CN109903298A - Restorative procedure, system and the computer storage medium of blood vessel segmentation image fracture - Google Patents
Restorative procedure, system and the computer storage medium of blood vessel segmentation image fracture Download PDFInfo
- Publication number
- CN109903298A CN109903298A CN201910186257.3A CN201910186257A CN109903298A CN 109903298 A CN109903298 A CN 109903298A CN 201910186257 A CN201910186257 A CN 201910186257A CN 109903298 A CN109903298 A CN 109903298A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- breaking part
- image
- segmentation image
- vessel segmentation
- 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
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 162
- 230000011218 segmentation Effects 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 28
- 241001269238 Data Species 0.000 claims description 32
- 230000008439 repair process Effects 0.000 claims description 22
- 239000000284 extract Substances 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 210000004351 coronary vessel Anatomy 0.000 abstract description 11
- 230000000694 effects Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 5
- 230000001225 therapeutic effect Effects 0.000 description 3
- 208000019553 vascular disease Diseases 0.000 description 3
- 238000002591 computed tomography Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides restorative procedure, system and the computer readable storage medium of a kind of blood vessel segmentation image fracture, and wherein the restorative procedure of blood vessel segmentation image fracture includes: to obtain blood vessel original image；Processing is split to form blood vessel segmentation image to the blood vessel original image using segmentation network；The breaking part in the blood vessel segmentation image is searched, and obtains the coordinate at the breaking part both ends；Part corresponding with the breaking part is chosen in the blood vessel original image according to the coordinate at the breaking part both ends；The breaking part in the blood vessel segmentation image is repaired using part corresponding with the breaking part in the blood vessel original image.The present invention can be improved the effect of coronary artery segmentation.
Description
Technical field
A kind of be broken the present invention relates to medical imaging technology more particularly to blood vessel segmentation image restorative procedure, system and
Computer storage medium.
Background technique
It is the current the most frequently used and most important means for treating coronary artery disease that coronary artery, which is rebuild, has important clinical valence
Value and practical significance.
Currently, can be led to using DiceLoss as the loss function of segmentation neural network in automation coronary artery reconstruction process
Machine learning, the neural metwork training acquisition coronary artery parted pattern for crossing sample image, using coronary artery parted pattern to data (such as CT
Image) coronary artery segmentation is carried out to form coronary artery segmented image.
However, in the process, coronary artery segmented image will appear the abnormal conditions such as noise, fracture, coronary artery segmentation is influenced
Effect.
Summary of the invention
The present invention provides restorative procedure, system and the computer storage medium of a kind of blood vessel segmentation image fracture, to improve
The effect of coronary artery segmentation.
One aspect of the present invention provides a kind of restorative procedure of blood vessel segmentation image fracture, comprising:
Obtain blood vessel original image；
Processing is split to form blood vessel segmentation image to the blood vessel original image using segmentation network；
The breaking part in the blood vessel segmentation image is searched, and obtains the coordinate at the breaking part both ends；
It is chosen in the blood vessel original image according to the coordinate at the breaking part both ends corresponding with the breaking part
Part；
Using part corresponding with the breaking part in the blood vessel original image in the blood vessel segmentation image
Breaking part is repaired.
Another aspect of the present invention provides a kind of repair system of blood vessel segmentation image fracture, comprising:
Original image obtains module, for obtaining blood vessel original image；
Blood vessel segmentation image collection module, for using segmentation network to the blood vessel original image be split processing with
Form blood vessel segmentation image；
Searching module for searching the breaking part in the blood vessel segmentation image, and obtains the seat at the breaking part both ends
Mark；
Module is chosen, chooses in the blood vessel original image for the coordinate according to the breaking part both ends and breaks with described
Split the corresponding part in place；
Repair module is used for using part corresponding with the breaking part in the blood vessel original image to the blood vessel
Breaking part in segmented image is repaired.
Further aspect of the present invention provides a kind of computer readable storage medium, and the storage medium includes one group of computer can
It executes instruction, requires the reparation of blood vessel segmentation image fracture of the present invention for perform claim when executed
Method.
The restorative procedure of blood vessel segmentation image provided by the invention fracture, using segmentation network to blood vessel original image into
During row dividing processing is to form blood vessel segmentation image, it will appear fracture in blood vessel segmentation image, breaking part includes fracture
Locate both ends and the lack part between breaking part both ends, in the breaking part found in blood vessel segmentation image and obtains fracture
After the coordinate for locating both ends, portion corresponding with breaking part can be chosen in blood vessel original image according to the coordinate at breaking part both ends
Point, it is corresponding due to that can have lack part with breaking part both ends and between breaking part both ends in blood vessel original image
Part, therefore the breaking part in blood vessel segmentation image can be repaired according to the corresponding part.Thereby, it is possible to make segmentation figure be in
Reveal more complete blood vessel, promotes the effect of coronary artery segmentation, enable a physician to the state of an illness for more comprehensively analyzing patient, thus
Conducive to the therapeutic effect for improving vascular diseases.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the restorative procedure of blood vessel segmentation image fracture provided in an embodiment of the present invention；
Fig. 2 is the flow chart of the restorative procedure of another blood vessel segmentation image fracture provided in an embodiment of the present invention；
Fig. 3 is the flow chart of the restorative procedure of another blood vessel segmentation image provided in an embodiment of the present invention fracture；
Fig. 4 A- Fig. 4 C is a kind of implementation result of the restorative procedure of blood vessel segmentation image fracture provided in an embodiment of the present invention
Schematic diagram；
Fig. 5 is a kind of structural schematic diagram of the repair system of blood vessel segmentation image fracture provided in an embodiment of the present invention.
Appended drawing reference:
101: original image obtains module；102: segmented image obtains module；
103: searching module；104: choosing module；
105: repair module；106: similitude judgment module；
107: comparison module；108: central line pick-up module；
109: endpoint extraction module；201: breaking part both ends；
301: two end datas；302: data to be judged.
Specific embodiment
To keep the purpose of the present invention, feature, advantage more obvious and understandable, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
It is only a part of the embodiment of the present invention, and not all embodiments.Based on the embodiments of the present invention, those skilled in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Embodiment one
Referring to FIG. 1, the embodiment of the present invention provides a kind of restorative procedure of blood vessel segmentation image fracture, including walk as follows
It is rapid:
Step S101 obtains blood vessel original image；
Tomoscan can be carried out to blood vessel by computed tomography (CT, Computed Tomography) equipment, with
Form blood vessel original image.
Step S201 is split processing to blood vessel original image using segmentation network to form blood vessel segmentation image；
By segmentation network can in blood vessel original image angiosomes and non-vascular region be labeled, with formed
Blood vessel segmentation image, however in the process, it will appear fracture in blood vessel segmentation image, i.e. breaking part includes breaking part both ends
201 and the lack part between breaking part both ends 201.
Step S301 searches the breaking part in blood vessel segmentation image, and obtains the coordinate at breaking part both ends 201；
It prepares as a result, for the processing next for breaking part.
Referring to FIG. 2, preferred, step S301 is specifically included:
Step S3011 extracts the center line of blood vessel segmentation image；
Since the center line of the breaking part of blood vessel segmentation image also will appear fracture, in the process for extracting center line
In, breaking part both ends 201 will be respectively formed respective center line.
Step S3012 extracts the endpoint of center line；
During extracting centerline end point, endpoint can be extracted on the center line at breaking part both ends 201.
Step S3013 searches the breaking part in blood vessel segmentation image according to the endpoint of center line, and obtains breaking part both ends
201 coordinate.
It, can be more according to the endpoint of center line due to can extract endpoint on the center line at breaking part both ends 201
Easily and accurately to find breaking part.
Step S401 chooses in blood vessel original image corresponding with breaking part according to the coordinate at breaking part both ends 201
Part；
Due to that can exist and breaking part both ends 201 and the missing between breaking part both ends 201 in blood vessel original image
The corresponding part in part, therefore can be accurately in blood vessel according to the coordinate at breaking part both ends 201 in blood vessel segmentation image
Part corresponding with the breaking part is chosen in original image.
Step S501, using part corresponding with breaking part in blood vessel original image to the fracture in blood vessel segmentation image
It is repaired at place.
