two-dimensional discrete point of matching is treated at edge, bring formula (3) into and obtain coefficient matrix b;
2) coefficient matrix b is decomposed using qr and obtain comprising r11, the matrix of r12, r22;
3) singular value decomposition r is adopted to matrix r 2222=u ∑ vt;
4) according to r11, r12 and the ellipse being determined last matching by the v of singular value decomposition;
3. a kind of extraction method of human chest organ-tissue according to claim 1 or claim 2 is it is characterised in that in step
In rapid three, apply 3d tv-l1 model removal breastbone with the picture noise of interior part and carry out dividing processing again, its process is such as
Under:
1) input three-dimensional ct volume data f, initialize v0=f, ξ0=0, and u0=0,
2) beginning iteration, k=0,1,2,3 ...;
3) adoptCalculate dual variable ξ;
4) adoptCalculate master variable uu;
5) adopt uk+1=uk+1+α(uk+1-uk) calculating difference variable u;
6) broad sense soft-threshold formula is adopted to calculate v;
7) until meeting the condition of convergence.
4. according to claim 3 a kind of extraction method of human chest organ-tissue it is characterised in that in step 4
In carry out volume drawing after, can manual interactive segmentation, choose manually unwanted region and carry out delete processing.
5. according to claim 4 a kind of extraction method of human chest organ-tissue it is characterised in that in step 5
In, application mc algorithm carries out iso-surface patch, obtains three-dimensional reconstruction result.
6. a kind of extraction method of human chest organ-tissue according to claim 1,2,4,5 or 6, its feature exists
In, in step 6, iso-surface patch result is saved as the 3d model format file of stl form, for 3d print.
7. according to claim 6 a kind of extraction method of human chest organ-tissue it is characterised in that in step one
Described in three-dimensional tomographic image adopt ct or close magnetic resonance equipment obtain.
8. according to claim 7 a kind of extraction method of human chest organ-tissue it is characterised in that in step one
Described in three-dimensional tomographic image form be dicom, bmp or jpg.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610793714.1A CN106355586B (en) | 2016-08-31 | 2016-08-31 | A kind of extraction method of human chest organ-tissue |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610793714.1A CN106355586B (en) | 2016-08-31 | 2016-08-31 | A kind of extraction method of human chest organ-tissue |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106355586A true CN106355586A (en) | 2017-01-25 |
CN106355586B CN106355586B (en) | 2019-06-21 |
Family
ID=57856945
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610793714.1A Active CN106355586B (en) | 2016-08-31 | 2016-08-31 | A kind of extraction method of human chest organ-tissue |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106355586B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107705305A (en) * | 2017-10-20 | 2018-02-16 | 上海联影医疗科技有限公司 | A kind of method and device of Medical Image Processing |
CN111833427A (en) * | 2020-07-21 | 2020-10-27 | 北京推想科技有限公司 | Method and device for volume rendering of three-dimensional image |
CN111833431A (en) * | 2019-04-19 | 2020-10-27 | 四川大学 | Bionic bone scaffold modeling method based on ellipsoid intersection model |
CN113160248A (en) * | 2021-04-22 | 2021-07-23 | 浙江明峰智能医疗科技有限公司 | Image processing method, device and equipment and readable storage medium |
CN117351526A (en) * | 2023-12-05 | 2024-01-05 | 深圳纯和医药有限公司 | Intravascular ultrasound image automatic identification method for intima |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103150723A (en) * | 2013-01-25 | 2013-06-12 | 西安电子科技大学 | Lymph gland detection system and method based on stomach computed tomography (CT) image with shape fitting with oval |
-
2016
- 2016-08-31 CN CN201610793714.1A patent/CN106355586B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103150723A (en) * | 2013-01-25 | 2013-06-12 | 西安电子科技大学 | Lymph gland detection system and method based on stomach computed tomography (CT) image with shape fitting with oval |
Non-Patent Citations (3)
Title |
---|
CHANGCAI YANG ET AL: "Level set contour extraction method based on support value filter", 《APPLIED MATHEMATICS AND COMPUTATION》 * |
CHRISTOPHER ZACH ET AL: "A Globally Optimal Algorithm for Robust TV-L1 Range Image Integration", 《2007 IEEE 11TH INTERNATIONAL CONFERENCE ON COMPUTER VISION》 * |
