CN108734771A - Vessel extraction system and analysis method based on 3 D medical image - Google Patents
Vessel extraction system and analysis method based on 3 D medical image Download PDFInfo
- Publication number
- CN108734771A CN108734771A CN201810453488.1A CN201810453488A CN108734771A CN 108734771 A CN108734771 A CN 108734771A CN 201810453488 A CN201810453488 A CN 201810453488A CN 108734771 A CN108734771 A CN 108734771A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- module
- image
- vessel
- extraction
- 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 49
- 238000004458 analytical method Methods 0.000 title claims abstract description 11
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 130
- 239000000284 extract Substances 0.000 claims abstract description 22
- 238000003384 imaging method Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 9
- 238000002591 computed tomography Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000002526 effect on cardiovascular system Effects 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 239000008280 blood Substances 0.000 claims description 6
- 210000004369 blood Anatomy 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 230000002792 vascular Effects 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 abstract description 6
- 230000011218 segmentation Effects 0.000 abstract description 4
- 239000011229 interlayer Substances 0.000 abstract description 3
- 238000003672 processing method Methods 0.000 abstract description 3
- 230000002708 enhancing effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 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
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses a kind of vessel extraction systems and analysis method based on 3 D medical image, it is intended to which from the blood vessel image of different contrast, segmentation extracts interested blood vessel, and to quantitative measurment that its Morphologic Parameters is automated；By using the geometric deformable models of multi-parameter, it is applicable to the blood vessel structure extraction of different shape；By using new processing method, dependence of the above-mentioned model to primary condition, boosting algorithm stability are significantly reduced, and expand its application scenarios, such as the extraction of low signal blood vessel, intravascular there are interlayers etc.；Algorithm uses parallel computation, vessel extraction speed fast；By the quantitative interested blood vessel Morphologic Parameters of automation, manually-operated triviality and uncertainty are avoided.
Description
Technical field
The invention belongs to medical imagings and technical field of image processing, are related to a kind of vessel extraction system of 3 D medical image
System, specifically a kind of vessel extraction system and analysis method based on 3 D medical image.
Background technology
Magnetic resonance (MRI) and computer tomography (CT) technology can carry out high-resolution three-dimensional to human body cardiovascular and cerebrovascular
Imaging, according to the difference of specific axis information, blood vessel can be presented on image high gray value or low gray value (also known as " bright blood " or
" black blood " is imaged).
Current blood vessel segmentation is mostly based on the high gray-value image of blood vessel enhancing with analytical technology, there are following a kind of or
A variety of deficiencies:
1) it is based on blood vessel cylindrical-shaped structure model, and there are certain deviations for the true form of blood vessel；
2) geometric deformable models used in require harshness to initialization condition, it is low to reduce stablizing for algorithm；
3) it is relatively long to calculate the time；
4) it can not handle in nuclear magnetic resonance image, the situation of low gray value is presented in blood vessel signal；
5) Morphological measurement of blood vessel is strong to artificial dependence.
Invention content
The purpose of the present invention is to provide a kind of vessel extraction systems and analysis method based on 3 D medical image, can fit
Blood vessel structure for different shape extracts, and vessel extraction speed is fast, avoids manually-operated triviality and uncertainty.
The purpose of the present invention can be achieved through the following technical solutions：
Vessel extraction system based on 3 D medical image, including blood vessel imaging module, region selection module, image are located in advance
Manage module, region growing module, image enhancement module, hodograph constructing module and vessel extraction module；
The blood vessel imaging module carries out high score using magnetic resonance and Computed tomography to human body cardiovascular and cerebrovascular
The three-dimensional imaging of resolution obtains the blood vessel image of different contrast；
The region selection module, in the blood vessel image of the different contrast obtained from blood vessel imaging module, using automatic
Or automanual method determines the size of blood vessel place area-of-interest；
Described image preprocessing module, according to the signal-to-noise ratio and geometry of the area-of-interest blood vessel of region selection module extraction
Form is different, selective that noise reduction, smooth, re-sampling operations are carried out to it；
The region growing module will pass through image pre-processing module treated blood vessel and and blood vessel by region growing
Signal similar in gray value is detached from blood vessel image；
Described image enhance module, the blood vessel isolated to region growing module and with signal similar in blood vessel gray value into
Row enhancing；
The hodograph constructing module constructs hodograph according to the enhanced blood vessel gray value of image enhancement module, makes
The corresponding velocity amplitude of angiosomes it is higher, the corresponding velocity amplitude in non-vascular region is relatively low；
The vessel extraction module extracts endovascular continuous road based on the hodograph of hodograph constructing module structure
Then diameter uses multi-parameter geometric deformable models to carry out angiosomes search, extracts the bianry image of blood vessel, complete carrying for blood vessel
It takes.