It can be by the way that the part chosen in blood vessel original image and blood vessel segmentation image be merged, thus to blood vessel segmentation
Breaking part in image is repaired.Thereby, it is possible to make segmentation figure show more complete blood vessel, enable a physician to more complete
The state of an illness of the analysis patient in face, to be conducive to improve the therapeutic effect of vascular diseases.
Embodiment two
Referring to FIG. 3, on the basis of example 1, step S401 is specifically included:
According to the coordinate at breaking part both ends 201, portion corresponding with breaking part both ends 201 is chosen in blood vessel original image
It is allocated as two end datas 301, and is choosing portion corresponding with lack part between breaking part both ends 201 in blood vessel original image
It is allocated as data 302 to be judged.
It further include step S402 after step S401, step S402 includes:
It is treated using similar network and judges that data 302 and two end datas 301 carry out similitude judgement and export similitude to sentence
Disconnected prediction data.
In similitude deterministic process, data 302 to be judged can be compared with two end datas 301 respectively, with judgement
Data 302 the to be judged similitude with two end datas 301 respectively.Wherein, it when being trained to similar network, can be set to training
It is standby to input multiple blood vessel original image cases so that similar network carries out similitude training, while similitude is inputted to training equipment
The labeled data of judgement, and the prediction data that similar network carries out similitude judgement obtained by similitude training is sentenced with similitude
Disconnected labeled data is compared, and so as to obtain loss function, and restrains loss function by the training of multiple similitude,
So that similitude network improves.
Corresponding, after step S402, step S501 is specifically included:
If similitude judges that prediction data shows that data 302 to be judged and two end datas 301 are similar, will data be judged
302 merge with blood vessel segmentation image, to repair to the breaking part in blood vessel segmentation image.
Since the adjacent part similarity on same blood vessel is higher, if similitude judges that prediction data is shown wait judge
Data 302 and two end datas 301 are similar, then it is adjacent on same blood vessel to illustrate that data 302 to be judged belong to two end datas 301
Part, so as to think that the data 302 to be judged are the lack part of blood vessel segmentation image breaking part.It later can will be wait sentence
Disconnected data 302 merge with blood vessel segmentation image, to complete the reparation to the breaking part in blood vessel segmentation image.It improves as a result,
The accuracy repaired.
It please refers to Fig. 4 A- Fig. 4 C and first looks for the breaking part in blood vessel segmentation image in a specific repair process,
And obtain the coordinate (as shown in Figure 4 A) at breaking part both ends 201；It is original in blood vessel later according to the coordinate at breaking part both ends 201
Corresponding with breaking part both ends 201 part is chosen in image as two end datas 301, and choose in blood vessel original image and
The corresponding part of lack part is used as data 302 to be judged between breaking part both ends 201, is treated sentence using similar network later
Disconnected data 302 and two end datas 301 carry out similitude judgement and export similitude judging prediction data (as shown in Figure 4 B)；Most
Afterwards, if similitude judges that prediction data shows that data 302 to be judged and two end datas 301 are similar, will data be judged 302 with
Blood vessel segmentation image merges, to be repaired (as shown in Figure 4 C) to the breaking part in blood vessel segmentation image.
Embodiment three
It on the basis of example 2, further include step S601 after step S402, step S601 includes:
By similitude judge prediction data with using data 302 to be judged and the corresponding labeled data of two end datas 301 into
The similitude of row similitude judgement judges that labeled data is compared.
Prediction data labeled data corresponding with utilization data 302 to be judged and two end datas 301 is judged by similitude
The similitude for carrying out similitude judgement judges that labeled data is compared, and can obtain loss function, therefore can be by the loss letter
The foundation that loss function obtained in several and similar network is trained before this is trained together as similar network, to be conducive to similar net
Network it is perfect.
Referring to FIG. 5, the embodiment of the present invention provides a kind of repair system of blood vessel segmentation image fracture, comprising: original graph
As obtaining module 101, for obtaining blood vessel original image；Segmented image obtains module 102, for utilizing segmentation network to blood vessel
Original image is split processing to form blood vessel segmentation image；Searching module 103, it is disconnected in blood vessel segmentation image for searching
Place is split, and obtains the coordinate at breaking part both ends 201；Choose module 104, for according to the coordinate at breaking part both ends 201 in blood vessel
Part corresponding with breaking part is chosen in original image；Repair module 105 is used to utilize in blood vessel original image and breaking part
Corresponding part is repaired by the breaking part in blood vessel segmentation image.
Processing is split to be formed to blood vessel original image using segmentation network in blood vessel segmentation image collection module 102
During blood vessel segmentation image, it will appear fracture in blood vessel segmentation image, breaking part includes breaking part both ends 201 and is located at disconnected
The lack part between place both ends 201 is split, breaking part and acquisition in blood vessel segmentation image are being found by searching for module 103
It, can be by choosing module 104 according to the coordinate at breaking part both ends 201 in blood vessel original image after the coordinate at breaking part both ends 201
It is middle to choose part corresponding with breaking part, due to that can exist in blood vessel original image with breaking part both ends 201 and positioned at fracture
Locate both ends 201 between the corresponding part of lack part, therefore can by repair module 105 according to the corresponding part to blood vessel
Breaking part in segmented image is repaired.Thereby, it is possible to make segmentation figure show more complete blood vessel, enable a physician to more
For the state of an illness for comprehensively analyzing patient, to be conducive to improve the therapeutic effect of vascular diseases.
In the present embodiment, it is preferred that the repair system of blood vessel segmentation image fracture further includes similitude judgment module 106；
Selection module 104 is used for the coordinate according to breaking part both ends 201, selection and 201 phase of breaking part both ends in blood vessel original image
The lack part phase between breaking part both ends 201 is being chosen in blood vessel original image as two end datas 301 in corresponding part
Corresponding part is used as data 302 to be judged；Similitude judgment module 106 judges data 302 for treating using similar network
It carries out similitude judgement with two end datas 301 and exports similitude to judge prediction data；Repair module 105 in similitude for sentencing
Disconnected prediction data is shown will data 302 and blood vessel segmentation be judged in the state that data 302 to be judged and two end datas 301 are similar
Image merges, to repair to the breaking part in blood vessel segmentation image.
Data 302 to be judged can be compared with two end datas 301 by similar network respectively, to judge data to be judged
302 similitudes with two end datas 301 respectively.It wherein, can be multiple to training equipment input when being trained to similar network
Blood vessel original image case carries out similitude training, while the mark judged to training equipment input similitude for similar network
Data, and similar network is carried out to the prediction data of the obtained similitude judgement of similitude training and the mark of similitude judgement
Data are compared, and so as to obtain loss function, and restrain loss function by the training of multiple similitude, so that similar
Property network improves.
Since the adjacent part similarity on same blood vessel is higher, if similitude judges that prediction data is shown wait judge
Data 302 and two end datas 301 are similar, then it is adjacent on same blood vessel to illustrate that data 302 to be judged belong to two end datas 301
It part later can be by repairing so as to think that the data 302 to be judged are the lack part of blood vessel segmentation image breaking part
Multiple module 105 merges data 302 to be judged with blood vessel segmentation image, to complete to the breaking part in blood vessel segmentation image
It repairs.Which thereby enhance the accuracy of reparation.
In the present embodiment, it is preferred that the repair system of blood vessel segmentation image fracture further includes comparison module 107, compares mould
Block 107 be used to judge similitude prediction data and utilization data 302 to be judged and the corresponding labeled data of two end datas 301 into
The similitude of row similitude judgement judges that labeled data is compared.
Similitude is judged into prediction data by comparison module 107 and utilizes data 302 to be judged and two end datas 301 right
The similitude that the labeled data answered carries out similitude judgement judges that labeled data is compared, and can obtain loss function, therefore
The foundation that loss function obtained in capable of training before this loss function and similar network is trained together as similar network, from
And it is conducive to the perfect of similar network.
In the present embodiment, it is preferred that further include central line pick-up module 108 and endpoint extraction module 109, central line pick-up
Module 108 is used to extract the center line of blood vessel segmentation image, and endpoint extraction module 109 is used to extract the endpoint of center line, searches
Module 103 is used to search the breaking part in blood vessel segmentation image according to the endpoint of center line, and obtains the seat at breaking part both ends 201
Mark.
Since the center line of the breaking part of blood vessel segmentation image also will appear fracture, in central line pick-up module 108
During extracting blood vessel segmentation picture centre line, the breaking part both ends in blood vessel segmentation image will be respectively formed respective center
Line.Later during endpoint extraction module 109 extracts centerline end point, can on the center line at breaking part both ends 201
Extract endpoint.Due to can extract endpoint on the center line at breaking part both ends, searching module 103 is according to center line
Endpoint more can easily and accurately find breaking part.
The embodiment of the invention also provides a kind of computer readable storage medium, the storage medium includes one group of computer
Executable instruction requires repairing for blood vessel segmentation image fracture of the present invention for perform claim when executed
Compound method.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hidden
It include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise
Clear specific restriction.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (11)
1. a kind of restorative procedure of blood vessel segmentation image fracture characterized by comprising
Obtain blood vessel original image；
Processing is split to form blood vessel segmentation image to the blood vessel original image using segmentation network；
The breaking part in the blood vessel segmentation image is searched, and obtains the coordinate at the breaking part both ends；
Part corresponding with the breaking part is chosen in the blood vessel original image according to the coordinate at the breaking part both ends；
Using part corresponding with the breaking part in the blood vessel original image to the fracture in the blood vessel segmentation image
It is repaired at place.
2. the restorative procedure of blood vessel segmentation image fracture according to claim 1, which is characterized in that according to the breaking part
The coordinate at both ends chooses part corresponding with the breaking part in the blood vessel original image, comprising:
According to the coordinate at the breaking part both ends, chosen in the blood vessel original image corresponding with the breaking part both ends
Part is used as two end datas, and corresponding with lack part between the breaking part both ends choosing in the blood vessel original image
Part be used as data to be judged.
3. the restorative procedure of blood vessel segmentation image fracture according to claim 2, which is characterized in that according to the fracture
The coordinate at place both ends chooses part corresponding with the breaking part both ends as two end datas in the blood vessel original image,
And it is used as choosing part corresponding with the lack part between the breaking part both ends in the blood vessel original image wait sentence
After disconnected data, further includes:
Similitude judgement is carried out to the data to be judged and two end datas using similar network and exports similitude judgement prediction
Data.
4. the restorative procedure of blood vessel segmentation image fracture according to claim 3, which is characterized in that former using the blood vessel
The breaking part in the blood vessel segmentation image is repaired in part corresponding with the breaking part in beginning image, comprising:
If similitude judges that prediction data shows that the data to be judged are similar with two end datas, by the data to be judged with
The blood vessel segmentation image merges, to repair to the breaking part in the blood vessel segmentation image.
5. the restorative procedure of blood vessel segmentation image fracture according to claim 4, which is characterized in that utilizing similar network
Similitude judgement is carried out to the data to be judged and two end datas and is exported after similitude judges prediction data, further includes:
The similitude is judged that prediction data labeled data corresponding with the data to be judged described in and two end datas carries out
The similitude of similitude judgement judges that labeled data is compared.
6. the restorative procedure of blood vessel segmentation image fracture according to claim 1, which is characterized in that search the blood vessel point
The breaking part in image is cut, and obtains the coordinate at the breaking part both ends, comprising:
Extract the center line of the blood vessel segmentation image；
Extract the endpoint of the center line；
The breaking part in the blood vessel segmentation image is searched according to the endpoint of the center line, and obtains the breaking part both ends
Coordinate.
7. a kind of repair system of blood vessel segmentation image fracture characterized by comprising
Original image obtains module, for obtaining blood vessel original image；
Blood vessel segmentation image collection module, for being split processing to the blood vessel original image using segmentation network to be formed
Blood vessel segmentation image；
Searching module for searching the breaking part in the blood vessel segmentation image, and obtains the coordinate at the breaking part both ends；
Module is chosen, is chosen in the blood vessel original image for the coordinate according to the breaking part both ends and the breaking part
Corresponding part；
Repair module is used for using part corresponding with the breaking part in the blood vessel original image to the blood vessel segmentation
Breaking part in image is repaired.
8. the repair system of blood vessel segmentation image fracture according to claim 7, which is characterized in that further include that similitude is sentenced
Disconnected module；
The module of choosing is chosen in the blood vessel original image and breaks with described for the coordinate according to the breaking part both ends
Split the place corresponding part in both ends as two end datas, and choose in the blood vessel original image with the breaking part both ends it
Between the corresponding part of lack part be used as data to be judged；
The similitude judgment module is used to carry out similitude to the data to be judged and two end datas using similar network to sentence
Break and export similitude and judges prediction data；
Repair module is used to judge that prediction data shows the data to be judged and the similar shape of two end datas in the similitude
The data to be judged are merged with the blood vessel segmentation image under state, to be carried out to the breaking part in the blood vessel segmentation image
It repairs.
9. the repair system of blood vessel segmentation image fracture according to claim 8, further includes comparison module, the comparison mould
Block be used to judge the similitude prediction data and data to be judged described in utilization and the corresponding labeled data of two end datas into
The similitude of row similitude judgement judges that labeled data is compared.
10. the repair system of blood vessel segmentation image fracture according to claim 7, which is characterized in that further include center line
Extraction module and endpoint extraction module, the central line pick-up module are used to extract the center line of the blood vessel segmentation image, institute
Endpoint extraction module is stated for extracting the endpoint of the center line, the searching module according to the endpoint of the center line for looking into
The breaking part in the blood vessel segmentation image is looked for, and obtains the coordinate at the breaking part both ends.
11. a kind of computer readable storage medium, which is characterized in that the storage medium, which includes that one group of computer is executable, to be referred to
It enables, requires the reparation side of the described in any item blood vessel segmentation image fractures of 1-6 for perform claim when executed
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910186257.3A CN109903298B (en) | 2019-03-12 | 2019-03-12 | Method, system and computer storage medium for repairing blood vessel segmentation image fracture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910186257.3A CN109903298B (en) | 2019-03-12 | 2019-03-12 | Method, system and computer storage medium for repairing blood vessel segmentation image fracture |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109903298A true CN109903298A (en) | 2019-06-18 |
| CN109903298B CN109903298B (en) | 2021-03-02 |
Family
ID=66947080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910186257.3A Active CN109903298B (en) | 2019-03-12 | 2019-03-12 | Method, system and computer storage medium for repairing blood vessel segmentation image fracture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109903298B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298846A (en) * | 2019-06-27 | 2019-10-01 | 数坤（北京）网络科技有限公司 | Based on polytypic coronary artery dividing method, device and storage equipment |
| CN111383191A (en) * | 2019-12-11 | 2020-07-07 | 北京深睿博联科技有限责任公司 | Image processing method and device for repairing blood vessel fracture |
| CN111539917A (en) * | 2020-04-09 | 2020-08-14 | 北京深睿博联科技有限责任公司 | Blood vessel segmentation method, system, terminal and storage medium based on coarse and fine granularity fusion |
| CN112241955A (en) * | 2020-10-27 | 2021-01-19 | 平安科技（深圳）有限公司 | Method and device for segmenting broken bones of three-dimensional image, computer equipment and storage medium |
| CN113593678A (en) * | 2021-08-03 | 2021-11-02 | 北京安德医智科技有限公司 | Cerebral apoplexy typing method and device based on blood vessel image completion |
| CN113822897A (en) * | 2021-11-22 | 2021-12-21 | 武汉楚精灵医疗科技有限公司 | Blood vessel segmentation method, terminal and computer-readable storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103310415A (en) * | 2013-03-15 | 2013-09-18 | 清华大学 | Face-based defected image inpainting method and system |
| CN104408453A (en) * | 2014-09-29 | 2015-03-11 | 北京理工大学 | Near-infrared subcutaneous vein segmentation method based on multi-feature clustering |
| CN107067398A (en) * | 2017-04-28 | 2017-08-18 | 青岛海信医疗设备股份有限公司 | Complementing method and device for lacking blood vessel in 3 D medical model |
| CN108095871A (en) * | 2011-04-29 | 2018-06-01 | 艾维斯科神经血管有限合伙公司 | Intravascular dummy and conveying device |
| US20180199997A1 (en) * | 2017-01-19 | 2018-07-19 | Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ciência | Method and apparatus for segmentation of blood vessels |
| CN108335277A (en) * | 2018-03-05 | 2018-07-27 | 北京中科嘉宁科技有限公司 | A kind of image recess method for repairing and mending based on double Graham scanning methods |
| CN108376048A (en) * | 2018-03-05 | 2018-08-07 | 四川和生视界医药技术开发有限公司 | The restorative procedure and prosthetic device of retinal vessel |
| WO2018237011A1 (en) * | 2017-06-20 | 2018-12-27 | University Of Louisville Research Foundation, Inc. | Segmentation of retinal blood vessels in optical coherence tomography angiography images |
| CN109377458A (en) * | 2018-09-30 | 2019-02-22 | 数坤（北京）网络科技有限公司 | A kind of restorative procedure and device of coronary artery segmentation fracture |
| CN109448006A (en) * | 2018-11-01 | 2019-03-08 | 江西理工大学 | A kind of U-shaped intensive connection Segmentation Method of Retinal Blood Vessels of attention mechanism |
-
2019
- 2019-03-12 CN CN201910186257.3A patent/CN109903298B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108095871A (en) * | 2011-04-29 | 2018-06-01 | 艾维斯科神经血管有限合伙公司 | Intravascular dummy and conveying device |
| CN103310415A (en) * | 2013-03-15 | 2013-09-18 | 清华大学 | Face-based defected image inpainting method and system |
| CN104408453A (en) * | 2014-09-29 | 2015-03-11 | 北京理工大学 | Near-infrared subcutaneous vein segmentation method based on multi-feature clustering |
| US20180199997A1 (en) * | 2017-01-19 | 2018-07-19 | Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ciência | Method and apparatus for segmentation of blood vessels |
| CN107067398A (en) * | 2017-04-28 | 2017-08-18 | 青岛海信医疗设备股份有限公司 | Complementing method and device for lacking blood vessel in 3 D medical model |
| WO2018237011A1 (en) * | 2017-06-20 | 2018-12-27 | University Of Louisville Research Foundation, Inc. | Segmentation of retinal blood vessels in optical coherence tomography angiography images |
| CN108335277A (en) * | 2018-03-05 | 2018-07-27 | 北京中科嘉宁科技有限公司 | A kind of image recess method for repairing and mending based on double Graham scanning methods |
| CN108376048A (en) * | 2018-03-05 | 2018-08-07 | 四川和生视界医药技术开发有限公司 | The restorative procedure and prosthetic device of retinal vessel |
| CN109377458A (en) * | 2018-09-30 | 2019-02-22 | 数坤（北京）网络科技有限公司 | A kind of restorative procedure and device of coronary artery segmentation fracture |
| CN109448006A (en) * | 2018-11-01 | 2019-03-08 | 江西理工大学 | A kind of U-shaped intensive connection Segmentation Method of Retinal Blood Vessels of attention mechanism |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298846A (en) * | 2019-06-27 | 2019-10-01 | 数坤（北京）网络科技有限公司 | Based on polytypic coronary artery dividing method, device and storage equipment |
| CN111383191A (en) * | 2019-12-11 | 2020-07-07 | 北京深睿博联科技有限责任公司 | Image processing method and device for repairing blood vessel fracture |
| CN111383191B (en) * | 2019-12-11 | 2024-03-08 | 北京深睿博联科技有限责任公司 | Image processing method and device for vascular fracture repair |
| CN111539917A (en) * | 2020-04-09 | 2020-08-14 | 北京深睿博联科技有限责任公司 | Blood vessel segmentation method, system, terminal and storage medium based on coarse and fine granularity fusion |
| CN111539917B (en) * | 2020-04-09 | 2023-08-25 | 北京深睿博联科技有限责任公司 | Blood vessel segmentation method, system, terminal and storage medium based on coarse-fine granularity fusion |
| CN112241955A (en) * | 2020-10-27 | 2021-01-19 | 平安科技（深圳）有限公司 | Method and device for segmenting broken bones of three-dimensional image, computer equipment and storage medium |
| CN112241955B (en) * | 2020-10-27 | 2023-08-25 | 平安科技（深圳）有限公司 | Broken bone segmentation method and device for three-dimensional image, computer equipment and storage medium |
| CN113593678A (en) * | 2021-08-03 | 2021-11-02 | 北京安德医智科技有限公司 | Cerebral apoplexy typing method and device based on blood vessel image completion |
| CN113822897A (en) * | 2021-11-22 | 2021-12-21 | 武汉楚精灵医疗科技有限公司 | Blood vessel segmentation method, terminal and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109903298B (en) | 2021-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109903298A (en) | Restorative procedure, system and the computer storage medium of blood vessel segmentation image fracture | |
| Mu et al. | Progressive global perception and local polishing network for lung infection segmentation of COVID-19 CT images | |
| Nalawade et al. | Classification of brain tumor isocitrate dehydrogenase status using MRI and deep learning | |
| CN109919937A (en) | Restorative procedure, system and the computer storage medium of blood vessel segmentation image fracture | |
| CN109691985A (en) | A kind of temporal epilepsy aided diagnosis method based on DTI technology and SVM | |
| Hu et al. | Automated interpretation of subcellular patterns from immunofluorescence microscopy | |
| Huang et al. | A structure-related fine-grained deep learning system with diversity data for universal glaucoma visual field grading | |
| WO2023168728A1 (en) | Multimodal radiomics-based epilepsy drug treatment outcome prediction method and apparatus | |
| Kotanidis et al. | Selfies in cardiovascular medicine: welcome to a new era of medical diagnostics | |
| Liu et al. | Anatomical-landmark-based deep learning for Alzheimer’s disease diagnosis with structural magnetic resonance imaging | |
| Van Buren et al. | Artificial intelligence and deep learning to map immune cell types in inflamed human tissue | |
| Yang et al. | Benchmarking the cow with the topcow challenge: Topology-aware anatomical segmentation of the circle of willis for cta and mra | |
| Tang et al. | Work like a doctor: Unifying scan localizer and dynamic generator for automated computed tomography report generation | |
| CN116310114A (en) | Coronary artery point cloud data processing optimization method of multitask label model | |
| Na et al. | Automated brain tumor segmentation from multimodal MRI data based on Tamura texture feature and an ensemble SVM classifier | |
| CN113792740B (en) | Artery and vein segmentation method, system, equipment and medium for fundus color illumination | |
| Scicolone et al. | Radiomics and artificial intelligence: General notions and applications in the carotid vulnerable plaque | |
| Ashtari-Majlan et al. | Deep learning and computer vision for glaucoma detection: A review | |
| Li et al. | Kinet: a non-invasive method for predicting Ki67 index of glioma | |
| Kaur et al. | A survey on medical image segmentation | |
| Skandha et al. | Magnetic resonance based Wilson’s disease tissue characterization in an artificial intelligence framework using transfer learning | |
| Abdullah et al. | Segmentation and classification of heart angiographic images using machine learning techniques | |
| Lu et al. | Development of Brain MRI Image Segmentation Methods Based on Computer Vision and Deep Learning | |
| Phillips et al. | Fully convolutional network for melanoma diagnostics | |
| Tripura et al. | A BrainNet (BrN) based new approach to classify brain stroke from CT scan images |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100102 No. 501 No. 12, 5th floor, No. 6, Wangjing Dongyuan District 4, Chaoyang District, Beijing Patentee after: Shukun (Beijing) Network Technology Co.,Ltd. Address before: 100102 No. 501 No. 12, 5th floor, No. 6, Wangjing Dongyuan District 4, Chaoyang District, Beijing Patentee before: SHUKUN (BEIJING) NETWORK TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100102 No. 501 No. 12, 5th floor, No. 6, Wangjing Dongyuan District 4, Chaoyang District, Beijing Patentee after: Shukun Technology Co.,Ltd. Address before: 100102 No. 501 No. 12, 5th floor, No. 6, Wangjing Dongyuan District 4, Chaoyang District, Beijing Patentee before: Shukun (Beijing) Network Technology Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |