TW202027091A - Method, non-transitory computer-readable media and apparatus for evaluating personalized brain imaging - Google Patents

Abstract

A method for evaluating personalized brain imaging is provided. The method includes the following steps: receiving a first T1 weighted image of a patient's brain; performing a segmentation process on the first T1 weighted image to obtain a first gray matter image; registering the first gray matter image to a standardized normal gray matter image template established by a superimposition procedure; obtaining a score value corresponding to each voxel through a voxel analysis formula based on the first gray matter image registered to the standardized normal gray matter image template; determining whether the score value corresponding to each voxel is greater than or less than an expected value; and deducing the brain regions according to the voxels whose score value is greater than or less than the expected value and outputting an evaluation report. Therefore, the method for evaluating personalized brain imaging can distinguish the difference in brain image between a single patient and healthy subjects under the exclusion of relevant interference factors.

Description

Personalized brain image evaluation method, non-transitory computer readable media and equipment

The present invention relates to a method, non-transitory computer-readable medium and equipment for image evaluation, in particular to a method, non-transient computer-readable medium and equipment for personalized brain image evaluation.

The current statistical analysis method commonly used in images is T-test, which is a many-to-many group analysis, for example: a comparison between a group of patients and a group of healthy people. If this analysis method is applied to a personalized evaluation , It is necessary to treat a single patient as the first group and all other healthy subjects as the second group. However, in the statistical assumptions of the T test, it is necessary to assume that the two groups have the same mean and variance ( variance). Therefore, when applied to individualized assessment, since there is only one person in the first group, there is a problem that does not meet this statistical assumption. In addition, if this analysis method is still applied to personalized evaluation, the statistical model and the number of samples in the database will be insufficient because there is only one person in the first group, which will lead to the problem of decreased sensitivity.

In summary, it can be seen that there is a T test in the prior art, because there is only one person in the first group, the statistical model and the number of samples in the database are insufficient and the sensitivity is reduced. Therefore, it is necessary to propose improved technical means to solve this problem. .

The present invention discloses a method, non-transitory computer-readable medium and equipment for personal brain image evaluation.

，TW為第i個體素對應的評分值，x*為配准至標準化正常灰質影像模板的第一灰質影像之第i個體素的體積大小，

為依據該病人的年齡與性別於資料庫取得預期影像之第i個體素的體積大小，s為依據資料庫取得估計殘差影像之第i個體素的體積標準差，

為T檢定的比例因子，n為建立資料庫的樣本數，i為大於或等於1的正整數； 判斷每一體素對應的評分值是否大於或小於預期值；依據大於或小於預期值的該些體素回推其所屬的腦區，並輸出評估報告。First of all, the present invention discloses a method for personalized brain image evaluation. The steps include: receiving a first T1 weighted image of a patient's brain; performing a tissue segmentation procedure on the first T1 weighted image to obtain the first Gray matter image; register the first gray matter image to the standardized normal gray matter image template created by the superimposition process; obtain each voxel of the first gray matter image registered to the standardized normal gray matter image template according to the voxel analysis formula The corresponding score value, where the voxel analysis formula is

, TW is the score value corresponding to the i-th voxel, x* is the volume of the i-th voxel of the first gray matter image registered to the standardized normal gray matter image template,

To obtain the volume of the i-th voxel of the expected image from the database based on the patient’s age and gender, s is the volume standard deviation of the i-th voxel of the estimated residual image obtained from the database,

Is the scale factor of the T test, n is the number of samples to build the database, and i is a positive integer greater than or equal to 1; judge whether the score value corresponding to each voxel is greater or less than the expected value; based on those greater than or less than the expected value The voxel pushes back the brain area it belongs to and outputs an evaluation report.

