CN105741310A - Heart's left ventricle image segmentation system and method - Google Patents
Heart's left ventricle image segmentation system and method Download PDFInfo
- Publication number
- CN105741310A CN105741310A CN201610161395.2A CN201610161395A CN105741310A CN 105741310 A CN105741310 A CN 105741310A CN 201610161395 A CN201610161395 A CN 201610161395A CN 105741310 A CN105741310 A CN 105741310A
- Authority
- CN
- China
- Prior art keywords
- left ventricle
- profile
- image
- aorta
- distance
- 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
Classifications
-
- 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
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/20112—Image segmentation details
- G06T2207/20116—Active contour; Active surface; Snakes
-
- 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
- G06T2207/30048—Heart; Cardiac
Landscapes
- Magnetic Resonance Imaging Apparatus (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a heart's left ventricle image segmentation system and method. The system comprises an image conversion unit; a left ventricle contour crude extraction unit; and a left ventricle contour refined extraction unit. The method comprises the steps that a nuclear magnetic resonance image is segmented so that a binary image is obtained, and the binary image is converted into a gray scale image through Euclidean distance transformation; all the communicated areas in the binary image are separated; and a left ventricle contour is crudely extracted; whether the left ventricle contour is connected with an aorta contour is judged, if the crudely extracted left ventricle contour is connected with the aorta contour, the aorta is removed to be segmented, and the left ventricle contour is repaired so that a heart's left ventricle image segmentation result is obtained; or the crudely extracted left ventricle contour is the left ventricle contour. Influence of connection of the left ventricle and the aorta can be eliminated in the aspect of the image so that the left ventricle underlying image can be accurately segmented, influence of edge disclosure on the left ventricle caused by the aorta can be overcome, and thus the accurate left ventricle segmentation result can be obtained.
Description
Technical field
The present invention relates to image processing field, be specifically related to a kind of cardiac left-ventricle image segmenting system and method.
Background technology
In numerous image partition methods, there is a lot of method being suitable for segmentation cardiac magnetic resonance short axis images, such as region growing method, threshold method and Level Set Method etc..As have employed the Mumford-Shah model dividing method in conjunction with shape Statistics in paper " the MR image left ventricle outline segmentation of shape Statistics Mumford-Shah model ", heart left ventricle is split, the situation of weak boundary and boundary fault has been considered.But it have ignored heart bottom and causes the non-existent situation in part left ventricle border due to aortal reason.And Texture classification information and statistical shape prior knowledge are introduced in Mumford-Shah model by paper " the TaggedMR image left ventricle partitioning algorithm of combined with texture and shape ", the method proposing the left ventricle inside and outside contour of the segmentation band mark line nuclear magnetic resonance image of a kind of improvement, situation about heart bottom not being connected with aorta equally takes in, texture is difficult to differentiate between, shape Statistics is not specifically introduced solution yet.In paper " the cardiac MR images left ventricle dividing method based on Snake improved model ", the segmentation of adventitia in the left ventricle of main emphasis heart middle level, situation about heart bottom edges not revealed takes in.
Heart bottom, owing to being connected with aorta, causes edge leakage, so segmentation is got up, difficulty is relatively larger, and major part dividing method is all difficult to process such problem.Major part scholar mainly focuses on the segmentation to middle level when splitting heart left ventricle, ignore the process to left ventricle bottom, but heart left ventricle's bottom is connected to aorta, the process to heart left ventricle's bottom is to obtain the various information of heart left ventricle and heart left ventricle is carried out necessary to three-dimensional reconstruction.
Summary of the invention
For the deficiency that prior art exists, the present invention provides a kind of cardiac left-ventricle image segmenting system and method.
The technical scheme is that
A kind of cardiac left-ventricle image segmenting system, including:
Image conversion unit: selected seed point in the left ventricle of nuclear magnetic resonance image, using the meansigma methods of the maximum gradation value of nuclear magnetic resonance image and minimum gradation value as initial segmentation threshold value, nuclear magnetic resonance image is divided into foreground and background, the average gray value of the average gray value of prospect Yu background is averaged as new segmentation threshold, if the difference of the segmentation threshold of new segmentation threshold and previous iteration gained is less than the allowed band set, then current segmentation threshold is final segmentation threshold, otherwise continue iterative computation, finally give binary image, again through Euclidean Distance Transform, binary image is converted into gray level image；
The thick extraction unit of left ventricle profile: the order being incremented by by gray scale sorts to the pixel of gray level image, use a fifo queue recursively to distribute to each gray scale very small region according to the mode of breadth-first and form new gray scale very small region respectively, and when distribution, the pixel of first gray scale very small region is collectively labeled as 0, the labelling of gray scale very small region below adds 1 successively, by labelling, each linking area in gray level image is distinguished, slightly extract left ventricle profile by the seed points chosen；
Left ventricle profile essence extraction unit: if the left ventricle profile slightly extracted is connected with aorta profile, then remove aorta, repairs left ventricle profile, obtains cardiac left-ventricle image segmentation result；If the left ventricle profile slightly extracted and aorta profile are not attached to, then the left ventricle profile slightly extracted, namely as left ventricle profile, obtains cardiac left-ventricle image segmentation result.
