CN115187594A - Cerebral cortex model reconstruction method and system - Google Patents
Cerebral cortex model reconstruction method and system Download PDFInfo
- Publication number
- CN115187594A CN115187594A CN202211092436.9A CN202211092436A CN115187594A CN 115187594 A CN115187594 A CN 115187594A CN 202211092436 A CN202211092436 A CN 202211092436A CN 115187594 A CN115187594 A CN 115187594A
- Authority
- CN
- China
- Prior art keywords
- brain
- magnetic resonance
- resonance imaging
- space
- spatial
- 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 41
- 210000003710 cerebral cortex Anatomy 0.000 title claims abstract description 30
- 210000004556 brain Anatomy 0.000 claims abstract description 55
- 238000002595 magnetic resonance imaging Methods 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 27
- 230000001054 cortical effect Effects 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000002490 cerebral effect Effects 0.000 claims 1
- 230000010339 dilation Effects 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 6
- 238000012937 correction Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- JTJMJGYZQZDUJJ-UHFFFAOYSA-N phencyclidine Chemical compound C1CCCCN1C1(C=2C=CC=CC=2)CCCCC1 JTJMJGYZQZDUJJ-UHFFFAOYSA-N 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 125000004435 hydrogen atom Chemical group [H]* 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000007920 subcutaneous administration Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T7/344—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving models
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Radiology & Medical Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- High Energy & Nuclear Physics (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Computer Graphics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The application belongs to the technical field of medical equipment, and particularly relates to a cerebral cortex model reconstruction method and a cerebral cortex model reconstruction system, which comprise the following steps: acquiring magnetic resonance imaging of the brain; preprocessing the acquired magnetic resonance imaging to complete the spatial registration of the brain magnetic resonance imaging; acquiring three-dimensional coordinates of brain space points after spatial registration; processing magnetic resonance imaging of the brain and three-dimensional coordinates of brain space points by using an implicit surface prediction network to obtain implicit surface expression of each space point; and constructing a zero isosurface according to the obtained implicit surface expression of each space point and combining a mobile cube algorithm to obtain a cerebral cortex model. The method and the device can construct the implicit curved surface with continuous space, can express abundant shape details, eliminate singular points through an expansion processing algorithm, effectively eliminate topological defects such as holes or handles through a spherical mode of topological correction, and improve the model reconstruction quality.
Description
Technical Field
The application belongs to the technical field of medical equipment, and particularly relates to a cerebral cortex model reconstruction method and a cerebral cortex model reconstruction system.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
In the medical field, medical images become an important basis for doctors to judge the state and development of a patient as one of important means for auxiliary diagnosis, and Magnetic Resonance Imaging (MRI) has the characteristic of Imaging by measuring the relaxation time of hydrogen atoms in a human body under an applied Magnetic field, so that compared with X-ray and CT, the MRI has less radiation damage to the human body and clearer Imaging, and becomes a research hotspot in the field of medical image processing in recent years.
However, for MRI of sequence imaging, a doctor with a great experience is often required to judge whether there is an abnormal condition from a plurality of scanned images, so that MRI-based three-dimensional reconstruction and cortical surface reconstruction can help the doctor to more intuitively observe the brain condition of a patient, thereby better judging the patient condition.
At present, a voxel-based mode is mainly adopted for performing three-dimensional brain reconstruction according to MRI, the voxel-based reconstruction mode is limited by resolution and memory, reconstructed surface details are prone to lose surface detail information due to excessive smoothing, free Surfer which is widely applied in the field of three-dimensional brain cortex surface reconstruction at present and a newly proposed accelerated version of Fast Surfer thereof are both a voxel segmentation-based method, and Partial Volume Effect (PVE) cannot be well inhibited, so that detail expression capability is limited.
Disclosure of Invention
In order to solve the above problems, the present application provides a method and a system for reconstructing a cortical model, which construct a spatially continuous implicit curved surface, and provide a method and a system for reconstructing a cortical model based on implicit functions, which can express rich shape details, so as to solve at least one technical problem in the above background art and improve the quality of reconstructing the cortical model.
According to some embodiments, a first aspect of the present application provides a cerebral cortex model reconstruction method, which adopts the following technical solutions:
a method of reconstructing a cortical model, comprising:
acquiring magnetic resonance imaging of the brain;
preprocessing the acquired magnetic resonance imaging to complete the spatial registration of the brain magnetic resonance imaging;
acquiring three-dimensional coordinates of brain space points after spatial registration;
processing magnetic resonance imaging of the brain and three-dimensional coordinates of brain space points by using an implicit surface prediction network to obtain implicit surface expression of each space point;
and constructing a zero isosurface according to the obtained implicit surface expression of each space point and combining a mobile cube algorithm to obtain a cerebral cortex model.
As a further technical limitation, pre-processing of magnetic resonance imaging of the brain to accomplish spatial registration includes: the FreeSprofer tool was used for spatial registration, uniform registration to MNI305 space, and intensity normalization.
As a further technical limitation, the implicit curved surface prediction network comprises a coding network, wherein the coding network outputs the global feature vector and the local feature vector of the spatial point by inputting MRI data and spatial sampling points, and superposes and fuses the fused global feature vector and the fused local feature vector.
Furthermore, the implicit surface prediction network also comprises a decoding network, and the decoding network decodes the three-dimensional space point coordinates and the fused global feature vector and local feature vector to obtain the implicit surface expression of the space point prediction.
Further, the implicit surface representation is expressed in the form of a symbolic distance function SDF:
wherein S is equal to the isosurface 0 to obtain S, R represents a real number, and P represents a three-dimensional coordinate of the space point.
Further, marking the obtained S in a connected region marking mode, and eliminating singular points through an expansion processing algorithm; and eliminating topological deformation caused by singular points in a mode of correcting the topology into a sphere.
Furthermore, by moving a cube algorithm, 8 adjacent space points are taken to form a cube, and a zero isosurface is constructed in the cube, so that the three-dimensional reconstruction of the whole cerebral cortex surface is completed.
According to some embodiments, a second aspect of the present application provides a system for reconstructing a cerebral cortex model, which adopts the following technical solutions:
a cerebral cortex model reconstruction system, comprising:
an acquisition module configured to acquire magnetic resonance imaging of the brain;
a registration module configured to pre-process the acquired magnetic resonance imaging to complete spatial registration of the brain magnetic resonance imaging;
an acquisition module configured to acquire three-dimensional coordinates of the spatially registered brain space points;
the prediction module is configured to process magnetic resonance imaging of the brain and three-dimensional coordinates of brain space points by using an implicit surface prediction network to obtain implicit surface expression of each space point;
and the reconstruction module is configured to construct a zero isosurface according to the obtained implicit surface expression of each space point and by combining a mobile cube algorithm, so as to obtain a cerebral cortex model.
According to some embodiments, a third aspect of the present application provides a computer-readable storage medium, which adopts the following technical solutions:
a computer-readable storage medium, having stored thereon a program which, when being executed by a processor, carries out the steps of a method of reconstructing a cortical model according to the first aspect of the application.
According to some embodiments, a fourth aspect of the present application provides an electronic device, which adopts the following technical solutions:
an electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, the processor when executing the program implementing the steps in the method of reconstructing a cortical model of the brain according to the first aspect of the application.
Compared with the prior art, the beneficial effect of this application is:
the method can construct the implicit curved surface with continuous space, can express abundant shape details, eliminates singular points through an expansion processing algorithm, effectively eliminates topological defects such as holes or handles through a mode of changing topology into a spherical shape, and improves the quality of model reconstruction.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
Fig. 1 is a block diagram of a system for reconstructing a cerebral cortex model according to a first embodiment of the present application;
FIG. 2 is a flowchart of a cerebral cortex model reconstruction method according to a second embodiment of the present application;
FIG. 3 is a flowchart showing a method for reconstructing a cortical model according to a second embodiment of the present application;
FIG. 4 is a schematic diagram of an implicit surface prediction network structure in a second embodiment of the present application;
FIG. 5 is a schematic comparison of the original MRI data before and after spatial registration in example two of the present application;
fig. 6 shows holes and handles created in the reconstructed cortical surface without applying topological correction in example two of the present application.
Detailed Description
The present application will be further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In the present application, terms such as "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "side", "bottom", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only terms of relationships determined for convenience in describing structural relationships of the components or elements of the present application, and are not intended to refer to any components or elements of the present application, and are not to be construed as limiting the present application.
In the present application, terms such as "fixedly connected", "connected", and the like are to be understood in a broad sense, and mean either a fixed connection or an integrally connected or detachable connection; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present application can be determined according to specific situations by persons skilled in the relevant scientific research or technical field, and the terms cannot be understood as limiting the present application.
The embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example one
The embodiment one of the present application introduces a system for reconstructing a cerebral cortex model.
A system for reconstructing a cortical model of a brain as shown in fig. 1, comprising:
an acquisition module configured to acquire magnetic resonance imaging of the brain;
a registration module configured to pre-process the acquired magnetic resonance imaging to complete spatial registration of the brain magnetic resonance imaging;
an acquisition module configured to acquire three-dimensional coordinates of the spatially registered brain space points;
a prediction module configured to process magnetic resonance imaging of the brain and three-dimensional coordinates of brain spatial points using an implicit surface prediction network to obtain an implicit surface representation of each spatial point;
and the reconstruction module is configured to construct a zero isosurface according to the obtained implicit surface expression of each space point and by combining a mobile cube algorithm, so as to obtain a cerebral cortex model.
In this embodiment, a method for reconstructing a cortical model is implemented by using the system for reconstructing a cortical model, which includes:
using a registration module to preprocess the magnetic resonance imaging of the brain to complete spatial registration;
acquiring three-dimensional coordinates of the brain space points after spatial registration by using an acquisition module;
processing magnetic resonance imaging of the brain and three-dimensional coordinates of brain space points by using a prediction module and utilizing an implicit curved surface prediction network to obtain implicit curved surface expression of each space point;
and (3) constructing a zero isosurface by using a reconstruction module according to the implicit surface expression of each space point and combining a moving cube algorithm to obtain a cerebral cortex model.
In one embodiment, the preprocessing of magnetic resonance imaging of the brain to achieve spatial registration comprises: the FreeSprofer tool was used for spatial registration, uniform registration to MNI305 space, and intensity normalization. The MNI space is a coordinate system established from a series of magnetic resonance images of a normal human brain. Native space is the original space. The image is in original space without any transformation. The dimensions, the origin, the voxel size, etc. of the images in this space are all different, there is no comparability between different tested images, and any calculated features cannot be statistically analyzed or used for machine learning. All images tested must be registered and normalized to the same template so that all dimensions, origins, voxel sizes are the same. Using the MNI standard template, it means that the image is converted into MNI space. The image of the standard space also refers to an image of the MNI space.
The Free Surfer tool is an existing software, and is a tool for processing brain 3D structural image data and performing automatic cortex and subcutaneous nucleus segmentation.
The implicit curved surface prediction network comprises a coding network, wherein the coding network outputs the global characteristic vector and the local characteristic vector of the spatial point by inputting MRI data and spatial sampling points, and the global characteristic vector and the local characteristic vector are superposed and fused. The implicit surface prediction network also comprises a decoding network, and the implicit surface expression of the spatial point prediction is obtained by decoding the spatial point coordinates and the fused global feature vector and local feature vector.
In this embodiment, the encoding network used is Alex Net, and a one-dimensional feature vector composed of the output features of the network, the feature vector of the position point of the intermediate layer, and the three-dimensional coordinate point is used as the input of the decoding network. The decoding network used is a network structure proposed in the document "Chen, zhiqin, and Hao zhang" Learning interpolating fields for generating shape modifying "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern recognition, 2019", and the output of the network in the original document is changed from binary classification prediction on whether a three-dimensional coordinate point is on an implicit surface to implicit expression of predicting the point on a zero-valued surface.
The implicit surface representation is expressed in the form of a symbolic distance function SDF:
Marking the obtained S in a connected region marking mode, and eliminating singular points through an expansion processing algorithm; and the topological deformation caused by the singular point is eliminated by a mode of correcting the topology into a sphere.
And finally, by a moving cube algorithm, taking 8 adjacent space points to form a cube, and constructing a zero isosurface in the cube to complete the three-dimensional reconstruction of the whole cerebral cortex surface.
Example two
The second embodiment of the present application introduces a method for reconstructing a cerebral cortex model.
A method of reconstructing a cortical model, as shown in fig. 2, comprising:
acquiring magnetic resonance imaging of the brain;
preprocessing the acquired magnetic resonance imaging to complete the spatial registration of the brain magnetic resonance imaging;
acquiring three-dimensional coordinates of brain space points after spatial registration;
processing magnetic resonance imaging of the brain and three-dimensional coordinates of brain space points by using an implicit surface prediction network to obtain implicit surface expression of each space point;
and constructing a zero isosurface according to the obtained implicit surface expression of each space point and combining a mobile cube algorithm to obtain a cerebral cortex model.
In this embodiment, a cortical surface reconstruction and segmentation algorithm based on an implicit surface is provided, in an ubuntu16.04 system, a FreeKurfer 5.3 tool is used to perform training data preprocessing on MRI data, and hardware environments are Intel i7-7200H @2.7Hz x 8 CPU and GTX1080Ti GPU. The input of the system is a complete MRI scanning sequence of a testee, the output of the system is obtained through a series of processing, the output of the system is a three-dimensional cortical surface with spatial continuity, and the whole reconstruction process takes about 20 minutes.
As shown in fig. 3, a schematic diagram of a system for MRI three-dimensional reconstruction proposed in this embodiment is given, where the system mainly includes preprocessing, implicit surface prediction on the surface of the cerebral cortex, singular point processing and topology correction, and Marching Cubes algorithm to construct the surface of the cerebral cortex.
The method for reconstructing the surface of the cerebral cortex in the embodiment comprises the following specific implementation steps:
step 1: MRI data of the brain was preprocessed: spatial registration using freesrush tool, unified registration to MNI305 space, and intensity normalization; the state pair after spatial registration is shown in fig. 5.
Step 2: densely sampling brain space points to obtain three-dimensional coordinate points, inputting the MRI data sequence of the scanned subject and the three-dimensional coordinate P of the points on the generated MRI data into an implicit curved surface prediction network
. As shown in FIG. 4The network mainly comprises an encoding network and a decoding network, wherein data is output into two parts through the encoding network, one part is a global feature vector, and the other part is a local feature vector. The global feature vector being the last output of the coding network
The dimension vector is obtained by fusing the feature vectors on the feature map of each layer
A vector of dimensions.
By superposing the three-dimensional coordinates of the space point, the global characteristics and the local characteristics can be well fused, the global characteristics and the local characteristics are sent to a decoder for decoding and outputting, the final output is the predicted implicit surface expression of the point, the implicit surface expression is expressed by adopting a Symbolic Distance Function (SDF) form,
wherein S is equal to the isosurface 0 to obtain S, R represents a real number, and P represents a three-dimensional coordinate of the space point.
And 3, step 3: in order to further obtain smooth point prediction, correcting the predicted singular point, and processing S by adopting a morphological method: marking the obtained S by using a connected region marking mode, eliminating singular points by using an expansion processing algorithm, wherein the singular points can also cause topological deformation to a great extent; as shown in fig. 6, in the reconstruction process, a hole or a handle is likely to occur, which causes a topological defect in the reconstructed three-dimensional object, and greatly affects the reconstruction quality of the surface of the cerebral cortex. Fig. 6 (a) shows no defect, fig. 6 (b) shows a hole defect, and fig. 6 (c) shows a handle defect.
And 4, step 4: after the above steps are completed, SDF values between a series of description points and a zero isosurface are obtained, a marching cube algorithm is adopted, adjacent 8 points are taken to form a cube, and the zero isosurface is constructed in the cube, so that the three-dimensional reconstruction work of the whole cerebral cortex surface is completed.
According to the implicit curved surface prediction network of the brain provided by the embodiment 2, the network framework includes: the input of the network is to scan the MRI data sequence of the testee and the three-dimensional coordinates of points on the MRI data, the coding network is AlexNet, and the output characteristics of the network, the characteristic vector of the position point of the middle layer and the three-dimensional coordinate point form a one-dimensional characteristic vector to be used as the input of the decoding network; the decoding network is a network structure proposed in the document "Chen, zhiqin, and Hao Zhang." Learning interpolating fields for generating shape modifying. "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern recognition. 2019." and the output of the network in the original document is changed from binary classification prediction on whether a three-dimensional coordinate point is on an implicit surface to implicit expression for predicting a zero-valued surface of the point.
EXAMPLE III
The third embodiment of the application provides a computer-readable storage medium.
A computer-readable storage medium, on which a program is stored, which, when being executed by a processor, carries out the steps of the method for reconstructing a cortical model according to the second embodiment of the present application.
The detailed steps are the same as those of the reconstruction method of the cortical model provided in the second embodiment, and are not repeated herein.
Example four
The fourth embodiment of the application provides electronic equipment.
An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the cerebral cortex model reconstruction method according to the second embodiment of the present application.
The detailed steps are the same as those of the reconstruction method of the cortical model provided in the second embodiment, and are not repeated herein.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Although the embodiments of the present application have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present application, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive effort by those skilled in the art.
Claims (10)
1. A method of reconstructing a cortical model, comprising:
acquiring magnetic resonance imaging of the brain;
preprocessing the acquired magnetic resonance imaging to complete the spatial registration of the brain magnetic resonance imaging;
acquiring three-dimensional coordinates of brain space points after spatial registration;
processing magnetic resonance imaging of the brain and three-dimensional coordinates of brain space points by using an implicit surface prediction network to obtain implicit surface expression of each space point;
and constructing a zero isosurface according to the obtained implicit surface expression of each space point and combining a mobile cube algorithm to obtain a cerebral cortex model.
2. A method of cerebral cortical model reconstruction as claimed in claim 1, wherein the spatial registration is performed by pre-processing the magnetic resonance imaging of the brain, comprising: the FreeSprofer tool was used for spatial registration, uniform registration to MNI305 space, and intensity normalization.
3. A method as claimed in claim 1, wherein the implicit surface prediction network comprises a coding network, the coding network outputs the global feature vector and the local feature vector of the spatial point by inputting the MRI data and the spatial sampling point, and the fused global feature vector and the fused local feature vector are overlapped and fused.
4. A method as claimed in claim 3, wherein the implicit surface prediction network further comprises a decoding network for decoding the coordinates of the three-dimensional spatial point and the fused global and local feature vectors to obtain the implicit surface representation of the spatial point prediction.
5. A method of cerebral cortex model reconstruction as claimed in claim 4, characterized in that the implicit surface representation is expressed in the form of a signed distance function SDF:
wherein S is equal to the isosurface 0 to obtain S, R represents a real number, and P represents a three-dimensional coordinate of the space point.
6. A method of reconstructing a cortical model according to claim 5, in which the resulting S is labelled with connected component labels, singularities being eliminated by a dilation algorithm; and eliminating topological deformation caused by singular points in a mode of correcting the topology into a sphere.
7. A method of reconstructing a cortical model according to claim 6, in which the three-dimensional reconstruction of the entire cortical surface is performed by constructing a zero-iso-surface in a cube by moving the cube algorithm, taking 8 adjacent spatial points to form a cube.
8. A system for reconstructing a cortical model of a brain, comprising:
an acquisition module configured to acquire magnetic resonance imaging of the brain;
a registration module configured to pre-process the acquired magnetic resonance imaging to complete spatial registration of the brain magnetic resonance imaging;
an acquisition module configured to acquire three-dimensional coordinates of the spatially registered brain space points;
a prediction module configured to process magnetic resonance imaging of the brain and three-dimensional coordinates of brain spatial points using an implicit surface prediction network to obtain an implicit surface representation of each spatial point;
and the reconstruction module is configured to construct a zero isosurface according to the obtained implicit surface expression of each space point and by combining a mobile cube algorithm, so as to obtain a cerebral cortex model.
9. A computer-readable storage medium, on which a program is stored which, when being executed by a processor, carries out the steps of the method of reconstructing a cortical model of the brain of any of claims 1-7.
10. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps in the method of reconstructing a cortical model of the brain of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211092436.9A CN115187594B (en) | 2022-09-08 | 2022-09-08 | Cerebral cortex model reconstruction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211092436.9A CN115187594B (en) | 2022-09-08 | 2022-09-08 | Cerebral cortex model reconstruction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115187594A true CN115187594A (en) | 2022-10-14 |
| CN115187594B CN115187594B (en) | 2023-09-08 |
Family
ID=83523364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211092436.9A Active CN115187594B (en) | 2022-09-08 | 2022-09-08 | Cerebral cortex model reconstruction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115187594B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010024514A1 (en) * | 2000-03-22 | 2001-09-27 | Shinichi Matsunaga | Image processing device, singular spot detection method, and recording medium upon which singular spot detection program is recorded |
| CN101051388A (en) * | 2007-05-15 | 2007-10-10 | 骆建华 | Magnetic resonant part K data image reestablishing method based on compound two dimension singular sprectrum analysis |
| WO2020191545A1 (en) * | 2019-03-22 | 2020-10-01 | 合刃科技（深圳）有限公司 | System for analyzing stress of curved detection sample |
| CN113838187A (en) * | 2021-08-27 | 2021-12-24 | 南方科技大学 | Method and device for generating three-dimensional surface of cerebral subcortical structure and storage medium |
| CN114001654A (en) * | 2021-11-01 | 2022-02-01 | 北京卫星制造厂有限公司 | Workpiece end face pose evaluation method |
| CN114581628A (en) * | 2022-03-03 | 2022-06-03 | 北京银河方圆科技有限公司 | Cerebral cortex surface reconstruction method and readable storage medium |
| CN114972366A (en) * | 2022-07-27 | 2022-08-30 | 山东大学 | Full-automatic segmentation method and system for cerebral cortex surface based on graph network |
-
2022
- 2022-09-08 CN CN202211092436.9A patent/CN115187594B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010024514A1 (en) * | 2000-03-22 | 2001-09-27 | Shinichi Matsunaga | Image processing device, singular spot detection method, and recording medium upon which singular spot detection program is recorded |
| CN101051388A (en) * | 2007-05-15 | 2007-10-10 | 骆建华 | Magnetic resonant part K data image reestablishing method based on compound two dimension singular sprectrum analysis |
| WO2020191545A1 (en) * | 2019-03-22 | 2020-10-01 | 合刃科技（深圳）有限公司 | System for analyzing stress of curved detection sample |
| CN113838187A (en) * | 2021-08-27 | 2021-12-24 | 南方科技大学 | Method and device for generating three-dimensional surface of cerebral subcortical structure and storage medium |
| CN114001654A (en) * | 2021-11-01 | 2022-02-01 | 北京卫星制造厂有限公司 | Workpiece end face pose evaluation method |
| CN114581628A (en) * | 2022-03-03 | 2022-06-03 | 北京银河方圆科技有限公司 | Cerebral cortex surface reconstruction method and readable storage medium |
| CN114972366A (en) * | 2022-07-27 | 2022-08-30 | 山东大学 | Full-automatic segmentation method and system for cerebral cortex surface based on graph network |
Non-Patent Citations (3)
| Title |
|---|
| 唐浩丰等: "基于深度学习的图像补全算法综述", 《计算机科学》 * |
| 许琳娟等: "《非均匀沙床面颗粒运动试验研究》", 31 October 2018, pages: 40 * |
| 黄迎松;吴剑;: "心腔动态重建的迭代替换算法", 中国医学物理学杂志, no. 01 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115187594B (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hu et al. | Bidirectional mapping generative adversarial networks for brain MR to PET synthesis | |
| US11610313B2 (en) | Systems and methods for generating normative imaging data for medical image processing using deep learning | |
| Huang et al. | Cross-modality image synthesis via weakly coupled and geometry co-regularized joint dictionary learning | |
| Liu et al. | Multimodal MR image synthesis using gradient prior and adversarial learning | |
| CN110444277B (en) | Multi-mode brain MRI image bidirectional conversion method based on multi-generation and multi-confrontation | |
| CN110570483A (en) | scanning method, scanning device, computer equipment and storage medium | |
| CN111311705A (en) | High-adaptability medical image multi-plane reconstruction method and system based on webgl | |
| Jin et al. | Object recognition in medical images via anatomy-guided deep learning | |
| CN111462139A (en) | Medical image display method, medical image display device, computer equipment and readable storage medium | |
| Masoudi et al. | No-reference image quality assessment of T2-weighted magnetic resonance images in prostate cancer patients | |
| Liu et al. | Rigid model‐based 3D segmentation of the bones of joints in MR and CT images for motion analysis | |
| CN112200780B (en) | Bone tissue positioning method, device, computer equipment and storage medium | |
| CN113724185A (en) | Model processing method and device for image classification and storage medium | |
| Mangalagiri et al. | Toward generating synthetic CT volumes using a 3D-conditional generative adversarial network | |
| Corouge et al. | A statistical shape model of individual fiber tracts extracted from diffusion tensor MRI | |
| CN115187594A (en) | Cerebral cortex model reconstruction method and system | |
| CN112489048A (en) | Deep network-based automatic optic nerve segmentation method | |
| CN117152173A (en) | Coronary artery segmentation method and system based on DUNetR model | |
| Shang et al. | Short-axis pet image quality improvement by attention CycleGAN using total-body pet | |
| Qi et al. | Blind image quality assessment for MRI with a deep three-dimensional content-adaptive hyper-network | |
| Rao et al. | Deep learning-based medical image fusion using integrated joint slope analysis with probabilistic parametric steered image filter | |
| Fralenko et al. | Tools for automatically finding and visualizing interest areas in MRI data to support decision making by medical researchers | |
| US11295451B2 (en) | Robust pulmonary lobe segmentation | |
| Shi et al. | Atlas construction via dictionary learning and group sparsity | |
| Yu et al. | Cortical surface shape analysis based on spherical wavelet transformation |
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 |