CN104978726A - Blood vessel extraction method - Google Patents
Blood vessel extraction method Download PDFInfo
- Publication number
- CN104978726A CN104978726A CN201410134530.5A CN201410134530A CN104978726A CN 104978726 A CN104978726 A CN 104978726A CN 201410134530 A CN201410134530 A CN 201410134530A CN 104978726 A CN104978726 A CN 104978726A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- result
- vessel
- mask
- connected domain
- 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
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides a blood vessel extraction method. The method comprises steps of reading angiography data; adopting a region growing method on the data to obtain a first result; adopting a level set method to obtain a second result; performing morphological combination according to the first result and the second result; and performing blood vessel extraction of the angiography data. According to the invention, advantages of the region growing method based on the threshold and the gradient and the level set method based on the radius and the gradient are effectively combined, and region growing of bones and blood vessels are flexibly utilized to assist the blood vessel extraction, so that the complete extraction of blood vessels can be achieved.
Description
Technical field
The present invention relates to field of medical image processing, particularly relate to a kind of vessel extraction method.
Background technology
Angiography (CTA) is one of important method of Current Diagnostic vascular diseases, is mainly used in the multiple vascular diseases of diagnosis and treatment clinically, as aneurysm, hemadostewnosis, angiosteosis etc.Being partitioned into from its hetero-organization by blood vessel is committed step in Angiography.Because CTA image medium vessels is overlapping with the CT value of its hetero-organizations such as bone, current main blood vessel segmentation method such as region growth, dynamic outline etc. are easy to the tissues such as bone to be mistakened as into vessel extraction, cause over-segmentation or minute blood vessel etc. is removed as non-vascular tissue, causing segmentation incomplete.
Document 1:P.T.Vieco, W.P.Shuman, the scissors for vessels image method provided in G.F.Alsofrom and C.E.Gross.Detection of circle of Willis aneurysms in patients with acutesubarachnoid hemorrhage:a comparison of CT angiography and digitalsubtraction angiography.AJR vol.165no.2425-430 (1995), the same position of client need scans 2 times, be respectively not injection of contrast medium scanning and injection of contrast medium scanning, obtain non-CTA image and CTA image.In non-CTA image, blood vessel CT value is low, and CTA image medium vessels CT value raises.Subtracting each other after such 2 kinds of image registrations just can by vessel extraction out.The method needs to scan 2 times to patient, more consuming time, brings more scanning radiation amount to patient simultaneously.
Document 2:Cristian Lorenz, Steffen Renisch, Thorsten
thomas B ü low.Simultaneous segmentation and tree reconstruction of thecoronary arteries in MSCT images.Proceedings of SPIE Vol.5031 (2003) provides a kind of dividing method based on level set, the method is after determining blood vessel starting point, propagated to surrounding by level set algorithm, by the process of the topological structure of blood vessel as the correction such as radius, the bifurcated propagation of blood vessel in communication process.The method effectively can extract the blood vessel of tree structure, but is not suitable for the situations such as large aneurysm, because tumour is easy to be judged rejection by radius.
Document 3:Olivi er Cui senairea, Sunny Virmanib, Mark E.Olszewskib, Roberto Ardona.Fully automated segmentation of carotid and vertebralarteries from contrast enhanced CTA.Proc.of SPIE Vol.6914,69143R, (2008) a kind of method based on model is provided, first by CTA image and existing vascular pattern registration, obtain the starting point of different blood vessel, then connect starting point by algorithm, obtain the center line of blood vessel.Finally being initial with center line, being expanded outwardly by simple grid, extracting blood vessel.The method effect is better, but calculates very complicated, and splitting speed is extremely slow, inapplicable practical clinical.
Prior art additionally provides a kind of region growing methods based on threshold value, and the neighbor of similar to Seed Points (as CT value is in same range), from one group of initial seed point, is attached on the Seed Points of region growth by this algorithm.The method computing velocity is fast, because of relevant to threshold size, and poor robustness.When threshold range is less than normal, cannot extract the tiny branch of blood vessel, when threshold range is bigger than normal, the tissues such as part bone can be treated as blood vessel, cause over-segmentation.
