CN110378910A - Abdominal cavity multiple organ dividing method and device based on map fusion - Google Patents
Abdominal cavity multiple organ dividing method and device based on map fusion Download PDFInfo
- Publication number
- CN110378910A CN110378910A CN201910579726.8A CN201910579726A CN110378910A CN 110378910 A CN110378910 A CN 110378910A CN 201910579726 A CN201910579726 A CN 201910579726A CN 110378910 A CN110378910 A CN 110378910A
- Authority
- CN
- China
- Prior art keywords
- image
- atlas
- segmented
- registered
- gold standard
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000004927 fusion Effects 0.000 title claims abstract description 31
- 210000000056 organ Anatomy 0.000 title claims abstract description 23
- 210000000683 abdominal cavity Anatomy 0.000 title claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims description 47
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 40
- 230000003187 abdominal effect Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 210000001015 abdomen Anatomy 0.000 description 3
- 230000002440 hepatic effect Effects 0.000 description 3
- 210000004185 liver Anatomy 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 210000000496 pancreas Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 210000002784 stomach Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The embodiment of the present invention provides a kind of abdominal cavity multiple organ dividing method and device based on map fusion, wherein method includes: to choose multiple mark points in the CT image and image to be split in map respectively, CT image is registrated to image to be split according to the multiple mark point, the goldstandard in map is accordingly adjusted later, so that goldstandard adjusted is consistent with the CT image after being registrated, for the CT image after secondary registration any one in map, the map similarity of CT image and the image to be split after calculating the registration, and combine goldstandard adjusted, CT image goldstandard corresponding with pixel any in image to be split after being registrated.The embodiment of the present invention can obtain multiple organs while alignment as a result, laying a good foundation for subsequent singulation image.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for abdominal cavity multi-organ segmentation based on atlas fusion.
Background
In many diseases including cancer diseases, multiple organs of the abdomen need to be segmented to develop a subsequent treatment scheme, and different from other multi-objective segmentation tasks, the boundaries of the organs of the abdomen CT image are fuzzy, the types of the organs are various, the organs are influenced by abdominal pressure, and certain organs (such as the stomach, the pancreas, the liver and the like) in the human body have larger deformation. Meanwhile, manual segmentation is time-consuming and labor-consuming, the burden of medical personnel is increased frequently, and even treatment is delayed possibly, so that the automatic segmentation of the abdominal multiple organs by using the multiple organ segmentation system is of great significance.
Multi-atlas segmentation (MAS) is one of the most widely used and most successful image segmentation techniques in biomedical applications. Atlas refers to the combination of a CT image and a corresponding gold standard, where the gold standard represents the annotation of the target in a segmentation method, usually an artificial annotation. The multi-atlas segmentation technique directly manipulates and utilizes the entire dataset of the atlas, with the flexibility to better capture anatomical variations, thus providing better effect segmentation accuracy. The goal of the atlas algorithm is to assign segmentation labels to pixels of the image to be segmented using the relationship between the intensity of the atlas and the segmentation labels. Initial algorithms for segmentation using atlases typically employ a two-step procedure, with the relevant atlases determined and used in a second registration-based segmentation process. At this stage, the mainstream atlas algorithm is a segmentation algorithm based on probabilistic classification. The algorithm has two characteristics, including a unified map coordinate system and statistical data about the tags. Firstly, defining a uniform coordinate system by co-registering training images for constructing an atlas; the probability of a particular tag is then pre-computed at a given location in atlas coordinate system space. And finally, segmenting the image to be segmented in the atlas coordinate system by using the probability inference process of the parameter statistical model. Spatial normalization of the atlas may be achieved by registration of an atlas template created during training, or co-estimated with segmentation in the probabilistic model. Many strategies in atlas algorithms revolve around how to exploit image similarity and how to overcome the specificity of different organ tissues, and therefore how to implement multi-organ segmentation based on atlas becomes one of the research focuses on image processing.
Disclosure of Invention
Embodiments of the present invention provide a method and apparatus for laparoscopic multi-organ segmentation based on atlas fusion that overcomes, or at least partially solves, the above-mentioned problems.
In a first aspect, an embodiment of the present invention provides an abdominal cavity multi-organ segmentation method based on atlas fusion, including:
respectively selecting a plurality of marking points from a CT image and an image to be segmented in an atlas, registering the CT image to the image to be segmented according to the marking points, and then correspondingly adjusting a gold standard in the atlas to ensure that the adjusted gold standard is consistent with the registered CT image;
and calculating the atlas similarity of the registered CT image and the image to be segmented for any registered CT image in the atlas, and combining the adjusted golden standard to obtain the golden standard corresponding to any pixel point in the registered CT image and the image to be segmented.
In a second aspect, an embodiment of the present invention provides an abdominal cavity multi-organ segmentation apparatus based on atlas fusion, including:
the registration module is used for respectively selecting a plurality of marking points in the CT image and the image to be segmented in the atlas, registering the CT image to the image to be segmented according to the marking points, and then correspondingly adjusting the gold standard in the atlas to ensure that the adjusted gold standard is consistent with the registered CT image;
and the segmentation module is used for calculating the atlas similarity between the registered CT image and the image to be segmented for any one pair of registered CT images in the atlas, and obtaining the gold standard corresponding to any pixel point in the registered CT image and the image to be segmented by combining the adjusted gold standard.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method provided in the first aspect when executing the program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method as provided in the first aspect.
According to the method and the device for abdominal multi-organ segmentation based on atlas fusion, provided by the embodiment of the invention, by selecting the annotation point and then configuring the CT image in the atlas to the image to be segmented by using the annotation point, the result that a plurality of organs are aligned simultaneously can be obtained, and a foundation is laid for the subsequent segmentation of the image.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a method and apparatus for abdominal multi-organ segmentation based on atlas fusion according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an abdominal cavity multi-organ segmentation apparatus based on atlas fusion according to an embodiment of the present invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a method for abdominal multi-organ segmentation based on atlas fusion according to an embodiment of the present invention, as shown in fig. 1, the method includes S101 and S102, specifically:
s101, respectively selecting a plurality of marking points from a CT image and an image to be segmented in an atlas, registering the CT image to the image to be segmented according to the marking points, and then correspondingly adjusting a gold standard in the atlas to enable the adjusted gold standard to be consistent with the registered CT image.
It will be appreciated that the atlas includes a number of CT images, each CT image having a predetermined Gold standard. For the division task of multiple organs in the abdomen, the result of simultaneous alignment of multiple organs is difficult to obtain through the traditional registration process, so the embodiment of the invention respectively selects multiple marking points for the CT image and the image to be divided in the atlas and uses the marking points for registration. In the abdominal multi-organ segmentation task, it is difficult to determine the feature points of each organ. For the liver, the embodiment of the present invention may select a plurality of feature points, such as the hepatic dome, anterior right lobe segment, hepatic right lobe tip, posterior right lobe segment, morrison's sack, hepatic portal and lateral left lobe segment of the liver. After the CT image is registered, the gold standard corresponding to the CT image needs to be adjusted, so that the adjusted gold standard is consistent with the registered CT image. Step S101 of the embodiment of the present invention can obtain a better organ alignment effect than that of the prior art, and provides a basis for subsequently determining each gold standard to be read in the image to be matched.
S102, for any one pair of registered CT images in the atlas, calculating atlas similarity of the registered CT image and the image to be segmented, and combining the adjusted golden standard to obtain the golden standard corresponding to any pixel point in the registered CT image and the image to be segmented.
It should be noted that, after the registered CT image obtained in step S101 of the embodiment of the present invention is adopted, the existing atlas fusion algorithm based on the global atlas similarity may be adopted to segment the image. It can be understood that the image fusion algorithm based on global atlas similarity belongs to the conventional technical means in the field, and is not described herein again.
It should be noted that, in the embodiment of the present invention, by selecting the annotation point and then configuring the CT image in the atlas to the image to be segmented by using the annotation point, a result of aligning a plurality of organs at the same time can be obtained, which lays a foundation for subsequent segmentation of the image.
On the basis of the above embodiments, as an optional embodiment, the selecting a plurality of labeling points in the CT image and the image to be segmented in the atlas respectively specifically includes:
obtaining a contour curved surface of an organ according to a gold standard corresponding to the CT image;
and taking the center of the organ as an origin, uniformly drawing rays outwards, and taking the intersection point of the rays and the contour curved surface as an annotation point.
For example, if an organ is a sphere, the contour surface is a spherical surface, and the rays are emitted outward from the center of the sphere at regular angular intervals, for example, 90 degrees, so that 6 labeled points are obtained, and the minimum angular difference between the labeled points is 90 degrees.
On the basis of the foregoing embodiments, as an optional embodiment, the registering the CT image to the image to be segmented according to the plurality of annotation points specifically includes:
the spatial consistency of the labeling points of the CT image and the image to be segmented is taken as a target, namely, the transformation target is to make the labeling points of the atlas CT image and the labeling points of the image to be segmented more close to each other in space after registration transformation. And registering the CT image to the image to be segmented by adopting rigid registration, affine registration and B-spline-based non-rigid registration.
In particular, the registration of B-splines may be defined as:
wherein xkTo mark points, beta3(x) Is a cubic multi-dimensional B-spline polynomial, pkIs B-spline coefficient vector, i.e. displacement of the marked points, sigma is the distance between the marked points of the B-spline, NxThe set of all the labeled points. The mesh of annotation points is defined by the spacing σ between the annotation points, which may be different for each direction.
Considering that the existing image segmentation based on global atlas similarity only has low precision, the embodiment of the invention determines the atlas similarity by combining global weight with local weight, specifically,
the global weight is determined according to the pixel intensity of any pixel point in the image to be segmented and the average difference intensity of the CT image after registration.
Global weights
Wherein the squared error intensity Δ (I, I)n)＝∑j∈R||I(xj)-In(xj)||2；ΔδRepresents an intensity threshold; i (x)j) Representing the jth pixel point in the image I to be segmented; i isn(xj) Representing a jth pixel point in the nth registered CT image in the atlas; r represents a real number.
The local weight is determined according to the gray values of the image blocks taking the given pixel as the center in the image to be segmented and the image blocks at the same spatial position on the CT image after registration and the distance on the uniform coordinate system.
Local weight
Wherein,representing a given pixel x in an image to be segmentediImage block with centerAnd a given pixel x in the n registered CT image in the atlasjImage block with centerThe gray scale difference between; h isvThe distance between the two image blocks on the same coordinate system is obtained; x is the number ofiAnd xjAre identical in spatial position.
On the basis of the foregoing embodiments, as an optional embodiment, the obtaining of the gold standard corresponding to any pixel point in the registered CT image and the image to be segmented specifically includes:
calculating the probability of a gold standard corresponding to any pixel point in the image to be segmented according to the following formula:
wherein, L (x) represents the probability of the golden standard corresponding to the pixel point x in the image to be segmented; n represents the total number of CT images in the atlas,representing the global weight of the nth CT image and the image to be segmented;representing the local weight of the nth CT image and the image to be segmented; l isn(xj) And (4) a label of a gold standard corresponding to the pixel point j in the image to be segmented is represented.
Fig. 2 is a schematic structural diagram of an abdominal cavity multi-organ segmentation apparatus based on atlas fusion according to an embodiment of the present invention, and as shown in fig. 2, the abdominal cavity multi-organ segmentation apparatus based on atlas fusion includes: a registration module 201 and a segmentation module 202, wherein:
the registration module 201 is configured to select a plurality of annotation points from the CT image and the image to be segmented in the atlas, register the CT image to the image to be segmented according to the plurality of annotation points, and then correspondingly adjust the gold standard in the atlas, so that the adjusted gold standard is consistent with the registered CT image.
The segmentation module 202 is configured to calculate, for any one pair of registered CT images in the atlas, atlas similarity between the registered CT image and the image to be segmented, and obtain, in combination with the adjusted gold standard, a gold standard corresponding to any pixel point in the registered CT image and the image to be segmented.
The device for dividing an abdominal cavity multi-organ based on atlas fusion provided in the embodiment of the present invention specifically executes the flows of the above-mentioned embodiments of the method for dividing an abdominal cavity multi-organ based on atlas fusion, and for details, the contents of the above-mentioned embodiments of the method for dividing an abdominal cavity multi-organ based on atlas fusion are referred to, and are not described herein again. The abdominal cavity multi-organ segmentation device based on atlas fusion provided by the embodiment of the invention can obtain the result of simultaneously aligning a plurality of organs by selecting the marking point and configuring the CT image in the atlas to the image to be segmented by using the marking point, thereby laying a foundation for subsequent segmentation images.
Fig. 3 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor)310, a communication Interface (communication Interface)320, a memory (memory)330 and a communication bus 340, wherein the processor 310, the communication Interface 320 and the memory 330 communicate with each other via the communication bus 340. The processor 310 may invoke a computer program stored on the memory 330 and executable on the processor 310 to perform the atlas fusion based abdominal cavity multi-organ segmentation method provided by the above embodiments, for example, including: respectively selecting a plurality of marking points from a CT image in an atlas and an image to be segmented, registering the CT image to the image to be segmented according to the marking points, then correspondingly adjusting a gold standard in the atlas to enable the adjusted gold standard to be consistent with the registered CT image, calculating atlas similarity of the registered CT image and the image to be segmented for any registered CT image in the atlas, and combining the adjusted gold standard to obtain the gold standard corresponding to any pixel point in the registered CT image and the image to be segmented.
In addition, the logic instructions in the memory 330 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or make a contribution to the prior art, or may be implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the method for abdominal multi-organ segmentation based on atlas fusion provided in the foregoing embodiments when executed by a processor, for example, the method includes: respectively selecting a plurality of marking points from a CT image in an atlas and an image to be segmented, registering the CT image to the image to be segmented according to the marking points, then correspondingly adjusting a gold standard in the atlas to enable the adjusted gold standard to be consistent with the registered CT image, calculating atlas similarity of the registered CT image and the image to be segmented for any registered CT image in the atlas, and combining the adjusted gold standard to obtain the gold standard corresponding to any pixel point in the registered CT image and the image to be segmented.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are merely illustrative of the technical solutions of the present invention, and not restrictive of alignment; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features in alignment may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An abdominal cavity multi-organ segmentation method based on atlas fusion is characterized by comprising the following steps:
respectively selecting a plurality of marking points from a CT image and an image to be segmented in an atlas, registering the CT image to the image to be segmented according to the marking points, and then correspondingly adjusting a gold standard in the atlas to ensure that the adjusted gold standard is consistent with the registered CT image;
and calculating the atlas similarity of the registered CT image and the image to be segmented for any registered CT image in the atlas, and combining the adjusted golden standard to obtain the golden standard corresponding to any pixel point in the registered CT image and the image to be segmented.
2. The abdominal cavity multi-organ segmentation method based on atlas fusion as claimed in claim 1, wherein the method comprises selecting a plurality of labeling points in the CT image and the image to be segmented in the atlas respectively, specifically:
obtaining a contour curved surface of an organ according to a gold standard corresponding to the CT image;
and taking the center of the organ as an origin, uniformly drawing rays outwards, and taking the intersection point of the rays and the contour curved surface as an annotation point.
3. The atlas fusion based abdominal cavity multi-organ segmentation method according to claim 1, wherein the registering of the CT image to the image to be segmented according to the plurality of annotation points specifically comprises:
and taking the spatial consistency of the labeling points of the CT image and the image to be segmented as a target, and registering the CT image to the image to be segmented by adopting rigid registration, affine registration and non-rigid registration based on B splines.
4. The atlas fusion based abdominal cavity multi-organ segmentation method according to claim 1, wherein the atlas similarity includes calculating a global weight and a local weight of the registered CT image and the image to be segmented;
the global weight is determined according to the pixel intensity of any pixel point in the image to be segmented and the average difference intensity of the CT image after registration;
the local weight is determined according to the gray values of the image blocks taking the given pixel as the center in the image to be segmented and the image blocks at the same spatial position on the CT image after registration and the distance on the uniform coordinate system.
5. The map fusion-based abdominal multi-organ segmentation method of claim 4, wherein the global weight
Wherein the squared error intensity Δ (I, I)n)＝∑j∈R||I(xj)-In(xj)||2；ΔδRepresents an intensity threshold; i (x)j) Representing the jth pixel point in the image I to be segmented; i isn(xj) Representing a jth pixel point in the nth registered CT image in the atlas; r represents a real number.
6. The map fusion-based abdominal multi-organ segmentation method of claim 4, wherein the local weights
Wherein,representing a given pixel x in an image to be segmentediImage block with centerAnd a given pixel x in the n registered CT image in the atlasjImage block with centerThe gray scale difference between; h isvThe distance between the two image blocks on the same coordinate system is obtained; x is the number ofiAnd xjAre identical in spatial position.
7. The atlas fusion-based abdominal cavity multi-organ segmentation method according to claim 4, wherein the obtaining of the gold standard corresponding to any pixel point in the registered CT image and the image to be segmented specifically comprises:
calculating the probability of a gold standard corresponding to any pixel point in the image to be segmented according to the following formula:
wherein, L (x) represents the probability of the golden standard corresponding to the pixel point x in the image to be segmented; n represents the total number of CT images in the atlas,representing the global weight of the nth CT image and the image to be segmented;representing the local weight of the nth CT image and the image to be segmented; l isn(xj) And (4) a label of a gold standard corresponding to the pixel point j in the image to be segmented is represented.
8. An abdominal cavity multi-organ segmentation device based on atlas fusion, comprising:
the registration module is used for respectively selecting a plurality of marking points in the CT image and the image to be segmented in the atlas, registering the CT image to the image to be segmented according to the marking points, and then correspondingly adjusting the gold standard in the atlas to ensure that the adjusted gold standard is consistent with the registered CT image;
and the segmentation module is used for calculating the atlas similarity between the registered CT image and the image to be segmented for any one pair of registered CT images in the atlas, and obtaining the gold standard corresponding to any pixel point in the registered CT image and the image to be segmented by combining the adjusted gold standard.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the atlas fusion based abdominal cavity multi-organ segmentation method of any of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the atlas fusion based abdominal cavity multi-organ segmentation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910579726.8A CN110378910B (en) | 2019-06-28 | 2019-06-28 | Abdominal cavity multi-organ segmentation method and device based on map fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910579726.8A CN110378910B (en) | 2019-06-28 | 2019-06-28 | Abdominal cavity multi-organ segmentation method and device based on map fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110378910A true CN110378910A (en) | 2019-10-25 |
| CN110378910B CN110378910B (en) | 2021-10-22 |
Family
ID=68251363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910579726.8A Active CN110378910B (en) | 2019-06-28 | 2019-06-28 | Abdominal cavity multi-organ segmentation method and device based on map fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110378910B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598634A (en) * | 2020-12-18 | 2021-04-02 | 燕山大学 | CT image organ positioning method based on 3D CNN and iterative search |
| CN114972764A (en) * | 2022-08-01 | 2022-08-30 | 浙江省肿瘤医院 | Multi-atlas segmentation method based on feature clustering |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065315A (en) * | 2012-12-28 | 2013-04-24 | 中国科学院深圳先进技术研究院 | Method, system and medical device of multiple atlas fusion |
| CN109523512A (en) * | 2018-10-17 | 2019-03-26 | 哈尔滨理工大学 | A kind of Automatic medical image segmentation method based on multichannel chromatogram tag fusion |
-
2019
- 2019-06-28 CN CN201910579726.8A patent/CN110378910B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065315A (en) * | 2012-12-28 | 2013-04-24 | 中国科学院深圳先进技术研究院 | Method, system and medical device of multiple atlas fusion |
| CN109523512A (en) * | 2018-10-17 | 2019-03-26 | 哈尔滨理工大学 | A kind of Automatic medical image segmentation method based on multichannel chromatogram tag fusion |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598634A (en) * | 2020-12-18 | 2021-04-02 | 燕山大学 | CT image organ positioning method based on 3D CNN and iterative search |
| CN112598634B (en) * | 2020-12-18 | 2022-11-25 | 燕山大学 | CT image organ positioning method based on 3D CNN and iterative search |
| CN114972764A (en) * | 2022-08-01 | 2022-08-30 | 浙江省肿瘤医院 | Multi-atlas segmentation method based on feature clustering |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110378910B (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11657509B2 (en) | Method for precisely and automatically positioning reference line for integrated images | |
| US10546014B2 (en) | Systems and methods for segmenting medical images based on anatomical landmark-based features | |
| CN106485695B (en) | Medical image Graph Cut dividing method based on statistical shape model | |
| US10853941B2 (en) | Registration method and system for non-rigid multi-modal medical image | |
| CN110599528A (en) | Unsupervised three-dimensional medical image registration method and system based on neural network | |
| US8861891B2 (en) | Hierarchical atlas-based segmentation | |
| Sokooti et al. | Quantitative error prediction of medical image registration using regression forests | |
| US9727975B2 (en) | Knowledge-based automatic image segmentation | |
| CN110378910B (en) | Abdominal cavity multi-organ segmentation method and device based on map fusion | |
| Gsaxner et al. | PET-train: Automatic ground truth generation from PET acquisitions for urinary bladder segmentation in CT images using deep learning | |
| Min et al. | Automatic radiotherapy delineation quality assurance on prostate MRI with deep learning in a multicentre clinical trial | |
| CN114332563A (en) | Image processing model training method, related device, equipment and storage medium | |
| EP3608872B1 (en) | Image segmentation method and system | |
| Rivest-Hénault et al. | Inverse-consistent rigid registration of CT and MR for MR-based planning and adaptive prostate radiation therapy | |
| Wodzinski et al. | Application of B-splines FFD image registration in breast cancer radiotherapy planning | |
| WO2023178527A1 (en) | Generation method and generation apparatus for tumor radiotherapy region | |
| Ninomiya et al. | Feasibility of anatomical feature points for the estimation of prostate locations in the Bayesian delineation frameworks for prostate cancer radiotherapy | |
| US20230191157A1 (en) | Automatic estimation of positions of brachytherapy seeds | |
| CN112950582B (en) | 3D lung focus segmentation method and device based on deep learning | |
| CN117672472B (en) | Symmetrical labeling method based on abdomen CT image | |
| Spinczyk et al. | Simple atlas selection strategies for liver segmentation in ct images | |
| CN115424720A (en) | Tubular structure fracture completion method and device and computer equipment | |
| CN116721341A (en) | Arable land extraction method based on semantic segmentation and object-oriented segmentation algorithm | |
| CN114022524A (en) | CT neck and rib positioning method and system based on atlas registration | |
| Huang et al. | Rodent brain extraction using B-spline based deformable model |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211009 Address after: 100081 0810 Haidian Science and technology building, Zhongguancun South Street, Haidian District, Beijing Applicant after: ARIEMEDI MEDICAL SCIENCE (BEIJING) Co.,Ltd. Address before: 050000 3rd floor, unit 1, building 7, Runjiang international headquarters, 319 Changjiang Avenue, high tech Zone, Shijiazhuang City, Hebei Province Applicant before: AIRUI MAIDI TECHNOLOGY SHIJIAZHUANG Co.,Ltd. |
|
| TA01 | Transfer of patent application right |