，TW為第i個體素對應的評分值，x*為配准至正常影像模板的第一灰質影像之第i個體素的體積大小，

為依據該病人的年齡與性別於資料庫取得預期影像之第i個體素的體積大小，s為依據資料庫取得估計殘差影像之第i個體素的體積標準差，

為T檢定的比例因子，n為建立資料庫的樣本數，i為大於或等於1的正整數； 判斷每一體素對應的評分值是否大於或小於預期值；依據大於或小於預期值的該些體素回推其所屬的腦區，並輸出評估報告。In addition, the present invention discloses a non-transitory computer-readable medium for personalized brain image evaluation, which is configured to store a number of instructions that, when executed by one or more processors, make the one or more processors Perform the following operations: receive the first T1-weighted image of a patient’s brain; perform a tissue segmentation process on the first T1-weighted image to obtain the first gray matter image; register the first gray matter image to the standardization established by the superimposition process Normal gray matter image template; the first gray matter image registered to the standardized normal gray matter image template obtains the score value corresponding to each voxel it has according to the voxel analysis formula, where the voxel analysis formula is

TW is the score value corresponding to the i-th voxel, and x* is the volume of the i-th voxel of the first gray matter image registered to the normal image template,

To obtain the volume of the i-th voxel of the expected image from the database based on the patient’s age and gender, s is the volume standard deviation of the i-th voxel of the estimated residual image obtained from the database,

Is the scale factor of the T test, n is the number of samples to build the database, and i is a positive integer greater than or equal to 1; judge whether the score value corresponding to each voxel is greater or less than the expected value; based on those greater than or less than the expected value The voxel pushes back the brain area it belongs to and outputs an evaluation report.

，TW為第i個體素對應的評分值，x*為配准至標準化正常灰質影像模板的第一灰質影像之第i個體素的體積大小，

為依據該病人的年齡與性別於資料庫取得預期影像之第i個體素的體積大小，s為依據資料庫取得估計殘差影像之第i個體素的體積標準差，

為T檢定的比例因子，n為建立資料庫的樣本數，i為大於或等於1的正整數； 判斷每一體素對應的評分值是否大於或小於預期值；依據大於或小於預期值的該些體素回推其所屬的腦區，並輸出評估報告。Furthermore, the present invention discloses a device for personalized brain image evaluation. The device includes: one or more processors, a storage unit, and at least one program, wherein the at least one program is stored in the storage unit and configured to be used by the Executed by one or more processors, the at least one program as a whole includes operating instructions for: receiving a first T1-weighted image of a patient’s brain; performing a tissue segmentation process on the first T1-weighted image to obtain the first gray matter image ; Register the first gray matter image to the standardized normal gray matter image template established by the superimposition process; obtain the first gray matter image registered to the standardized normal gray matter image template according to the voxel analysis formula corresponding to each voxel it has The score value, where the voxel analysis formula is

, TW is the score value corresponding to the i-th voxel, x* is the volume of the i-th voxel of the first gray matter image registered to the standardized normal gray matter image template,

To obtain the volume of the i-th voxel of the expected image from the database based on the patient’s age and gender, s is the volume standard deviation of the i-th voxel of the estimated residual image obtained from the database,

Is the scale factor of the T test, n is the number of samples to build the database, and i is a positive integer greater than or equal to 1; judge whether the score value corresponding to each voxel is greater or less than the expected value; based on those greater than or less than the expected value The voxel pushes back the brain area it belongs to and outputs an evaluation report.

The system and method disclosed in the present invention are as above. The difference from the prior art is that the present invention receives the first T1-weighted image of the patient’s brain; performs a tissue segmentation process on the first T1-weighted image to obtain the first gray matter image; The first gray matter image is registered to the standardized normal gray matter image template created by the superimposing process; the first gray matter image registered to the standardized normal gray matter image template is obtained through the voxel analysis formula to obtain the corresponding score value of each voxel. ; Judge whether the score value corresponding to each voxel is greater than or less than the expected value; and push back the brain area to which it belongs based on the voxels that are greater than or less than the expected value, and output an evaluation report.

Through the above-mentioned technical means, the present invention can know the difference of brain images between a single patient and healthy subjects under the elimination of related interference factors (age factor and gender factor), which is helpful for brain image digitization and detection of naked eyes The subtle changes in brain structure that are imperceptible.

Hereinafter, the implementation of the present invention will be described in detail with the drawings and embodiments, so as to fully understand and implement the implementation process of how the present invention uses technical means to solve technical problems and achieve technical effects. It should be noted that the images described in this case are all three-dimensional images. In order to avoid overly complicated graphics, only two-dimensional images are used to present schematic diagrams of each embodiment. In addition, although the words "first", "second", etc. can be used here to describe various images, these images should not be limited by these words.

，TW為第i個體素對應的評分值，x*為配准至標準化正常灰質影像模板的第一灰質影像之第i個體素的體積大小，

為依據該病人的年齡與性別於資料庫取得預期影像之第i個體素的體積大小，s為依據資料庫取得估計殘差影像之第i個體素的體積標準差，

為T檢定的比例因子，n為建立資料庫的樣本數，i為大於或等於1的正整數（步驟140）；判斷每一體素對應的評分值是否大於或小於預期值；（步驟150）；依據大於或小於預期值的該些體素回推其所屬的腦區，並輸出評估報告（步驟160）。Please refer to "Figure 1". "Figure 1" is a method flow chart of an embodiment of the method for personalized brain image evaluation of the present invention. The steps include: receiving a first T1-weighted image of a patient's brain (step 110 ); Perform a tissue segmentation process on the first T1-weighted image to obtain the first gray matter image (step 120); register the first gray matter image to the standardized normal gray matter image template established by the overlay process (step 130); The first gray matter image registered to the standardized normal gray matter image template obtains the score value corresponding to each voxel it has according to the voxel analysis formula, where the voxel analysis formula is

, TW is the score value corresponding to the i-th voxel, x* is the volume of the i-th voxel of the first gray matter image registered to the standardized normal gray matter image template,

To obtain the volume of the i-th voxel of the expected image from the database based on the patient’s age and gender, s is the volume standard deviation of the i-th voxel of the estimated residual image obtained from the database,

Is the scale factor of the T test, n is the number of samples to build the database, and i is a positive integer greater than or equal to 1 (step 140); judge whether the score value corresponding to each voxel is greater than or less than the expected value; (step 150); According to the voxels larger or smaller than the expected value, the brain area to which they belong is pushed back, and an evaluation report is output (step 160).

The patient mentioned in step 110 can be, but is not limited to, a patient who wants to evaluate the possible abnormal state of the brain. The patient can know the relationship between the patient and the healthy subject after removing relevant interference factors through the above steps 110 to 160. The difference in brain images between the two, and helps to digitize brain images and detect subtle changes in brain structure that are not detectable by the naked eye. Among them, the patient is an adult.

The tissue segmentation procedure described in step 120 can be, but is not limited to, using the open source software FSL to perform tissue segmentation on the first T1-weighted image to obtain gray matter images (ie, the first gray matter images), white matter images, and cerebrospinal fluid images of the patient. However, this embodiment is not intended to limit the present invention, and can be adjusted according to actual needs. For example, the gray matter image of the patient (ie, the first gray matter image) can also be obtained through the brain functional magnetic resonance data processing technology of Statistical Parametric Mapping (SPM).

Please refer to "Figure 1" and "Figure 2". "Figure 2" is a flowchart of one embodiment of the superimposing procedure described in step 130 of "Figure 1". In this embodiment, the superimposing procedure described in step 130 includes the following steps: obtaining second T1-weighted images of the brains of n healthy subjects, where n is a positive integer greater than or equal to 30 (step 210); Each second T1-weighted image is subjected to a tissue segmentation procedure to obtain a corresponding second gray matter image (step 220); the second gray matter images are registered to the MNI (Montreal Neurological Institute) standard space template (step 230) And the second gray matter images registered to the MNI standard space template are superimposed, and a standardized normal gray matter image template is established by averaging the image brightness (step 240). Among them, the MNI standard space template is a standard brain template widely used in the field of international brain imaging.

Since this embodiment is used to perform personalized brain imaging evaluation on adults, the healthy subjects mentioned in step 210 are healthy adults.

In step 240, the standardized normal gray matter image template is established by averaging the image brightness. Each voxel of each second gray matter image registered to the MNI standard space template has its brightness value. When the image is registered to the MNI After the second gray matter images of the standard space template are superimposed, the brightness values of the i-th voxel (i is a positive integer greater than or equal to 1) of different second gray matter images can be added to obtain the average value, and Obtain the brightness value of the i-th voxel of the normal image template, and then establish a standardized normal gray matter image template.

Since the above n healthy subjects can all be Taiwanese, a standard spatial template (ie, standardized normal gray matter image template) suitable for Taiwan can be obtained through step 210 to step 240. Therefore, the first T1-weighted images of the brains of healthy subjects in different regions can be used to establish a standard spatial template suitable for the region.

與s，因此，在執行步驟140之前要先建立該資料庫，而該資料庫的建立方法包含以下步驟：將每一第二灰質影像配准至標準化正常灰質影像模板（步驟310）；對配准至標準化正常灰質影像模板的每一第二灰質影像進行平滑化處理（步驟320）；將平滑化的該些第二灰質影像依據一般線性模型並整合年齡因子與性別因子，估算出年齡因子的權重係數與性別因子的權重係數，並取得平滑化的每一第二灰質影像對應的殘差影像（步驟330）；以及將每一殘差影像的第i個體素的體積大小進行標準差計算，以取得估計殘差影像的第i個體素之體積標準差，進而建立資料庫（步驟340）。Please refer to "Figure 1" and "Figure 3". "Figure 3" is a flowchart of one embodiment of the database creation method described in step 140 of "Figure 1". In this embodiment, when performing the "first gray matter image registered to the standardized normal gray matter image template to obtain the score value corresponding to each voxel according to the voxel analysis formula" described in step 140, it is necessary to borrow Required to obtain the voxel analysis formula from the database

And s, therefore, the database must be created before performing step 140, and the method for creating the database includes the following steps: register each second gray matter image to a standardized normal gray matter image template (step 310); Smoothing is performed on each second gray matter image that is aligned to the standardized normal gray matter image template (step 320); the smoothed second gray matter images are combined according to the general linear model and the age factor and gender factor are integrated to estimate the age factor Weight coefficients and weight coefficients of gender factors, and obtain the residual image corresponding to each second gray matter image smoothed (step 330); and calculate the standard deviation of the volume size of the i-th voxel of each residual image, To obtain the volume standard deviation of the i-th voxel of the estimated residual image, and then establish a database (step 340).

In this embodiment, the smoothing process described in step 320 can be, but is not limited to, the three-dimensional Gaussian flattening process, which can be adjusted according to actual needs. Among them, the smoothing process can reduce the error when the second gray matter image is registered to the standardized normal gray matter image template.

Since age and gender are related factors that affect brain changes, in step 330, when analyzing the smoothed second gray matter images using a general linear model, the age factor and gender factor can be integrated to estimate The weight coefficient of the age factor and the weight coefficient of the gender factor are obtained, and the residual image corresponding to each second gray matter image smoothed is obtained. Among them, the weight coefficient of the estimated age factor and the weight coefficient of the gender factor can be a numerical range respectively. Then, calculate the standard deviation of the volume size of the i-th voxel of each residual image to obtain the volume standard deviation of the i-th voxel of the estimated residual image (that is, the s of the voxel analysis formula), and then build a database (That is, step 340). Therefore, the database is a database using voxel linear regression based on age factor and gender factor. In this embodiment, the factors integrated for analysis using a general linear model can be age factors and gender factors, but this embodiment is not intended to limit the present invention. For example, using the general linear model to analyze the integrated factors can also be integrated for various factors that affect brain changes, such as education level or cognitive function performance, etc., which can be adjusted according to actual needs.

係為將該病人的年齡與性別導入利用基於年齡因子與性別因子的體素線性回歸之資料庫後所取得的預期影像的第i個體素的體積大小，s為依據資料庫取得估計殘差影像之第i個體素的體積標準差。After the database is established through step 310 to step 340, the “first gray matter image registered to the standardized normal gray matter image template is obtained according to the voxel analysis formula to obtain the corresponding score value of each voxel” described in step 140. among them,

It is the volume of the i-th voxel of the expected image obtained after importing the patient’s age and gender into the database using voxel linear regression based on age factor and gender factor, s is the estimated residual image obtained from the database The volume standard deviation of the i-th voxel.

Please continue to refer to "Figure 1". In step 150, the expected value can be but not limited to 0.05, which can be adjusted according to actual needs.

In step 160, the brain regions to which the voxels that are larger or smaller than the preset value belong may be, but are not limited to, Frontal Lobe, Parietal Lobe, Occipital Lobe, Temporal Lobe lobe), insula (Insula), hippocampus (Hippocampus) or amygdala (Amygdala). The content of the evaluation report may include the first gray matter image on which the voxels whose score values are greater than or less than the expected value are marked in a visual manner. Therefore, through the above steps 110 to 160, the differences in brain images between a single patient and healthy subjects can be learned after eliminating the relevant interference factors (age factor and gender factor), which is helpful for brain image digitization and detection. Measure subtle changes in brain structure that are imperceptible to the naked eye.

Next, please refer to "Figure 4". "Figure 4" is a block diagram of an embodiment of a non-transitory computer-readable medium for personalized brain image evaluation of the present invention. The non-transitory computer-readable medium 400 for personalized brain image evaluation includes operating instructions 402 that can be used by one or more processors 404 to execute the method including the brain image evaluation described above. These operating instructions may include any (one or more) other steps described herein. The implementation of operation instructions 402 such as those described herein can be stored on a non-transitory computer-readable medium 400 for personalized brain image evaluation. The non-transitory computer-readable medium 400 for personalized brain image evaluation can be a storage medium such as a magnetic disk or optical disc or a tape, or any other suitable non-transitory computer-readable medium known in the art.

Next, please refer to "Figure 5". "Figure 5" is a block diagram of an embodiment of the device for personalized brain image evaluation of the present invention. The apparatus 500 for personalized brain image evaluation includes a processor 502, a storage unit 504, and a program 506. The program 506 is stored in the storage unit 504 and configured to be executed by the processor 502. The program 506 as a whole can include the above-explained The operation instructions of the method of brain imaging evaluation. Among them, the number of the processor 502, the storage unit 504, and the program 506 can be but not limited to one, and can be adjusted according to actual needs.

The following description will be given by way of examples in conjunction with "Figure 6" to "Figure 7B".

(Analysis of the stability of individualized brain image evaluation by the number of samples in the healthy adult database)

Since the method of personalized brain image evaluation is a method to evaluate the degree of change in the gray matter image of a single patient's brain compared to the database created by normal healthy subjects, it is used to build a database The number of samples of brain gray matter images of normal healthy subjects may affect the evaluation of the stability of brain gray matter images of a single patient. Please refer to "Figure 6". "Figure 6" is the first gray matter image of the evaluation report output after the method of personalizing the brain image evaluation on the same patient in a database established with different sample numbers. Among them, n is the number of samples to establish a database, and each first gray matter image is visualized with voxels whose evaluation value is greater than or less than the expected value. In this embodiment, the brain gray matter images of a 61-year-old female Alzheimer's disease patient are respectively used to create a database of different sample sizes for personalized brain image evaluation. As can be seen from "Figure 6", when used to create When the number of samples of brain gray matter images of normal healthy subjects in the database is 30 people, it can achieve very similar results with the database established with the number of samples of 152 people. In other words, the method of personalized brain image evaluation can use a database established with a small sample size to obtain extremely stable statistical results.

(Sensitivity analysis of the method of personal brain imaging evaluation)

In this embodiment, the sensitivity for detecting hippocampal volume shrinkage is discussed. Please refer to "Figure 7A" and "Figure 7B". "Figure 7A" and "Figure 7B" respectively show the use of the "Figure 1" method of personalized brain imaging evaluation and traditional T test statistical methods for the same patient Schematic diagram of computer simulation assessment of atrophy of the hippocampus. Among them, the vertical axis is the percentage of hippocampus atrophy; the horizontal axis is the number of voxels corrected by clustering-wise multiple comparisons; the light-colored area is the situation when the uncorrected P value is less than 0.05; the dark-colored area is When the cluster level corrected P value is less than 0.05. In this embodiment, the P value is less than 0.05 as being statistically significant.

The method of personalized brain image evaluation in this embodiment uses a database of 152 people for evaluation. It can be seen from "Figure 7A" that the method of personalized brain image evaluation can produce 9% of the hippocampus volume. When shrinking, it is detected that the patient has an abnormal volume reduction phenomenon; while the traditional T test statistical method can only be detected when the hippocampus volume shrinks by 12%. Therefore, it can be seen that the method of personalized brain imaging evaluation can provide better sensitivity in the detection of the size of the brain gray matter of a single patient.