Summary of the invention
The problem that the present invention solves is to provide a kind of vessel extraction method, in order to complete extraction blood vessel.
In order to solve the problem, the invention provides a kind of vessel extraction method, comprise: read angiographic data, and adopt region growing method to obtain the first result respectively to described data, and adopt Level Set Method to obtain the second result, and carry out morphology combination according to described first result and the second result, vessel extraction is carried out to described angiographic data.
Optionally, the region growing method that described region growing method comprises based on threshold value and gradient is tentatively boned, and the region growing method then based on gradient extracts blood vessel; Described Level Set Method is extract blood vessel based on the Level Set Method of radius and gradient.
Optionally, result corresponding for described morphology combination is carried out the add operation of union phase with described second result, to carry out the extraction of supplementary blood vessel to described second result.
Optionally, described morphological outcomes comprises the first subtraction mask being subtracted each other acquisition by described first result and described second result.
Optionally, the independent connected domain obtaining some numbers in described first subtraction mask is also comprised; And structure decision is carried out to described connected domain, to remove bone in described first subtraction mask and tissue.
Optionally, described structure decision comprise connected domain count judgement and connected domain cross-sectional area judge.
Optionally, described connected domain cross-sectional area judges to comprise: first calculate the two-layer vascular cross-section that described connected domain number is maximum, carry out connected domain calculating to described two-layer vascular cross-section, calculate maximum connected domain cross-sectional area; And judge bone and blood vessel based on described cross-sectional area.
Optionally, also comprise after blood vessel is extracted in described morphology combination and extract kidney and minute blood vessel.
Optionally, described extraction kidney and minute blood vessel comprise: described angiographic data is CT angiographic data, first threshold and Second Threshold are provided, the pixel that CT value is greater than described first threshold is extracted as Seed Points, from described angiographic data, extract the pixel being greater than described Second Threshold, obtain the first mask of bone and blood vessel; Described first mask is deducted mask corresponding to the second result, obtains the second subtraction mask.
Optionally, also comprise and the 3rd threshold value is provided, and using the point being greater than described 3rd threshold value as Seed Points, extract in described second subtraction mask and remove bone, obtaining the second mask; Second result is carried out region growing on described second mask, to complete the vessel extraction comprising kidney and minute blood vessel.
Optionally, described first threshold scope is 200 ~ 400; Described Second Threshold scope is 120 ~ 170; Described 3rd threshold range is 700 ~ 900.
The advantage that the present invention proposes the growth of a kind of calmodulin binding domain CaM and level set completes the method for blood vessel complete extraction.Region growing method based on threshold value and gradient can find 3-4 level blood vessel, but may grow to part bone and tissue; The blood vessel extracted based on the Level Set Method of radius and gradient is comparatively clean, generally do not grow to bone, but minute blood vessel can not find completely.The advantage of these two kinds of methods effectively combines by the present invention, and the extraction of the region growing secondary vessel of apply in a flexible way bone and blood vessel, thus realize the complete extraction of blood vessel.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the vessel extraction method of one embodiment of the invention.
Fig. 2 is the morphology combined method schematic flow sheet of one embodiment of the invention.
Fig. 3 is each phase results comparison diagram of the vessel extraction method of one embodiment of the invention.
Figure 4 shows that the vessel extraction middle kidney of one embodiment of the invention and the schematic flow sheet of minute blood vessel extraction.
Figure 5 shows that the vessel extraction middle kidney of one embodiment of the invention and the effect schematic diagram of minute blood vessel extraction.
Figure 6 shows that the effect schematic diagram of the vessel extraction method of other embodiments.
Embodiment
Set forth a lot of detail in the following description so that fully understand the present invention.But the present invention can be much different from alternate manner described here to implement, those skilled in the art can when without prejudice to doing similar popularization when intension of the present invention, therefore the present invention is by the restriction of following public concrete enforcement.
Secondly, the present invention utilizes schematic diagram to be described in detail, and when describing the embodiment of the present invention in detail, for ease of illustrating, described schematic diagram is example, and it should not limit the scope of protection of the invention at this.