Further, further include centerline determination module and parameters measurement module；
The centerline determination module, based on the blood vessel bianry image of vessel extraction module extraction, the space according to blood vessel
Geometric position again pulls up hodograph, and is scanned for angiosomes, obtains the center line of extracted blood vessel；
The parameters measurement module automatically extracts out a series of according to the vessel centerline of centerline determination module extraction
Two-dimentional vessel cross-sections obtain blood vessel morphology parameter.
Vessel extraction based on 3 D medical image and analysis method, include the following steps：
Step S1 carries out high-resolution three-dimensional using magnetic resonance and Computed tomography to human body cardiovascular and cerebrovascular
Imaging, obtains the blood vessel image of different contrast；
Step S2, from the blood vessel image of different contrast, sense where determining blood vessel using automatically or semi-automatically method
The size in interest region；
Step S3, it is different according to the signal-to-noise ratio of area-of-interest blood vessel and geometric shape, it is selective it is carried out noise reduction,
Smoothly, re-sampling operations；
Step S4 is detached by blood vessel and with signal similar in blood vessel gray value from blood vessel image by region growing；
Step S5 enhances to the blood vessel isolated and with signal similar in blood vessel gray value；
Step S6 constructs hodograph according to enhanced blood vessel gray value so that the corresponding velocity amplitude of angiosomes compared with
Height, the corresponding velocity amplitude in non-vascular region are relatively low；
Step S7, the hodograph based on structure extract endovascular continuous path；
Step S8 carries out angiosomes search using multi-parameter geometric deformable models, extracts the bianry image of blood vessel, completes
The extraction of blood vessel.
Further, further comprising the steps of：
Step S9 is based on blood vessel bianry image, and the space geometry position according to blood vessel again pulls up hodograph, and to blood vessel
Region scans for, and obtains the center line of extracted blood vessel；
Step S10 automatically extracts out a series of two-dimentional vessel cross-sections, obtains blood vessel morphology according to vessel centerline
Parameter.
Beneficial effects of the present invention：It is provided by the invention based on the vessel extraction system of 3 D medical image and analysis side
For method, it can be achieved that from the blood vessel image of different contrast, segmentation extracts interested blood vessel, and is carried out to its Morphologic Parameters
The quantitative measurment of automation；By using the geometric deformable models of multi-parameter, it is applicable to the blood vessel structure extraction of different shape；
By using new processing method, dependence of the above-mentioned model to primary condition, boosting algorithm stability are significantly reduced, and expand
Its application scenarios, such as the extraction of low signal blood vessel, intravascular there are interlayers etc.；Algorithm uses parallel computation, vessel extraction speed
Soon；By the quantitative interested blood vessel Morphologic Parameters of automation, manually-operated triviality and uncertainty are avoided.
Description of the drawings
Present invention is further described in detail in the following with reference to the drawings and specific embodiments.
Fig. 1 is the system schematic of the present invention.
Fig. 2 is flow chart of the method for the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained all other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, the present invention provides a kind of vessel extraction system based on 3 D medical image, including blood vessel imaging
Module, region selection module, image pre-processing module, region growing module, image enhancement module, hodograph constructing module, blood
Pipe extraction module, centerline determination module and parameters measurement module.
Blood vessel imaging module carries out high-resolution using magnetic resonance and Computed tomography to human body cardiovascular and cerebrovascular
Three-dimensional imaging, obtain the blood vessel image of different contrast.
Region selection module, in the blood vessel image of the different contrast obtained from blood vessel imaging module, using automatic or half
The size of area-of-interest where automatic method determines blood vessel.
Image pre-processing module, according to the signal-to-noise ratio and geometric shape of the area-of-interest blood vessel of region selection module extraction
Difference, it is selective that noise reduction, smooth, re-sampling operations are carried out to it, in order to subsequent processing.
Region growing module, by region growing will pass through image pre-processing module treated blood vessel and with blood vessel gray scale
Signal is detached from blood vessel image similar in value.
Image enhancement module, the blood vessel isolated to region growing module and increases with signal similar in blood vessel gray value
By force.
Hodograph constructing module constructs hodograph so that blood according to the enhanced blood vessel gray value of image enhancement module
The corresponding velocity amplitude in area under control domain is higher, and the corresponding velocity amplitude in non-vascular region is relatively low.
