CN110232708B - Method, device, medium and terminal equipment for quantitatively calculating hippocampal sclerosis degree - Google Patents
Method, device, medium and terminal equipment for quantitatively calculating hippocampal sclerosis degree Download PDFInfo
- Publication number
- CN110232708B CN110232708B CN201910398096.4A CN201910398096A CN110232708B CN 110232708 B CN110232708 B CN 110232708B CN 201910398096 A CN201910398096 A CN 201910398096A CN 110232708 B CN110232708 B CN 110232708B
- Authority
- CN
- China
- Prior art keywords
- brain
- hippocampus
- magnetic resonance
- resonance image
- analyzed
- 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
- 206010063629 Hippocampal sclerosis Diseases 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 47
- 210000004556 brain Anatomy 0.000 claims abstract description 134
- 210000001320 hippocampus Anatomy 0.000 claims abstract description 120
- 230000000971 hippocampal effect Effects 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000003860 storage Methods 0.000 claims abstract description 11
- 238000010606 normalization Methods 0.000 claims abstract description 9
- 230000011218 segmentation Effects 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 26
- 230000009466 transformation Effects 0.000 claims description 26
- 238000013507 mapping Methods 0.000 claims description 22
- 238000007500 overflow downdraw method Methods 0.000 claims description 12
- 210000005013 brain tissue Anatomy 0.000 claims description 10
- 210000004884 grey matter Anatomy 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 6
- 238000011002 quantification Methods 0.000 abstract description 6
- 101000831205 Danio rerio Dynein axonemal assembly factor 11 Proteins 0.000 abstract description 2
- 102100024282 Dynein axonemal assembly factor 11 Human genes 0.000 abstract description 2
- 241001559542 Hippocampus hippocampus Species 0.000 abstract description 2
- 101000831210 Homo sapiens Dynein axonemal assembly factor 11 Proteins 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 206010003694 Atrophy Diseases 0.000 description 3
- 230000037444 atrophy Effects 0.000 description 3
- 230000002146 bilateral effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000004770 neurodegeneration Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 238000001356 surgical procedure Methods 0.000 description 2
- 201000008914 temporal lobe epilepsy Diseases 0.000 description 2
- 241001478425 Hippocampus japonicus Species 0.000 description 1
- 208000034189 Sclerosis Diseases 0.000 description 1
- 210000004727 amygdala Anatomy 0.000 description 1
- 210000001130 astrocyte Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 206010015037 epilepsy Diseases 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 210000003478 temporal lobe Anatomy 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G06T5/92—
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
Abstract
The invention belongs to the technical field of image processing, and particularly relates to a method and a device for quantitatively calculating the hardening degree of a sea horse, a computer-readable storage medium and terminal equipment. The method acquires a T1W magnetic resonance image of a brain to be analyzed, and calculates the relative volume of a hippocampus in the brain to be analyzed according to the T1W magnetic resonance image; acquiring a T2-FLAIR magnetic resonance image of the brain to be analyzed, and calculating a first signal mean value according to the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image, wherein the first signal mean value is the signal mean value of the hippocampal region in the T2-FLAIR magnetic resonance image; carrying out normalization processing on the first signal mean value to obtain a signal magnitude value of the hippocampus; calculating the hippocampal sclerosis degree of the brain to be analyzed according to the relative volume of the hippocampus and the signal magnitude of the hippocampus. The method has the advantages of simplicity, convenience, rapidness, high quantification degree, accuracy in judgment and the like, and provides an objective quantification method for evaluating the degree of the hippocampus sclerosis.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a method and a device for quantitatively calculating the hardening degree of a sea horse, a computer-readable storage medium and terminal equipment.
Background
Hippocampal Sclerosis (HS), also known as Medial Temporal Sclerosis (MTS), may be a causal entity of epilepsy. The gross pathology is characterized by small hippocampus volume, atrophy and hardening, which often involve both sulci, amygdala and juxtapose. Histologically, selective neuronal loss and astroglia. Hippocampal sclerosis is the most common pathological type of refractory temporal lobe epilepsy, and most patients can achieve good curative effect by cutting off the anterior temporal lobe of the hippocampus. The correct assessment of the lesion prior to surgery is an essential condition for the surgery to achieve the intended purpose. Currently, research is constantly being directed to improving the evaluation of hippocampal sclerosis based on imaging.
The most common manifestation of hippocampal sclerosis is hippocampal atrophy, which is now demonstrated to reflect the number of neurons by the volume of hippocampal structures, and thus neuronal loss on Magnetic Resonance Imaging (MRI). Secondly, on the T2-FLAIR magnetic resonance image, hippocampal sclerosis was manifested as an increase in hippocampal structural signals. Hippocampal atrophy and signal enhancement, although manifested separately, occur in most cases simultaneously. Although the imaging characteristics are well-documented, the judgment of the degree of hippocampal sclerosis is currently carried out subjectively by the skilled person based on personal experience. To date, there is no objective quantitative method to assess the degree of hippocampal sclerosis.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for quantitatively calculating a degree of hardening of a hippocampus, a computer-readable storage medium, and a terminal device, so as to solve the problem in the prior art that an objective quantitative method is not available for evaluating the degree of hardening of the hippocampus.
A first aspect of an embodiment of the present invention provides a method for quantitatively calculating a hippocampal sclerosis degree, which may include:
acquiring a T1W magnetic resonance image of a brain to be analyzed, and calculating the relative volume of a hippocampus in the brain to be analyzed according to the T1W magnetic resonance image;
acquiring a T2-FLAIR magnetic resonance image of the brain to be analyzed, and calculating a first signal mean value according to the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image, wherein the first signal mean value is the signal mean value of the hippocampal region in the T2-FLAIR magnetic resonance image;
carrying out normalization processing on the first signal mean value to obtain a signal magnitude value of the hippocampus;
calculating the hippocampal sclerosis degree of the brain to be analyzed according to the relative volume of the hippocampus and the signal magnitude of the hippocampus.
Further, said calculating a hippocampal sclerosis level of said brain to be analyzed from a relative volume of said hippocampus and a signal magnitude of said hippocampus comprises:
calculating the degree of hippocampal sclerosis of the brain to be analyzed according to the following formula:
wherein x is the relative volume of the hippocampus, y is the signal magnitude of the hippocampus, a, b and p are preset weight parameters, c and q are preset constant parameters, m is the preset number of grades of hippocampal sclerosis degree, and HSI is the quantitative value of hippocampal sclerosis degree of the brain to be analyzed.
Further, said calculating a relative volume of a hippocampus in the brain to be analyzed from the T1W magnetic resonance image comprises:
taking T1W magnetic resonance images of brains with different brain structures in batches as a brain template library, and segmenting to obtain hippocampal regions on each template;
mapping a template in the brain template library to a T1W magnetic resonance image of the brain to be analyzed by utilizing nonlinear registration to obtain a spatial transformation relation between the template and the brain to be analyzed, and mapping a hippocampal region on the template to the brain to be analyzed by utilizing the spatial transformation relation;
fusing to obtain a segmentation result of the hippocampus of the brain to be analyzed by using a label fusion method;
and calculating the volume of the hippocampus and the volume of the brain to be analyzed according to the segmentation result of the hippocampus, and taking the ratio of the volume of the hippocampus to the volume of the brain to be analyzed as the relative volume of the hippocampus.
Further, said computing a first signal mean from said T1W magnetic resonance image and said T2-FLAIR magnetic resonance image comprises:
obtaining a linear spatial transformation relationship between the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image by linear registration between the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image;
mapping the segmentation result of the hippocampus on the T1W magnetic resonance image onto the T2-FLAIR magnetic resonance image by using the linear spatial transformation relation;
the mean signal value of the hippocampus on the T2-FLAIR magnetic resonance image was taken as the first mean signal value.
Further, the normalizing the first signal mean value to obtain the signal magnitude of the hippocampus includes:
performing brain tissue segmentation on the T2-FLAIR magnetic resonance image by using a brain tissue segmentation method based on a Bayesian network to obtain a gray matter region of the brain to be analyzed, and calculating a second signal mean value, wherein the second signal mean value is a signal mean value of the gray matter region in the T2-FLAIR magnetic resonance image;
taking the ratio between the first signal mean and the second signal mean as the signal magnitude of the hippocampus.
A second aspect of an embodiment of the present invention provides a device for quantitatively calculating a degree of hippocampal sclerosis, which may include:
a relative volume calculation module, configured to acquire a T1W magnetic resonance image of a brain to be analyzed, and calculate a relative volume of a hippocampus in the brain to be analyzed according to the T1W magnetic resonance image;
a signal mean value calculating module, configured to acquire a T2-FLAIR magnetic resonance image of the brain to be analyzed, and calculate a first signal mean value according to the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image, where the first signal mean value is a signal mean value of the hippocampus in the T2-FLAIR magnetic resonance image;
the signal magnitude calculation module is used for carrying out normalization processing on the first signal mean value to obtain a signal magnitude of the hippocampal region;
and the hippocampal sclerosis degree calculation module is used for calculating the hippocampal sclerosis degree of the brain to be analyzed according to the relative volume of the hippocampal region and the signal magnitude of the hippocampal region.
Further, the hippocampal sclerosis degree calculation module is specifically configured to calculate the hippocampal sclerosis degree of the brain to be analyzed according to the following formula:
wherein x is the relative volume of the hippocampus, y is the signal magnitude of the hippocampus, a, b and p are preset weight parameters, c and q are preset constant parameters, m is the preset number of grades of hippocampal sclerosis degree, and HSI is the quantitative value of hippocampal sclerosis degree of the brain to be analyzed.
Further, the relative volume calculation module may include:
the hippocampal region segmentation unit is used for taking T1W magnetic resonance images of brains with different brain structures in batches as a brain template library and segmenting to obtain hippocampal regions on each template;
the hippocampal region mapping unit is used for mapping the template in the brain template library to a T1W magnetic resonance image of the brain to be analyzed by utilizing nonlinear registration to obtain a spatial transformation relation between the template and the brain to be analyzed, and mapping the hippocampal region on the template to the brain to be analyzed by utilizing the spatial transformation relation;
the label fusion unit is used for obtaining a segmentation result of the hippocampal region of the brain to be analyzed by fusion by using a label fusion method;
and the relative volume calculating unit is used for calculating the volume of the hippocampus and the volume of the brain to be analyzed according to the segmentation result of the hippocampus, and taking the ratio of the volume of the hippocampus to the volume of the brain to be analyzed as the relative volume of the hippocampus.
Further, the signal mean calculation module may include:
a linear registration unit for obtaining a linear spatial transformation relationship between the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image by linear registration between the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image;
a result mapping unit for mapping the segmentation result of the hippocampus on the T1W magnetic resonance image onto the T2-FLAIR magnetic resonance image by using the linear spatial transformation relation;
a first signal mean value calculating unit, configured to take a signal mean value of a hippocampus on the T2-FLAIR magnetic resonance image as the first signal mean value.
Further, the semaphore value calculation module may include:
a second signal mean value calculating unit, configured to perform brain tissue segmentation on the T2-FLAIR magnetic resonance image by using a brain tissue segmentation method based on a bayesian network to obtain a gray matter region of the brain to be analyzed, and calculate a second signal mean value, where the second signal mean value is a signal mean value of the gray matter region in the T2-FLAIR magnetic resonance image;
a signal magnitude calculation unit for taking a ratio between the first signal mean value and the second signal mean value as a signal magnitude of the hippocampus.
A third aspect of embodiments of the present invention provides a computer readable storage medium storing computer readable instructions which, when executed by a processor, implement any of the above-mentioned steps of the method for quantitative calculation of the degree of hippocampal sclerosis.
A fourth aspect of the embodiments of the present invention provides a terminal device, including a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, where the processor implements any one of the above-mentioned steps of the method for quantitatively calculating the degree of hippocampus sclerosis when executing the computer readable instructions.
Compared with the prior art, the embodiment of the invention has the following beneficial effects: the method comprises the steps of acquiring a T1W magnetic resonance image of a brain to be analyzed, and calculating the relative volume of a hippocampus in the brain to be analyzed according to the T1W magnetic resonance image; acquiring a T2-FLAIR magnetic resonance image of the brain to be analyzed, and calculating a first signal mean value according to the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image, wherein the first signal mean value is the signal mean value of the hippocampal region in the T2-FLAIR magnetic resonance image; carrying out normalization processing on the first signal mean value to obtain a signal magnitude value of the hippocampus; calculating the hippocampal sclerosis degree of the brain to be analyzed according to the relative volume of the hippocampus and the signal magnitude of the hippocampus. The embodiment of the invention has the advantages of simplicity, convenience, rapidness, high quantification degree, accurate judgment and the like, and provides an objective quantification method for evaluating the degree of the hippocampus sclerosis.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flowchart of a method for quantitatively calculating a hippocampal sclerosis level according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of the calculation of the relative volume of the hippocampus in the brain to be analyzed from the T1W magnetic resonance image;
FIG. 3 is a block diagram of an embodiment of a device for quantitatively calculating the degree of hardening of hippocampus according to an embodiment of the present invention;
fig. 4 is a schematic block diagram of a terminal device in an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of a method for quantitatively calculating a hippocampal sclerosis level according to an embodiment of the present invention may include:
step S101, obtaining a T1W magnetic resonance image of a brain to be analyzed, and calculating the relative volume of a hippocampus in the brain to be analyzed according to the T1W magnetic resonance image.
The hippocampus includes both the left and right hippocampus of the brain. The relative volume of the hippocampus may be calculated in particular by the procedure shown in fig. 2:
step S1011, taking T1W magnetic resonance images of brains with different brain structures in batches as a brain template library, and segmenting to obtain hippocampus on each template.
The purpose of this step is mainly to build a brain template library. The brain with different brain structures in batches referred to herein refers to the brain with different degrees of hippocampal sclerosis, and specifically includes a normal brain template, a brain template with mild and moderate hippocampal sclerosis, a brain template with severe hippocampal sclerosis and the like. In order to ensure the accuracy of the calculation result, the number of the templates of different brains included in the brain template library should be increased as much as possible, so that the coverage of the brain structures in the brain template library is as wide as possible. The specific number of templates may be set according to actual situations, for example, it may be set to 3, 5, 10, or other values.
Step S1012, mapping the template in the brain template library to the T1W magnetic resonance image of the brain to be analyzed by using nonlinear registration to obtain a spatial transformation relationship between the template and the brain to be analyzed, and mapping the hippocampus of the template to the brain to be analyzed by using the spatial transformation relationship.
The non-linear registration may include, but is not limited to, a symmetric non-linear registration algorithm based on a differential homoembryo model or other similar non-linear registration algorithm. And mapping the hippocampal region on the template to the brain to be analyzed by utilizing a spatial transformation relation.
And (3) performing repeated iterative optimization on the spatial transformation relation, wherein local pixel cross-correlation between a target image (namely the T1W magnetic resonance image of the brain to be analyzed) and a template image is taken as an optimization target, and the spatial transformation relation between each template and the target image is obtained. By using this transformation relation, the hippocampus divided in advance in the template space is mapped to the target image space, and the target image is segmented.
And S1013, fusing by using a label fusion method to obtain a segmentation result of the hippocampal region of the brain to be analyzed.
The label fusion method may be a Simultaneous Performance evaluation (stack) label fusion method, the stack algorithm is a segmentation result that combines segmentation results obtained from different templates into an optimal target image by using an Expectation Maximization (EM) algorithm, And the segmentation method based on a plurality of templates can solve the deviation caused by a single template, so that the result is more accurate. The label fusion method is not limited to the STAPLE algorithm, and other fusion methods such as a majority agreement rule, a label fusion method based on confidence level, a label fusion method with weight, and the like can be used.
Step S1014, calculating the volume of the hippocampus and the volume of the brain to be analyzed according to the segmentation result of the hippocampus, and taking the ratio of the volume of the hippocampus to the volume of the brain to be analyzed as the relative volume of the hippocampus.
And S102, acquiring a T2-FLAIR magnetic resonance image of the brain to be analyzed, and calculating a first signal mean value according to the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image.
The first signal mean is the signal mean of the hippocampus in the T2-FLAIR magnetic resonance image.
Specifically, a linear spatial transformation relationship between the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image may be first obtained by linear registration between the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image, then a segmentation result of a hippocampus on the T1W magnetic resonance image is mapped onto the T2-FLAIR magnetic resonance image by using the linear spatial transformation relationship, and finally, a signal mean of the hippocampus on the T2-FLAIR magnetic resonance image is taken as the first signal mean.
And S103, carrying out normalization processing on the first signal mean value to obtain a signal magnitude value of the hippocampus.
Specifically, firstly, a bayesian network-based brain tissue segmentation method may be used to perform brain tissue segmentation on the T2-FLAIR magnetic resonance image to obtain a gray matter region of the brain to be analyzed, then a second signal mean value is calculated, where the second signal mean value is a signal mean value of the gray matter region in the T2-FLAIR magnetic resonance image, and finally a ratio between the first signal mean value and the second signal mean value is used as a signal magnitude of the hippocampus. In this way, differences in the T2-FLAIR signal values caused by different imaging parameters can be avoided.
And step S104, calculating the hippocampal sclerosis degree of the brain to be analyzed according to the relative volume of the hippocampus and the signal magnitude of the hippocampus.
In particular, the degree of hippocampal sclerosis of the brain to be analyzed can be calculated according to the following formula:
the calculation formula is characterized in that the relative volume of the hippocampus and the signal magnitude of the hippocampus are used as variables, an ordered regression method is adopted, and the evaluation result of clinical hippocampal sclerosis degree is used as a target to fit to obtain each parameter. Wherein x is the relative volume of the hippocampus, y is the signal magnitude of the hippocampus, and m is the preset number of grades of the hardening degree of the hippocampus, for example, the hardening degree of the hippocampus can be graded into three grades of normal, mild and moderate degrees and severe degrees, i is 3, i is the serial number of each grade, i is more than or equal to 1 and less than or equal to m, a, b and p are preset weight parameters, c is the weight parameter of the hippocampus, and the likeiAnd q is a preset constant parameter, HSI is a hippocampal sclerosis index, namely a quantized value of the hippocampal sclerosis degree of the brain to be analyzed, the HSI is between 0 and 1, and the larger the value is, the higher the hippocampal sclerosis degree of the brain to be analyzed is.