The invention provides a kind of vessel extraction method, it is characterized in that, comprise: read angiographic data, and adopt region growing method to obtain the first result respectively to described data, and adopt Level Set Method to obtain the second result, and carry out morphology combination according to described first result and the second result, vessel extraction is carried out to described angiographic data.Wherein, the region growing method that described region growing method comprises based on threshold value and gradient is tentatively boned, and the region growing method then based on gradient extracts blood vessel; Described Level Set Method is extract blood vessel based on the Level Set Method of radius and gradient.
Further, after obtaining two above-mentioned results, also comprise and deduct mask corresponding to the second result with the mask that described first result is corresponding, obtain the first subtraction mask, to carry out described morphology combination.
After obtaining described first subtraction mask, connected domain calculating is carried out to described first subtraction mask, obtain the independently connected domain of the some numbers in described first subtraction mask.And structure decision is carried out to the connected domain of described first subtraction mask, to remove bone in described mask and tissue.Described structure decision comprise connected domain count judgement and connected domain cross-sectional area judge.
Further, described connected domain cross-sectional area judges to comprise: first calculate the two-layer vascular cross-section that described connected domain number is maximum, connected domain calculating is carried out to described two-layer vascular cross-section, obtain maximum connected domain, and calculating the cross-sectional area of described connected domain, described connected domain cross-sectional area is that counting of connected domain is multiplied by the resolution of data.
Wherein, described connected domain cross-sectional area judges also to comprise: provide area threshold, if described cross-sectional area is greater than described area threshold, then described connected domain is then bone, if described cross-sectional area is not more than described area threshold, then described connected domain is then blood vessel.
Particularly, described area threshold scope is 100 ~ 200.Preferably, described area threshold is 140.
After obtaining the first subtraction mask of above-mentioned removal bone and tissue, also comprise and the morphological outcomes of the first subtraction mask of described removal bone is carried out the add operation of union phase with the second result, to carry out the extraction of supplementary blood vessel to the second result.Namely carry out blood vessel to described second result to supplement, to supplement the vessel information being extracted in the second result and failing and extract.
Further, also comprise after blood vessel is extracted in described morphology combination: extract kidney and minute blood vessel.
As an embodiment, described angiographic data is CT angiographic data, described extraction kidney and minute blood vessel comprise: provide first threshold and Second Threshold, CT value is greater than the pixel of described first threshold as Seed Points, and extract with described Seed Points, from described angiographic data, extract the pixel being greater than described Second Threshold, obtain the first mask of bone and blood vessel.
Then, described first mask is deducted mask corresponding to the second result, obtain the second subtraction mask.And extract from described second subtraction mask and remove bone, obtain the second mask.
Further, comprise and the 3rd threshold value is provided, and to be greater than the point of described 3rd threshold value as Seed Points in described second subtraction mask, from described second subtraction mask, extract bone, and remove described bone, obtain the second mask.
Further, described first threshold scope is 200 ~ 400, is preferably 300; Described Second Threshold scope is 120 ~ 170, preferably position 130; Described 3rd threshold range is 700 ~ 900, is preferably 800.
Finally, the second result of above-mentioned acquisition is carried out region growing on described second mask, to obtain described kidney and minute blood vessel.
Be described in detail below in conjunction with the vessel extraction method of accompanying drawing to one embodiment of the invention.
Fig. 1 is the schematic flow sheet of the vessel extraction method of one embodiment of the invention.
As shown in Figure 1, comprise and perform step S1, angiographic data is provided; Then perform step S21 and step S22, namely described angiographic data is slightly carried blood vessel and is obtained the first result respectively, and carries out essence and carry blood vessel and obtain the second result; Then perform the combination of step S3 morphology, be about to slightly to put forward the second result that the first result of blood vessel and essence carry blood vessel and carry out morphology combination, the second result carrying blood vessel to described essence is carried out blood vessel and is supplemented, with complete described vessel extraction.Finally after morphology combination, also comprise and perform step S4, supplement kidney and minute blood vessel.
Be illustrated in figure 2 the morphology combined method schematic flow sheet of one embodiment of the invention, comprise: perform step S21, the result slightly carrying blood vessel deducts the result that essence carries blood vessel; Perform step S22, connected domain calculating is carried out to the result of subtracting each other acquisition; Perform step S23, remove bone connected domain; Perform step S24, residue connected domain and essence are carried blood vessel and combines, namely carry out the add operation of union phase, to propose the extraction that blood vessel carries out supplementary blood vessel to essence.Above-mentioned slightly carry blood vessel and essence puies forward blood vessel corresponding first result and the second result respectively.The described result slightly carrying blood vessel deduct essence carry blood vessel result obtain be the first subtraction mask.Subsequently, also comprise and connected domain calculating is carried out to described first subtraction mask, obtain the independently connected domain of the some numbers in described first subtraction mask; And structure decision is carried out to the connected domain of described first subtraction mask, to remove bone in described mask and tissue.Described structure decision comprise connected domain count judgement and connected domain cross-sectional area judge.
Wherein, described connected domain cross-sectional area judges to comprise: first calculate maximum two-layer of this connected domain blood vessel, two-layerly connected domain calculating is carried out to described, get wherein maximum connected domain, calculate the area of described maximum connected domain, the area of described connected domain is that counting of described connected domain is multiplied by the resolution of data.
Connected domain area threshold is provided, if described connected domain area is greater than described connected domain area threshold, is then bone, otherwise is blood vessel.The threshold range of described connected domain area can be 100 ~ 200.In the present embodiment, described connected domain area threshold is 140.
Fig. 3 is each phase results comparison diagram of the vessel extraction method of one embodiment of the invention.Particularly, the 3a in Fig. 3 represents that essence puies forward the result schematic diagram of blood vessel.Wherein, the left side of 3a is the blood-vessel image that essence is carried, and right side is the angiogram after blood vessel essence is carried, and the figure on left side and right side adds up to the original angiogram provided.Illustrate the angiogram carrying blood vessel merely through essence, can find out that a lot of minute blood vessel and kidney all fail to propose.
3b in Fig. 3 is the result schematic diagram carrying blood vessel through the blood vessel essence of supplementing of morphology combination.Wherein, the left side of 3b is the blood-vessel image of the essence proposition through morphology combination, and the right side of 3b is the angiogram after the blood vessel essence of morphology combination is carried, and the figure on left side and right side adds up to the original angiogram provided.Can find out that kidney and part minute blood vessel still fail to extract, be retained in the angiogram after vessel extraction.
3c in Fig. 3 is without morphology combination, but the essence of supplementing being through kidney and minute blood vessel puies forward the result schematic diagram of blood vessel.Wherein, the left side of 3c is the blood-vessel image that the essence of supplementing through kidney and minute blood vessel is carried, and the right side of 3c is the angiographic data after the essence of supplementing through kidney and minute blood vessel carries blood vessel, and the figure on left side and right side adds up to the original angiogram provided.As can be seen from the figure, or the minute blood vessel of portions proximate vertebra fail successfully to extract from described angiogram.
3d in Fig. 3 is the result schematic diagram carrying blood vessel through the essence of supplementing of morphology combination and kidney and minute blood vessel.Wherein, the left side of 3d is the blood-vessel image that the essence of supplementing through morphology combination and kidney and minute blood vessel is carried, the right side of 3d is the angiographic data after the essence of supplementing through morphology combination and kidney and minute blood vessel carries blood vessel, and the figure on left side and right side adds up to the original angiogram provided.Can find out corresponding, minute blood vessel and kidney all can be extracted, thus realize the complete extraction of blood vessel.
Be illustrated in figure 4 the vessel extraction middle kidney of one embodiment of the invention and the schematic flow sheet of minute blood vessel extraction, Fig. 5 is the vessel extraction middle kidney of one embodiment of the invention and the effect schematic diagram of minute blood vessel.Composition graphs 4 and Fig. 5, comprising: perform step S31, provide CTA data, i.e. angiographic data; Perform step S32, extract bone and blood vessel, obtain mask A, namely obtain the mask A as shown in 5a in Fig. 5; Perform step S33, mask A deducted essence and puies forward blood vessel result, obtain mask B, as 5b in Fig. 5 be depicted as described in essence put forward the result of blood vessel, as the 5c in Fig. 5 is depicted as mask B; Perform step S34, remove the bone in mask B, obtaining mask C, is described mask C as fig 5d; Perform step S35, carry blood vessel for Seed Points with essence, mask C result carries out region growing, obtains final blood vessel.Namely carry blood vessel for Seed Points with the essence in Fig. 5 shown in 5b, the mask C result shown in 5d in Figure 5 carries out region growing, obtains the blood vessel of the final extraction as shown in the 5e in Fig. 5.5f in Fig. 5 is the remaining angiogram of angiogram after above-mentioned vessel extraction of 5a, can find out that blood vessel and kidney extract complete by diagram.
Be illustrated in figure 6 the effect schematic diagram of the vessel extraction method at each position of other embodiments, wherein, 6a is the effect schematic diagram of the vessel extraction method of lower extremity; 6b is the effect schematic diagram of the vessel extraction method of belly; 6c is the effect schematic diagram of the vessel extraction method of incidence.In the vessel extraction effect schematic diagram at each position of above-mentioned 6a/6b/6c, respectively be from left to right and slightly put forward result, essence puies forward blood vessel result schematic diagram, the vascular effects schematic diagram of the first subtraction mask, net result.
Energy Fast Segmentation of the present invention goes out the blood vessel in CTA image, and lower limb abdominal vascular splits about 10-30s, cephalothorax about 1 minute.By contrast, other workstations of same segmentation effect, its lower limb vascular splits about 2-4 minute, and other positions are about 1-3 minute.
The advantage that the present invention proposes the growth of a kind of calmodulin binding domain CaM and level set completes the method for blood vessel complete extraction.Region growing method based on threshold value and gradient can find 3-4 level blood vessel, but may grow to part bone and tissue; The blood vessel extracted based on the Level Set Method of radius and gradient is comparatively clean, generally do not grow to bone, but minute blood vessel can not find completely.The advantage of these 2 kinds of methods effectively combines by the present invention, and the extraction of the region growing secondary vessel of apply in a flexible way bone and blood vessel, thus realize the complete extraction of blood vessel.
Although the present invention with preferred embodiment openly as above; but it is not for limiting the present invention; any those skilled in the art without departing from the spirit and scope of the present invention; the Method and Technology content of above-mentioned announcement can be utilized to make possible variation and amendment to technical solution of the present invention; therefore; every content not departing from technical solution of the present invention; the any simple modification done above embodiment according to technical spirit of the present invention, equivalent variations and modification, all belong to the protection domain of technical solution of the present invention.
Claims (11)
1. a vessel extraction method, it is characterized in that, comprise: read angiographic data, and adopt region growing method to obtain the first result respectively to described data, and adopt Level Set Method to obtain the second result, and carry out morphology combination according to described first result and the second result, vessel extraction is carried out to described angiographic data.
2. vessel extraction method as claimed in claim 1, it is characterized in that, the region growing method that described region growing method comprises based on threshold value and gradient is tentatively boned, and the region growing method then based on gradient extracts blood vessel; Described Level Set Method is extract blood vessel based on the Level Set Method of radius and gradient.
3. vessel extraction method as claimed in claim 1, is characterized in that, result corresponding for described morphology combination is carried out the add operation of union phase with described second result, to carry out the extraction of supplementary blood vessel to described second result.
4. vessel extraction method as claimed in claim 1, it is characterized in that, described morphological outcomes comprises the first subtraction mask being subtracted each other acquisition by described first result and described second result.
5. vessel extraction method as claimed in claim 4, is characterized in that, also comprises the independent connected domain obtaining some numbers in described first subtraction mask; And structure decision is carried out to described connected domain, to remove bone in described first subtraction mask and tissue.
6. vessel extraction method as claimed in claim 5, is characterized in that, described structure decision comprises count judgement and connected domain cross-sectional area of connected domain and judges.
7. vessel extraction method as claimed in claim 6, it is characterized in that, described connected domain cross-sectional area judges to comprise: first calculate the two-layer vascular cross-section that described connected domain number is maximum, carry out connected domain calculating to described two-layer vascular cross-section, calculate maximum connected domain cross-sectional area; And judge bone and blood vessel based on described cross-sectional area.
8. vessel extraction method as claimed in claim 1, is characterized in that, also comprises and extract kidney and minute blood vessel after blood vessel is extracted in described morphology combination.
9. vessel extraction method as claimed in claim 8, it is characterized in that, described extraction kidney and minute blood vessel comprise: described angiographic data is CT angiographic data, first threshold and Second Threshold are provided, the pixel that CT value is greater than described first threshold is extracted as Seed Points, from described angiographic data, extract the pixel being greater than described Second Threshold, obtain the first mask of bone and blood vessel; Described first mask is deducted mask corresponding to the second result, obtains the second subtraction mask.
10. vessel extraction method as claimed in claim 9, is characterized in that, also comprise and provide the 3rd threshold value, and using the point being greater than described 3rd threshold value as Seed Points, extract and remove bone, obtain the second mask in described second subtraction mask; Second result is carried out region growing on described second mask, to complete the vessel extraction comprising kidney and minute blood vessel.
11. vessel extraction methods as claimed in claim 10, it is characterized in that, described first threshold scope is 200 ~ 400; Described Second Threshold scope is 120 ~ 170; Described 3rd threshold range is 700 ~ 900.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410134530.5A CN104978726A (en) | 2014-04-03 | 2014-04-03 | Blood vessel extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410134530.5A CN104978726A (en) | 2014-04-03 | 2014-04-03 | Blood vessel extraction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104978726A true CN104978726A (en) | 2015-10-14 |
Family
ID=54275207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410134530.5A Pending CN104978726A (en) | 2014-04-03 | 2014-04-03 | Blood vessel extraction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104978726A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427277A (en) * | 2015-10-30 | 2016-03-23 | 上海联影医疗科技有限公司 | Blood vessel extraction method |
| CN106296664A (en) * | 2016-07-30 | 2017-01-04 | 上海联影医疗科技有限公司 | Vessel extraction method |
| CN106485704A (en) * | 2016-09-30 | 2017-03-08 | 上海联影医疗科技有限公司 | The extracting method of vessel centerline |
| CN106530283A (en) * | 2016-10-20 | 2017-03-22 | 北京工业大学 | SVM (support vector machine)-based medical image blood vessel recognition method |
| CN106682636A (en) * | 2016-12-31 | 2017-05-17 | 上海联影医疗科技有限公司 | Blood vessel extraction method and system |
| CN106875375A (en) * | 2016-12-28 | 2017-06-20 | 浙江工业大学 | Three-dimensional blood vessel axis detection method based on tubulose feature enhancing filtering and ridge line tracking |
| CN107248155A (en) * | 2017-06-08 | 2017-10-13 | 东北大学 | A kind of Cerebral venous dividing method based on SWI images |
| CN108805871A (en) * | 2018-06-14 | 2018-11-13 | 艾瑞迈迪医疗科技（北京）有限公司 | Blood-vessel image processing method, device, computer equipment and storage medium |
| CN108876794A (en) * | 2017-05-16 | 2018-11-23 | 西门子保健有限责任公司 | Aneurysm in volumetric image data with carry being isolated for tumor blood vessel |
| CN109410221A (en) * | 2018-10-31 | 2019-03-01 | 上海联影医疗科技有限公司 | Brain perfusion image dividing method, device, server and storage medium |
| CN109410191A (en) * | 2018-10-18 | 2019-03-01 | 中南大学 | Optical fundus blood vessel localization method and its anaemia screening method based on OCT image |
| CN110706246A (en) * | 2019-10-15 | 2020-01-17 | 上海微创医疗器械（集团）有限公司 | Blood vessel image segmentation method and device, electronic equipment and storage medium |
| US10869644B2 (en) | 2016-07-30 | 2020-12-22 | Shanghai United Imaging Healthcare Co., Ltd. | Method and system for extracting lower limb vasculature |
| CN112767332A (en) * | 2021-01-08 | 2021-05-07 | 心医国际数字医疗系统(大连)有限公司 | Blood vessel region judgment method and system based on CTA image |
| CN113012114A (en) * | 2021-03-02 | 2021-06-22 | 推想医疗科技股份有限公司 | Blood vessel identification method and device, storage medium and electronic equipment |
| CN113192099A (en) * | 2021-04-30 | 2021-07-30 | 上海联影医疗科技股份有限公司 | Tissue extraction method, device, equipment and medium |
| CN114445445A (en) * | 2022-04-08 | 2022-05-06 | 广东欧谱曼迪科技有限公司 | Artery segmentation method and device for CT image, electronic device and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551906A (en) * | 2009-05-13 | 2009-10-07 | 西安电子科技大学 | Extraction method of main blood vessels from abdominal CT images based on watershed of three-dimensional region |
| 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 |
-
2014
- 2014-04-03 CN CN201410134530.5A patent/CN104978726A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551906A (en) * | 2009-05-13 | 2009-10-07 | 西安电子科技大学 | Extraction method of main blood vessels from abdominal CT images based on watershed of three-dimensional region |
| 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 |
Non-Patent Citations (4)
| Title |
|---|
| JIANG LIU等: "CALM：CAscading system with Leaking detection mechanism for Medical image segmentation", 《PROCEEDINGS OF THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING》 * |
| M. K. BASHAR等: "Automatic Segmentation of Abdominal Blood Vessels from Contrasted X-ray CT Images", 《6TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING》 * |
| XU DANHUA等: "Level-set Based Bone Removal and Cerebral Vessel Detection in CTA", 《CHINESE JOURNAL OF ELECTRONICS》 * |
| YU QIANZHAO等: "Retinal vessels segmentation based on level set and region growing", 《PATTERN RECOGNITION》 * |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427277A (en) * | 2015-10-30 | 2016-03-23 | 上海联影医疗科技有限公司 | Blood vessel extraction method |
| CN105427277B (en) * | 2015-10-30 | 2018-01-16 | 上海联影医疗科技有限公司 | Vessel extraction method |
| WO2018023917A1 (en) * | 2016-07-30 | 2018-02-08 | 上海联影医疗科技有限公司 | Method and system for extracting lower limb blood vessel |
| CN106296664A (en) * | 2016-07-30 | 2017-01-04 | 上海联影医疗科技有限公司 | Vessel extraction method |
| US10869644B2 (en) | 2016-07-30 | 2020-12-22 | Shanghai United Imaging Healthcare Co., Ltd. | Method and system for extracting lower limb vasculature |
| CN106296664B (en) * | 2016-07-30 | 2019-10-08 | 上海联影医疗科技有限公司 | Vessel extraction method |
| CN106485704A (en) * | 2016-09-30 | 2017-03-08 | 上海联影医疗科技有限公司 | The extracting method of vessel centerline |
| CN106530283A (en) * | 2016-10-20 | 2017-03-22 | 北京工业大学 | SVM (support vector machine)-based medical image blood vessel recognition method |
| CN106875375B (en) * | 2016-12-28 | 2019-07-30 | 浙江工业大学 | A kind of three-dimensional blood vessel axis detection method based on tubulose signature tracking |
| CN106875375A (en) * | 2016-12-28 | 2017-06-20 | 浙江工业大学 | Three-dimensional blood vessel axis detection method based on tubulose feature enhancing filtering and ridge line tracking |
| US11062449B2 (en) | 2016-12-31 | 2021-07-13 | Shanghai United Imaging Healthcare Co., Ltd. | Method and system for extracting vasculature |
| CN106682636A (en) * | 2016-12-31 | 2017-05-17 | 上海联影医疗科技有限公司 | Blood vessel extraction method and system |
| WO2018120644A1 (en) * | 2016-12-31 | 2018-07-05 | 上海联影医疗科技有限公司 | Blood vessel extraction method and system |
| CN106682636B (en) * | 2016-12-31 | 2020-10-16 | 上海联影医疗科技有限公司 | Blood vessel extraction method and system |
| CN108876794A (en) * | 2017-05-16 | 2018-11-23 | 西门子保健有限责任公司 | Aneurysm in volumetric image data with carry being isolated for tumor blood vessel |
| CN107248155A (en) * | 2017-06-08 | 2017-10-13 | 东北大学 | A kind of Cerebral venous dividing method based on SWI images |
| CN108805871A (en) * | 2018-06-14 | 2018-11-13 | 艾瑞迈迪医疗科技（北京）有限公司 | Blood-vessel image processing method, device, computer equipment and storage medium |
| CN109410191B (en) * | 2018-10-18 | 2022-03-25 | 中南大学 | OCT (optical coherence tomography) image-based fundus blood vessel positioning method and anemia screening method thereof |
| CN109410191A (en) * | 2018-10-18 | 2019-03-01 | 中南大学 | Optical fundus blood vessel localization method and its anaemia screening method based on OCT image |
| CN109410221A (en) * | 2018-10-31 | 2019-03-01 | 上海联影医疗科技有限公司 | Brain perfusion image dividing method, device, server and storage medium |
| CN109410221B (en) * | 2018-10-31 | 2022-01-11 | 上海联影医疗科技股份有限公司 | Cerebral perfusion image segmentation method, device, server and storage medium |
| CN110706246A (en) * | 2019-10-15 | 2020-01-17 | 上海微创医疗器械（集团）有限公司 | Blood vessel image segmentation method and device, electronic equipment and storage medium |
| CN112767332B (en) * | 2021-01-08 | 2024-05-17 | 心医国际数字医疗系统(大连)有限公司 | Blood vessel region judging method and system based on CTA image |
| CN112767332A (en) * | 2021-01-08 | 2021-05-07 | 心医国际数字医疗系统(大连)有限公司 | Blood vessel region judgment method and system based on CTA image |
| CN113012114A (en) * | 2021-03-02 | 2021-06-22 | 推想医疗科技股份有限公司 | Blood vessel identification method and device, storage medium and electronic equipment |
| CN113192099A (en) * | 2021-04-30 | 2021-07-30 | 上海联影医疗科技股份有限公司 | Tissue extraction method, device, equipment and medium |
| CN113192099B (en) * | 2021-04-30 | 2023-02-17 | 上海联影医疗科技股份有限公司 | Tissue extraction method, device, equipment and medium |
| CN114445445A (en) * | 2022-04-08 | 2022-05-06 | 广东欧谱曼迪科技有限公司 | Artery segmentation method and device for CT image, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104978726A (en) | Blood vessel extraction method | |
| CN106296664B (en) | Vessel extraction method | |
| CN106682636B (en) | Blood vessel extraction method and system | |
| CN106485704B (en) | Method for extracting center line of blood vessel | |
| CN103886621B (en) | A kind of method for automatically extracting bed board | |
| CN108335304B (en) | Aortic aneurysm segmentation method of abdominal CT scanning sequence image | |
| CN104463860A (en) | Method for segmenting liver | |
| CN112767333B (en) | Dual-lower limb blood vessel region judging method and system based on CTA image | |
| CN109740602A (en) | Pulmonary artery phase vessel extraction method and system | |
| JP2004222864A (en) | Diagnosis supporting system, diagnosis supporting method and diagnosis supporting program | |
| Lloréns et al. | Jaw tissues segmentation in dental 3D CT images using fuzzy-connectedness and morphological processing | |
| CN109886973A (en) | A kind of vessel extraction method, apparatus and computer readable storage medium | |
| Alirr et al. | Hepatic vessels segmentation using deep learning and preprocessing enhancement | |
| CN104166979A (en) | Blood vessel extracting method | |
| Yu et al. | Quantification of the bone lacunocanalicular network from 3D X‐ray phase nanotomography images | |
| Lidayová et al. | Fast vascular skeleton extraction algorithm | |
| Affane et al. | Robust deep 3-D architectures based on vascular patterns for liver vessel segmentation | |
| CN111627023B (en) | Method and device for generating coronary artery projection image and computer readable medium | |
| CN106204546A (en) | The dividing method of venous sinus | |
| Wang et al. | Automatic multi-scale segmentation of intrahepatic vessel in CT images for liver surgery planning | |
| Kuo et al. | Three-dimensional reconstruction of trachea using computed tomography imaging as therapy for tracheal stenosis in infants | |
| CN112767332B (en) | Blood vessel region judging method and system based on CTA image | |
| KR101479845B1 (en) | Anterior cruciate ligament segmentation apparatus and the method from Knee MR images | |
| Ceresa et al. | Automatic leakage detection and recovery for airway tree extraction in chest CT images | |
| El Soufi et al. | CIMOR: An automatic segmentation to extract bone tissue in hand x-ray images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151014 |
|
| RJ01 | Rejection of invention patent application after publication |