Vessel extraction module extracts endovascular continuous path, so based on the hodograph of hodograph constructing module structure
It uses multi-parameter geometric deformable models to carry out angiosomes search afterwards, extracts the bianry image of blood vessel, complete the extraction of blood vessel.
Centerline determination module, based on the blood vessel bianry image of vessel extraction module extraction, the space geometry according to blood vessel
Position again pulls up hodograph, and is scanned for angiosomes, to obtain the center line of extracted blood vessel.
Parameters measurement module automatically extracts out a series of two dimensions according to the vessel centerline of centerline determination module extraction
Vessel cross-sections obtain blood vessel morphology parameter；Wherein, blood vessel morphology parameter includes maximum gauge, equivalent diameter, most imperial palace
Tangential circle diameter, area, perimeter and magnification etc..
As shown in Fig. 2, a kind of vessel extraction and analysis method based on 3 D medical image, specifically include following steps：
Step S1 carries out high-resolution three-dimensional using magnetic resonance and Computed tomography to human body cardiovascular and cerebrovascular
Imaging, obtains the blood vessel image of different contrast.
Step S2, from the blood vessel image of different contrast, sense where determining blood vessel using automatically or semi-automatically method
The size in interest region.
Step S3, it is different according to the signal-to-noise ratio of area-of-interest blood vessel and geometric shape, it is selective it is carried out noise reduction,
Smoothly, re-sampling operations.
Step S4 is detached by blood vessel and with signal similar in blood vessel gray value from blood vessel image by region growing.
Step S5 enhances to the blood vessel isolated and with signal similar in blood vessel gray value.
Step S6 constructs hodograph according to enhanced blood vessel gray value so that the corresponding velocity amplitude of angiosomes compared with
Height, the corresponding velocity amplitude in non-vascular region are relatively low.
Step S7, the hodograph based on structure extract endovascular continuous path.
Step S8 carries out angiosomes search using multi-parameter geometric deformable models, extracts the bianry image of blood vessel, completes
The extraction of blood vessel.
Step S9 is based on blood vessel bianry image, and the space geometry position according to blood vessel again pulls up hodograph, and to blood vessel
Region scans for, and obtains the center line of extracted blood vessel.
Step S10 automatically extracts out a series of two-dimentional vessel cross-sections, obtains blood vessel morphology according to vessel centerline
Parameter.
Vessel extraction system and analysis method provided by the invention based on 3 D medical image, it is intended to from different contrast
Blood vessel image in, segmentation extracts interested blood vessel, and to quantitative measurment that its Morphologic Parameters is automated.Pass through
Using the geometric deformable models of multi-parameter, it is applicable to the blood vessel structure extraction of different shape；By using new processing method,
Dependence of the above-mentioned model to primary condition, boosting algorithm stability are significantly reduced, and expands its application scenarios, such as low signal blood
The extraction of pipe, intravascular there are interlayers etc.；Algorithm uses parallel computation, vessel extraction speed fast；Quantitatively feel emerging by automation
Interesting blood vessel morphology parameter avoids manually-operated triviality and uncertainty.
In the description of this specification, the description of reference term " one embodiment ", " example ", " specific example " etc. means
Particular features, structures, materials, or characteristics described in conjunction with this embodiment or example are contained at least one implementation of the present invention
In example or example.In the present specification, schematic expression of the above terms may not refer to the same embodiment or example.
Moreover, particular features, structures, materials, or characteristics described can be in any one or more of the embodiments or examples to close
Suitable mode combines.
Above content is only to structure of the invention example and explanation, affiliated those skilled in the art couple
Described specific embodiment does various modifications or additions or substitutes by a similar method, without departing from invention
Structure or beyond the scope defined by this claim, is within the scope of protection of the invention.
Claims (4)
1. the vessel extraction system based on 3 D medical image, which is characterized in that including blood vessel imaging module, regional choice mould
Block, image pre-processing module, region growing module, image enhancement module, hodograph constructing module and vessel extraction module；
The blood vessel imaging module carries out high-resolution using magnetic resonance and Computed tomography to human body cardiovascular and cerebrovascular
Three-dimensional imaging, obtain the blood vessel image of different contrast；
The region selection module, in the blood vessel image of the different contrast obtained from blood vessel imaging module, using automatic or half
The size of area-of-interest where automatic method determines blood vessel；
Described image preprocessing module, according to the signal-to-noise ratio and geometric shape of the area-of-interest blood vessel of region selection module extraction
Difference, it is selective that noise reduction, smooth, re-sampling operations are carried out to it；
The region growing module, by region growing will pass through image pre-processing module treated blood vessel and with blood vessel gray scale
Signal is detached from blood vessel image similar in value；
Described image enhances module, the blood vessel isolated to region growing module and increases with signal similar in blood vessel gray value
By force；
The hodograph constructing module constructs hodograph so that blood according to the enhanced blood vessel gray value of image enhancement module
The corresponding velocity amplitude in area under control domain is higher, and the corresponding velocity amplitude in non-vascular region is relatively low；
The vessel extraction module extracts endovascular continuous path, so based on the hodograph of hodograph constructing module structure
It uses multi-parameter geometric deformable models to carry out angiosomes search afterwards, extracts the bianry image of blood vessel, complete the extraction of blood vessel.
2. the vessel extraction system according to claim 1 based on 3 D medical image, which is characterized in that further include center
Line search module and parameters measurement module；
The centerline determination module, based on the blood vessel bianry image of vessel extraction module extraction, the space geometry according to blood vessel
Position again pulls up hodograph, and is scanned for angiosomes, obtains the center line of extracted blood vessel；
The parameters measurement module automatically extracts out a series of two dimensions according to the vessel centerline of centerline determination module extraction
Vessel cross-sections obtain blood vessel morphology parameter.
3. the vessel extraction based on 3 D medical image and analysis method, which is characterized in that include the following steps：
Step S1, using magnetic resonance and Computed tomography to human body cardiovascular and cerebrovascular carry out it is high-resolution it is three-dimensional at
Picture obtains the blood vessel image of different contrast；
Step S2 determines that blood vessel place is interested from the blood vessel image of different contrast using automatically or semi-automatically method
The size in region；
Step S3, it is selective to carry out noise reduction to it, put down according to the signal-to-noise ratio of area-of-interest blood vessel and geometric shape difference
Sliding, re-sampling operations；
Step S4 is detached by blood vessel and with signal similar in blood vessel gray value from blood vessel image by region growing；
Step S5 enhances to the blood vessel isolated and with signal similar in blood vessel gray value；
Step S6 constructs hodograph so that the corresponding velocity amplitude of angiosomes is higher, non-according to enhanced blood vessel gray value
The corresponding velocity amplitude of angiosomes is relatively low；
Step S7, the hodograph based on structure extract endovascular continuous path；
Step S8 carries out angiosomes search using multi-parameter geometric deformable models, extracts the bianry image of blood vessel, completes blood vessel
Extraction.
4. vessel extraction and analysis method according to claim 3 based on 3 D medical image, which is characterized in that also wrap
Include following steps：
Step S9 is based on blood vessel bianry image, and the space geometry position according to blood vessel again pulls up hodograph, and to angiosomes
It scans for, obtains the center line of extracted blood vessel；
Step S10 automatically extracts out a series of two-dimentional vessel cross-sections, obtains blood vessel morphology parameter according to vessel centerline.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810453488.1A CN108734771B (en) | 2018-05-14 | 2018-05-14 | Blood vessel extraction system and analysis method based on three-dimensional medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810453488.1A CN108734771B (en) | 2018-05-14 | 2018-05-14 | Blood vessel extraction system and analysis method based on three-dimensional medical image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108734771A true CN108734771A (en) | 2018-11-02 |
| CN108734771B CN108734771B (en) | 2020-01-21 |
Family
ID=63938252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810453488.1A Active CN108734771B (en) | 2018-05-14 | 2018-05-14 | Blood vessel extraction system and analysis method based on three-dimensional medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108734771B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109801271A (en) * | 2019-01-04 | 2019-05-24 | 上海联影医疗科技有限公司 | Localization method, device, computer equipment and the storage medium of calcification clusters |
| CN110353639A (en) * | 2019-07-16 | 2019-10-22 | 脑玺(上海)智能科技有限公司 | A kind of blood supply area quantitative approach and system based on blood vessel enhancing radiography |
| CN110477955A (en) * | 2019-08-22 | 2019-11-22 | 电子科技大学 | A kind of blood vessel automatic identifying method based on I/Q data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218797A (en) * | 2012-01-19 | 2013-07-24 | 中国科学院上海生命科学研究院 | Method and system for processing and analyzing blood vessel image |
| CN107203741A (en) * | 2017-05-03 | 2017-09-26 | 上海联影医疗科技有限公司 | Vessel extraction method, device and its system |
| CN107292928A (en) * | 2017-06-16 | 2017-10-24 | 沈阳东软医疗系统有限公司 | A kind of method and device of blood vessel positioning |
| US20180005085A1 (en) * | 2016-06-29 | 2018-01-04 | Niramai Health Analytix Pvt. Ltd. | Blood vessel extraction in two-dimensional thermography |
-
2018
- 2018-05-14 CN CN201810453488.1A patent/CN108734771B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218797A (en) * | 2012-01-19 | 2013-07-24 | 中国科学院上海生命科学研究院 | Method and system for processing and analyzing blood vessel image |
| US20180005085A1 (en) * | 2016-06-29 | 2018-01-04 | Niramai Health Analytix Pvt. Ltd. | Blood vessel extraction in two-dimensional thermography |
| CN107203741A (en) * | 2017-05-03 | 2017-09-26 | 上海联影医疗科技有限公司 | Vessel extraction method, device and its system |
| CN107292928A (en) * | 2017-06-16 | 2017-10-24 | 沈阳东软医疗系统有限公司 | A kind of method and device of blood vessel positioning |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109801271A (en) * | 2019-01-04 | 2019-05-24 | 上海联影医疗科技有限公司 | Localization method, device, computer equipment and the storage medium of calcification clusters |
| CN109801271B (en) * | 2019-01-04 | 2021-11-23 | 上海联影医疗科技股份有限公司 | Method and device for locating calcified cluster, computer equipment and storage medium |
| CN110353639A (en) * | 2019-07-16 | 2019-10-22 | 脑玺(上海)智能科技有限公司 | A kind of blood supply area quantitative approach and system based on blood vessel enhancing radiography |
| CN110477955A (en) * | 2019-08-22 | 2019-11-22 | 电子科技大学 | A kind of blood vessel automatic identifying method based on I/Q data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108734771B (en) | 2020-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110448319B (en) | Blood flow velocity calculation method based on contrast image and coronary artery | |
| CN107644420B (en) | Blood vessel image segmentation method based on centerline extraction and nuclear magnetic resonance imaging system | |
| EP3723038A1 (en) | Fast calculation method and system employing plaque stability index of medical image sequence | |
| CN109741335B (en) | Method and device for segmenting vascular wall and blood flow area in blood vessel OCT image | |
| CN110189258B (en) | Arteria carotis lumen and tube wall automatic division method based on the multi-modal sequence of MRI | |
| CN110111296B (en) | Deep learning automatic segmentation system and method for new hair subcortical infarction focus | |
| CN112308846B (en) | Blood vessel segmentation method and device and electronic equipment | |
| CN105279759A (en) | Abdominal aortic aneurysm outer contour segmentation method capable of combining context information narrow band constraints | |
| CN108734771A (en) | Vessel extraction system and analysis method based on 3 D medical image | |
| CN108109151B (en) | Method and device for segmenting ventricle of echocardiogram based on deep learning and deformation model | |
| CN107154047A (en) | Multi-mode brain tumor image blend dividing method and device | |
| WO2016159379A1 (en) | Apparatus and method for constructing blood vessel configuration and computer software program | |
| CN109478327A (en) | Method for detecting systemic arterial automatically in any kampometer calculation tomographic angiography (CTA) | |
| CN113066091A (en) | Cerebral vessel segmentation method and device based on black vessel wall curved surface reconstruction and storage medium | |
| CN113240684B (en) | Method for converting mask data extracted to contain coronary artery central line into central line point set | |
| CN101425140A (en) | Encephalic angioma image recognizing and detecting method based on framework characteristic | |
| CN115409859A (en) | Coronary artery blood vessel image segmentation method and device, storage medium and terminal | |
| CN113516644B (en) | Intravascular optical coherence tomography branch blood vessel identification method | |
| CN114533002A (en) | Carotid artery central line extraction method and device, storage medium and electronic equipment | |
| CN104915989A (en) | CT image-based blood vessel three-dimensional segmentation method | |
| CN116883341A (en) | Liver tumor CT image automatic segmentation method based on deep learning | |
| CN113744215B (en) | Extraction method and device for central line of tree-shaped lumen structure in three-dimensional tomographic image | |
| CN116547710A (en) | Method and system for segmenting and identifying at least one tubular structure in a medical image | |
| Miao et al. | CoWRadar: Visual Quantification of the Circle of Willis in Stroke Patients. | |
| Luo et al. | Resliced image space construction for coronary artery collagen fibers |
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 |