Described left ventricle profile essence extraction unit, including:
Analyze judging unit: calculate the left ventricle profile barycenter that slightly the extracts distance to each marginal point, find out distance maximum Ma and distance minimum M i, and according to distance maximum with distance minima analysis with judge whether left ventricle is connected with aorta: if Ma<30 pixel unit length and (Ma-Mi)/Ma>0.55, or Ma>30 pixel unit length and (Ma-Mi)/Ma>0.38, then left ventricle is connected with aorta, needing to carry out Morphological scale-space, the left ventricle profile otherwise slightly extracted is namely as left ventricle profile.
Described left ventricle profile essence extraction unit, also includes:
Morphological scale-space unit: find out in the left ventricle profile slightly extracted barycenter to all minimums of marginal point, if the position of distance maximum Ma is between two adjacent minimum points, then make straight line with the two minimum point for cut-point left ventricle profile and aorta profile to be separated, redefine the barycenter of left ventricle profile, take two cut-points and make the 3rd cut-point in be connected with this barycenter center line direction of angulation of two cut-points to the distance average of barycenter, make curve completion left ventricle contour edge with these three cut-point, obtain left ventricle profile.
Described minimum point Pi meets (Pi-Mi)/(Ma-Mi) < 0.3.
The present invention also provides for a kind of cardiac left-ventricle image dividing method, including:
Image is changed: selected seed point in the left ventricle of nuclear magnetic resonance image, using the meansigma methods of the maximum gradation value of nuclear magnetic resonance image and minimum gradation value as initial segmentation threshold value, nuclear magnetic resonance image is divided into foreground and background, the average gray value of the average gray value of prospect Yu background is averaged as new segmentation threshold, if the difference of the segmentation threshold of new segmentation threshold and previous iteration gained is less than the allowed band set, then current segmentation threshold is final segmentation threshold, otherwise continue iterative computation, finally give binary image, again through Euclidean Distance Transform, binary image is converted into gray level image；
Thick extraction left ventricle profile: the order being incremented by by gray scale sorts to the pixel of gray level image, use a fifo queue recursively to distribute to each gray scale very small region according to the mode of breadth-first and form new gray scale very small region respectively, and when distribution, the pixel of first gray scale very small region is collectively labeled as 0, the labelling of gray scale very small region below adds 1 successively, by labelling, each linking area in gray level image is distinguished, slightly extract left ventricle profile by the seed points chosen；
Essence extracts left ventricle profile: if the left ventricle profile slightly extracted is connected with aorta profile, then remove aorta, repairs left ventricle profile, obtains cardiac left-ventricle image segmentation result；If the left ventricle profile slightly extracted and aorta profile are not attached to, then the left ventricle profile slightly extracted, namely as left ventricle profile, obtains cardiac left-ventricle image segmentation result.
The concrete steps that described essence extracts left ventricle profile include:
Calculate the left ventricle profile barycenter that slightly the extracts distance to each marginal point；
Find out distance maximum Ma and distance minimum M i；
According to distance maximum with distance minima analysis with judge whether left ventricle is connected with aorta: if Ma<30 pixel unit length and (Ma-Mi)/Ma>0.55, or Ma>30 pixel unit length and (Ma-Mi)/Ma>0.38, then left ventricle is connected with aorta, obtaining left ventricle profile after needing to carry out Morphological scale-space, the left ventricle profile otherwise slightly extracted is namely as left ventricle profile.
The concrete steps of described Morphological scale-space include:
Find out in the left ventricle profile slightly extracted barycenter to all minimums of marginal point；
If the position of distance maximum Ma is between two adjacent minimum points, then makes straight line with the two minimum point for cut-point and left ventricle profile and aorta profile are separated；
Redefine the barycenter of left ventricle profile；
Take two cut-points and make the 3rd cut-point in be connected with this barycenter center line direction of angulation of two cut-points to the distance average of barycenter；
Make curve completion left ventricle contour edge with these three cut-point, obtain left ventricle profile.
Beneficial effect:
The cardiac left-ventricle image segmenting system of the present invention and method can get rid of the impact that left ventricle is connected with aorta in image, exactly segmentation left ventricle bottom layer image.Judge that whether left ventricle is connected with aorta and whether causes the situation of edge leakage, if producing the situation of edge leakage, then morphology is removed aorta edge and is made up with the curve similar to left ventricle edge at the edge of disappearance, overcome the impact of the edge leakage that left ventricle causes by aorta, thus obtaining left ventricle segmentation result accurately.
Accompanying drawing explanation
Fig. 1 is the cardiac left-ventricle image segmenting system block diagram of the embodiment of the present invention 1；
Fig. 2 is the cardiac left-ventricle image dividing method flow chart of the embodiment of the present invention 2；
Fig. 3 is the flow chart of the essence extraction left ventricle profile of the embodiment of the present invention 2；
Fig. 4 is the flow chart of the Morphological scale-space of the embodiment of the present invention 2；
Fig. 5 is the binary image of the embodiment of the present invention 2；
Fig. 6 is the conversion results of the Euclidean Distance Transform of the embodiment of the present invention 2；
The left ventricle profile that Fig. 7 is the embodiment of the present invention 2 slightly extracts result figure；
Fig. 8 is that the left ventricle profile barycenter of the embodiment of the present invention 2 is to each marginal point distance Curve figure；
Fig. 9 is one group of left ventricle bottom (the Ma-Mi)/MA ratio curve figure of the embodiment of the present invention 2；
Figure 10 be the embodiment of the present invention 2 make curve completion left ventricle contour edge result figure with three cut-points；
The essence that Figure 11 is the embodiment of the present invention 2 extracts the left ventricle profile results figure obtained.
Detailed description of the invention
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is elaborated.
Embodiment 1
A kind of cardiac left-ventricle image segmenting system, as it is shown in figure 1, include:
nullImage conversion unit: selected seed point in the left ventricle of nuclear magnetic resonance image，Obtain the maximum gradation value Z0 and minimum gradation value Z1 of nuclear magnetic resonance image，Using the meansigma methods of the maximum gradation value of nuclear magnetic resonance image and minimum gradation value as initial segmentation threshold value T=(Z0+Z1)/2，Nuclear magnetic resonance image is divided into foreground and background，Obtain the average gray value T0 of prospect and the average gray value T1 of background respectively，The average gray value of the average gray value of prospect Yu background is averaged as new segmentation threshold，If the difference of the segmentation threshold of new segmentation threshold TT=(T0+T1)/2 and previous iteration gained is less than the allowed band set，Then current segmentation threshold is final segmentation threshold，Otherwise continue iterative computation，Finally give binary image，Again through Euclidean Distance Transform, binary image is converted into gray level image；Image conversion unit extracts major organs and tissue in nuclear magnetic resonance image, filters useless region, and complicated gray level image is converted into regional center gray value simple gray-scale image that is minimum and that be incremented by edge.
The thick extraction unit of left ventricle profile: the order being incremented by by gray scale sorts to the pixel of gray level image, use a fifo queue recursively to distribute to each gray scale very small region according to the mode of breadth-first and form new gray scale very small region respectively, and when distribution, the pixel of first gray scale very small region is collectively labeled as 0, the labelling of gray scale very small region below adds 1 successively, by labelling, each linking area in gray level image is distinguished, slightly extract left ventricle profile by the seed points chosen.
Left ventricle profile essence extraction unit: if the left ventricle profile slightly extracted is connected with aorta profile, then remove aorta, repairs left ventricle profile, obtains cardiac left-ventricle image segmentation result；If the left ventricle profile slightly extracted and aorta profile are not attached to, then the left ventricle profile slightly extracted, namely as left ventricle profile, obtains cardiac left-ventricle image segmentation result.
Left ventricle profile essence extraction unit, including:
Analyze judging unit: obtain empirical value by processing 400 groups of heart left ventricle's bottom datas of 10 patients, calculate the left ventricle profile barycenter that slightly the extracts distance to each marginal point, find out distance maximum Ma and distance minimum M i, and according to distance maximum with distance minima analysis with judge whether left ventricle is connected with aorta: if Ma<30 pixel unit length and (Ma-Mi)/Ma>0.55, or Ma>30 pixel unit length and (Ma-Mi)/Ma>0.38, then left ventricle is connected with aorta, need to carry out Morphological scale-space, the left ventricle profile otherwise slightly extracted is namely as left ventricle profile.
Morphological scale-space unit: find out all minimum point Pi meeting (Pi-Mi)/(Ma-Mi) < 0.3 to marginal point of barycenter in the left ventricle profile slightly extracted, if the position of distance maximum Ma is between two adjacent minimum points, then make straight line with the two minimum point for cut-point left ventricle profile and aorta profile to be separated, redefine the barycenter of left ventricle profile, take two cut-points and make the 3rd cut-point in be connected with this barycenter center line direction of angulation of two cut-points to the distance average of barycenter, curve completion left ventricle contour edge is made with these three cut-point, obtain left ventricle profile.
Apply system provided by the invention, can comparatively accurately find left ventricle and aortal cut-point, thus avoiding the impact that left ventricle is split by aorta, the three-dimensional reconstruction for heart left ventricle provides accurate left ventricle segmentation result so that the observation of left ventricle is more accurate and effective.
Embodiment 2
The present invention also provides for a kind of method adopting system described in embodiment 1 to carry out cardiac left-ventricle image segmentation, as in figure 2 it is shown, include:
nullStep 201、Selected seed point in the left ventricle of nuclear magnetic resonance image，Obtain the maximum gradation value Z0 and minimum gradation value Z1 of nuclear magnetic resonance image，Using the meansigma methods of the maximum gradation value of nuclear magnetic resonance image and minimum gradation value as initial segmentation threshold value T=(Z0+Z1)/2，Nuclear magnetic resonance image is divided into foreground and background，Obtain the average gray value T0 of prospect and the average gray value T1 of background respectively，The average gray value of the average gray value of prospect Yu background is averaged as new segmentation threshold，If the difference of the segmentation threshold of new segmentation threshold TT=(T0+T1)/2 and previous iteration gained is less than the allowed band set，Then current segmentation threshold is final segmentation threshold，Otherwise continue iterative computation，Finally give binary image as shown in Figure 5，Again through Euclidean Distance Transform, binary image is converted into gray level image as shown in Figure 6；Image conversion unit extracts major organs and tissue in nuclear magnetic resonance image, filters useless region, and complicated gray level image is converted into regional center gray value simple gray-scale image that is minimum and that be incremented by edge.
Step 202, by gray scale be incremented by order sort to the pixel of gray level image, use a fifo queue recursively to distribute to each gray scale very small region according to the mode of breadth-first and form new gray scale very small region respectively, and when distribution, the pixel of first gray scale very small region is collectively labeled as 0, the labelling of gray scale very small region below adds 1 successively, by labelling, each linking area in gray level image is distinguished, slightly extract left ventricle profile as shown in Figure 7 by the seed points chosen；
Step 203, essence extract left ventricle profile: if the left ventricle profile slightly extracted is connected with aorta profile, then turn step 204；If the left ventricle profile slightly extracted and aorta profile are not attached to, then the left ventricle profile slightly extracted, namely as left ventricle profile, turns and goes step 205；
Step 204, removal aorta, repair left ventricle profile；
Step 205, obtain cardiac left-ventricle image segmentation result.
As it is shown on figure 3, essence extracts specifically comprising the following steps that of left ventricle profile
The left ventricle profile barycenter that step 301, calculating slightly extract, to the distance of each marginal point, obtains curve chart as shown in Figure 8；
Step 302, find out distance maximum Ma and distance minimum M i；
If step 303 Ma<30 pixel unit length and (Ma-Mi)/Ma>0.55, then turn step 305, otherwise turn step 304；
If step 304 Ma > 30 pixel unit length and (Ma-Mi)/Ma > 0.38, then turn step 305, otherwise turn step 306；
Step 305, left ventricle are connected with aorta, obtain left ventricle profile after carrying out Morphological scale-space；
Step 306, the left ventricle profile slightly extracted are namely as left ventricle profile.
Fig. 9 is one group of left ventricle bottom (Ma-Mi)/MA ratio curve figure, and Ma > 30 pixel unit length in these group data, (Ma-Mi)/Ma is all higher than 0.38 as seen from the figure, all there is the situation that left ventricle is connected with aorta.
As shown in Figure 4, the specifically comprising the following steps that of Morphological scale-space
Step 401, find out in the left ventricle profile slightly extracted barycenter to all minimums of marginal point；
If the position of step 402 distance maximum Ma is between two adjacent minimum points, then turn step 403, otherwise return step 401；
Step 403, make straight line with the two minimum point for cut-point left ventricle profile and aorta profile are separated；
Step 404, redefine the barycenter of left ventricle profile；
Step 405, take two cut-points and make the 3rd cut-point in be connected with this barycenter center line direction of angulation of two cut-points to the distance average of barycenter；
Step 406, make curve completion left ventricle contour edge with these three cut-point, as shown in Figure 10.Take connected region by the seed points chosen, extract left ventricle profile, obtain left ventricle profile more accurately as shown in figure 11.
Visible, left ventricle bottom and aorta can not only be separated by method provided by the invention, additionally it is possible to make up the left ventricle profile of disappearance with the curve of approximate left ventricle profile, thus obtaining left ventricle profile accurately.
Claims (7)
1. a cardiac left-ventricle image segmenting system, it is characterised in that including:
Image conversion unit: selected seed point in the left ventricle of nuclear magnetic resonance image, using the meansigma methods of the maximum gradation value of nuclear magnetic resonance image and minimum gradation value as initial segmentation threshold value, nuclear magnetic resonance image is divided into foreground and background, the average gray value of the average gray value of prospect Yu background is averaged as new segmentation threshold, if the difference of the segmentation threshold of new segmentation threshold and previous iteration gained is less than the allowed band set, then current segmentation threshold is final segmentation threshold, otherwise continue iterative computation, finally give binary image, again through Euclidean Distance Transform, binary image is converted into gray level image；
The thick extraction unit of left ventricle profile: the order being incremented by by gray scale sorts to the pixel of gray level image, use a fifo queue recursively to distribute to each gray scale very small region according to the mode of breadth-first and form new gray scale very small region respectively, and when distribution, the pixel of first gray scale very small region is collectively labeled as 0, the labelling of gray scale very small region below adds 1 successively, by labelling, each linking area in gray level image is distinguished, slightly extract left ventricle profile by the seed points chosen；
Left ventricle profile essence extraction unit: if the left ventricle profile slightly extracted is connected with aorta profile, then remove aorta, repairs left ventricle profile, obtains cardiac left-ventricle image segmentation result；If the left ventricle profile slightly extracted and aorta profile are not attached to, then the left ventricle profile slightly extracted, namely as left ventricle profile, obtains cardiac left-ventricle image segmentation result.
2. cardiac left-ventricle image segmenting system according to claim 1, it is characterised in that described left ventricle profile essence extraction unit, including:
Analyze judging unit: calculate the left ventricle profile barycenter that slightly the extracts distance to each marginal point, find out distance maximum Ma and distance minimum M i, and according to distance maximum with distance minima analysis with judge whether left ventricle is connected with aorta: if Ma<30 pixel unit length and (Ma-Mi)/Ma>0.55, or Ma>30 pixel unit length and (Ma-Mi)/Ma>0.38, then left ventricle is connected with aorta, needing to carry out Morphological scale-space, the left ventricle profile otherwise slightly extracted is namely as left ventricle profile.
3. cardiac left-ventricle image segmenting system according to claim 2, it is characterised in that described left ventricle profile essence extraction unit, also includes:
Morphological scale-space unit: find out in the left ventricle profile slightly extracted barycenter to all minimums of marginal point, if the position of distance maximum Ma is between two adjacent minimum points, then make straight line with the two minimum point for cut-point left ventricle profile and aorta profile to be separated, redefine the barycenter of left ventricle profile, take two cut-points and make the 3rd cut-point in be connected with this barycenter center line direction of angulation of two cut-points to the distance average of barycenter, make curve completion left ventricle contour edge with these three cut-point, obtain left ventricle profile.
4. cardiac left-ventricle image segmenting system according to claim 3, it is characterised in that described minimum point Pi meets (Pi-Mi)/(Ma-Mi) < 0.3.
5. a cardiac left-ventricle image dividing method, it is characterised in that including:
Image is changed: selected seed point in the left ventricle of nuclear magnetic resonance image, using the meansigma methods of the maximum gradation value of nuclear magnetic resonance image and minimum gradation value as initial segmentation threshold value, nuclear magnetic resonance image is divided into foreground and background, the average gray value of the average gray value of prospect Yu background is averaged as new segmentation threshold, if the difference of the segmentation threshold of new segmentation threshold and previous iteration gained is less than the allowed band set, then current segmentation threshold is final segmentation threshold, otherwise continue iterative computation, finally give binary image, again through Euclidean Distance Transform, binary image is converted into gray level image；
Thick extraction left ventricle profile: the order being incremented by by gray scale sorts to the pixel of gray level image, use a fifo queue recursively to distribute to each gray scale very small region according to the mode of breadth-first and form new gray scale very small region respectively, and when distribution, the pixel of first gray scale very small region is collectively labeled as 0, the labelling of gray scale very small region below adds 1 successively, by labelling, each linking area in gray level image is distinguished, slightly extract left ventricle profile by the seed points chosen；
Essence extracts left ventricle profile: if the left ventricle profile slightly extracted is connected with aorta profile, then remove aorta, repairs left ventricle profile, obtains cardiac left-ventricle image segmentation result；If the left ventricle profile slightly extracted and aorta profile are not attached to, then the left ventricle profile slightly extracted, namely as left ventricle profile, obtains cardiac left-ventricle image segmentation result.
6. method according to claim 5, it is characterised in that the concrete steps that described essence extracts left ventricle profile include:
Calculate the left ventricle profile barycenter that slightly the extracts distance to each marginal point；
Find out distance maximum Ma and distance minimum M i；
According to distance maximum with distance minima analysis with judge whether left ventricle is connected with aorta: if Ma<30 pixel unit length and (Ma-Mi)/Ma>0.55, or Ma>30 pixel unit length and (Ma-Mi)/Ma>0.38, then left ventricle is connected with aorta, obtaining left ventricle profile after needing to carry out Morphological scale-space, the left ventricle profile otherwise slightly extracted is namely as left ventricle profile.
7. method according to claim 6, it is characterised in that the concrete steps of described Morphological scale-space include:
Find out in the left ventricle profile slightly extracted barycenter to all minimums of marginal point；
If the position of distance maximum Ma is between two adjacent minimum points, then makes straight line with the two minimum point for cut-point and left ventricle profile and aorta profile are separated；
Redefine the barycenter of left ventricle profile；
Take two cut-points and make the 3rd cut-point in be connected with this barycenter center line direction of angulation of two cut-points to the distance average of barycenter；
Make curve completion left ventricle contour edge with these three cut-point, obtain left ventricle profile.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610161395.2A CN105741310B (en) | 2016-03-21 | 2016-03-21 | A kind of cardiac left-ventricle image segmenting system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610161395.2A CN105741310B (en) | 2016-03-21 | 2016-03-21 | A kind of cardiac left-ventricle image segmenting system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105741310A true CN105741310A (en) | 2016-07-06 |
| CN105741310B CN105741310B (en) | 2018-05-04 |
Family
ID=56251733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610161395.2A Active CN105741310B (en) | 2016-03-21 | 2016-03-21 | A kind of cardiac left-ventricle image segmenting system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105741310B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220984A (en) * | 2017-05-05 | 2017-09-29 | 上海联影医疗科技有限公司 | A kind of image partition method, system and grid model |
| CN107610095A (en) * | 2017-08-04 | 2018-01-19 | 南京邮电大学 | Heart CT coronary artery full-automatic partition methods based on image co-registration |
| CN109272512A (en) * | 2018-09-25 | 2019-01-25 | 南昌航空大学 | A kind of method of outer membrane in automatic segmentation left ventricle |
| CN110033466A (en) * | 2019-04-01 | 2019-07-19 | 数坤（北京）网络科技有限公司 | Image segmentation boundary determining method is straightened in a kind of coronary artery based on multi-grey level |
| CN110378948A (en) * | 2019-07-02 | 2019-10-25 | 北京字节跳动网络技术有限公司 | 3D model reconstruction method, device and electronic equipment |
| CN110471469A (en) * | 2019-09-26 | 2019-11-19 | 湖南航天机电设备与特种材料研究所 | A kind of adaptive temperature control method based on PI algorithm |
| CN111028254A (en) * | 2019-12-09 | 2020-04-17 | 上海交通大学医学院附属上海儿童医学中心 | Left myocardium segmentation method based on cardiac cine magnetic resonance image |
| CN111369525A (en) * | 2020-03-02 | 2020-07-03 | 联影智能医疗科技(北京)有限公司 | Image analysis method, apparatus and storage medium |
| CN111815586A (en) * | 2020-06-29 | 2020-10-23 | 苏州润心医疗器械有限公司 | Method and system for acquiring connected domain of left atrium and left ventricle based on CT image |
| CN112215839A (en) * | 2020-10-27 | 2021-01-12 | 大连东软教育科技集团有限公司 | Method, system and storage medium for six-segment division of left ventricular wall of echocardiogram |
| CN112308845A (en) * | 2020-11-03 | 2021-02-02 | 赛诺威盛科技（北京）有限公司 | Left ventricle segmentation method and device and electronic equipment |
| CN112330708A (en) * | 2020-11-24 | 2021-02-05 | 沈阳东软智能医疗科技研究院有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN112614062A (en) * | 2020-12-17 | 2021-04-06 | 北京陆桥技术股份有限公司 | Bacterial colony counting method and device and computer storage medium |
| CN112712530A (en) * | 2020-12-24 | 2021-04-27 | 中国人民解放军陆军军医大学第一附属医院 | Cardiac MRI left ventricle segmentation method and device |
| CN113160116A (en) * | 2021-02-03 | 2021-07-23 | 中南民族大学 | Method, system and equipment for automatically segmenting inner membrane and outer membrane of left ventricle |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102397070A (en) * | 2011-01-26 | 2012-04-04 | 无锡宙示医学软件开发有限公司 | Method for fully-automatically segmenting and quantifying left ventricle of cardiac magnetic resonance image |
| US20120165674A1 (en) * | 2010-09-08 | 2012-06-28 | Toshiba Medical Systems Corporation | Ultrasound diagnosis apparatus, image processing apparatus, and image processing method |
| CN103886603A (en) * | 2014-03-31 | 2014-06-25 | 西北工业大学 | Left ventricle nuclear magnetic resonance image segmentation and three-dimensional reconstruction method |
-
2016
- 2016-03-21 CN CN201610161395.2A patent/CN105741310B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120165674A1 (en) * | 2010-09-08 | 2012-06-28 | Toshiba Medical Systems Corporation | Ultrasound diagnosis apparatus, image processing apparatus, and image processing method |
| CN102397070A (en) * | 2011-01-26 | 2012-04-04 | 无锡宙示医学软件开发有限公司 | Method for fully-automatically segmenting and quantifying left ventricle of cardiac magnetic resonance image |
| CN103886603A (en) * | 2014-03-31 | 2014-06-25 | 西北工业大学 | Left ventricle nuclear magnetic resonance image segmentation and three-dimensional reconstruction method |
Non-Patent Citations (2)
| Title |
|---|
| 张建伟 等: "基于活动轮廓模型的左心室MR图像分割", 《电子学报》 * |
| 李小红 等: "结合分水岭和区域合并的彩色图像分割", 《电子测量与仪器学报》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220984A (en) * | 2017-05-05 | 2017-09-29 | 上海联影医疗科技有限公司 | A kind of image partition method, system and grid model |
| CN107220984B (en) * | 2017-05-05 | 2021-07-16 | 上海联影医疗科技股份有限公司 | Image segmentation method, image segmentation system and image segmentation device |
| CN107610095A (en) * | 2017-08-04 | 2018-01-19 | 南京邮电大学 | Heart CT coronary artery full-automatic partition methods based on image co-registration |
| CN109272512A (en) * | 2018-09-25 | 2019-01-25 | 南昌航空大学 | A kind of method of outer membrane in automatic segmentation left ventricle |
| CN109272512B (en) * | 2018-09-25 | 2022-02-15 | 南昌航空大学 | Method for automatically segmenting left ventricle inner and outer membranes |
| CN110033466A (en) * | 2019-04-01 | 2019-07-19 | 数坤（北京）网络科技有限公司 | Image segmentation boundary determining method is straightened in a kind of coronary artery based on multi-grey level |
| CN110378948A (en) * | 2019-07-02 | 2019-10-25 | 北京字节跳动网络技术有限公司 | 3D model reconstruction method, device and electronic equipment |
| CN110378948B (en) * | 2019-07-02 | 2023-08-25 | 北京字节跳动网络技术有限公司 | 3D model reconstruction method and device and electronic equipment |
| CN110471469B (en) * | 2019-09-26 | 2021-03-16 | 湖南航天机电设备与特种材料研究所 | Self-adaptive temperature control method based on PI algorithm |
| CN110471469A (en) * | 2019-09-26 | 2019-11-19 | 湖南航天机电设备与特种材料研究所 | A kind of adaptive temperature control method based on PI algorithm |
| CN111028254A (en) * | 2019-12-09 | 2020-04-17 | 上海交通大学医学院附属上海儿童医学中心 | Left myocardium segmentation method based on cardiac cine magnetic resonance image |
| CN111028254B (en) * | 2019-12-09 | 2023-03-24 | 上海交通大学医学院附属上海儿童医学中心 | Left myocardium segmentation method based on cardiac cine magnetic resonance image |
| CN111369525A (en) * | 2020-03-02 | 2020-07-03 | 联影智能医疗科技(北京)有限公司 | Image analysis method, apparatus and storage medium |
| CN111369525B (en) * | 2020-03-02 | 2023-05-30 | 联影智能医疗科技(北京)有限公司 | Image analysis method, apparatus and storage medium |
| WO2022000726A1 (en) * | 2020-06-29 | 2022-01-06 | 苏州润迈德医疗科技有限公司 | Method and system for obtaining connected domains of left atrium and left ventricle on basis of ct image |
| CN111815586A (en) * | 2020-06-29 | 2020-10-23 | 苏州润心医疗器械有限公司 | Method and system for acquiring connected domain of left atrium and left ventricle based on CT image |
| CN112215839B (en) * | 2020-10-27 | 2024-04-19 | 东软教育科技集团有限公司 | Six-segment segmentation method, system and storage medium for left ventricular wall of echocardiogram |
| CN112215839A (en) * | 2020-10-27 | 2021-01-12 | 大连东软教育科技集团有限公司 | Method, system and storage medium for six-segment division of left ventricular wall of echocardiogram |
| CN112308845A (en) * | 2020-11-03 | 2021-02-02 | 赛诺威盛科技（北京）有限公司 | Left ventricle segmentation method and device and electronic equipment |
| CN112308845B (en) * | 2020-11-03 | 2021-07-02 | 赛诺威盛科技(北京)股份有限公司 | Left ventricle segmentation method and device and electronic equipment |
| CN112330708A (en) * | 2020-11-24 | 2021-02-05 | 沈阳东软智能医疗科技研究院有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN112330708B (en) * | 2020-11-24 | 2024-04-23 | 沈阳东软智能医疗科技研究院有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN112614062B (en) * | 2020-12-17 | 2024-04-26 | 北京陆桥技术股份有限公司 | Colony counting method, colony counting device and computer storage medium |
| CN112614062A (en) * | 2020-12-17 | 2021-04-06 | 北京陆桥技术股份有限公司 | Bacterial colony counting method and device and computer storage medium |
| CN112712530A (en) * | 2020-12-24 | 2021-04-27 | 中国人民解放军陆军军医大学第一附属医院 | Cardiac MRI left ventricle segmentation method and device |
| CN113160116A (en) * | 2021-02-03 | 2021-07-23 | 中南民族大学 | Method, system and equipment for automatically segmenting inner membrane and outer membrane of left ventricle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105741310B (en) | 2018-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105741310A (en) | Heart's left ventricle image segmentation system and method | |
| CN103824295B (en) | The dividing method of adherent hyaline-vascular type lung nodule in a kind of lung CT image | |
| CN102385751B (en) | Liver tumor region segmentation method based on watershed transform and classification through support vector machine | |
| CN107403201A (en) | Tumour radiotherapy target area and jeopardize that organ is intelligent, automation delineation method | |
| CN103106408B (en) | The automatic assisted detection system of stomach CT image lymph node of non-formaldehyde finishing | |
| CN104268873A (en) | Breast tumor partition method based on nuclear magnetic resonance images | |
| CN106127753B (en) | CT images body surface handmarking's extraction method in a kind of surgical operation | |
| CN102048550A (en) | Method for automatically generating liver 3D (three-dimensional) image and accurately positioning liver vascular domination region | |
| CN104899851A (en) | Lung nodule image segmentation method | |
| Casiraghi et al. | Automatic abdominal organ segmentation from CT images | |
| Hadhoud et al. | Left ventricle segmentation in cardiac MRI images | |
| CN101515367A (en) | Method for segmenting sulus regions on surface of pallium of a three-dimensional cerebral magnetic resonance image | |
| Zhang et al. | Medical image segmentation based on watershed and graph theory | |
| El-Baz et al. | A novel 3D joint Markov-Gibbs model for extracting blood vessels from PC–MRA images | |
| CN103035009A (en) | Pulmonary nodule edge rebuilding and partitioning method based on computed tomography (CT) image | |
| Baudin et al. | Automatic skeletal muscle segmentation through random walks and graph-based seed placement | |
| CN106846346A (en) | Sequence C T image pelvis profile rapid extracting methods based on key frame marker | |
| Zidan et al. | Level set-based CT liver image segmentation with watershed and artificial neural networks | |
| CN106846330A (en) | Human liver's feature modeling and vascular pattern space normalizing method | |
| CN102663762B (en) | The dividing method of symmetrical organ in medical image | |
| Guo et al. | A novel myocardium segmentation approach based on neutrosophic active contour model | |
| Xia et al. | 3D cascaded convolutional networks for multi-vertebrae segmentation | |
| Kitrungrotsakul et al. | Interactive deep refinement network for medical image segmentation | |
| KR101831340B1 (en) | Method and apparatus for automatic segmentation of renal parenchyma using graph-cuts with shape constraint based on multi-probabilistic atlas in abdominal ct images | |
| El-Baz et al. | Cerebrovascular segmentation by accurate probabilistic modeling of TOF-MRA 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |