CN111583189B - Brain nucleus positioning method, device, storage medium and computer equipment - Google Patents
Brain nucleus positioning method, device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN111583189B CN111583189B CN202010299950.4A CN202010299950A CN111583189B CN 111583189 B CN111583189 B CN 111583189B CN 202010299950 A CN202010299950 A CN 202010299950A CN 111583189 B CN111583189 B CN 111583189B
- Authority
- CN
- China
- Prior art keywords
- image
- brain image
- brain
- nucleus
- segmentation mask
- 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.)
- Active
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 250
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000007457 establishment of nucleus localization Effects 0.000 title description 7
- 230000011218 segmentation Effects 0.000 claims abstract description 75
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000009466 transformation Effects 0.000 claims description 64
- 230000001131 transforming effect Effects 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 23
- 230000002490 cerebral effect Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000030648 nucleus localization Effects 0.000 claims description 9
- 239000000758 substrate Substances 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 7
- 208000018737 Parkinson disease Diseases 0.000 description 6
- 210000001905 globus pallidus Anatomy 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 210000004281 subthalamic nucleus Anatomy 0.000 description 4
- 210000004227 basal ganglia Anatomy 0.000 description 3
- HGBLNBBNRORJKI-WCABBAIRSA-N cyclacillin Chemical compound N([C@H]1[C@H]2SC([C@@H](N2C1=O)C(O)=O)(C)C)C(=O)C1(N)CCCCC1 HGBLNBBNRORJKI-WCABBAIRSA-N 0.000 description 3
- 230000000638 stimulation Effects 0.000 description 3
- 238000001356 surgical procedure Methods 0.000 description 3
- 210000001175 cerebrospinal fluid Anatomy 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 210000004761 scalp Anatomy 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 101100269850 Caenorhabditis elegans mask-1 gene Proteins 0.000 description 1
- 208000014094 Dystonic disease Diseases 0.000 description 1
- 208000012902 Nervous system disease Diseases 0.000 description 1
- 208000025966 Neurological disease Diseases 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 208000010118 dystonia Diseases 0.000 description 1
- 206010015037 epilepsy Diseases 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004770 neurodegeneration Effects 0.000 description 1
- 208000015122 neurodegenerative disease Diseases 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000002945 steepest descent method Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 210000001103 thalamus Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T7/60—Analysis of geometric attributes
- G06T7/68—Analysis of geometric attributes of symmetry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras 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
- G06T2207/10088—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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The present application relates to a method, an apparatus, a storage medium and a computer device for locating a brain nucleus, and unlike the method in the prior art, which needs to rely on the experience of a doctor to locate, the present application is capable of improving the locating efficiency of a brain nucleus by processing a brain image by the computer device according to a template image including a nucleus segmentation mask to determine a nucleus in the brain image. In addition, the method and the device for locating the nuclear cluster in the brain image perform registration processing on the brain image and the template image, then determine the nuclear cluster in the brain image according to the nuclear cluster segmentation mask and the registration result, accurately locate the nuclear cluster in the brain image, and effectively improve the accuracy of the nuclear cluster locating result compared with a manual locating mode.
Description
Technical Field
The present disclosure relates to the field of medical imaging technologies, and in particular, to a method and apparatus for locating a cerebral nucleus, a storage medium, and a computer device.
Background
Parkinson's Disease (PD) is a common neurodegenerative Disease, and current treatment protocols are usually performed using deep brain electrical stimulation (Deep Brain Stimulation, DBS). Target nuclei commonly used for DBS treatment include subthalamic nucleus (Subthalamic Nucleus, STN) and globus pallidus medial nucleus (Globus Pallidus Internas, GPI), among others.
In the DBS diagnostic process, it is necessary to locate target nuclei, which are distributed in deep brain. In the prior art, the positioning is needed to be performed by depending on the experience of doctors, the positioning efficiency is low, and errors are easy to occur.
Disclosure of Invention
Based on this, it is necessary to provide a brain nucleus localization method, apparatus, storage medium and computer device that contribute to the improvement of localization efficiency and accuracy, in view of the problems existing in the prior art.
A method of brain nucleus localization comprising:
acquiring a first brain image and a template image comprising a first nucleus segmentation mask;
determining a first positioning feature in the first brain image, and transforming the first brain image to a target coordinate space based on the first positioning feature to obtain a second brain image, wherein the target coordinate space is a coordinate space in which the template image is located;
determining a second positioning feature in the second brain image, and registering the second brain image and the template image based on the first positioning feature and the second positioning feature to obtain a transformation relation between the second brain image and the template image;
and determining the nuclear cluster in the second brain image based on the first nuclear cluster segmentation mask and the transformation relation between the second brain image and the template image.
A cerebral nucleus localization device comprising:
the image acquisition module is used for acquiring a first brain image and a template image containing a first nucleus segmentation mask;
the first processing module is used for determining first positioning features in the first brain image, transforming the first brain image into a target coordinate space based on the first positioning features to obtain a second brain image, wherein the target coordinate space is a coordinate space in which the template image is located;
the second processing module is used for determining a second positioning feature in the second brain image, registering the second brain image and the template image based on the first positioning feature and the second positioning feature, and obtaining a transformation relation between the second brain image and the template image;
and the nucleus determining module is used for determining the nucleus in the second brain image based on the transformation relation among the first nucleus segmentation mask, the second brain image and the template image.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.
The method, the device, the storage medium and the computer equipment for positioning the brain nucleus are used for acquiring a first brain image and a template image comprising a first nucleus segmentation mask; determining a first positioning feature in the first brain image, and transforming the first brain image to a target coordinate space based on the first positioning feature to obtain a second brain image, wherein the target coordinate space is a coordinate space in which the template image is located; determining a second positioning feature in the second brain image, and registering the second brain image and the template image based on the first positioning feature and the second positioning feature to obtain a transformation relation between the second brain image and the template image; and determining the nuclear cluster in the second brain image based on the first nuclear cluster segmentation mask and the transformation relation between the second brain image and the template image.
The method is different from the method which needs to rely on doctors' experience to locate in the prior art, but processes the brain image according to the template image comprising the nucleus segmentation mask by the computer equipment to determine the nucleus in the brain image, and has higher locating efficiency, so the method can improve the locating efficiency of the brain nucleus. In addition, the method carries out registration processing on the brain image and the template image, then determines the nucleus in the brain image according to the nucleus segmentation mask and the registration result, can accurately position the nucleus in the brain image, and can effectively improve the accuracy of the nucleus positioning result compared with a manual positioning mode.
Drawings
FIG. 1 is a flow chart of a method for locating a brain nucleus in one embodiment;
FIG. 2 is a schematic diagram of a Talairach coordinate system and a portion of a second positioning feature in one embodiment;
FIG. 3 is a schematic diagram illustrating a positional relationship between a second positioning feature and a first positioning feature according to an embodiment;
FIG. 4 is a flow chart of transforming a first brain image to a target coordinate space based on a first positioning feature to obtain a second brain image in one embodiment;
FIG. 5 is a flowchart of registering a second brain image and a template image based on a first positioning feature and a second positioning feature to obtain a transformation relationship between the second brain image and the template image in one embodiment;
FIG. 6 is a schematic diagram of a sub-region division of a second brain image according to one embodiment;
FIG. 7 is a flowchart of registering a second brain image and a template image based on a first positioning feature and a second positioning feature to obtain a transformation relationship between the second brain image and the template image in another embodiment;
FIG. 8 is a flow chart of determining a bolus in a second brain image, according to one embodiment;
FIG. 9 is a schematic diagram of a brain nucleus localization apparatus according to one embodiment;
fig. 10 is an internal structural view of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The technical scheme of the application can be applied to deep brain electro-stimulation (Deep Brain Stimulation, DBS), and DBS is an effective means for treating neurological diseases such as Parkinson's Disease (PD), dystonia, depression, epilepsy and the like. Long-term medication can cause resistance to the patient, where DBS is required to replace medication. Whether DBS surgery is successful or not depends on whether the physician can accurately locate the location of the nucleus. The most common target nuclei for DBS surgery in PD patients include subthalamic nucleus (SubthalamicNucleus, STN) and globus pallidus medial nucleus (Globus Pallidus Internas, GPI), both of which can significantly improve the clinical symptoms in PD patients. Based on the problems of low efficiency and low accuracy of the existing target nucleus positioning method, the method aims at improving the positioning efficiency of the target nucleus and the accuracy of the positioning result, and further improving the success rate of DBS operation.
It is understood that the technical solution of the present application is not limited to be applied to DBS, but may be applied to other technologies/methods requiring cerebral occlusions localization.
In one embodiment, as shown in fig. 1, a method for locating a cerebral nucleus is provided, and the method is explained by taking an example that the method is applied to a processor capable of locating a cerebral nucleus, and the method mainly comprises the following steps:
step S100, a first brain image is acquired, and a template image including a first epipolar segmentation mask is acquired.
The first brain image acquired by the processor is a brain image of a subject in need of DBS surgery, and the first brain image may specifically be an MRI (Magnetic Resonance Imaging ) image. Specifically, the processor may obtain the first brain image by performing image reconstruction and correction on scan data acquired by the magnetic resonance scanning apparatus. Of course, the first brain image may be reconstructed and corrected in advance and stored in the memory of the computer device, and the processor directly reads the first brain image from the memory of the computer device when processing thereof is required. Of course, the processor may also acquire the first brain image from the external device. For example, a first brain image is stored in a cloud, and when a processing operation is required, a processor acquires the first brain image from the cloud. The method for acquiring the first brain image by the processor is not limited in this embodiment.
In order to accurately position the brain nucleus in the first brain image, the method of map registration is used for registering the first brain image and map data (namely a template image) to the greatest extent, and then the template image is transmitted to the first brain image through a first nucleus segmentation Mask (Mask 1) with the template image. The template image is an average map registered to the same space by a large amount of individual data so as to ensure the universality of the map. For example, the template image selected by the application is derived from 7.0T magnetic resonance scanning data of brains of 168 adults, and the 7.0T magnetic resonance scanning data is provided with a base nucleus group structure with a clear boundary, which comprises a target nucleus group thalamus nucleus common to DBS operation, a globus pallidus nucleus and the like, so that a first nucleus group segmentation mask in the template image can be accurately determined.
Step S200, determining first positioning features in the first brain image, and transforming the first brain image to a target coordinate space based on the first positioning features to obtain a second brain image, wherein the target coordinate space is a coordinate space in which the template image is located.
After the processor acquires the first brain image and the template image, the processor firstly performs space coordinate transformation of the image, so that the subsequent image registration is facilitated. In this step, the processor performs a transformation of the coordinate space of the first brain image based on the first positioning feature in the first brain image, and obtains a second brain image that is consistent with the coordinate space of the template image. The target coordinate space may specifically be, for example, a talapiach coordinate space or the like.
Optionally, the first positioning features include a front join point (Anterior Commissure, AC), a rear join point (Posterior Commissure, PC), and a mid-sagittal plane (Midsagittal Plane, MSP). Wherein MSP represents the mid-sagittal plane of the brain, which passes through the sulcus of the brain to bisect the brain into left and right hemispheres.
Specifically, the determination of the first positioning features AC, PC and MSP may be done by manual selection. Firstly, determining two anatomical landmark points, namely an AC (alternating current) and a PC (personal computer) based on a first brain image, and then determining any point (IH) on any MSP which is not collinear with an AC-PC connecting line, so that the position of the MSP can be determined. In addition, in order to realize full automation of the whole flow, the positioning of the AC, the PC and the MSP can be automatically completed through an algorithm. Specifically, MSP is used as the left and right bisection central axis surface of the brain hemisphere, the symmetry surface of the left and right hemispheres can be solved iteratively by a steepest descent method through a method for maximizing mutual information of the left and right hemispheres, and the MSP is obtained through solving. The AC and the PC are on the mid-sagittal plane, and have obvious anatomical features, and the positions of the AC and the PC can be determined by template matching on the mid-sagittal plane.
It can be understood that the determination of AC, PC and MSP may also be performed automatically by an algorithm, and then combined with manual confirmation and adjustment, so that the accuracy can be ensured while simplifying the process flow and improving the efficiency.
Step S300, determining a second positioning feature in the second brain image, and registering the second brain image and the template image based on the first positioning feature and the second positioning feature to obtain a transformation relationship between the second brain image and the template image.
The processor transforms the first brain image to a target coordinate space based on the first positioning feature, and then performs registration of the second brain image and the template image based on the second positioning feature of the second brain image in combination with the first positioning feature after obtaining the second brain image.
Optionally, the second positioning features include a front endpoint (AP), a rear endpoint (PP), a left endpoint (LP), a right endpoint (RP), an upper endpoint (SP), and a lower endpoint (IP) of the brain. The second positioning features AP, PP, LP, RP, SP, IP represent the most anterior, most posterior, most left, most right, most uppermost, and most lowermost points of the brain (without scalp and cerebrospinal fluid), respectively, in Talairach coordinate space.
Referring to fig. 2, the Talairach coordinate system uses AC as an origin, the direction from PC to AC is a Y-axis direction, an X-axis is perpendicular to the MSP, and a Z-axis direction is determined according to the X-axis and the Y-axis.
As shown in fig. 3, which is a schematic diagram of the positional relationship between the second positioning feature and the first positioning feature, referring to fig. 3, the sp is directly above the PC, and the IP is directly below the AC; LP and RP are on the left and right sides of the PC.
Specifically, the determination of the second locating feature AP, PP, LP, RP, SP, IP can be accomplished by manual selection. In addition, in order to realize full automation of the whole flow, the positioning of AP, PP, LP, RP, SP, IP can be automatically finished through an algorithm. Specifically, the automatic positioning algorithm is realized according to the following steps: (1) Removing scalp and cerebrospinal fluid through a cortex segmentation algorithm to obtain a brain contour; (2) The forward intersection point and the backward intersection point of the AC-PC connecting line and the brain outline respectively determine AP and PP; (3) Determining SP by the intersection point of the ascending line of the axial plane vertical line passing through the PC point and the outline of the brain; (4) determining IP by a downline of the axial plane perpendicular line passing through the AC point; (5) The perpendicular to the mid-sagittal plane passing through the PC point and the left and right intersection points of the brain contour determine LP and RP, respectively.
It can be understood that the determination of AP, PP, LP, RP, SP, IP can also be automatically completed by an algorithm, and then the manual confirmation and adjustment are combined, so that the accuracy can be ensured while the processing flow is simplified and the efficiency is improved.
Step S400, determining the nucleus in the second brain image based on the transformation relation of the first nucleus segmentation mask, the second brain image and the template image.
The processor registers the second brain image and the template image based on the first positioning feature and the second positioning feature, and after obtaining the transformation relation between the second brain image and the template image, the processor can determine the nucleus in the second brain image based on the first nucleus segmentation mask contained in the template image and the transformation relation. Specifically, the first nucleus segmentation mask included in the template image may be transformed based on the transformation relationship to obtain a transformed segmentation mask, and the transformed segmentation mask may represent the nucleus position in the second brain image, so that the nucleus in the second brain image may be determined based on the transformed segmentation mask.
The present embodiment proposes a method for locating a cerebral nucleus, which is different from the method in the prior art that needs to rely on the experience of a doctor to locate, but processes a cerebral image according to a template image including a nucleus segmentation mask by using a computer device to determine a nucleus in the cerebral image, and has high locating efficiency, so that the method can improve the locating efficiency of the cerebral nucleus. In addition, the method carries out registration processing on the brain image and the template image, then determines the nucleus in the brain image according to the nucleus segmentation mask and the registration result, can accurately position the nucleus in the brain image, and can effectively improve the accuracy of the nucleus positioning result compared with a manual positioning mode.
In one embodiment, as shown in fig. 4, in step S200, the first brain image is transformed into the target coordinate space based on the first positioning feature to obtain the second brain image, including steps S220 to S240.
Step S220, determining a transformation matrix of a current coordinate space and a target coordinate space according to the first positioning feature, wherein the current coordinate space is the coordinate space in which the first brain image is located;
step S240, transforming the first brain image according to the transformation matrix to obtain a second brain image.
Specifically, based on the first positioning feature, the transformation matrix of the current coordinate space where the first brain image is located and the target coordinate space where the template image is located can be obtained, and then the transformation matrix is based on the transformation matrix to transform the first brain image located in the current coordinate space, so that the second brain image located in the target coordinate space can be obtained. Therefore, the subsequent registration processing of the images can be facilitated by carrying out the transformation of the coordinate space, and the accuracy of the locating result of the nuclear cluster is further improved.
In one embodiment, as shown in fig. 5, in step S300, the second brain image and the template image are registered based on the first positioning feature and the second positioning feature to obtain a transformation relationship between the second brain image and the template image, which includes steps S320 to S340.
Step S320, dividing the second brain image into at least two sub-areas based on the first positioning feature and the second positioning feature;
step S340, scaling and transforming each corresponding region of each subarea in the template image to obtain each transformed corresponding region with the same size as each subarea; the transformation relation between the second brain image and the template image comprises the scaling of each corresponding region.
Fig. 6 is a schematic diagram of the division of the second brain image into sub-regions. Specifically, based on the first positioning feature AC, PC, MSP, and the second positioning feature AP, PP, LP, RP, SP, IP, the second brain image can be divided into 12 sub-regions, i.e., 6 regions each of the left and right brain halves.
In order to achieve the greatest degree of linear alignment of the second brain image and the template image, the present embodiment divides the template image and the second brain image into 12 sub-areas simultaneously. And then obtaining the lengths of the AP-AC, AC-PC, PC-PP, SP-PC, IP-AC, RP-PC and LP-PC line segments in the template image and the second brain image based on the second positioning features AP, PP, LP, RP, SP, IP in the template image and the second brain image respectively. And finally, scaling each subarea in the template image according to the length of each line segment in the two images so that the corresponding subareas in the two images have the same size, thereby realizing piecewise linear alignment of the second brain image and the template image. The second brain image and the template image after piecewise linear alignment are realized, and accurate registration can be obtained at each part of the brain, including target nuclei concerned by DBS operation.
In one embodiment, as shown in fig. 7, in step S300, the registration of the second brain image and the template image based on the first positioning feature and the second positioning feature, to obtain the transformation relationship between the second brain image and the template image, further includes steps S360 to S380.
Step S360, respectively extracting a first target area in the subarea and a second target area in the transformed corresponding area, wherein the first target area and the second target area are image areas containing the same substrate nucleus;
step S380, elastic registration based on gray information is carried out on the first target area and the second target area, and the registration deformation relation between the first target area and the second target area is determined; the transformation relationship between the second brain image and the template image further comprises a registration deformation relationship between the first target area and the second target area.
The piecewise linear alignment can realize the alignment of target nucleus positions on the second brain image and the template image, but because different individual nucleus morphologies still have certain differences, the matching degree of the second brain image and the template image can be further improved through elastic registration. Since the DBS operation is concerned only with the basal ganglia, the elastic registration can be performed only in a local area containing the basal ganglia, and thus the amount of computation can be greatly reduced.
Specifically, for the second brain image, and the scaled template image, the registration deformation relationship of the image areas containing the same basal ganglia in the two images may be calculated. The elastic registration based on gray information can be specifically obtained by calculating mutual information of two images as a similarity measurement index to optimize and obtain a registration deformation field, namely obtaining a registration deformation relation between the second brain image and the scaled template image. According to the embodiment, on the basis of piecewise linear alignment, the accuracy of the registration result of the second brain image and the template image can be further improved by performing elastic registration of part of the subregions.
In one embodiment, step S400, determining a nucleus in the second brain image based on the transformation relationship between the first nucleus segmentation mask, the second brain image and the template image, specifically includes: and determining the epipolar in the second brain image based on the scaling of each corresponding region and the first epipolar segmentation mask, or based on the scaling of each corresponding region, the registration deformation relationship of the first target region and the second target region, and the first epipolar segmentation mask.
Optionally, as shown in fig. 8, determining the epipolar in the second brain image based on the scaling of each corresponding region and the first epipolar segmentation mask, or based on the scaling of each corresponding region, the registration deformation relationship of the first target region and the second target region, and the first epipolar segmentation mask includes steps S420 to S440.
Step S420, transforming the first nucleus segmentation mask based on the scaling or based on the scaling and the registration deformation relationship to obtain a second nucleus segmentation mask;
in step S440, the second brain image is segmented through the second nucleus segmentation mask, so as to obtain a nucleus in the second brain image.
Specifically, in the process of registering the second brain image and the template image, if only piecewise linear alignment is performed, transforming the first nucleus segmentation mask based on the scaling ratio to obtain a second nucleus segmentation mask; if piecewise linear alignment and elastic registration of partial subregions are performed simultaneously, the first nucleus segmentation Mask is transformed based on the scaling and the registration deformation relationship to obtain a second nucleus segmentation Mask (Mask 2), so that a nucleus in the second brain image can be obtained based on the second nucleus segmentation Mask. Optionally, the second kernel segmentation mask may be further subjected to open operation to smooth the boundary.
It should be understood that, under reasonable conditions, although the steps in the flowcharts referred to in the foregoing embodiments are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, and the order of execution of the sub-steps or stages is not necessarily sequential, but may be performed in rotation or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
In one embodiment, as shown in fig. 9, there is provided a cerebral nucleus localization apparatus, which mainly includes the following modules:
an image acquisition module 100, configured to acquire a first brain image and a template image including a first nucleus segmentation mask;
the first processing module 200 is configured to determine a first positioning feature in the first brain image, transform the first brain image to a target coordinate space based on the first positioning feature, and obtain a second brain image, where the target coordinate space is a coordinate space in which the template image is located;
the second processing module 300 is configured to determine a second positioning feature in the second brain image, register the second brain image and the template image based on the first positioning feature and the second positioning feature, and obtain a transformation relationship between the second brain image and the template image;
the nucleus determining module 400 is configured to determine a nucleus in the second brain image based on the transformation relationship between the first nucleus segmentation mask, the second brain image and the template image.
The utility model provides a brain nucleus positioning device, the device is handled the brain image according to the template image that contains the nucleus segmentation mask through computer unit in order to confirm the nucleus in the brain image, and its location efficiency is higher, therefore, the device can improve the location efficiency of brain nucleus. In addition, the device carries out registration processing on the brain image and the template image, then determines the nucleus in the brain image according to the nucleus segmentation mask and the registration result, can accurately position the nucleus in the brain image, and can effectively improve the accuracy of the nucleus positioning result compared with a manual positioning mode.
In one embodiment, the first processing module 200 is further configured to: determining a transformation matrix of a current coordinate space and a target coordinate space according to the first positioning features, wherein the current coordinate space is a coordinate space in which the first brain image is located; and transforming the first brain image according to the transformation matrix to obtain a second brain image.
In one embodiment, the second processing module 300 is further configured to: dividing the second brain image into at least two sub-regions based on the first positioning feature and the second positioning feature; scaling transformation is carried out on each corresponding region of each subarea in the template image respectively, and each transformed corresponding region with the same size as each subarea is obtained; the transformation relation between the second brain image and the template image comprises the scaling of each corresponding region.
In one embodiment, the second processing module 300 is further configured to: respectively extracting a first target area in the subarea and a second target area in the corresponding area after transformation, wherein the first target area and the second target area are image areas containing the same substrate nucleus; elastic registration based on gray information is carried out on the first target area and the second target area, and the registration deformation relation between the first target area and the second target area is determined; the transformation relationship between the second brain image and the template image further comprises a registration deformation relationship between the first target area and the second target area.
In one embodiment, the clique determination module 400 is further to: and determining the epipolar in the second brain image based on the scaling of each corresponding region and the first epipolar segmentation mask, or based on the scaling of each corresponding region, the registration deformation relationship of the first target region and the second target region, and the first epipolar segmentation mask.
In one embodiment, the clique determination module 400 is further to: based on the scaling or based on the scaling and the registration deformation relationship, transforming the first kernel segmentation mask to obtain a second kernel segmentation mask; and segmenting the second brain image through a second nucleus segmentation mask to obtain a nucleus in the second brain image.
Specific limitations regarding the cerebral nucleus localization apparatus may be found in the above definitions of cerebral nucleus localization methods, and are not described in detail herein. The above-described modules in the cerebral nucleus localization apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of: acquiring a first brain image and a template image comprising a first nucleus segmentation mask; determining first positioning features in the first brain image, and transforming the first brain image to a target coordinate space based on the first positioning features to obtain a second brain image, wherein the target coordinate space is a coordinate space in which the template image is located; determining a second positioning feature in the second brain image, and registering the second brain image and the template image based on the first positioning feature and the second positioning feature to obtain a transformation relation between the second brain image and the template image; and determining the nuclear cluster in the second brain image based on the first nuclear cluster segmentation mask and the transformation relation between the second brain image and the template image.
In one embodiment, the processor when executing the computer program further performs the steps of: determining a transformation matrix of a current coordinate space and a target coordinate space according to the first positioning features, wherein the current coordinate space is a coordinate space in which the first brain image is located; and transforming the first brain image according to the transformation matrix to obtain a second brain image.
In one embodiment, the processor when executing the computer program further performs the steps of: dividing the second brain image into at least two sub-regions based on the first positioning feature and the second positioning feature; scaling transformation is carried out on each corresponding region of each subarea in the template image respectively, and each transformed corresponding region with the same size as each subarea is obtained; the transformation relation between the second brain image and the template image comprises the scaling of each corresponding region.
In one embodiment, the processor when executing the computer program further performs the steps of: respectively extracting a first target area in the subarea and a second target area in the corresponding area after transformation, wherein the first target area and the second target area are image areas containing the same substrate nucleus; elastic registration based on gray information is carried out on the first target area and the second target area, and the registration deformation relation between the first target area and the second target area is determined; the transformation relationship between the second brain image and the template image further comprises a registration deformation relationship between the first target area and the second target area.
In one embodiment, the processor when executing the computer program further performs the steps of: and determining the epipolar in the second brain image based on the scaling of each corresponding region and the first epipolar segmentation mask, or based on the scaling of each corresponding region, the registration deformation relationship of the first target region and the second target region, and the first epipolar segmentation mask.
In one embodiment, the processor when executing the computer program further performs the steps of: based on the scaling or based on the scaling and the registration deformation relationship, transforming the first kernel segmentation mask to obtain a second kernel segmentation mask; and segmenting the second brain image through a second nucleus segmentation mask to obtain a nucleus in the second brain image.
Fig. 10 is an internal structural view of a computer device in one embodiment. The computer device may in particular be a terminal (or a server). As shown in fig. 10, the computer device includes a processor, a memory, a network interface, an input device, and a display screen connected by a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and may also store a computer program that, when executed by a processor, causes the processor to implement a method for locating a brain nucleus. The internal memory may also store a computer program which, when executed by the processor, causes the processor to perform a method of locating a cerebral nucleus. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring a first brain image and a template image comprising a first nucleus segmentation mask; determining first positioning features in the first brain image, and transforming the first brain image to a target coordinate space based on the first positioning features to obtain a second brain image, wherein the target coordinate space is a coordinate space in which the template image is located; determining a second positioning feature in the second brain image, and registering the second brain image and the template image based on the first positioning feature and the second positioning feature to obtain a transformation relation between the second brain image and the template image; and determining the nuclear cluster in the second brain image based on the first nuclear cluster segmentation mask and the transformation relation between the second brain image and the template image.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining a transformation matrix of a current coordinate space and a target coordinate space according to the first positioning features, wherein the current coordinate space is a coordinate space in which the first brain image is located; and transforming the first brain image according to the transformation matrix to obtain a second brain image.
In one embodiment, the computer program when executed by the processor further performs the steps of: dividing the second brain image into at least two sub-regions based on the first positioning feature and the second positioning feature; scaling transformation is carried out on each corresponding region of each subarea in the template image respectively, and each transformed corresponding region with the same size as each subarea is obtained; the transformation relation between the second brain image and the template image comprises the scaling of each corresponding region.
In one embodiment, the computer program when executed by the processor further performs the steps of: respectively extracting a first target area in the subarea and a second target area in the corresponding area after transformation, wherein the first target area and the second target area are image areas containing the same substrate nucleus; elastic registration based on gray information is carried out on the first target area and the second target area, and the registration deformation relation between the first target area and the second target area is determined; the transformation relationship between the second brain image and the template image further comprises a registration deformation relationship between the first target area and the second target area.
In one embodiment, the computer program when executed by the processor further performs the steps of: and determining the epipolar in the second brain image based on the scaling of each corresponding region and the first epipolar segmentation mask, or based on the scaling of each corresponding region, the registration deformation relationship of the first target region and the second target region, and the first epipolar segmentation mask.
In one embodiment, the computer program when executed by the processor further performs the steps of: based on the scaling or based on the scaling and the registration deformation relationship, transforming the first kernel segmentation mask to obtain a second kernel segmentation mask; and segmenting the second brain image through a second nucleus segmentation mask to obtain a nucleus in the second brain image.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program, which may be stored on a non-transitory computer readable storage medium and which, when executed, may comprise the steps of the above-described embodiments of the methods. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. A method of locating a brain nucleus, comprising:
acquiring a first brain image and a template image comprising a first nucleus segmentation mask;
determining a first positioning feature in the first brain image, and transforming the first brain image to a target coordinate space based on the first positioning feature to obtain a second brain image, wherein the target coordinate space is a coordinate space in which the template image is located;
determining a second positioning feature in the second brain image, and registering the second brain image and the template image based on the first positioning feature and the second positioning feature to obtain a transformation relation between the second brain image and the template image;
and transforming the first nucleus segmentation mask in the template image based on the transformation relation between the second brain image and the template image to obtain a second nucleus segmentation mask, and determining the nucleus in the second brain image according to the second nucleus segmentation mask.
2. The method of claim 1, wherein transforming the first brain image to a target coordinate space based on the first positioning feature results in a second brain image, comprising:
determining a transformation matrix of a current coordinate space and the target coordinate space according to the first positioning features, wherein the current coordinate space is a coordinate space in which the first brain image is located;
and transforming the first brain image according to the transformation matrix to obtain the second brain image.
3. The method of claim 1, wherein registering the second brain image and the template image based on the first positioning feature and the second positioning feature, the obtaining a transformation relationship of the second brain image and the template image comprises:
dividing the second brain image into at least two sub-regions based on the first positioning feature and the second positioning feature;
scaling transformation is carried out on each corresponding region of each subarea in the template image respectively, so as to obtain each transformed corresponding region with the same size as each subarea;
the transformation relation between the second brain image and the template image comprises the scaling of each corresponding region.
4. The method of claim 3, wherein registering the second brain image and the template image based on the first positioning feature and the second positioning feature, the obtaining a transformation relationship of the second brain image and the template image further comprises:
respectively extracting a first target area in the subarea and a second target area in the transformed corresponding area, wherein the first target area and the second target area are image areas containing the same substrate nucleus;
elastic registration based on gray information is carried out on the first target area and the second target area, and the registration deformation relation between the first target area and the second target area is determined;
the transformation relationship between the second brain image and the template image further comprises a registration deformation relationship between the first target area and the second target area.
5. The method of claim 4, wherein transforming the first epipolar segmentation mask in the template image based on the transformation relationship of the second brain image to the template image results in a second epipolar segmentation mask, comprising:
under the condition that the transformation relation between the second brain image and the template image comprises the scaling of each corresponding region, transforming the first nucleus segmentation mask based on the scaling of each corresponding region to obtain a second nucleus segmentation mask;
or,
the transformation relation between the second brain image and the template image comprises: and under the conditions of the scaling of each corresponding region and the registration deformation relation between the first target region and the second target region, transforming the first nucleus segmentation mask based on the scaling of each corresponding region and the registration deformation relation between the first target region and the second target region to obtain a second nucleus segmentation mask.
6. The method of claim 1, wherein determining a bolus in the second brain image from the second bolus segmentation mask comprises:
and dividing the second brain image through the second nucleus segmentation mask to obtain a nucleus in the second brain image.
7. The method of any of claims 1-6, wherein the first positioning feature comprises a front junction, a rear junction, and a mid-sagittal plane;
the second positioning feature includes a front end point, a rear end point, a left end point, a right end point, an upper end point, and a lower end point of the brain.
8. A cerebral nucleus localization device, comprising:
the image acquisition module is used for acquiring a first brain image and a template image containing a first nucleus segmentation mask;
the first processing module is used for determining first positioning features in the first brain image, transforming the first brain image into a target coordinate space based on the first positioning features to obtain a second brain image, wherein the target coordinate space is a coordinate space in which the template image is located;
the second processing module is used for determining a second positioning feature in the second brain image, registering the second brain image and the template image based on the first positioning feature and the second positioning feature, and obtaining a transformation relation between the second brain image and the template image;
the nucleus determining module is used for transforming the first nucleus segmentation mask in the template image based on the transformation relation between the second brain image and the template image to obtain a second nucleus segmentation mask, and determining the nucleus in the second brain image according to the second nucleus segmentation mask.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010299950.4A CN111583189B (en) | 2020-04-16 | 2020-04-16 | Brain nucleus positioning method, device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010299950.4A CN111583189B (en) | 2020-04-16 | 2020-04-16 | Brain nucleus positioning method, device, storage medium and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111583189A CN111583189A (en) | 2020-08-25 |
| CN111583189B true CN111583189B (en) | 2024-02-27 |
Family
ID=72124477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010299950.4A Active CN111583189B (en) | 2020-04-16 | 2020-04-16 | Brain nucleus positioning method, device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111583189B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112950600B (en) * | 2021-03-10 | 2024-06-28 | 武汉联影智融医疗科技有限公司 | Brain identification extraction method, device, computer equipment and storage medium |
| CN114066827A (en) * | 2021-11-02 | 2022-02-18 | 武汉联影智融医疗科技有限公司 | Method and device for determining nuclear group area, computer equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1005832A2 (en) * | 1998-11-23 | 2000-06-07 | Lunar Corporation | Apparatus for bilateral femur measurement |
| JP2004174217A (en) * | 2002-10-01 | 2004-06-24 | Japan Science & Technology Corp | Image processing apparatus, image processing method, and recording medium which stores program according to which computer perform pertinent image processing |
| CN102028546A (en) * | 2010-12-24 | 2011-04-27 | 燕山大学 | Carp electrode transforation implantation brain stereotaxic method |
| WO2012016242A2 (en) * | 2010-07-30 | 2012-02-02 | Aureon Biosciences, Inc. | Systems and methods for segmentation and processing of tissue images and feature extraction from same for treating, diagnosing, or predicting medical conditions |
| CN106898000A (en) * | 2017-02-15 | 2017-06-27 | 华东师范大学 | A kind of automatic division method of magnetic resonance imaging cerebral gray matter core group |
| CN108765483A (en) * | 2018-06-04 | 2018-11-06 | 东北大学 | The method and system of sagittal plane in being determined in a kind of CT images from brain |
-
2020
- 2020-04-16 CN CN202010299950.4A patent/CN111583189B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1005832A2 (en) * | 1998-11-23 | 2000-06-07 | Lunar Corporation | Apparatus for bilateral femur measurement |
| JP2004174217A (en) * | 2002-10-01 | 2004-06-24 | Japan Science & Technology Corp | Image processing apparatus, image processing method, and recording medium which stores program according to which computer perform pertinent image processing |
| WO2012016242A2 (en) * | 2010-07-30 | 2012-02-02 | Aureon Biosciences, Inc. | Systems and methods for segmentation and processing of tissue images and feature extraction from same for treating, diagnosing, or predicting medical conditions |
| CN102028546A (en) * | 2010-12-24 | 2011-04-27 | 燕山大学 | Carp electrode transforation implantation brain stereotaxic method |
| CN106898000A (en) * | 2017-02-15 | 2017-06-27 | 华东师范大学 | A kind of automatic division method of magnetic resonance imaging cerebral gray matter core group |
| CN108765483A (en) * | 2018-06-04 | 2018-11-06 | 东北大学 | The method and system of sagittal plane in being determined in a kind of CT images from brain |
Non-Patent Citations (3)
| Title |
|---|
| Sang Seok Yeo 等.《Anatomical Location of the Pedunculopontine Nucleus in the Human Brain: Diffusion Tensor Imaging Study》.《ResearchGate》.2011,第1-6页. * |
| 张阔野 等.《人脑神经核团空间定位研究》.《吉林医药学院学报》.2008,第29卷(第3期),第 157-159页. * |
| 荣晶晶.《人脑基底神经节区数字化组织学图谱构建》.《知网硕士论文库》.2013,第2部分. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111583189A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Horn et al. | Lead-DBS: a toolbox for deep brain stimulation electrode localizations and visualizations | |
| Toga et al. | Maps of the brain | |
| Rorden et al. | Stereotaxic display of brain lesions | |
| US10537277B2 (en) | Methods, systems, and computer readable media for visualization of resection target during epilepsy surgery and for real time spatiotemporal visualization of neurophysiologic biomarkers | |
| Ardekani et al. | Model-based automatic detection of the anterior and posterior commissures on MRI scans | |
| Xiao et al. | Multi-contrast unbiased MRI atlas of a Parkinson’s disease population | |
| CN110234394A (en) | Treating patients with TTFields with electrode positions optimized with deformable templates | |
| WO2023280002A1 (en) | Target determination method and apparatus, electronic device, storage medium, and neuro regulation device | |
| US20050165294A1 (en) | Automated brain MRI and CT prescriptions in Talairach space | |
| US20120033865A1 (en) | Quantification of medical image data | |
| CN111583189B (en) | Brain nucleus positioning method, device, storage medium and computer equipment | |
| Rodriguez-Rojas et al. | Functional impact of subthalamotomy by magnetic resonance–guided focused ultrasound in Parkinson’s disease: a hybrid PET/MR study of resting-state brain metabolism | |
| WO2023280003A1 (en) | Target determination method and apparatus, electronic device, storage medium and neuromodulation device | |
| CN114359277B (en) | Brain image processing method and system for stroke patients | |
| Kuijf et al. | Registration of brain CT images to an MRI template for the purpose of lesion-symptom mapping | |
| Erickson et al. | Correlation of single photon emission CT with MR image data using fiduciary markers. | |
| US11315263B2 (en) | Medical image processing apparatus, medical image processing method, and medical image processing program | |
| JP6788113B2 (en) | Medical image processing equipment, methods and programs | |
| Sammartino et al. | Diffusion tensor imaging of the basal ganglia for functional neurosurgery applications | |
| Nadian et al. | A novel methodology for exact targeting of human and non-human primate brain structures and skull implants using atlas-based 3D reconstruction | |
| Zeng et al. | Automated identification of the retinogeniculate visual pathway using a high-dimensional tractography atlas | |
| CN110874614A (en) | Brain image classification method, computer device and readable storage medium | |
| CN112465900A (en) | Stereo electroencephalogram electrode positioning method | |
| Ting et al. | Pre-alignment for Co-registration in Native Space | |
| Liu et al. | Multi-modal learning-based pre-operative targeting in deep brain stimulation procedures |
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 |