WO2019214750A1 - 一种脑萎缩程度的定量检测方法、检测装置及终端设备 - Google Patents

一种脑萎缩程度的定量检测方法、检测装置及终端设备 Download PDF

Info

Publication number
WO2019214750A1
WO2019214750A1 PCT/CN2019/087946 CN2019087946W WO2019214750A1 WO 2019214750 A1 WO2019214750 A1 WO 2019214750A1 CN 2019087946 W CN2019087946 W CN 2019087946W WO 2019214750 A1 WO2019214750 A1 WO 2019214750A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
brain
magnitude
atrophy
volume
Prior art date
Application number
PCT/CN2019/087946
Other languages
English (en)
French (fr)
Inventor
罗怡珊
Original Assignee
深圳博脑医疗科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳博脑医疗科技有限公司 filed Critical 深圳博脑医疗科技有限公司
Publication of WO2019214750A1 publication Critical patent/WO2019214750A1/zh

Links

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
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • 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

Definitions

  • the present application relates to the field of image processing technologies, and in particular, to a quantitative detection method, a detection device, and a terminal device for the degree of brain atrophy.
  • AD Alzheimer's Disease
  • the embodiments of the present application provide a quantitative detection method, a detection device, and a terminal device for the degree of brain atrophy, so as to solve the problem that the degree of brain atrophy cannot be effectively evaluated in the prior art.
  • a first aspect of the embodiments of the present application provides a quantitative detection method for the degree of brain atrophy, comprising:
  • a second aspect of the embodiments of the present application provides a quantitative detecting device for the degree of brain atrophy, comprising:
  • a marking unit configured to acquire a first preset number of first template images and a target quantity value of the first template image, and record a target quantity value of the first template image as a first target quantity value
  • the first template image is a brain magnetic resonance image of a brain healthy individual of a preset age
  • An acquiring unit configured to acquire a brain magnetic resonance image of the individual to be tested, obtain an image to be tested, and calculate a target quantity value of the image to be tested to obtain a second target quantity value;
  • a calculating unit configured to calculate a percentile of the second target magnitude according to the first target magnitude, to obtain a degree of brain atrophy of the subject to be tested.
  • a third aspect of the embodiments of the present application provides a terminal device including a memory, a processor, and a computer program stored in the memory and operable on the processor, when the processor executes the computer program
  • the steps of the method provided by the first aspect of the embodiments of the present application are implemented.
  • a fourth aspect of the embodiments of the present application provides a computer readable storage medium storing a computer program, the computer program being executed by one or more processors to implement the first embodiment of the present application Aspects of the method provided by the aspect.
  • the embodiment of the present application obtains a first preset number of first template images and a target quantity value of the first template image, and records a target quantity value of the first template image as a first target quantity value
  • the first template image is a brain magnetic resonance image of a brain healthy individual of a preset age; acquiring a brain magnetic resonance image of the individual to be tested, obtaining an image to be tested, and calculating a target magnitude of the image to be measured to obtain a second target amount a value; calculating a percentile of the second target magnitude according to the first target magnitude, to obtain a degree of brain atrophy of the subject to be tested.
  • FIG. 1 is a schematic flow chart showing an implementation process of a quantitative detection method for brain atrophy degree provided by an embodiment of the present application
  • FIG. 2 is a schematic diagram of a quantitative detecting device for brain atrophy degree provided by an embodiment of the present application
  • FIG. 3 is a schematic diagram of a terminal device according to an embodiment of the present application.
  • FIG. 4 is a comparison table of brain atrophy values of a normal group and a brain degeneration group calculated by the quantitative detection method of brain atrophy degree in the present application provided by an embodiment of the present application;
  • Fig. 5 is a graph showing the results of whole brain atrophy values of the normal group and the brain degeneration group provided in the examples of the present application.
  • the term “if” can be interpreted as “when” or “on” or “in response to determining” or “in response to detecting” depending on the context. .
  • the phrase “if determined” or “if detected [condition or event described]” may be interpreted in context to mean “once determined” or “in response to determining” or “once detected [condition or event described] ] or “in response to detecting [conditions or events described]”.
  • FIG. 1 is a schematic diagram of an implementation process of a quantitative detection method for brain atrophy degree provided by an embodiment of the present application. As shown in the figure, the method may include the following steps:
  • Step S101 acquiring a first preset number of first template images and target quantity values of the first template image, and recording a target quantity value of the first template image as a first target quantity, the first
  • the template image is a brain magnetic resonance image of a brain healthy individual of a preset age.
  • the target quantity value comprises:
  • the ratio of the volume of the target brain structure to the volume of the brain, and the atrophy of the target brain region is the ratio of the volume of the target brain structure to the volume of the brain, and the atrophy of the target brain region.
  • the target brain structure includes:
  • Hippocampus amygdala, lateral ventricle.
  • the target brain region includes:
  • the brain lobe includes:
  • the target magnitude includes:
  • Atrophy of left frontal lobe, atrophy of right frontal lobe, atrophy of left occipital lobe, atrophy of right occipital lobe, atrophy of left parietal lobe, atrophy of right parietal lobe, atrophy of left temporal lobe, right The atrophy value of the temporal lobe, the atrophy value of the left cingulate gyrus, the atrophy value of the right cingulate gyrus, the atrophy value of the left island leaf, and the atrophy value of the right island leaf.
  • the first preset quantity may be artificially set, as long as there are enough target quantity values.
  • Each first template image may have all of the target magnitudes, or there may be one or several of the target magnitudes.
  • three first template images A, B, and C are obtained.
  • A has 15 target magnitudes, which are the ratio of the volume of the hippocampus to the volume of the brain, the ratio of the volume of the amygdala to the volume of the brain, and the lateral ventricle.
  • B has 2 target
  • the values are the ratio of the volume of the hippocampus to the volume of the brain, and the atrophy of the left frontal lobe;
  • C has a target magnitude that is the ratio of the volume of the hippocampus to the volume of the brain. Then there are 18 first target magnitudes, of which the ratio of the volume of three hippocampus to the volume of the brain, and the atrophy of the two left frontal lob
  • the preset age can refer to a specific age or an age group. If the preset age is a specific age, the preset age is the age of the individual to be tested; if the preset age is an age group, the preset age is the age group of the age of the individual to be tested, and the specific age group is divided. It can be artificially preset.
  • the brain magnetic resonance image of the brain healthy individual with the preset age is used as the first template image, and the degree of brain atrophy of the individual to be tested is compared with that of the brain healthy individual of the same age, so that the degree of brain atrophy of the individual to be tested can be more accurately evaluated.
  • the target value of the first template image and the first template image may be obtained from a preset brain template library, that is, a magnetic resonance image of a normal individual of each age brain stored in the preset brain template library and the images of the images are Target quantity value; the first template image may also be obtained from the preset brain template library, and then the target quantity value of each first template image is separately calculated, that is, only the magnetic body of the normal brain of each age is stored in the preset brain template library. Resonance image.
  • the method of calculating the target magnitude of each of the first template images is the same as the method of calculating the target magnitude of the image to be tested. See the detailed description in step S102. Studies have found that the structure of the brain changes with age.
  • Step S102 Acquire a brain magnetic resonance image of the individual to be tested, obtain an image to be tested, and calculate a target quantity value of the image to be tested to obtain a second target quantity value.
  • the image to be tested may correspond to a second target quantity value, or may correspond to multiple second target quantity values.
  • the calculating a target quantity value of the image to be tested includes:
  • the preset brain template library And acquiring, by the preset brain template library, a second preset number of second template images, wherein the second template image includes the target brain structure and/or the target brain region.
  • the target segmentation image is A target area is included, the target area being an area occupied by the target brain structure and/or the target brain area.
  • the target area is the area occupied by the target brain structure
  • the volume of the target brain structure is calculated.
  • a volume of the brain in the target segmentation image is calculated, and a ratio of a volume of the target brain structure to a volume of the brain is calculated.
  • the calculating the target quantity value of the image to be tested further includes:
  • the target area After determining whether the target area is the area occupied by the target brain structure, if the target area is the area occupied by the target brain area, calculating the cerebrospinal fluid volume and the white matter volume in the target brain area And the gray matter volume of the brain.
  • A is the atrophy value of the target brain region
  • V CSF is the cerebrospinal fluid volume in the target brain region
  • V WM is the white matter volume in the target brain region
  • V GM is the target brain region Gray matter volume.
  • a preset brain image library can store a large number of magnetic resonance images of brains with different brain structures.
  • the image to be measured is segmented, and all the obtained segmented images are merged into one target image.
  • various different brain structures are comprehensively considered, so that the segmentation result is more accurate.
  • performing the segmentation process on the image to be tested according to each second template image may include the following steps:
  • the target brain structure and/or the area occupied by the target brain region in the second template image are mapped onto the image to be tested, and the target region is obtained on the image to be detected.
  • the target area in the image to be measured is marked to obtain a divided image.
  • the second template image may include one or more target brain structures, and may also include one or more target brain regions, and may also include both the target brain structure and the target brain region. It is only necessary to ensure that the target brain structure and the target brain region can be segmented in the image to be tested by using the second template image. In other words, it is necessary to ensure that the target segmentation image of the image to be tested includes the image with the first template.
  • the target magnitude of the first template image has a ratio of the volume of the hippocampus to the volume of the brain, and the atrophy value of the left frontal lobe. Then, the target segmentation image of the image to be tested needs a region occupied by the hippocampus and the left frontal lobe. The area occupied.
  • the volume ratio of the volume of some brain structures (such as hippocampus, amygdala, lateral ventricle, or target brain structure) to the total volume of the brain can reflect the degree of brain degeneration, while some brain regions (such as the brain lobe, including 12)
  • the atrophy value of the brain lobe, ie the target brain region can reflect the degree of brain degeneration.
  • the target region in the target segmentation image is the region occupied by the target brain structure or the region occupied by the target brain region; if it is occupied by the target brain structure In the region, the volume of the target brain structure and the volume of the brain need to be calculated to obtain the ratio of the volume of the target brain structure to the volume of the brain; if it is the region occupied by the target brain region, the volume of the cerebrospinal fluid in the target brain region needs to be calculated, The white matter volume and the gray matter volume of the brain to obtain the atrophy value of the target brain region.
  • Step S103 calculating a percentile of the second target magnitude according to the first target magnitude, to obtain a degree of brain atrophy of the subject to be tested.
  • the value of the data corresponding to a certain percentile is called the percentile of this percentile. It can be expressed as: a set of n observations are arranged by numerical value. For example, the value at the p% position is called the p-th percentile.
  • the method further includes:
  • the calculating a percentile of the second target magnitude according to the first target magnitude includes:
  • z is a normalized magnitude of the second target magnitude
  • x is the second target magnitude
  • ⁇ is the mean of the first target magnitude
  • ⁇ is the variance of the first target magnitude
  • the preset correspondence table may be a preset table for manually recording the correspondence between the z value and the percentile.
  • the first target magnitude comprises a total of 300 magnitudes
  • the 300 magnitudes are divided into two categories, and the first type of magnitude is the ratio of the volume of the hippocampus to the volume of the brain, a total of 100;
  • the magnitude is the atrophy of the left frontal lobe, a total of 200.
  • the percentile of the normalized magnitude 50 of the first type of magnitude is 50%
  • the percentile of the normalized magnitude of the second type of magnitude is 70. 70%. In this way, a quantitative assessment of the degree of brain atrophy is achieved. It should be noted that the above is only an example of the quantitative calculation of the degree of brain atrophy, and the number and the percentile correspondence table of the magnitude are not specifically limited.
  • the method further includes:
  • the percentile of the ratio of the volume of the target brain structure to the volume of the brain in the second target magnitude, the second The percentiles of the atrophy value of the target brain region in the target magnitude are added according to the preset weights, and include:
  • P' is the percentile of the updated second target magnitude
  • P is the percentile of the second target magnitude calculated from the first target magnitude
  • the percentile of the second target magnitude is: the percentile of the ratio of the volume of the hippocampus to the volume of the brain is 50%, and the percentile of the ratio of the volume of the amygdala to the volume of the brain.
  • the number is 40%, the ratio of the volume ratio of the volume of the lateral ventricle to the volume of the brain is 45%, the percentile of the atrophic value of the left frontal lobe is 30%, and the atrophy of the right frontal lobe is 100%.
  • the quantile is 30%, the percentile of the left occipital atrophy is 30%, the percentile of the right occipital atrophy is 30%, and the percentile of the left parietal atrophy is 30.
  • the percentile of the right parietal lobe is 30%, the percentile of the left parotid leaf is 20%, and the percentile of the right temporal lobe is 20%, left clasp
  • the percentile of the back atrophy value is 20%
  • the percentile of the atrophic value of the right cingulate band is 20%
  • the percentile of the atrophy value of the left island leaf is 20%
  • the atrophy value of the right island leaf The percentile is 20%.
  • the preset weights are both 1/15
  • the second target quantity is weighted and summed according to the preset weight, and the total brain atrophy is 12.8%. It should be noted that here is only an example of how to calculate the amount of global brain atrophy, and is not specifically limited.
  • the ratio of the volume of the hippocampus and the amygdala to the volume of the brain is the greater the degree of brain atrophy, the smaller the volume ratio, and the ratio of the volume of the lateral ventricle to the volume of the brain and the brain atrophy value of each brain The greater the degree of brain atrophy, the greater its value. Therefore, the weight percent of the hippocampus and amygdala to the brain needs to be changed to (100-p) at the time of weighted sum.
  • FIG. 4 is a comparison table of brain atrophy values of the normal group and the brain degeneration group calculated by the quantitative detection method of brain atrophy degree provided by the embodiment of the present application
  • FIG. 5 is a implementation of the present application.
  • the results of the results of the total brain atrophy values of the normal group and the brain degeneration group are provided.
  • Figures 4 and 5 are experimental results obtained from magnetic resonance images of 79 brain normal individuals and 69 brain degraded patients collected. As shown in the figure, there is a significant difference in the total brain brain atrophy between normal brain and brain degenerative patients, so it can be shown that the total brain atrophy value is a good indicator for assessing the degree of brain atrophy.
  • the embodiment of the present application obtains a first preset number of first template images and a target quantity value of the first template image, and records a target quantity value of the first template image as a first target quantity value
  • the first template image is a brain magnetic resonance image of a brain healthy individual of a preset age; acquiring a brain magnetic resonance image of the individual to be tested, obtaining an image to be tested, and calculating a target magnitude of the image to be measured to obtain a second target amount a value; calculating a percentile of the second target magnitude according to the first target magnitude, to obtain a degree of brain atrophy of the subject to be tested.
  • FIG. 2 is a schematic diagram of a quantitative detecting device for brain atrophy degree provided by an embodiment of the present application, and for convenience of explanation, only parts related to the embodiment of the present application are shown.
  • the quantitative detection device for the degree of brain atrophy shown in FIG. 2 may be a software unit, a hardware unit, or a combination of soft and hard units built in an existing terminal device, or may be integrated into the terminal device as a separate pendant. It can also exist as a stand-alone terminal device.
  • the quantitative detecting device 2 for the degree of brain atrophy includes:
  • the marking unit 21 configured to acquire a first preset number of first template images and a target magnitude of the first template image, and record a target magnitude of the first template image as a first target amount
  • the first template image is a brain magnetic resonance image of a brain healthy individual of a predetermined age.
  • the obtaining unit 22 is configured to acquire a brain magnetic resonance image of the individual to be tested, obtain an image to be tested, and calculate a target quantity value of the image to be tested to obtain a second target quantity value.
  • the first calculating unit 23 is configured to calculate a percentile of the second target magnitude according to the first target magnitude, to obtain a degree of brain atrophy of the subject to be tested.
  • the device 2 further includes:
  • the second calculating unit 24 is configured to calculate a mean value and a variance of the first target quantity value after the target quantity value of the first template image is recorded as the first target quantity value.
  • the first calculating unit 23 includes:
  • a searching module configured to search, from the preset correspondence table, a percentile corresponding to the normalized magnitude of the second target magnitude.
  • z is a normalized magnitude of the second target magnitude
  • x is the second target magnitude
  • ⁇ is the mean of the first target magnitude
  • ⁇ is the variance of the first target magnitude
  • the target quantity value comprises:
  • the ratio of the target brain structure to the brain and the atrophy of the target brain region is the ratio of the target brain structure to the brain and the atrophy of the target brain region.
  • the target brain structure includes:
  • Hippocampus amygdala, lateral ventricle.
  • the target brain region includes:
  • the brain lobe includes:
  • the obtaining unit 22 includes:
  • a acquiring module configured to obtain a second preset number of second template images from the preset brain template library, where the target image structure and/or the target brain region is included in the second template image.
  • a segmentation module configured to separately perform segmentation processing on the image to be tested according to each second template image, to obtain a second preset number of segmentation images, and fuse the preset number of segmentation images into a target segmentation image
  • the target segmentation image includes a target region, which is a region occupied by the target brain structure and/or the target brain region.
  • the determining module is configured to determine whether the target area is an area occupied by the target brain structure.
  • a first calculating module configured to calculate a volume of the target brain structure if the target area is an area occupied by the target brain structure.
  • a second calculating module configured to calculate a volume of the brain in the target segmentation image, and calculate a ratio of a volume of the target brain structure to a volume of the brain.
  • the obtaining unit 22 further includes:
  • a third calculating module configured to calculate, after the target area is an area occupied by the target brain structure, if the target area is an area occupied by the target brain area, calculate the target brain area Cerebrospinal fluid volume, white matter volume, and gray matter volume.
  • A is the atrophy value of the target brain region
  • V CSF is the cerebrospinal fluid volume in the target brain region
  • V WM is the white matter volume in the target brain region
  • V GM is the target brain region Gray matter volume.
  • the device 2 further includes:
  • a weighting unit 25 configured to calculate a volume of the target brain structure and a volume of the brain in the second target amount after calculating the percentile of the second target amount according to the first target amount
  • the percentile of the ratio and the percentile of the atrophy value of the target brain region in the second target magnitude are added according to a preset weight to obtain a total brain atrophy value of the individual to be tested.
  • the result unit 26 is configured to obtain a magnitude of brain atrophy of the individual to be tested according to the total brain atrophy value of the test subject.
  • the weighting unit 25 includes:
  • P' is the percentile of the updated second target magnitude
  • P is the percentile of the second target magnitude calculated from the first target magnitude
  • each functional unit and module described above is exemplified. In practical applications, the above functions may be assigned to different functional units as needed.
  • the module is completed by dividing the internal structure of the device into different functional units or modules to perform all or part of the functions described above.
  • Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit, and the integrated unit may be hardware.
  • Formal implementation can also be implemented in the form of software functional units.
  • the specific names of the respective functional units and modules are only for the purpose of facilitating mutual differentiation, and are not intended to limit the scope of protection of the present application.
  • For the specific working process of the unit and the module in the foregoing system reference may be made to the corresponding process in the foregoing method embodiment, and details are not described herein again.
  • FIG. 3 is a schematic diagram of a terminal device according to an embodiment of the present application.
  • the terminal device 3 of this embodiment includes a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and operable on the processor 30.
  • the processor 30 performs the steps in the embodiment of the quantitative detection method for each degree of brain atrophy when the computer program 32 is executed, for example, steps S101 to S103 shown in FIG.
  • the processor 30 executes the computer program 32, the functions of the modules/units in the above various device embodiments are implemented, such as the functions of the modules 21 to 26 shown in FIG.
  • the computer program 32 can be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 30 to complete This application.
  • the one or more modules/units may be a series of computer program instruction segments capable of performing a particular function, the instruction segments being used to describe the execution of the computer program 32 in the terminal device 3.
  • the computer program 32 can be divided into a marking unit, an obtaining unit, and a first computing unit, and the specific functions of each unit are as follows:
  • a marking unit configured to acquire a first preset number of first template images and a target quantity value of the first template image, and record a target quantity value of the first template image as a first target quantity value
  • the first template image is a brain magnetic resonance image of a brain healthy individual of a predetermined age.
  • an acquiring unit configured to acquire a brain magnetic resonance image of the individual to be tested, obtain an image to be tested, and calculate a target quantity value of the image to be tested to obtain a second target quantity value.
  • a first calculating unit configured to calculate a percentile of the second target magnitude according to the first target magnitude, to obtain a degree of brain atrophy of the subject to be tested.
  • the device further includes:
  • a second calculating unit configured to calculate a mean value and a variance of the first target quantity value after the target quantity value of the first template image is recorded as the first target quantity value.
  • the first calculating unit includes:
  • a searching module configured to search, from the preset correspondence table, a percentile corresponding to the normalized magnitude of the second target magnitude.
  • z is a normalized magnitude of the second target magnitude
  • x is the second target magnitude
  • ⁇ is the mean of the first target magnitude
  • ⁇ is the variance of the first target magnitude
  • the target quantity value comprises:
  • the ratio of the volume of the target brain structure to the volume of the brain, and the atrophy of the target brain region is the ratio of the volume of the target brain structure to the volume of the brain, and the atrophy of the target brain region.
  • the target brain structure includes:
  • Hippocampus amygdala, lateral ventricle.
  • the target brain region includes:
  • the brain lobe includes:
  • the obtaining unit includes:
  • a acquiring module configured to obtain a second preset number of second template images from the preset brain template library, where the target image structure and/or the target brain region is included in the second template image.
  • a segmentation module configured to separately perform segmentation processing on the image to be tested according to each second template image, to obtain a second preset number of segmentation images, and fuse the preset number of segmentation images into a target segmentation image
  • the target segmentation image includes a target region, which is a region occupied by the target brain structure and/or the target brain region.
  • the determining module is configured to determine whether the target area is an area occupied by the target brain structure.
  • a first calculating module configured to calculate a volume of the target brain structure if the target area is an area occupied by the target brain structure.
  • a second calculating module configured to calculate a volume of the brain in the target segmentation image, and calculate a ratio of a volume of the target brain structure to a volume of the brain.
  • the obtaining unit further includes:
  • a third calculating module configured to calculate, after the target area is an area occupied by the target brain structure, if the target area is an area occupied by the target brain area, calculate the target brain area Cerebrospinal fluid volume, white matter volume, and gray matter volume.
  • A is the atrophy value of the target brain region
  • V CSF is the cerebrospinal fluid volume in the target brain region
  • V WM is the white matter volume in the target brain region
  • V GM is the target brain region Gray matter volume.
  • the device further includes:
  • a weighting unit configured to calculate a ratio of a volume of the target brain structure to a volume of the brain in the second target magnitude after calculating a percentile of the second target magnitude according to the first target magnitude And the percentile of the atrophy value of the target brain region in the second target magnitude is added according to a preset weight to obtain a total brain atrophy value of the individual to be tested.
  • a result unit configured to obtain a magnitude of brain atrophy of the individual to be tested according to the total brain atrophy value of the test subject.
  • the weighting unit includes:
  • P' is the percentile of the updated second target magnitude
  • P is the percentile of the second target magnitude calculated from the first target magnitude
  • the terminal device 3 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
  • the terminal device may include, but is not limited to, the processor 30 and the memory 31. It will be understood by those skilled in the art that FIG. 3 is merely an example of the terminal device 3, does not constitute a limitation of the terminal device 3, may include more or less components than those illustrated, or combine some components, or different components.
  • the terminal device may further include an input/output device, a network access device, a bus, and the like.
  • the so-called processor 30 can be a central processing unit (Central Processing Unit, CPU), can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the memory 31 may be an internal storage unit of the terminal device 3, such as a hard disk or a memory of the terminal device 3.
  • the memory 31 may also be an external storage device of the terminal device 3, for example, a plug-in hard disk equipped on the terminal device 3, a smart memory card (SMC), and a secure digital (SD). Card, flash card (Flash Card) and so on.
  • the memory 31 may also include both an internal storage unit of the terminal device 3 and an external storage device.
  • the memory 31 is used to store the computer program and other programs and data required by the terminal device.
  • the memory 31 can also be used to temporarily store data that has been output or is about to be output.
  • the disclosed device/terminal device and method may be implemented in other manners.
  • the device/terminal device embodiments described above are merely illustrative.
  • the division of the modules or units is only a logical function division.
  • there may be another division manner for example, multiple units.
  • components may be combined or integrated into another system, or some features may be omitted or not performed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the 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, the present application implements all or part of the processes in the foregoing embodiments, and may also be completed by a computer program to instruct related hardware.
  • the computer program may be stored in a computer readable storage medium. The steps of the various method embodiments described above may be implemented when the program is executed by the processor.
  • the computer program comprises computer program code, which may be in the form of source code, object code form, executable file or some intermediate form.
  • the computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard drive, a magnetic disk, an optical disk, a computer memory, a read only memory (ROM, Read-Only) Memory), random access memory (RAM, Random) Access Memory), electrical carrier signals, telecommunications signals, and software distribution media.
  • ROM Read Only memory
  • RAM Random Access Memory
  • electrical carrier signals telecommunications signals
  • telecommunications signals and software distribution media. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in a jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer readable media It does not include electrical carrier signals and telecommunication signals.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)

Abstract

本申请适用于图像处理技术领域，提供了一种脑萎缩程度的定量检测方法、检测装置及终端设备，包括：获取第一预设数量的第一模板图像以及所述第一模板图像的目标量值，并将所述第一模板图像的目标量值记为第一目标量值，所述第一模板图像为预设年龄的脑健康个体的大脑磁共振图像；获取待测个体的大脑磁共振图像，得到待测图像，并计算所述待测图像的目标量值，得到第二目标量值；根据所述第一目标量值，计算所述第二目标量值的百分位数，得到所述待测个体的脑萎缩程度。通过上述方法，将脑萎缩程度定量化，进而能够实现对脑萎缩程度的有效评估。

Description

一种脑萎缩程度的定量检测方法、检测装置及终端设备 技术领域
本申请涉及图像处理技术领域，尤其涉及一种脑萎缩程度的定量检测方法、检测装置及终端设备。
 背景技术
阿尔茨海默病（Alzheimer’s Disease , AD）是老人痴呆症中最常见的类型，患者主要会出现记忆力，学习和执行能力的下降，使他们失去正常活动的功能。目前导致AD的病因还不明确，但可以肯定的是，脑萎缩是AD的明显病征。
 技术问题
目前，脑萎缩程度的评估大多是根据经验主观判断，缺少简单客观的量化指标。因此，对脑萎缩程度的量化方法的研究，将有助于AD病征的准确判断。
 技术解决方案
有鉴于此，本申请实施例提供了一种脑萎缩程度的定量检测方法、检测装置及终端设备，以解决现有技术中无法有效评估脑萎缩程度的问题。
本申请实施例的第一方面提供了一种脑萎缩程度的定量检测方法，包括：
获取第一预设数量的第一模板图像以及所述第一模板图像的目标量值，并将所述第一模板图像的目标量值记为第一目标量值，所述第一模板图像为预设年龄的脑健康个体的大脑磁共振图像；
获取待测个体的大脑磁共振图像，得到待测图像，并计算所述待测图像的目标量值，得到第二目标量值；
根据所述第一目标量值，计算所述第二目标量值的百分位数，得到所述待测个体的脑萎缩程度。
本申请实施例的第二方面提供了一种脑萎缩程度的定量检测装置，包括：
标记单元，用于获取第一预设数量的第一模板图像以及所述第一模板图像的目标量值，并将所述第一模板图像的目标量值记为第一目标量值，所述第一模板图像为预设年龄的脑健康个体的大脑磁共振图像；
获取单元，用于获取待测个体的大脑磁共振图像，得到待测图像，并计算所述待测图像的目标量值，得到第二目标量值；
计算单元，用于根据所述第一目标量值，计算所述第二目标量值的百分位数，得到所述待测个体的脑萎缩程度。
本申请实施例的第三方面提供了一种终端设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现本申请实施例第一方面提供的所述方法的步骤。
本申请实施例的第四方面提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被一个或多个处理器执行时实现本申请实施例第一方面提供的所述方法的步骤。
 有益效果
本申请实施例通过获取第一预设数量的第一模板图像以及所述第一模板图像的目标量值，并将所述第一模板图像的目标量值记为第一目标量值，所述第一模板图像为预设年龄的脑健康个体的大脑磁共振图像；获取待测个体的大脑磁共振图像，得到待测图像，并计算所述待测图像的目标量值，得到第二目标量值；根据所述第一目标量值，计算所述第二目标量值的百分位数，得到所述待测个体的脑萎缩程度。通过上述方法，将脑萎缩程度定量化，进而能够实现对脑萎缩程度的有效评估。
 附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的脑萎缩程度的定量检测方法的实现流程示意图；
图2是本申请实施例提供的脑萎缩程度的定量检测装置的示意图；
图3是本申请实施例提供的终端设备的示意图；
图4是本申请实施例提供的利用本申请中的脑萎缩程度的定量检测方法计算出的正常组和脑退化组的脑萎缩值对比表；
图5是本申请实施例提供的正常组和脑退化组的全脑萎缩量值的结果图。
 本发明的实施方式
以下描述中，为了说明而不是为了限定，提出了诸如特定系统结构、技术之类的具体细节，以便透彻理解本申请实施例。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本申请。在其它情况中，省略对众所周知的系统、装置、电路以及方法的详细说明，以免不必要的细节妨碍本申请的描述。
应当理解，当在本说明书和所附权利要求书中使用时，术语“包括”指示所描述特征、整体、步骤、操作、元素和/或组件的存在，但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。
还应当理解，在此本申请说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本申请。如在本申请说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。
还应当进一步理解，在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。
如在本说明书和所附权利要求书中所使用的那样，术语“如果”可以依据上下文被解释为“当...时”或“一旦”或“响应于确定”或“响应于检测到”。类似地，短语“如果确定”或“如果检测到[所描述条件或事件]”可以依据上下文被解释为意指“一旦确定”或“响应于确定”或“一旦检测到[所描述条件或事件]”或“响应于检测到[所描述条件或事件]”。
为了说明本申请所述的技术方案，下面通过具体实施例来进行说明。
图1是本申请实施例提供的脑萎缩程度的定量检测方法的实现流程示意图，如图所示，所述方法可以包括以下步骤：
步骤S101，获取第一预设数量的第一模板图像以及所述第一模板图像的目标量值，并将所述第一模板图像的目标量值记为第一目标量值，所述第一模板图像为预设年龄的脑健康个体的大脑磁共振图像。
其中，所述目标量值包括：
目标脑结构的体积与大脑的体积的比值、目标脑区的萎缩值。
所述目标脑结构包括：
海马、杏仁核、侧脑室。
所述目标脑区包括：
脑叶。
所述脑叶包括：
左额叶、右额叶、左枕叶、右枕叶、左顶叶、右顶叶、左颞叶、右颞叶、左扣带回、右扣带回、左岛叶、右岛叶。
示例性的，目标量值包括：
海马的体积与大脑的体积的比值、杏仁核的体积与大脑的体积的比值、侧脑室的体积与大脑的体积的比值；
左额叶的萎缩值、右额叶的萎缩值、左枕叶的萎缩值、右枕叶的萎缩值、左顶叶的萎缩值、右顶叶的萎缩值、左颞叶的萎缩值、右颞叶的萎缩值、左扣带回的萎缩值、右扣带回的萎缩值、左岛叶的萎缩值、右岛叶的萎缩值。
其中，第一预设数量可以是人为设定的，只要保证有足够多的目标量值即可。每个第一模板图像可能有全部的目标量值，也可能有一个或其中几个目标量值。示例性的，获取3个第一模板图像A、B、C，A有15个目标量值分别为海马的体积与大脑的体积的比值、杏仁核的体积与大脑的体积的比值、侧脑室的体积与大脑的体积的比值、左额叶的萎缩值、右额叶的萎缩值、左枕叶的萎缩值、右枕叶的萎缩值、左顶叶的萎缩值、右顶叶的萎缩值、左颞叶的萎缩值、右颞叶的萎缩值、左扣带回的萎缩值、右扣带回的萎缩值、左岛叶的萎缩值、右岛叶的萎缩值；B有2个目标量值分别为海马的体积与大脑的体积的比值、左额叶的萎缩值；C有1个目标量值为海马的体积与大脑的体积的比值。那么第一目标量值共有18个，其中3个海马的体积与大脑的体积的比值，2个左额叶的萎缩值。
预设年龄可以指一个具体的年龄，也可以指一个年龄段。如果预设年龄是一个具体的年龄，则预设年龄为待测个体的年龄；如果预设年龄是一个年龄段，则预设年龄是待测个体的年龄所在的年龄段，具体的年龄段划分可以是人为预先设定的。采用预设年龄的脑健康个体的大脑磁共振图像作为第一模板图像，将待测个体与其同龄脑健康个体的脑萎缩程度作对比，可以更准确地评估待测个体的脑萎缩程度。
在实际应用中，可以从预设脑模板库中获取第一模板图像及第一模板图像的目标量值，即预设脑模板库中存储有各年龄脑正常个体的磁共振图像及这些图像的目标量值；还可以从预设脑模板库中获取第一模板图像，再分别计算每个第一模板图像的目标量值，即预设脑模板库中只存储有各年龄脑正常个体的磁共振图像。计算每个第一模板图像的目标量值的方法与计算待测图像的目标量值的方法相同，可以参见步骤S102中的具体描述。有研究发现，大脑的结构会随着年龄增加而变化的，正常老年人随着年龄增加，大脑中的灰质体积会出现减少，而变化通常会在55岁后出现得最明显。因此，了解老年人正常的脑部变化有助于识别出现脑萎缩迹象的人。所以，在实际应用中，预设脑模板库中只需要收集40~90岁的脑正常个体的磁共振图像即可。
步骤S102，获取待测个体的大脑磁共振图像，得到待测图像，并计算所述待测图像的目标量值，得到第二目标量值。
其中，每个待测图像可以对应一个第二目标量值，也可以对应多个第二目标量值。
在一个实施例中，所述计算所述待测图像的目标量值，包括：
从预设脑模板库中获取第二预设数量的第二模板图像，所述第二模板图像中包含所述目标脑结构和/或所述目标脑区。
分别根据每个第二模板图像对所述待测图像进行分割处理，得到第二预设数量的分割图像，并将所述预设数量的分割图像融合成目标分割图像，所述目标分割图像中包含目标区域，所述目标区域为所述目标脑结构和/或所述目标脑区所占的区域。
判断所述目标区域是否为所述目标脑结构所占的区域。
若所述目标区域为所述目标脑结构所占的区域，则计算所述目标脑结构的体积。
计算所述目标分割图像中大脑的体积，并计算所述目标脑结构的体积与所述大脑的体积的比值。
在一个实施例中，所述计算所述待测图像的目标量值，还包括：
在判断所述目标区域是否为所述目标脑结构所占的区域之后，若所述目标区域为所述目标脑区所占的区域，则计算所述目标脑区内的脑脊液体积、脑白质体积和脑灰质体积。
通过A＝V CSF/(V WM+V GM)计算所述目标脑区的萎缩值。
其中，A为所述目标脑区的萎缩值，V CSF为所述目标脑区内的脑脊液体积，V WM为所述目标脑区内的脑白质体积，V GM为所述目标脑区内的脑灰质体积。
在实际应用中，预设脑模板库中可以存储有大量的脑结构有差异的大脑的磁共振图像。根据每个第二模板图像对待测图像进行分割处理，再将得到的所有分割图像融合成一个目标图像，利用这样的方法，综合考虑了各种有差异的脑结构，使得分割结果更加精确。具体的，根据每个第二模板图像对待测图像进行分割处理可以包括以下步骤：
将所述第二模板图像映射到待测图像上，并计算第二模板图像与待测图像的坐标转换关系。
根据所述坐标转换关系，将第二模板图像中的目标脑结构和/或目标脑区所占的区域映射到待测图像上，在待检图像上得到目标区域。
对待测图像中的目标区域进行标记，得到分割图像。
在实际应用中，第二模板图像上可以包含一个或多个目标脑结构，也可以包含一个或多个目标脑区，还可以既包含目标脑结构又包含目标脑区。只需要保证能够利用第二模板图像在待测图像中分割出需要的目标脑结构、目标脑区即可，换句话说，需要保证待测图像的目标分割图像中包含有与第一模板图像的目标量值对应的目标脑结构，且包含有与第一模板图像的目标量值对应的目标脑区。示例性的，第一模板图像的目标量值有海马的体积与大脑的体积的比值、左额叶的萎缩值，那么待测图像的目标分割图像中需要有海马所占的区域、左额叶所占的区域。
在实际应用中，一些脑结构（如海马、杏仁核、侧脑室，即目标脑结构）的体积与大脑总体积的体积比值能够反映脑退化程度，而一些脑区（如脑叶，包括12个脑叶分区，即目标脑区）的萎缩值能够反映脑退化程度。所以，在对待测图像进行分割处理得到目标分割图像之后，还需要区分目标分割图像中的目标区域为目标脑结构所占的区域还是目标脑区所占的区域；若为目标脑结构所占的区域，则需要计算目标脑结构的体积、大脑的体积，以得到目标脑结构的体积与大脑的体积的比值；若为目标脑区所占的区域，则需要计算目标脑区内的脑脊液体积、脑白质体积和脑灰质体积，以得到目标脑区的萎缩值。
步骤S103，根据所述第一目标量值，计算所述第二目标量值的百分位数，得到所述待测个体的脑萎缩程度。
其中，如果将一组数据从小到大排序，并计算相应的累计百分位，则某一百分位所对应数据的值就称为这一百分位的百分位数。可表示为：一组n个观测值按数值大小排列。如，处于p%位置的值称第p百分位数。
在一个实施例中，在将所述第一模板图像的目标量值记为第一目标量值之后，还包括：
计算所述第一目标量值的均值和方差。
在一个实施例中，所述根据所述第一目标量值，计算所述第二目标量值的百分位数，包括：
通过z=(x-μ)/σ，将所述第二目标量值标准化，得到所述第二目标量值的标准化量值。
从预设对应关系表中查找所述第二目标量值的标准化量值对应的百分位数。
其中，z为所述第二目标量值的标准化量值，x为所述第二目标量值，μ为所述第一目标量值的均值，σ为所述第一目标量值的方差。
在实际应用中，计算第一目标量值的均值和方差是指，将所有第一模板图像的第一目标量值进行统计、分类，分别计算第一目标量值中每一类量值的均值和方差，然后再将第二目标量值进行统计、分类，在第一目标量值中分别找出与第二目标量值中的每一类量值对应的那一类量值，再通过z=(x-μ)/σ分别将第二目标量值中的每一类量值标准化。
预设对应关系表可以是人为预先设定的，用来记录z值和百分位数的对应关系的表。
示例性的，假设第一目标量值共包含300个量值，300个量值共分为2类，第一类量值为海马的体积与大脑的体积的比值，共有100个；第二类量值为左额叶的萎缩值，共有200个。则需要计算100个第一类量值的均值和方差，还要计算200个第二类量值的均值和方差。根据第一目标量值中第一类量值的均值和方差对第二目标量值中的海马的体积与大脑的体积的比值进行标准化（假设计算出的第一类量值的标准化量值为50），根据第一目标量值中的第二类量值的均值和方差对第二目标量值中的左额叶的萎缩值进行标准化（假设计算出的第二类量值的标准化量值为70）根据预设对应表，可以查出，第一类量值的标准化量值50对应的百分位数为50%，第二类量值的标准化量值70对应的百分位数为70%。这样，就实现了对脑萎缩程度的定量评估。需要说明的是，上述只是脑萎缩程度定量计算的一个示例，并不对量值的个数、百分位数对应表做具体限定。
在一个实施例中，在根据所述第一目标量值，计算所述第二目标量值的百分位数之后，还包括：
将所述第二目标量值中目标脑结构的体积与大脑的体积的比值的百分位数、所述第二目标量值中目标脑区的萎缩值的百分位数按照预设权重相加，得到所述待测个体的全脑萎缩量值。
根据所述待测个体的全脑萎缩量值，得到所述待测个体的脑萎缩程度量值。
在一个实施例中，当所述目标脑结构为海马或杏仁核时，在将所述第二目标量值中目标脑结构的体积与大脑的体积的比值的百分位数、所述第二目标量值中目标脑区的萎缩值的百分位数按照预设权重相加之前，还包括：
通过P’=100-P更新所述第二目标量值的百分位；
其中，P’为更新后的所述第二目标量值的百分位数，P为根据所述第一目标量值计算出的所述第二目标量值的百分位数。
在实际应用中，为了使脑萎缩程度的定量评估更精确，需要将所有的第二目标量值的百分位数进行加权求和。预设权重可以是根据大量实验的经验人为预先设定的。示例性的，假设第二目标量值的百分位数分别为：海马的体积与大脑的体积的比值的百分位数为50%，杏仁核的体积与大脑的体积的比值的百分位数为40%、侧脑室的体积与大脑的体积的比值的体积比的百分位数为45%、左额叶的萎缩值的百分位数为30%、右额叶的萎缩值的百分位数为30%、左枕叶的萎缩值的百分位数为30%、右枕叶的萎缩值的百分位数为30%、左顶叶的萎缩值的百分位数为30%、右顶叶的萎缩值的百分位数为30%、左颞叶的萎缩值的百分位数为20%、右颞叶的萎缩值的百分位数为20%、左扣带回的萎缩值的百分位数为20%、右扣带回的萎缩值的百分位数为20%、左岛叶的萎缩值的百分位数为20%、右岛叶的萎缩值的百分位数为20%。假设预设权重均为1/15，则将上述第二目标量值按照预设权重进行加权求和，得到的全脑萎缩量为12.8%。需要说明的是，此处只是如何计算全脑萎缩量的一个示例，并不做具体限定。
在实际应用中，由于海马和杏仁核的体积与大脑的体积的比值是脑萎缩程度越大，体积的比值越小，而侧脑室的体积与大脑的体积的比值及各脑叶脑萎缩值是脑萎缩程度越大，其值越大。因此，在加权和的时候需将海马和杏仁核与大脑的体积比的百分位数变为(100-p)。
参见图4和图5，图4是本申请实施例提供的利用本申请中的脑萎缩程度的定量检测方法计算出的正常组和脑退化组的脑萎缩值对比表，图5是本申请实施例提供的正常组和脑退化组的全脑萎缩量值的结果图。图4和图5是根据收集的79个脑正常个体和69个脑退化患者的磁共振图像得到的实验结果。如图所示，脑正常个体与脑退化患者的全脑脑萎缩值存在显著差异，因此可以表明全脑萎缩量值是评估脑萎缩程度的一个很好的指标。
本申请实施例通过获取第一预设数量的第一模板图像以及所述第一模板图像的目标量值，并将所述第一模板图像的目标量值记为第一目标量值，所述第一模板图像为预设年龄的脑健康个体的大脑磁共振图像；获取待测个体的大脑磁共振图像，得到待测图像，并计算所述待测图像的目标量值，得到第二目标量值；根据所述第一目标量值，计算所述第二目标量值的百分位数，得到所述待测个体的脑萎缩程度。通过上述方法，将脑萎缩程度定量化，进而能够实现对脑萎缩程度的有效评估。
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
图2是本申请实施例提供的脑萎缩程度的定量检测装置的示意图，为了便于说明，仅示出与本申请实施例相关的部分。
图2所示的脑萎缩程度的定量检测装置可以是内置于现有的终端设备内的软件单元、硬件单元、或软硬结合的单元，也可以作为独立的挂件集成到所述终端设备中，还可以作为独立的终端设备存在。
所述脑萎缩程度的定量检测装置2包括：
标记单元21，用于获取第一预设数量的第一模板图像以及所述第一模板图像的目标量值，并将所述第一模板图像的目标量值记为第一目标量值，所述第一模板图像为预设年龄的脑健康个体的大脑磁共振图像。
获取单元22，用于获取待测个体的大脑磁共振图像，得到待测图像，并计算所述待测图像的目标量值，得到第二目标量值。
第一计算单元23，用于根据所述第一目标量值，计算所述第二目标量值的百分位数，得到所述待测个体的脑萎缩程度。
可选的，所述装置2还包括：
第二计算单元24，用于在将所述第一模板图像的目标量值记为第一目标量值之后，计算所述第一目标量值的均值和方差。
可选的，所述第一计算单元23包括：
标准化模块，用于通过z=(x-μ)/σ，将所述第二目标量值标准化，得到所述第二目标量值的标准化量值。
查找模块，用于从预设对应关系表中查找所述第二目标量值的标准化量值对应的百分位数。
其中，z为所述第二目标量值的标准化量值，x为所述第二目标量值，μ为所述第一目标量值的均值，σ为所述第一目标量值的方差。
其中，所述目标量值包括：
目标脑结构与大脑的体积比、目标脑区的萎缩值。
所述目标脑结构包括：
海马、杏仁核、侧脑室。
所述目标脑区包括：
脑叶。
所述脑叶包括：
左额叶、右额叶、左枕叶、右枕叶、左顶叶、右顶叶、左颞叶、右颞叶、左扣带回、右扣带回、左岛叶、右岛叶。
可选的，所述获取单元22包括：
获取模块，用于从预设脑模板库中获取第二预设数量的第二模板图像，所述第二模板图像中包含所述目标脑结构和/或所述目标脑区。
分割模块，用于分别根据每个第二模板图像对所述待测图像进行分割处理，得到第二预设数量的分割图像，并将所述预设数量的分割图像融合成目标分割图像，所述目标分割图像中包含目标区域，所述目标区域为所述目标脑结构和/或所述目标脑区所占的区域。
判断模块，用于判断所述目标区域是否为所述目标脑结构所占的区域。
第一计算模块，用于若所述目标区域为所述目标脑结构所占的区域，则计算所述目标脑结构的体积。
第二计算模块，用于计算所述目标分割图像中大脑的体积，并计算所述目标脑结构的体积与所述大脑的体积的比值。
可选的，所述获取单元22还包括：
第三计算模块，用于在判断所述目标区域是否为所述目标脑结构所占的区域之后，若所述目标区域为所述目标脑区所占的区域，则计算所述目标脑区内的脑脊液体积、脑白质体积和脑灰质体积。
第四计算模块，用于通过A＝V CSF/(V WM+V GM)计算所述目标脑区的萎缩值。
其中，A为所述目标脑区的萎缩值，V CSF为所述目标脑区内的脑脊液体积，V WM为所述目标脑区内的脑白质体积，V GM为所述目标脑区内的脑灰质体积。
可选的，所述装置2还包括：
加权单元25，用于在根据所述第一目标量值，计算所述第二目标量值的百分位数之后，将所述第二目标量值中目标脑结构的体积与大脑的体积的比值的百分位数、所述第二目标量值中目标脑区的萎缩值的百分位数按照预设权重相加，得到所述待测个体的全脑萎缩量值。
结果单元26，用于根据所述待测个体的全脑萎缩量值，得到所述待测个体的脑萎缩程度量值。
可选的，所述加权单元25包括：
更新模块，用于当所述目标脑结构为海马或杏仁核时，在将所述第二目标量值中目标脑结构的体积与大脑的体积的比值的百分位数、所述第二目标量值中目标脑区的萎缩值的百分位数按照预设权重相加之前，通过P’=100-P更新所述第二目标量值的百分位。
其中，P’为更新后的所述第二目标量值的百分位数，P为根据所述第一目标量值计算出的所述第二目标量值的百分位数。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将所述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上述系统中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
图3是本申请实施例提供的终端设备的示意图。如图3所示，该实施例的终端设备3包括：处理器30、存储器31以及存储在所述存储器31中并可在所述处理器30上运行的计算机程序32。所述处理器30执行所述计算机程序32时实现上述各个脑萎缩程度的定量检测方法实施例中的步骤，例如图1所示的步骤S101至S103。或者，所述处理器30执行所述计算机程序32时实现上述各装置实施例中各模块/单元的功能，例如图2所示模块21至26的功能。
示例性的，所述计算机程序32可以被分割成一个或多个模块/单元，所述一个或者多个模块/单元被存储在所述存储器31中，并由所述处理器30执行，以完成本申请。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序32在所述终端设备3中的执行过程。例如，所述计算机程序32可以被分割成标记单元、获取单元、第一计算单元，各单元具体功能如下：
标记单元，用于获取第一预设数量的第一模板图像以及所述第一模板图像的目标量值，并将所述第一模板图像的目标量值记为第一目标量值，所述第一模板图像为预设年龄的脑健康个体的大脑磁共振图像。
获取单元，用于获取待测个体的大脑磁共振图像，得到待测图像，并计算所述待测图像的目标量值，得到第二目标量值。
第一计算单元，用于根据所述第一目标量值，计算所述第二目标量值的百分位数，得到所述待测个体的脑萎缩程度。
可选的，所述装置还包括：
第二计算单元，用于在将所述第一模板图像的目标量值记为第一目标量值之后，计算所述第一目标量值的均值和方差。
可选的，所述第一计算单元包括：
标准化模块，用于通过z=(x-μ)/σ，将所述第二目标量值标准化，得到所述第二目标量值的标准化量值。
查找模块，用于从预设对应关系表中查找所述第二目标量值的标准化量值对应的百分位数。
其中，z为所述第二目标量值的标准化量值，x为所述第二目标量值，μ为所述第一目标量值的均值，σ为所述第一目标量值的方差。
其中，所述目标量值包括：
目标脑结构的体积与大脑的体积的比值、目标脑区的萎缩值。
所述目标脑结构包括：
海马、杏仁核、侧脑室。
所述目标脑区包括：
脑叶。
所述脑叶包括：
左额叶、右额叶、左枕叶、右枕叶、左顶叶、右顶叶、左颞叶、右颞叶、左扣带回、右扣带回、左岛叶、右岛叶。
可选的，所述获取单元包括：
获取模块，用于从预设脑模板库中获取第二预设数量的第二模板图像，所述第二模板图像中包含所述目标脑结构和/或所述目标脑区。
分割模块，用于分别根据每个第二模板图像对所述待测图像进行分割处理，得到第二预设数量的分割图像，并将所述预设数量的分割图像融合成目标分割图像，所述目标分割图像中包含目标区域，所述目标区域为所述目标脑结构和/或所述目标脑区所占的区域。
判断模块，用于判断所述目标区域是否为所述目标脑结构所占的区域。
第一计算模块，用于若所述目标区域为所述目标脑结构所占的区域，则计算所述目标脑结构的体积。
第二计算模块，用于计算所述目标分割图像中大脑的体积，并计算所述目标脑结构的体积与所述大脑的体积的比值。
可选的，所述获取单元还包括：
第三计算模块，用于在判断所述目标区域是否为所述目标脑结构所占的区域之后，若所述目标区域为所述目标脑区所占的区域，则计算所述目标脑区内的脑脊液体积、脑白质体积和脑灰质体积。
第四计算模块，用于通过A＝V CSF/(V WM+V GM)计算所述目标脑区的萎缩值。
其中，A为所述目标脑区的萎缩值，V CSF为所述目标脑区内的脑脊液体积，V WM为所述目标脑区内的脑白质体积，V GM为所述目标脑区内的脑灰质体积。
可选的，所述装置还包括：
加权单元，用于在根据所述第一目标量值，计算所述第二目标量值的百分位数之后，将所述第二目标量值中目标脑结构的体积与大脑的体积的比值的百分位数、所述第二目标量值中目标脑区的萎缩值的百分位数按照预设权重相加，得到所述待测个体的全脑萎缩量值。
结果单元，用于根据所述待测个体的全脑萎缩量值，得到所述待测个体的脑萎缩程度量值。
可选的，所述加权单元包括：
更新模块，用于当所述目标脑结构为海马或杏仁核时，在将所述第二目标量值中目标脑结构的体积与大脑的体积的比值的百分位数、所述第二目标量值中目标脑区的萎缩值的百分位数按照预设权重相加之前，通过 P’=100-P更新所述第二目标量值的百分位。
其中，P’为更新后的所述第二目标量值的百分位数，P为根据所述第一目标量值计算出的所述第二目标量值的百分位数。
所述终端设备3可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。所述终端设备可包括，但不仅限于，处理器30、存储器31。本领域技术人员可以理解，图3仅仅是终端设备3的示例，并不构成对终端设备3的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述终端设备还可以包括输入输出设备、网络接入设备、总线等。
所称处理器30可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器 (Digital Signal Processor，DSP)、专用集成电路 (Application Specific Integrated Circuit，ASIC)、现成可编程门阵列 (Field-Programmable Gate Array，FPGA) 或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
所述存储器31可以是所述终端设备3的内部存储单元，例如终端设备3的硬盘或内存。所述存储器31也可以是所述终端设备3的外部存储设备，例如所述终端设备3上配备的插接式硬盘，智能存储卡（Smart Media Card, SMC），安全数字（Secure Digital, SD）卡，闪存卡（Flash Card）等。进一步地，所述存储器31还可以既包括所述终端设备3的内部存储单元也包括外部存储设备。所述存储器31用于存储所述计算机程序以及所述终端设备所需的其他程序和数据。所述存储器31还可以用于暂时地存储已经输出或者将要输出的数据。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
在本申请所提供的实施例中，应该理解到，所揭露的装置/终端设备和方法，可以通过其它的方式实现。例如，以上所描述的装置/终端设备实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口，装置或单元的间接耦合或通讯连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，所述计算机程序包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器（ROM，Read-Only Memory）、随机存取存储器（RAM，Random Access Memory）、电载波信号、电信信号以及软件分发介质等。需要说明的是，所述计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读介质不包括是电载波信号和电信信号。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (16)

  1. 一种脑萎缩程度的定量检测方法，其特征在于，包括：
    获取第一预设数量的第一模板图像以及所述第一模板图像的目标量值，并将所述第一模板图像的目标量值记为第一目标量值，所述第一模板图像为预设年龄的脑健康个体的大脑磁共振图像；
    获取待测个体的大脑磁共振图像，得到待测图像，并计算所述待测图像的目标量值，得到第二目标量值；
    根据所述第一目标量值，计算所述第二目标量值的百分位数，得到所述待测个体的脑萎缩程度。
  2. 如权利要求1所述的脑萎缩程度的定量检测方法，其特征在于，在将所述第一模板图像的目标量值记为第一目标量值之后，还包括：
    计算所述第一目标量值的均值和方差；
    所述根据所述第一目标量值，计算所述第二目标量值的百分位数，包括：
    通过z=(x-μ)/σ，将所述第二目标量值标准化，得到所述第二目标量值的标准化量值；
    从预设对应关系表中查找所述第二目标量值的标准化量值对应的百分位数；
    其中，z为所述第二目标量值的标准化量值，x为所述第二目标量值，μ为所述第一目标量值的均值，σ为所述第一目标量值的方差。
  3. 如权利要求1所述的脑萎缩程度的定量检测方法，其特征在于，所述目标量值包括：
    目标脑结构的体积与大脑的体积的比值、目标脑区的萎缩值；
    所述目标脑结构包括：
    海马、杏仁核、侧脑室；
    所述目标脑区包括：
    脑叶；
    所述脑叶包括：
    左额叶、右额叶、左枕叶、右枕叶、左顶叶、右顶叶、左颞叶、右颞叶、左扣带回、右扣带回、左岛叶、右岛叶。
  4. 如权利要求3所述的脑萎缩程度的定量检测方法，其特征在于，所述计算所述待测图像的目标量值，包括：
    从预设脑模板库中获取第二预设数量的第二模板图像，所述第二模板图像中包含所述目标脑结构和/或所述目标脑区；
    分别根据每个第二模板图像对所述待测图像进行分割处理，得到第二预设数量的分割图像，并将所述预设数量的分割图像融合成目标分割图像，所述目标分割图像中包含目标区域，所述目标区域为所述目标脑结构和/或所述目标脑区所占的区域；
    判断所述目标区域是否为所述目标脑结构所占的区域；
    若所述目标区域为所述目标脑结构所占的区域，则计算所述目标脑结构的体积；
    计算所述目标分割图像中大脑的体积，并计算所述目标脑结构的体积与所述大脑的体积的比值。
  5. 如权利要求4所述的脑萎缩程度的定量检测方法，其特征在于，所述计算所述待测图像的目标量值，还包括：
    在判断所述目标区域是否为所述目标脑结构所占的区域之后，若所述目标区域为所述目标脑区所占的区域，则计算所述目标脑区内的脑脊液体积、脑白质体积和脑灰质体积；
    通过A＝V CSF/(V WM+V GM)计算所述目标脑区的萎缩值；
    其中，A为所述目标脑区的萎缩值，V CSF为所述目标脑区内的脑脊液体积，V WM为所述目标脑区内的脑白质体积，V GM为所述目标脑区内的脑灰质体积。
  6. 如权利要求5所述的脑萎缩程度的定量检测方法，其特征在于，在根据所述第一目标量值，计算所述第二目标量值的百分位数之后，还包括：
    将所述第二目标量值中目标脑结构的体积与大脑的体积的比值的百分位数、所述第二目标量值中目标脑区的萎缩值的百分位数按照预设权重相加，得到所述待测个体的全脑萎缩量值；
    根据所述待测个体的全脑萎缩量值，得到所述待测个体的脑萎缩程度量值。
  7. 如权利要求6所述的脑萎缩程度的定量检测方法，其特征在于，当所述目标脑结构为海马或杏仁核时，在将所述第二目标量值中目标脑结构的体积与大脑的体积的比值的百分位数、所述第二目标量值中目标脑区的萎缩值的百分位数按照预设权重相加之前，还包括：
    通过P’=100-P更新所述第二目标量值的百分位；
    其中，P’为更新后的所述第二目标量值的百分位数，P为根据所述第一目标量值计算出的所述第二目标量值的百分位数。
  8. 一种脑萎缩程度的定量检测装置，其特征在于，包括：
    标记单元，用于获取第一预设数量的第一模板图像以及所述第一模板图像的目标量值，并将所述第一模板图像的目标量值记为第一目标量值，所述第一模板图像为预设年龄的脑健康个体的大脑磁共振图像；
    获取单元，用于获取待测个体的大脑磁共振图像，得到待测图像，并计算所述待测图像的目标量值，得到第二目标量值；
    计算单元，用于根据所述第一目标量值，计算所述第二目标量值的百分位数，得到所述待测个体的脑萎缩程度。
  9. 如权利要求8所述的脑萎缩程度的定量检测装置，其特征在于，还包括：
    第二计算单元，用于在将所述第一模板图像的目标量值记为第一目标量值之后，计算所述第一目标量值的均值和方差；
    所述第一计算单元包括：
    标准化模块，用于通过z=(x-μ)/σ，将所述第二目标量值标准化，得到所述第二目标量值的标准化量值；
    查找模块，用于从预设对应关系表中查找所述第二目标量值的标准化量值对应的百分位数；
    其中，z为所述第二目标量值的标准化量值，x为所述第二目标量值，μ为所述第一目标量值的均值，σ为所述第一目标量值的方差。
  10. 如权利要求8所述的脑萎缩程度的定量检测装置，其特征在于，所述目标量值包括：
    目标脑结构与大脑的体积比、目标脑区的萎缩值；
    所述目标脑结构包括：
    海马、杏仁核、侧脑室；
    所述目标脑区包括：
    脑叶；
    所述脑叶包括：
    左额叶、右额叶、左枕叶、右枕叶、左顶叶、右顶叶、左颞叶、右颞叶、左扣带回、右扣带回、左岛叶、右岛叶。
  11. 如权利要求10所述的脑萎缩程度的定量检测装置，其特征在于，述获取单元包括：
    获取模块，用于从预设脑模板库中获取第二预设数量的第二模板图像，所述第二模板图像中包含所述目标脑结构和/或所述目标脑区；
    分割模块，用于分别根据每个第二模板图像对所述待测图像进行分割处理，得到第二预设数量的分割图像，并将所述预设数量的分割图像融合成目标分割图像，所述目标分割图像中包含目标区域，所述目标区域为所述目标脑结构和/或所述目标脑区所占的区域；
    判断模块，用于判断所述目标区域是否为所述目标脑结构所占的区域；
    第一计算模块，用于若所述目标区域为所述目标脑结构所占的区域，则计算所述目标脑结构的体积；
    第二计算模块，用于计算所述目标分割图像中大脑的体积，并计算所述目标脑结构的体积与所述大脑的体积的比值。
  12. 如权利要求11所述的脑萎缩程度的定量检测装置，其特征在于，所述获取单元还包括：
    第三计算模块，用于在判断所述目标区域是否为所述目标脑结构所占的区域之后，若所述目标区域为所述目标脑区所占的区域，则计算所述目标脑区内的脑脊液体积、脑白质体积和脑灰质体积；
    第四计算模块，用于通过A＝V CSF/(V WM+V GM)计算所述目标脑区的萎缩值；
    其中，A为所述目标脑区的萎缩值，V CSF为所述目标脑区内的脑脊液体积，V WM为所述目标脑区内的脑白质体积，V GM为所述目标脑区内的脑灰质体积。
  13. 如权利要求12所述的脑萎缩程度的定量检测装置，其特征在于，还包括：
    加权单元，用于在根据所述第一目标量值，计算所述第二目标量值的百分位数之后，将所述第二目标量值中目标脑结构的体积与大脑的体积的比值的百分位数、所述第二目标量值中目标脑区的萎缩值的百分位数按照预设权重相加，得到所述待测个体的全脑萎缩量值；
    结果单元，用于根据所述待测个体的全脑萎缩量值，得到所述待测个体的脑萎缩程度量值。
  14. 如权利要求13所述的脑萎缩程度的定量检测装置，其特征在于，所述加权单元包括：
    更新模块，用于当所述目标脑结构为海马或杏仁核时，在将所述第二目标量值中目标脑结构的体积与大脑的体积的比值的百分位数、所述第二目标量值中目标脑区的萎缩值的百分位数按照预设权重相加之前，通过P’=100-P更新所述第二目标量值的百分位；
    其中，P’为更新后的所述第二目标量值的百分位数，P为根据所述第一目标量值计算出的所述第二目标量值的百分位数。
  15. 一种终端设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至7任一项所述方法的步骤。
  16. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至7任一项所述方法的步骤。
PCT/CN2019/087946 2018-05-11 2019-05-22 一种脑萎缩程度的定量检测方法、检测装置及终端设备 WO2019214750A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810446410.7 2018-05-11
CN201810446410.7A CN108830830A (zh) 2018-05-11 2018-05-11 一种脑萎缩程度的定量检测方法、检测装置及终端设备

Publications (1)

Publication Number Publication Date
WO2019214750A1 true WO2019214750A1 (zh) 2019-11-14

Family

ID=64147890

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/087946 WO2019214750A1 (zh) 2018-05-11 2019-05-22 一种脑萎缩程度的定量检测方法、检测装置及终端设备

Country Status (2)

Country Link
CN (1) CN108830830A (zh)
WO (1) WO2019214750A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108830830A (zh) * 2018-05-11 2018-11-16 深圳博脑医疗科技有限公司 一种脑萎缩程度的定量检测方法、检测装置及终端设备
CN110232708B (zh) * 2019-05-14 2021-04-30 深圳博脑医疗科技有限公司 海马硬化程度的定量计算方法、装置、介质及终端设备
CN110334604A (zh) * 2019-06-06 2019-10-15 广州金域医学检验中心有限公司 细胞展示方法、装置、计算机设备和计算机可读存储介质
CN110473171A (zh) * 2019-07-18 2019-11-19 上海联影智能医疗科技有限公司 脑龄检测方法、计算机设备和存储介质
CN112529868B (zh) * 2020-12-10 2023-06-27 上海联影医疗科技股份有限公司 图像分析方法、装置、计算机设备和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6366797B1 (en) * 1998-08-25 2002-04-02 The Cleveland Clinic Foundation Method and system for brain volume analysis
CN106659424A (zh) * 2014-09-25 2017-05-10 大日本印刷株式会社 医用图像显示处理方法、医用图像显示处理装置及程序
CN107103612A (zh) * 2017-03-28 2017-08-29 深圳博脑医疗科技有限公司 自动化分区域脑萎缩程度的定量计算方法
US9808175B1 (en) * 2009-02-02 2017-11-07 Parexel International Corporation Method and system for analyzing images to quantify brain atrophy
CN108830830A (zh) * 2018-05-11 2018-11-16 深圳博脑医疗科技有限公司 一种脑萎缩程度的定量检测方法、检测装置及终端设备

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2570539A1 (en) * 2004-06-18 2006-01-26 Banner Health Evaluation of a treatment to decrease the risk of a progressive brain disorder or to slow brain aging
JP5243865B2 (ja) * 2008-07-07 2013-07-24 浜松ホトニクス株式会社 脳疾患診断システム
CN101739681B (zh) * 2009-12-14 2011-09-14 西北工业大学 基于相关预测模型的磁共振图像中检测结构形变的方法
WO2011130355A1 (en) * 2010-04-13 2011-10-20 Baxter International Inc. Use of ventricular enlargement rate in intravenous immunoglobulin treatment of alzheimer's disease
DE102011085404A1 (de) * 2011-10-28 2013-05-02 Siemens Aktiengesellschaft Verfahren zur Vermessung von Strukturen des menschlichen Gehirns

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6366797B1 (en) * 1998-08-25 2002-04-02 The Cleveland Clinic Foundation Method and system for brain volume analysis
US9808175B1 (en) * 2009-02-02 2017-11-07 Parexel International Corporation Method and system for analyzing images to quantify brain atrophy
CN106659424A (zh) * 2014-09-25 2017-05-10 大日本印刷株式会社 医用图像显示处理方法、医用图像显示处理装置及程序
CN107103612A (zh) * 2017-03-28 2017-08-29 深圳博脑医疗科技有限公司 自动化分区域脑萎缩程度的定量计算方法
CN108830830A (zh) * 2018-05-11 2018-11-16 深圳博脑医疗科技有限公司 一种脑萎缩程度的定量检测方法、检测装置及终端设备

Also Published As

Publication number Publication date
CN108830830A (zh) 2018-11-16

Similar Documents

Publication Publication Date Title
WO2019214750A1 (zh) 一种脑萎缩程度的定量检测方法、检测装置及终端设备
Zhan et al. Comparison of nine tractography algorithms for detecting abnormal structural brain networks in Alzheimer’s disease
Westman et al. Multivariate analysis of MRI data for Alzheimer's disease, mild cognitive impairment and healthy controls
Lebedev et al. Random Forest ensembles for detection and prediction of Alzheimer's disease with a good between-cohort robustness
Hosmer et al. Confidence interval estimates of an index of quality performance based on logistic regression models
US10891444B2 (en) Automated generation of sentence-based descriptors from imaging data
Bourgeat et al. β-Amyloid burden in the temporal neocortex is related to hippocampal atrophy in elderly subjects without dementia
Doan et al. Dissociable diffusion MRI patterns of white matter microstructure and connectivity in Alzheimer’s disease spectrum
Bullmore et al. Fractal analysis of the boundary between white matter and cerebral cortex in magnetic resonance images: a controlled study of schizophrenic and manic-depressive patients
US10074173B2 (en) Methods and systems for analyzing anatomy from multiple granularity levels
Leung et al. A three-stage, deep learning, ensemble approach for prognosis in patients with Parkinson’s disease
Li et al. Nonparametric and semiparametric estimation of the three way receiver operating characteristic surface
CN110337670B (zh) 一种基于磁共振图像的脑龄测试方法及脑龄测试装置
CN110840468A (zh) 自闭症风险评估方法及装置、终端设备、存储介质
Al-Adhaileh Diagnosis and classification of Alzheimer's disease by using a convolution neural network algorithm
CN105229471A (zh) 用于基于生物化学标记分析确定先兆子痫风险的系统和方法
CN113366499A (zh) 将群体描述符与经训练模型相关联
Kattem Husøy et al. Diffusion tensor imaging in middle-aged headache sufferers in the general population: a cross-sectional population-based imaging study in the Nord-Trøndelag health study (HUNT-MRI)
US20200167939A1 (en) Brain image normalization apparatus, brain image normalization method, and brain image normalization program
Shin et al. Predictors of abnormal brain computed tomography findings in patients with acute altered mental status in the emergency department
KR20190067477A (ko) 아밀로이드 페트(pet) 영상을 이용한 알츠하이머 치매의 병기 측정 방법 및 장치
WO2015085319A1 (en) Gross feature recognition of anatomical images based on atlas grid
Thacker et al. Dementing disorders: volumetric measurement of cerebrospinal fluid to distinguish normal from pathologic findings—feasibility study
Johansson et al. Diagnostic evaluation of three cardiac software packages using a consecutive group of patients
US20170323176A1 (en) System and Method for an Otitis Media Database Constructing and an Image Analyzing

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19800895

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19800895

Country of ref document: EP

Kind code of ref document: A1