To verify the effectiveness of this method, magnetic resonance images of 40 temporal lobe epilepsy patients were collected, and hippocampal sclerosis index was calculated by the above method and compared with hippocampal sclerosis degree evaluation of the relevant professionals, and the results are shown in the following table:
| professional rating for degree of hippocampal sclerosis | HSI (mean. + -. variance) |
| Normal (bilateral hippocampal cumulative n ═ 42) | 0.12±0.14 |
| Mild to moderate (bilateral hippocampus cumulative n ═ 27) | 0.51±0.26 |
| Severe (bilateral hippocampus japonicus cumulative n ═ 11) | 0.80±0.16 |
It can be seen from the table that the hippocampal sclerosis index calculated by the method of the embodiment of the present invention has a good discrimination for the hippocampal sclerosis degree judged by the related technical personnel (with a significant statistical difference between groups by Kruskal-Wallis non-parametric test, p is less than 0.0001), which indicates that the hippocampal sclerosis index provided by the embodiment of the present invention can effectively evaluate the hippocampal sclerosis degree.
In summary, the embodiments of the present invention acquire a T1W magnetic resonance image of a brain to be analyzed, and calculate a relative volume of a hippocampus in the brain to be analyzed according to the T1W magnetic resonance image; acquiring a T2-FLAIR magnetic resonance image of the brain to be analyzed, and calculating a first signal mean value according to the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image, wherein the first signal mean value is the signal mean value of the hippocampal region in the T2-FLAIR magnetic resonance image; carrying out normalization processing on the first signal mean value to obtain a signal magnitude value of the hippocampus; calculating the hippocampal sclerosis degree of the brain to be analyzed according to the relative volume of the hippocampus and the signal magnitude of the hippocampus. The embodiment of the invention has the advantages of simplicity, convenience, rapidness, high quantification degree, accurate judgment and the like, and provides an objective quantification method for evaluating the degree of the hippocampus sclerosis.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Fig. 3 is a block diagram of an embodiment of a device for quantitatively calculating the degree of hardening of the hippocampus according to an embodiment of the present invention, which corresponds to the method for quantitatively calculating the degree of hardening of the hippocampus according to the above embodiment.
In this embodiment, a device for quantitatively calculating the degree of hardening of the hippocampus may include:
a relative volume calculation module 301, configured to acquire a T1W magnetic resonance image of a brain to be analyzed, and calculate a relative volume of a hippocampus in the brain to be analyzed according to the T1W magnetic resonance image;
a signal mean value calculating module 302, configured to acquire a T2-FLAIR magnetic resonance image of the brain to be analyzed, and calculate a first signal mean value according to the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image, where the first signal mean value is a signal mean value of the hippocampus in the T2-FLAIR magnetic resonance image;
a signal magnitude calculation module 303, configured to perform normalization processing on the first signal mean value to obtain a signal magnitude of the hippocampus;
a hippocampal sclerosis degree calculating module 304, for calculating the hippocampal sclerosis degree of the brain to be analyzed according to the relative volume of the hippocampus and the signal magnitude of the hippocampus.
Further, the hippocampal sclerosis degree calculation module is specifically configured to calculate the hippocampal sclerosis degree of the brain to be analyzed according to the following formula:
wherein x is the relative volume of the hippocampus, y is the signal magnitude of the hippocampus, a, b and p are preset weight parameters, c and q are preset constant parameters, m is the preset number of grades of hippocampal sclerosis degree, and HSI is the quantitative value of hippocampal sclerosis degree of the brain to be analyzed.
Further, the relative volume calculation module may include:
the hippocampal region segmentation unit is used for taking T1W magnetic resonance images of brains with different brain structures in batches as a brain template library and segmenting to obtain hippocampal regions on each template;
the hippocampal region mapping unit is used for mapping the template in the brain template library to a T1W magnetic resonance image of the brain to be analyzed by utilizing nonlinear registration to obtain a spatial transformation relation between the template and the brain to be analyzed, and mapping the hippocampal region on the template to the brain to be analyzed by utilizing the spatial transformation relation;
the label fusion unit is used for obtaining a segmentation result of the hippocampal region of the brain to be analyzed by fusion by using a label fusion method;
and the relative volume calculating unit is used for calculating the volume of the hippocampus and the volume of the brain to be analyzed according to the segmentation result of the hippocampus, and taking the ratio of the volume of the hippocampus to the volume of the brain to be analyzed as the relative volume of the hippocampus.
Further, the signal mean calculation module may include:
a linear registration unit for obtaining a linear spatial transformation relationship between the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image by linear registration between the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image;
a result mapping unit for mapping the segmentation result of the hippocampus on the T1W magnetic resonance image onto the T2-FLAIR magnetic resonance image by using the linear spatial transformation relation;
a first signal mean value calculating unit, configured to take a signal mean value of a hippocampus on the T2-FLAIR magnetic resonance image as the first signal mean value.
Further, the semaphore value calculation module may include:
a second signal mean value calculating unit, configured to perform brain tissue segmentation on the T2-FLAIR magnetic resonance image by using a brain tissue segmentation method based on a bayesian network to obtain a gray matter region of the brain to be analyzed, and calculate a second signal mean value, where the second signal mean value is a signal mean value of the gray matter region in the T2-FLAIR magnetic resonance image;
a signal magnitude calculation unit for taking a ratio between the first signal mean value and the second signal mean value as a signal magnitude of the hippocampus.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, modules and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Fig. 4 shows a schematic block diagram of a terminal device according to an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown.
As shown in fig. 4, the terminal device 4 of this embodiment includes: a processor 40, a memory 41 and a computer program 42 stored in said memory 41 and executable on said processor 40. The processor 40, when executing the computer program 42, implements the steps of the above-described embodiments of the method for quantitatively calculating the degree of hippocampus hardening, such as steps S101 to S104 shown in fig. 1. Alternatively, the processor 40, when executing the computer program 42, implements the functions of each module/unit in the above-mentioned device embodiments, such as the functions of the modules 301 to 304 shown in fig. 3.
Illustratively, the computer program 42 may be partitioned into one or more modules/units that are stored in the memory 41 and executed by the processor 40 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 42 in the terminal device 4.
The terminal device 4 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. It will be understood by those skilled in the art that fig. 4 is only an example of the terminal device 4, and does not constitute a limitation to the terminal device 4, and may include more or less components than those shown, or combine some components, or different components, for example, the terminal device 4 may further include an input-output device, a network access device, a bus, etc.
The Processor 40 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 41 may be an internal storage unit of the terminal device 4, such as a hard disk or a memory of the terminal device 4. The memory 41 may also be an external storage device of the terminal device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal device 4. The memory 41 is used for storing the computer program and other programs and data required by the terminal device 4. The memory 41 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (8)
1. A method for quantitatively calculating the degree of hardening of the hippocampus, comprising:
acquiring a T1W magnetic resonance image of a brain to be analyzed, and calculating the relative volume of a hippocampus in the brain to be analyzed according to the T1W magnetic resonance image; wherein the hippocampus includes hippocampus on both left and right sides of the brain;
acquiring a T2-FLAIR magnetic resonance image of the brain to be analyzed, and calculating a first signal mean value according to the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image, wherein the first signal mean value is the signal mean value of the hippocampal region in the T2-FLAIR magnetic resonance image;
carrying out normalization processing on the first signal mean value to obtain a signal magnitude value of the hippocampus;
calculating a degree of hippocampal sclerosis of the brain to be analyzed from the relative volume of the hippocampus and the signal magnitude of the hippocampus, comprising: calculating the degree of hippocampal sclerosis of the brain to be analyzed according to the following formula:
wherein x is the relative volume of the hippocampus, y is the signal magnitude of the hippocampus, a, b and p are preset weight parameters, c and q are preset constant parameters, m is the preset number of grades of hippocampal sclerosis degree, and HSI is the quantitative value of hippocampal sclerosis degree of the brain to be analyzed.
2. The method of claim 1, wherein the calculating of the relative volume of the hippocampus in the brain to be analyzed from the T1W magnetic resonance image comprises:
taking T1W magnetic resonance images of brains with different brain structures in batches as a brain template library, and segmenting to obtain hippocampal regions on each template;
mapping a template in the brain template library to a T1W magnetic resonance image of the brain to be analyzed by utilizing nonlinear registration to obtain a spatial transformation relation between the template and the brain to be analyzed, and mapping a hippocampal region on the template to the brain to be analyzed by utilizing the spatial transformation relation;
fusing to obtain a segmentation result of the hippocampus of the brain to be analyzed by using a label fusion method;
and calculating the volume of the hippocampus and the volume of the brain to be analyzed according to the segmentation result of the hippocampus, and taking the ratio of the volume of the hippocampus to the volume of the brain to be analyzed as the relative volume of the hippocampus.
3. The method of claim 1, wherein the calculating a mean first signal value from the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image comprises:
obtaining a linear spatial transformation relationship between the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image by linear registration between the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image;
mapping the segmentation result of the hippocampus on the T1W magnetic resonance image onto the T2-FLAIR magnetic resonance image by using the linear spatial transformation relation;
the mean signal value of the hippocampus on the T2-FLAIR magnetic resonance image was taken as the first mean signal value.
4. The method as claimed in any one of claims 1 to 3, wherein the normalizing the first signal mean value to obtain the signal magnitude of the hippocampus comprises:
performing brain tissue segmentation on the T2-FLAIR magnetic resonance image by using a brain tissue segmentation method based on a Bayesian network to obtain a gray matter region of the brain to be analyzed, and calculating a second signal mean value, wherein the second signal mean value is a signal mean value of the gray matter region in the T2-FLAIR magnetic resonance image;
taking the ratio between the first signal mean and the second signal mean as the signal magnitude of the hippocampus.
5. A quantitative calculation apparatus of hippocampal sclerosis degree, comprising:
a relative volume calculation module, configured to acquire a T1W magnetic resonance image of a brain to be analyzed, and calculate a relative volume of a hippocampus in the brain to be analyzed according to the T1W magnetic resonance image; wherein the hippocampus includes hippocampus on both left and right sides of the brain;
a signal mean value calculating module, configured to acquire a T2-FLAIR magnetic resonance image of the brain to be analyzed, and calculate a first signal mean value according to the T1W magnetic resonance image and the T2-FLAIR magnetic resonance image, where the first signal mean value is a signal mean value of the hippocampus in the T2-FLAIR magnetic resonance image;
the signal magnitude calculation module is used for carrying out normalization processing on the first signal mean value to obtain a signal magnitude of the hippocampal region;
a hippocampal sclerosis degree calculation module, which is used for calculating the hippocampal sclerosis degree of the brain to be analyzed according to the relative volume of the hippocampal region and the signal magnitude of the hippocampal region;
the hippocampal sclerosis degree calculation module is specifically used for calculating the hippocampal sclerosis degree of the brain to be analyzed according to the following formula:
wherein x is the relative volume of the hippocampus, y is the signal magnitude of the hippocampus, a, b and p are preset weight parameters, c and q are preset constant parameters, m is the preset number of grades of hippocampal sclerosis degree, and HSI is the quantitative value of hippocampal sclerosis degree of the brain to be analyzed.
6. The apparatus of claim 5, wherein the relative volume calculating module comprises:
the hippocampal region segmentation unit is used for taking T1W magnetic resonance images of brains with different brain structures in batches as a brain template library and segmenting to obtain hippocampal regions on each template;
the hippocampal region mapping unit is used for mapping the template in the brain template library to a T1W magnetic resonance image of the brain to be analyzed by utilizing nonlinear registration to obtain a spatial transformation relation between the template and the brain to be analyzed, and mapping the hippocampal region on the template to the brain to be analyzed by utilizing the spatial transformation relation;
the label fusion unit is used for obtaining a segmentation result of the hippocampal region of the brain to be analyzed by fusion by using a label fusion method;
and the relative volume calculating unit is used for calculating the volume of the hippocampus and the volume of the brain to be analyzed according to the segmentation result of the hippocampus, and taking the ratio of the volume of the hippocampus to the volume of the brain to be analyzed as the relative volume of the hippocampus.
7. A computer readable storage medium storing computer readable instructions, wherein the computer readable instructions, when executed by a processor, implement the steps of the method for quantitative calculation of hippocampal sclerosis according to any one of claims 1 to 4.
8. A terminal device comprising a memory, a processor and computer readable instructions stored in said memory and executable on said processor, characterized in that said processor, when executing said computer readable instructions, carries out the steps of the method for quantitative calculation of the degree of hippocampal sclerosis according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910398096.4A CN110232708B (en) | 2019-05-14 | 2019-05-14 | Method, device, medium and terminal equipment for quantitatively calculating hippocampal sclerosis degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910398096.4A CN110232708B (en) | 2019-05-14 | 2019-05-14 | Method, device, medium and terminal equipment for quantitatively calculating hippocampal sclerosis degree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110232708A CN110232708A (en) | 2019-09-13 |
| CN110232708B true CN110232708B (en) | 2021-04-30 |
Family
ID=67861229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910398096.4A Active CN110232708B (en) | 2019-05-14 | 2019-05-14 | Method, device, medium and terminal equipment for quantitatively calculating hippocampal sclerosis degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110232708B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107103612A (en) * | 2017-03-28 | 2017-08-29 | 深圳博脑医疗科技有限公司 | Automate the quantitative calculation method of subregion brain atrophy |
| CN108765447A (en) * | 2018-04-26 | 2018-11-06 | 深圳博脑医疗科技有限公司 | A kind of image partition method, image segmentation device and electronic equipment |
| CN108830830A (en) * | 2018-05-11 | 2018-11-16 | 深圳博脑医疗科技有限公司 | A kind of quantitative detecting method of brain atrophy, detection device and terminal device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130190606A1 (en) * | 2012-01-25 | 2013-07-25 | Huntington Medical Research Institutes | Combined quantitative mri and quantitative mrs for diagnosis of alzheimers disease and hippocampal sclerosis |
-
2019
- 2019-05-14 CN CN201910398096.4A patent/CN110232708B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107103612A (en) * | 2017-03-28 | 2017-08-29 | 深圳博脑医疗科技有限公司 | Automate the quantitative calculation method of subregion brain atrophy |
| CN108765447A (en) * | 2018-04-26 | 2018-11-06 | 深圳博脑医疗科技有限公司 | A kind of image partition method, image segmentation device and electronic equipment |
| CN108830830A (en) * | 2018-05-11 | 2018-11-16 | 深圳博脑医疗科技有限公司 | A kind of quantitative detecting method of brain atrophy, detection device and terminal device |
Non-Patent Citations (2)
| Title |
|---|
| MRI对儿童癫痫患者海马硬化的应用价值分析;宋跃锋;《中国CT和MRI杂志》;20170630;第15卷(第6期);全文 * |
| Use of an Automated Quantitative Analysis of Hippocampal Volume, Signal, and Glucose Metabolism to Detect Hippocampal Sclerosis;Hu Wen-Han;Liu Li-Na;Zhao Bao-Tian;Wang Xiu;Zhang Chao;Shao Xiao;《Frontiers in neurology》;20181004;第2页第1栏-第7页第1栏及附图1,2 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110232708A (en) | 2019-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111310775B (en) | Data training method, device, terminal equipment and computer readable storage medium | |
| CN109300107B (en) | Plaque processing method, device and computing equipment for magnetic resonance blood vessel wall imaging | |
| CN109949219B (en) | Reconstruction method, device and equipment of super-resolution image | |
| CN110021053B (en) | Image positioning method and device based on coordinate transformation, storage medium and equipment | |
| Zhou et al. | Utilizing dictionary learning and machine learning for blind quality assessment of 3-D images | |
| Goez et al. | Preprocessing of 2-dimensional gel electrophoresis images applied to proteomic analysis: a review | |
| CN108765447B (en) | Image segmentation method, image segmentation device and electronic equipment | |
| CN109146891B (en) | Hippocampus segmentation method and device applied to MRI and electronic equipment | |
| CN110675334A (en) | Image enhancement method and device | |
| CN115730605B (en) | Data analysis method based on multidimensional information | |
| Damangir et al. | Reproducible segmentation of white matter hyperintensities using a new statistical definition | |
| Liu et al. | Low-light image enhancement based on membership function and gamma correction | |
| CN110232708B (en) | Method, device, medium and terminal equipment for quantitatively calculating hippocampal sclerosis degree | |
| Zhang et al. | A novel tool to provide predictable alignment data irrespective of source and image quality acquired on mobile phones: what engineers can offer clinicians | |
| Chen et al. | Phase congruency based on derivatives of circular symmetric Gaussian function: an efficient feature map for image quality assessment | |
| CN113704236A (en) | Government affair system data quality evaluation method, device, terminal and storage medium | |
| US20170351844A1 (en) | System and method for determining relative operational performance in a clinical trial | |
| CN111968140B (en) | Contour detection method based on classical receptive field vision-strengthening micro-motion mechanism | |
| De et al. | No-reference image contrast measure using image statistics and random forest | |
| Nozawa et al. | Magnetic resonance image segmentation of the compressed spinal cord in patients with degenerative cervical myelopathy using convolutional neural networks | |
| CN113609445A (en) | Multi-source heterogeneous monitoring data processing method, terminal device and readable storage medium | |
| CN112102295A (en) | DR image registration method, device, terminal and computer-readable storage medium | |
| CN112053779B (en) | Disease detection model construction method, disease detection model construction device and terminal equipment | |
| Aetesam et al. | Perceptually motivated generative model for magnetic resonance image denoising | |
| CN114580948B (en) | Water service annual budget analysis system |
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 |