董庆 等: "3D打印技术在非小细胞肺癌诊疗中的应用", 《中国数字医学》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107705305A (en) * | 2017-10-20 | 2018-02-16 | 上海联影医疗科技有限公司 | A kind of method and device of Medical Image Processing |
CN111833431A (en) * | 2019-04-19 | 2020-10-27 | 四川大学 | Bionic bone scaffold modeling method based on ellipsoid intersection model |
CN111833427A (en) * | 2020-07-21 | 2020-10-27 | 北京推想科技有限公司 | Method and device for volume rendering of three-dimensional image |
CN111833427B (en) * | 2020-07-21 | 2021-01-05 | 推想医疗科技股份有限公司 | Method and device for volume rendering of three-dimensional image |
CN113160248A (en) * | 2021-04-22 | 2021-07-23 | 浙江明峰智能医疗科技有限公司 | Image processing method, device and equipment and readable storage medium |
CN113160248B (en) * | 2021-04-22 | 2023-03-14 | 浙江明峰智能医疗科技有限公司 | Image processing method, device and equipment and readable storage medium |
CN117351526A (en) * | 2023-12-05 | 2024-01-05 | 深圳纯和医药有限公司 | Intravascular ultrasound image automatic identification method for intima |
CN117351526B (en) * | 2023-12-05 | 2024-03-22 | 深圳纯和医药有限公司 | Intravascular ultrasound image automatic identification method for intima |
Also Published As
Publication number | Publication date |
---|---|
CN106355586B (en) | 2019-06-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106355586B (en) | A kind of extraction method of human chest organ-tissue | |
CN104462650B (en) | A kind of hypostazation heart 3D model production methods of achievable external and internal compositionses | |
US20070280521A1 (en) | Methods for Volumetric Contouring with Expert Guidance | |
US20120027278A1 (en) | Methods, systems, and computer readable media for mapping regions in a model of an object comprising an anatomical structure from one image data set to images used in a diagnostic or therapeutic intervention | |
CN105078514A (en) | Construction method and device of three-dimensional model, image monitoring method and device | |
Soler et al. | An automatic virtual patient reconstruction from CT-scans for hepatic surgical planning | |
CN107157580A (en) | A kind of Digital location minimally invasive spine surgical 3D printing guide plate and preparation method | |
CN106952285B (en) | Lung motion estimation method based on prior statistical motion model and adaptive registration | |
CN113100935A (en) | Preoperative puncture path planning method and training system for lung puncture operation | |
Alvarez et al. | A hybrid, image-based and biomechanics-based registration approach to markerless intraoperative nodule localization during video-assisted thoracoscopic surgery | |
Gholizadeh et al. | Minimally invasive and invasive liver surgery based on augmented reality training: A review of the literature | |
CN109893224A (en) | It is a kind of to assist cerebral hemorrhage puncture drainage method using 3D printing fixed equipment | |
CN112639887B (en) | Image processing system and method | |
Yatsishina et al. | Interdisciplinary study of Egyptian mummies from the Pushkin State Museum of Fine Arts collection at the National Research Centre “Kurchatov Institute” | |
Seemann et al. | Hybrid 3D visualization of the chest and virtual endoscopy of the tracheobronchial system: possibilities and limitations of clinical application | |
KR102490504B1 (en) | Medical image processing method and device for pediatric simple x-ray image processing using machine learning model | |
CN111127636B (en) | Intelligent complex intra-articular fracture desktop-level three-dimensional diagnosis system | |
CN106446572A (en) | Lung respiratory movement acquisition method based on boundary meta-model and local region correction | |
Liu | 3D Reconstruction of Lung by MIMICS | |
Alfano et al. | Breast Tumor Localization by Prone to Supine Landmark Driven Registration for Surgical Planning | |
Vera et al. | Smart operator for the human liver automatic segmentation, present in medical images | |
Newman et al. | A volumetric segmentation technique for diagnosis and surgical planning in lower torso CT images | |
Schreyer et al. | Surface rendering | |
Zhou et al. | Enhancement of lesions in CT images of lung cancer based on MIMICS software | |
Díaz-Parra et al. | Fully automatic spinal canal segmentation for radiation therapy using a gradient vector flow-based method on computed tomography images: A preliminary study |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 |