CN109741441A - Fibroid method for reconstructing three-dimensional model and system - Google Patents
Fibroid method for reconstructing three-dimensional model and system Download PDFInfo
- Publication number
- CN109741441A CN109741441A CN201811558314.8A CN201811558314A CN109741441A CN 109741441 A CN109741441 A CN 109741441A CN 201811558314 A CN201811558314 A CN 201811558314A CN 109741441 A CN109741441 A CN 109741441A
- Authority
- CN
- China
- Prior art keywords
- region
- myomata
- voxel
- nuclear
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Magnetic Resonance Imaging Apparatus (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a curing hysteromyoma method for reconstructing three-dimensional model, including defined area step: according to the voxel value of nuclear-magnetism image, being partitioned into the region of certain voxel value range, be denoted as myomata region；Removal interference step: choosing the point in myomata region, increases the interference region other than removal myomata region using region；Myomata region amendment step: revision myomata region is limited using erasing filling or range；Image conversion step: extracting the nuclear-magnetism image in myomata region, is denoted as nuclear-magnetism image after extraction, enables nuclear-magnetism image after extracting carry out image binaryzation, obtains converted images；Three-dimensional reconstruction step: enabling converted images carry out resurfacing, obtains the myomata threedimensional model of the grid data of triangular facet composition.The threedimensional model of fibroid, and combined high-strength ultrasonic therapeutic apparatus are quickly rebuild, solves the problems, such as auxiliary positioning and monitoring；Go out the threedimensional model of fibroid lesion by patient's nuclear-magnetism picture construction, can clearly show myomata size, shape, direction.
Description
Technical field
The present invention relates to field of medical imagings, and in particular, to a curing hysteromyoma method for reconstructing three-dimensional model and is
System, more particularly, to a kind of fibroid threedimensional model fast reconstructing method based on nuclear-magnetism image region segmentation growth algorithm.
Background technique
Fibroid is also known as leiomyoma of uterus, is the relatively conventional benign tumour of female reproductive system, and majority is often without disease
Shape, with the exacerbation of symptom, gradually lump or pressure symptom, this disease are apt to occur in women 35~50 years old to abdomen, and the cause of disease is so far not yet
Know, the disease disease incidence rises and is gradually in rejuvenation trend in recent years.Since the disease symptoms are hidden, so early diagnosing and controlling
Treatment is one of the main means for reducing the disease disease incidence.Medically generally acknowledged diagnostic mode has ultrasound detection, tomoscan at present
(CT), nuclear magnetic resonance (MRI) etc., since MRI has the spies such as high resolution, multi-faceted imaging, the big visual field in tissue
Point improves fibroid positioning, qualitative accuracy rate, reduces rate of missed diagnosis, just gradually replacing B ultrasound, CT at present, becoming and face
To the main diagnostic method of fibroid on bed.But above-mentioned diagnosis presentation is two dimensional image, causes doctor intuitive
Experience the form and dimension of fibroid.
Patent document CN103679808A discloses a kind of method using two-dimensional nucleus magnetic image reconstructed head threedimensional model
And system, wherein method includes: to pre-process to the two-dimensional nucleus magnetic image of human body head, is removed in two-dimensional nucleus magnetic image
Noise；All non-empty voxels in two-dimensional nucleus magnetic image after obtaining adjacent two denoisings；Search non-empty voxel and contour surface
Overlapping relation, and choose intersection point of the midpoint on the side that non-empty voxel intersects with contour surface as non-empty voxel and contour surface；It will
All intersection points of each non-empty voxel and contour surface are sequentially connected with, and form three-dimensional polygon dough sheet；By all non-hollow bodies
The three-dimensional polygon dough sheet that element is crossed to form with contour surface connects, and obtains head threedimensional model.Utilize two-dimensional nucleus magnetic image
The method and system of reconstructed head threedimensional model, reconstruction precision is high, calculation amount is small, high-efficient, improves human body head on the whole
The reconstruction performance of portion's threedimensional model.But above patent document needs to carry out noise suppression preprocessing to two-dimensional nucleus magnetic image, is denoising
Certain important informations may be lost in the process, cause image information imperfect, and need to find out all non-empty voxels, operation
It is inefficient, three-dimensional polygon dough sheet is based on when reconstructing three-dimensional model, it is inaccurate in building precision.
Summary of the invention
For the defects in the prior art, the object of the present invention is to provide a curing hysteromyoma method for reconstructing three-dimensional model
And system.
The curing hysteromyoma method for reconstructing three-dimensional model provided according to the present invention, comprising the following steps:
Defined area step: according to the voxel value of nuclear-magnetism image, it is partitioned into the region of setting voxel value range, is denoted as myomata
Region；
Removal interference step: choosing the point in myomata region, increases the interference region other than removal myomata region using region；
Myomata region amendment step: revision myomata region is limited using erasing filling or range；
Image conversion step: extracting the nuclear-magnetism image in myomata region, is denoted as nuclear-magnetism image after extraction, enables nuclear-magnetism figure after extracting
As carrying out image binaryzation, converted images are obtained；
Three-dimensional reconstruction step: enabling converted images carry out resurfacing, obtains the myomata of the grid data of triangular facet composition
Threedimensional model.
Preferably, the region of the setting voxel value range is to choose tri- directions X, Y, Z in the nuclear-magnetism image, point
Not Ji Suan tri- directions X, Y, Z voxel value, by the high region division of voxel value be set voxel value range region.
Preferably, it is to remove interference region by growth algorithm that the region, which increases,.
Preferably, the fibroid method for reconstructing three-dimensional model, the three-dimensional reconstruction step include:
Data read in step: 3 d-dem regular data being layered and reads in memory；
Scanning step: two layer datas of scanning construct voxel, 8 angle points in a voxel are derived from adjacent two layers one by one；
Comparison step: the contour surface of the functional value of each angle point of voxel and setting is compared, according to comparison result, construction
The state table of voxel；
It calculates intersection point step: according to state table, obtaining the boundary voxel for having intersection point with contour surface, pass through linear interpolation method
Calculate the seamed edge of boundary voxel and the intersection point of contour surface；
It seeks normal vector step: using centered Finite Difference Methods, finding out the normal vector of each angle point of voxel, form tri patch, lead to
Linear interpolation method is crossed, obtains the normal vector of the apex of tri patch；
Plot step: iso-surface images are drawn according to the coordinate on vertex each on each tri patch and normal vector.
The curing hysteromyoma reconstructing three-dimensional model system provided according to the present invention, comprises the following modules:
Defined area module: according to the voxel value of nuclear-magnetism image, it is partitioned into the region of setting voxel value range, is denoted as myomata
Region；
It removes interference module: choosing the point in myomata region, the interference region other than removal myomata region is increased using region；
Myomata region correction module: revision myomata region is limited using erasing filling or range；
Image conversion module: extracting the nuclear-magnetism image in myomata region, is denoted as nuclear-magnetism image after extraction, enables nuclear-magnetism figure after extracting
As carrying out image binaryzation, converted images are obtained；
Three-dimensional reconstruction module: enabling converted images carry out resurfacing, obtains the myomata of the grid data of triangular facet composition
Threedimensional model.
Preferably, the fibroid reconstructing three-dimensional model system, the three-dimensional reconstruction module include:
Data read in module: 3 d-dem regular data being layered and reads in memory；
Scan module: two layer datas of scanning construct voxel, 8 angle points in a voxel are derived from adjacent two layers one by one；
Comparison module: the contour surface of the functional value of each angle point of voxel and setting is compared, according to comparison result, construction
The state table of voxel；
It calculates intersection point module: according to state table, obtaining the boundary voxel for having intersection point with contour surface, pass through linear interpolation system
Calculate the seamed edge of boundary voxel and the intersection point of contour surface；
It seeks normal vector module: using centered difference system, finding out the normal vector of each angle point of voxel, form tri patch, lead to
Linear interpolation system is crossed, obtains the normal vector of the apex of tri patch；
Drafting module: iso-surface images are drawn according to the coordinate on vertex each on each tri patch and normal vector.
Compared with prior art, the present invention have it is following the utility model has the advantages that
1, the threedimensional model of fibroid is quickly rebuild, and by solving further combined with high intensity ultrasound treatment equipment
Auxiliary positioning and monitoring problem；
2, the threedimensional model for going out fibroid lesion by using patient's nuclear-magnetism picture construction, can clearly show myomata
Size, shape, direction.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is flow diagram of the invention；
Fig. 2 is myomata area schematic；
Fig. 3 is the voxel value distribution schematic diagram that myomata region X-direction passes through YZ planar central；
Fig. 4 is the voxel value distribution schematic diagram that myomata region Y-direction passes through XZ planar central；
Fig. 5 is the voxel value distribution schematic diagram that myomata region Z-direction passes through X/Y plane center；
Fig. 6 is myomata region removal interference schematic diagram.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the common skill of this field
For art personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to this
The protection scope of invention.
The curing hysteromyoma reconstructing three-dimensional model system provided according to the present invention, comprises the following modules:
Defined area module: according to the voxel value of nuclear-magnetism image, it is partitioned into the region of setting voxel value range, is denoted as myomata
Region；
It removes interference module: choosing the point in myomata region, the interference region other than removal myomata region is increased using region；
Myomata region correction module: revision myomata region is limited using erasing filling or range；
Image conversion module: extracting the nuclear-magnetism image in myomata region, is denoted as nuclear-magnetism image after extraction, enables nuclear-magnetism figure after extracting
As carrying out image binaryzation, converted images are obtained；
Three-dimensional reconstruction module: enabling converted images carry out resurfacing, obtains the myomata of the grid data of triangular facet composition
Threedimensional model.
Specifically, the fibroid reconstructing three-dimensional model system, the three-dimensional reconstruction module include:
Data read in module: 3 d-dem regular data being layered and reads in memory；
Scan module: two layer datas of scanning construct voxel, 8 angle points in a voxel are derived from adjacent two layers one by one；
Comparison module: the contour surface of the functional value of each angle point of voxel and setting is compared, according to comparison result, construction
The state table of voxel；
It calculates intersection point module: according to state table, obtaining the boundary voxel for having intersection point with contour surface, pass through linear interpolation system
Calculate the seamed edge of boundary voxel and the intersection point of contour surface；
It seeks normal vector module: using centered difference system, finding out the normal vector of each angle point of voxel, form tri patch, lead to
Linear interpolation system is crossed, obtains the normal vector of the apex of tri patch；
Drafting module: iso-surface images are drawn according to the coordinate on vertex each on each tri patch and normal vector.
Fibroid reconstructing three-dimensional model system provided by the invention can pass through following fibroid reconstructing three-dimensional model
The step process of method is realized.Fibroid method for reconstructing three-dimensional model can be interpreted as the son by those skilled in the art
The preference of palace myomata reconstructing three-dimensional model system.
The curing hysteromyoma method for reconstructing three-dimensional model provided according to the present invention, comprising the following steps:
Defined area step: according to the voxel value of nuclear-magnetism image, it is partitioned into the region of setting voxel value range, is denoted as myomata
Region；
Removal interference step: choosing the point in myomata region, increases the interference region other than removal myomata region using region；
Myomata region amendment step: revision myomata region is limited using erasing filling or range；
Image conversion step: extracting the nuclear-magnetism image in myomata region, is denoted as nuclear-magnetism image after extraction, enables nuclear-magnetism figure after extracting
As carrying out image binaryzation, converted images are obtained；
Three-dimensional reconstruction step: enabling converted images carry out resurfacing, obtains the myomata of the grid data of triangular facet composition
Threedimensional model.
Specifically, the region of the setting voxel value range is to choose tri- directions X, Y, Z in the nuclear-magnetism image, point
Not Ji Suan tri- directions X, Y, Z voxel value, by the high region division of voxel value be set voxel value range region.
Specifically, it is to remove interference region by growth algorithm that the region, which increases,.
Specifically, the three-dimensional reconstruction step includes:
Data read in step: 3 d-dem regular data being layered and reads in memory；
Scanning step: two layer datas of scanning construct voxel, 8 angle points in a voxel are derived from adjacent two layers one by one；
Comparison step: the contour surface of the functional value of each angle point of voxel and setting is compared, according to comparison result, construction
The state table of voxel；
It calculates intersection point step: according to state table, obtaining the boundary voxel for having intersection point with contour surface, pass through linear interpolation method
Calculate the seamed edge of boundary voxel and the intersection point of contour surface；
It seeks normal vector step: using centered Finite Difference Methods, finding out the normal vector of each angle point of voxel, form tri patch, lead to
Linear interpolation method is crossed, obtains the normal vector of the apex of tri patch；
Plot step: iso-surface images are drawn according to the coordinate on vertex each on each tri patch and normal vector.
As shown in Figure 1, the present invention is first directed to nuclear-magnetism image；Certain voxel value is partitioned into using the voxel value of nuclear-magnetism image
The region of range；The certain point for choosing myomata region increases other interference regions outside removal myomata using region；Myomata region
Amendment is limited using erasing filling or range to correct myomata region；The nuclear-magnetism image for extracting myomata region is carried out two
Value conversion；The 3-D image of binaryzation is subjected to resurfacing, obtains the myomata three-dimensional mould of the grid data of triangular facet composition
Type.
As shown in Fig. 2, myomata region segmentation obtain myomata region, by choose myomata region, analyze the region from
X, tri- directions Y, Z pass through the distribution situation of the voxel value at center, and by voxel value, obvious region less than normal is determined compared with surrounding
For myomata region, it is possible thereby to which Fast Segmentation goes out myomata region.
Although the segmentation of simple voxel value can isolate tumor region, have other equally in this voxel value range
Interior region can be extracted.By setting myomata region internal point, the area of these interference can be removed by growth algorithm
Domain.As shown in fig. 6, increasing removal interference region using tumor region, in specific implement, area is carried out using red green color
Divide myomata region and interference region, RED sector is to pass through algorithm with the interference region in a certain voxel value range with myomata
The myomata region of green is only remained, red interference region is removed.
After obtaining myomata region, it is still necessary to further be corrected to myomata region, by wiping function, directly be existed
Unwanted region is wiped in image shown in fig. 6, the voxel value for wiping region is deleted from the voxel value set of myomata region；
By adding function, added in Fig. 6, the voxel value of Adding Area increases to myomata region voxel value set.
Preferably, image reconstruction of the invention uses Marching Cubes algorithm: by 3 d-dem regular data field point
Layer reads in memory；Two layer datas are scanned, construct voxel one by one, 8 angle points in each voxel are derived from adjacent two layers；By body
The functional value of each angle point of element is compared with given equivalent face amount c, according to comparison result, constructs the state table of the voxel；Root
According to state table, the boundary voxel that there will be intersection point with contour surface is obtained；Voxel seamed edge and equivalence are calculated by linear interpolation method
The intersection point in face；Using centered Finite Difference Methods, the normal vector of each corner point of voxel is found out, then by linear interpolation method, finds out three
The normal direction of each apex of edged surface piece；Iso-surface images are drawn according to the coordinate on vertex each on each tri patch and normal vector.
One skilled in the art will appreciate that in addition to realizing system provided by the invention in a manner of pure computer readable program code
It, completely can be by the way that method and step be carried out programming in logic come so that provided by the invention other than system, device and its modules
System, device and its modules are with logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and embedded
The form of microcontroller etc. realizes identical program.So system provided by the invention, device and its modules can be by
It is considered a kind of hardware component, and the module for realizing various programs for including in it can also be considered as in hardware component
Structure；It can also will be considered as realizing the module of various functions either the software program of implementation method can be again
Structure in hardware component.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow
Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (6)
1. a curing hysteromyoma method for reconstructing three-dimensional model, which comprises the following steps:
Defined area step: according to the voxel value of nuclear-magnetism image, it is partitioned into the region of setting voxel value range, is denoted as myomata area
Domain；
Removal interference step: choosing the point in myomata region, increases the interference region other than removal myomata region using region；
Myomata region amendment step: revision myomata region is limited using erasing filling or range；
Image conversion step: extract myomata region nuclear-magnetism image, be denoted as extraction after nuclear-magnetism image, enable extract after nuclear-magnetism image into
Row image binaryzation, obtains converted images；
Three-dimensional reconstruction step: enabling converted images carry out resurfacing, and the myomata for obtaining the grid data of triangular facet composition is three-dimensional
Model.
2. fibroid method for reconstructing three-dimensional model according to claim 1, which is characterized in that the setting voxel value model
The region enclosed is to choose tri- directions X, Y, Z in the nuclear-magnetism image, the voxel value in tri- directions X, Y, Z is calculated separately, by body
It is to set the region of voxel value range that element, which is worth high region division,.
3. fibroid method for reconstructing three-dimensional model according to claim 1, which is characterized in that it is logical that the region, which increases,
Cross growth algorithm removal interference region.
4. fibroid method for reconstructing three-dimensional model according to claim 1, which is characterized in that the three-dimensional reconstruction step
Include:
Data read in step: 3 d-dem regular data being layered and reads in memory；
Scanning step: two layer datas of scanning construct voxel, 8 angle points in a voxel are derived from adjacent two layers one by one；
Comparison step: the contour surface of the functional value of each angle point of voxel and setting is compared, and according to comparison result, constructs voxel
State table；
It calculates intersection point step: according to state table, obtaining the boundary voxel for having intersection point with contour surface, calculated by linear interpolation method
The intersection point of the seamed edge and contour surface of boundary voxel out；
It seeks normal vector step: using centered Finite Difference Methods, finding out the normal vector of each angle point of voxel, form tri patch, pass through line
Property interpolation method, obtains the normal vector of the apex of tri patch；
Plot step: iso-surface images are drawn according to the coordinate on vertex each on each tri patch and normal vector.
5. a curing hysteromyoma reconstructing three-dimensional model system, which is characterized in that comprise the following modules:
Defined area module: according to the voxel value of nuclear-magnetism image, it is partitioned into the region of setting voxel value range, is denoted as myomata area
Domain；
It removes interference module: choosing the point in myomata region, the interference region other than removal myomata region is increased using region；
Myomata region correction module: revision myomata region is limited using erasing filling or range；
Image conversion module: extract myomata region nuclear-magnetism image, be denoted as extraction after nuclear-magnetism image, enable extract after nuclear-magnetism image into
Row image binaryzation, obtains converted images；
Three-dimensional reconstruction module: enabling converted images carry out resurfacing, and the myomata for obtaining the grid data of triangular facet composition is three-dimensional
Model.
6. fibroid reconstructing three-dimensional model system according to claim 5, which is characterized in that the three-dimensional reconstruction module
Include:
Data read in module: 3 d-dem regular data being layered and reads in memory；
Scan module: two layer datas of scanning construct voxel, 8 angle points in a voxel are derived from adjacent two layers one by one；
Comparison module: the contour surface of the functional value of each angle point of voxel and setting is compared, and according to comparison result, constructs voxel
State table；
It calculates intersection point module: according to state table, obtaining the boundary voxel for having intersection point with contour surface, pass through linear interpolation system-computed
The intersection point of the seamed edge and contour surface of boundary voxel out；
It seeks normal vector module: using centered difference system, finding out the normal vector of each angle point of voxel, form tri patch, pass through line
Property interplotation system, obtains the normal vector of the apex of tri patch；
Drafting module: iso-surface images are drawn according to the coordinate on vertex each on each tri patch and normal vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811558314.8A CN109741441A (en) | 2018-12-19 | 2018-12-19 | Fibroid method for reconstructing three-dimensional model and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811558314.8A CN109741441A (en) | 2018-12-19 | 2018-12-19 | Fibroid method for reconstructing three-dimensional model and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109741441A true CN109741441A (en) | 2019-05-10 |
Family
ID=66360567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811558314.8A Pending CN109741441A (en) | 2018-12-19 | 2018-12-19 | Fibroid method for reconstructing three-dimensional model and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109741441A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111462150A (en) * | 2020-02-21 | 2020-07-28 | 中惠医疗科技（上海）有限公司 | Method, system and medium for segmenting uterine fibroids in nuclear magnetic images |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271574A (en) * | 2008-03-20 | 2008-09-24 | 华南师范大学 | Three-dimensional visualization method and device |
| CN103180876A (en) * | 2010-10-19 | 2013-06-26 | 皇家飞利浦电子股份有限公司 | Medical imaging system, computer-implemented method, and computer program product for identifying treated region in medical image |
| CN103679808A (en) * | 2013-12-24 | 2014-03-26 | 通号通信信息集团有限公司 | Method and system for rebuilding three-dimensional head model by two-dimensional nuclear magnetic images |
| CN106780460A (en) * | 2016-12-13 | 2017-05-31 | 杭州健培科技有限公司 | A kind of Lung neoplasm automatic checkout system for chest CT image |
| CN106887039A (en) * | 2017-02-28 | 2017-06-23 | 成都金盘电子科大多媒体技术有限公司 | The three-D imaging method and system of a kind of organ and focus based on medical image |
-
2018
- 2018-12-19 CN CN201811558314.8A patent/CN109741441A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271574A (en) * | 2008-03-20 | 2008-09-24 | 华南师范大学 | Three-dimensional visualization method and device |
| CN103180876A (en) * | 2010-10-19 | 2013-06-26 | 皇家飞利浦电子股份有限公司 | Medical imaging system, computer-implemented method, and computer program product for identifying treated region in medical image |
| CN103679808A (en) * | 2013-12-24 | 2014-03-26 | 通号通信信息集团有限公司 | Method and system for rebuilding three-dimensional head model by two-dimensional nuclear magnetic images |
| CN106780460A (en) * | 2016-12-13 | 2017-05-31 | 杭州健培科技有限公司 | A kind of Lung neoplasm automatic checkout system for chest CT image |
| CN106887039A (en) * | 2017-02-28 | 2017-06-23 | 成都金盘电子科大多媒体技术有限公司 | The three-D imaging method and system of a kind of organ and focus based on medical image |
Non-Patent Citations (4)
| Title |
|---|
| 张大饼的最爱: "Marching Cubes", 《CSDN博客》, 26 July 2016 (2016-07-26), pages 1 * |
| 苏秀云等: "《Mimics软件临床应用 计算机辅助外科入门技术》", 人民军医出版社, pages: 80 - 84 * |
| 薛迎峰等: "三维数字化模型在子宫肌瘤术前规划中的应用", 《医学与哲学》 * |
| 薛迎峰等: "三维数字化模型在子宫肌瘤术前规划中的应用", 《医学与哲学》, vol. 36, no. 6, 30 June 2015 (2015-06-30), pages 45 - 47 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111462150A (en) * | 2020-02-21 | 2020-07-28 | 中惠医疗科技（上海）有限公司 | Method, system and medium for segmenting uterine fibroids in nuclear magnetic images |
| CN111462150B (en) * | 2020-02-21 | 2023-05-16 | 中惠医疗科技（上海）有限公司 | Method, system and medium for segmenting hysteromyoma by nuclear magnetic imaging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107808156B (en) | Region-of-interest extraction method | |
| Uus et al. | Deformable slice-to-volume registration for motion correction of fetal body and placenta MRI | |
| CN107622492B (en) | Lung fissure segmentation method and system | |
| US7903849B2 (en) | Medical image processing apparatus | |
| CN103679810A (en) | Method for three-dimensional reconstruction of liver computed tomography (CT) image | |
| CN105078514A (en) | Construction method and device of three-dimensional model, image monitoring method and device | |
| CN106780649B (en) | Image artifact removing method and device | |
| CN110717961B (en) | Multi-modal image reconstruction method and device, computer equipment and storage medium | |
| CN110738701A (en) | tumor three-dimensional positioning system | |
| KR20130023735A (en) | Method and apparatus for generating organ medel image | |
| CN107103605A (en) | A kind of dividing method of breast tissue | |
| Chougule et al. | Development of patient specific implants for Minimum Invasive Spine Surgeries (MISS) from non-invasive imaging techniques by reverse engineering and additive manufacturing techniques | |
| CN104794749A (en) | Method for establishing three-dimensional electromagnetic breast simulation model on basis of clinical MRI (magnetic resonance imaging) images | |
| US20040160440A1 (en) | Method for surface-contouring of a three-dimensional image | |
| CN113421226B (en) | CT-DR multi-modal esophageal image registration method and system based on mutual information | |
| CN109741441A (en) | Fibroid method for reconstructing three-dimensional model and system | |
| CN111627023B (en) | Method and device for generating coronary artery projection image and computer readable medium | |
| CN112022345A (en) | Three-dimensional visual preoperative planning method, system and terminal for abdominal wall defect reconstruction | |
| Militello et al. | A semi-automatic multi-seed region-growing approach for uterine fibroids segmentation in MRgFUS treatment | |
| CN110858412B (en) | Heart coronary artery CTA model building method based on image registration | |
| JP4598910B2 (en) | 3D image display device | |
| Hopp et al. | Automatic multimodal 2D/3D image fusion of ultrasound computer tomography and x-ray mammography for breast cancer diagnosis | |
| CN114299096A (en) | Outline delineation method, device, equipment and storage medium | |
| CN115311191A (en) | Generating reformatted views of three-dimensional anatomical scans using deep learning estimated scan scheme masks | |
| CN114419071A (en) | Heart three-dimensional positioning method based on MR transverse axis image segmentation |
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 |