In summary, it can be seen that the difference between the present invention and the prior art lies in receiving the first T1-weighted image of the patient’s brain; performing a tissue segmentation procedure on the first T1-weighted image to obtain the first gray matter image; The image is registered to the standardized normal gray matter image template created by the superimposition process; the first gray matter image registered to the standardized normal gray matter image template is obtained through the voxel analysis formula to obtain the corresponding score value of each voxel; Whether the evaluation value corresponding to the one element is greater than or less than the expected value; and according to the voxels greater than or less than the expected value, the brain area to which it belongs is pushed back, and the evaluation report is output. This technical method can solve the existing technology In turn, the difference in brain images between a single patient and healthy subjects can be learned after eliminating the relevant interference factors (age factor and gender factor), which helps to digitize the brain image and detect the undetected by the naked eye Changes in subtle brain structure.

Although the present invention is disclosed in the foregoing embodiments as above, it is not intended to limit the present invention. Anyone familiar with similar art can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the present invention The scope of patent protection shall be determined by the scope of the patent application attached to this specification.

，TW為第i個體素對應的評分值，x*為配准至標準化正常灰質影像模板的第一灰質影像之第i個體素的體積大小，

為依據該病人的年齡與性別於資料庫取得預期影像之第i個體素的體積大小，s為依據資料庫取得估計殘差影像之第i個體素的體積標準差，

為T檢定的比例因子，n為建立資料庫的樣本數，i為大於或等於1的正整數 步驟150:判斷每一體素對應的評分值是否大於或小於預期值 步驟160:依據大於或小於預期值的該些體素回推其所屬的腦區，並輸出評估報告 步驟210:取得n個健康受試者的大腦之第二T1加權影像，n為大於或等於三十之正整數 步驟220:對每一第二T1加權影像分別進行組織分割程序，以取得對應的第二灰質影像 步驟230:將該些第二灰質影像分別配准至MNI標準空間模板 步驟240:將配准至MNI標準空間模板的該些第二灰質影像進行疊合，並以影像亮度取平均值的方式建立標準化正常灰質影像模板 步驟310:將每一第二灰質影像配准至標準化正常灰質影像模板 步驟320:對配准至標準化正常灰質影像模板的每一第二灰質影像進行平滑化處理 步驟330:將平滑化的該些第二灰質影像依據一般線性模型並整合年齡因子與性別因子，估算出年齡因子的權重係數與性別因子的權重係數，並取得平滑化的每一第二灰質影像對應的殘差影像 步驟340:將每一殘差影像的第i個體素的體積大小進行標準差計算，以取得估計殘差影像的第i個體素之體積標準差，進而建立資料庫400: Non-transitory computer-readable media for personalized brain image evaluation 402: Operation instructions 404, 502: Processor 500: Personalized brain image evaluation equipment 504: Storage unit 506: Program step 110: Receive a patient’s brain First T1-weighted image Step 120: Perform a tissue segmentation process on the first T1-weighted image to obtain the first gray matter image Step 130: Register the first gray matter image to the standardized normal gray matter image template created by the overlay process Step 140 : The first gray matter image registered to the standardized normal gray matter image template obtains the score value corresponding to each voxel it has according to the voxel analysis formula, where the voxel analysis formula is

, TW is the score value corresponding to the i-th voxel, x* is the volume of the i-th voxel of the first gray matter image registered to the standardized normal gray matter image template,

To obtain the volume of the i-th voxel of the expected image from the database based on the patient’s age and gender, s is the volume standard deviation of the i-th voxel of the estimated residual image obtained from the database,

Is the scale factor of the T test, n is the number of samples to build the database, and i is a positive integer greater than or equal to 1. Step 150: Determine whether the score corresponding to each voxel is greater or less than the expected value Step 160: Based on greater or less than expected The voxels of the value are pushed back to the brain area to which they belong, and the evaluation report is output. Step 210: Obtain the second T1-weighted image of the brains of n healthy subjects, where n is a positive integer greater than or equal to 30. Step 220: Perform a tissue segmentation procedure on each second T1-weighted image to obtain the corresponding second gray matter image. Step 230: Register the second gray matter images to the MNI standard space template. Step 240: Register to the MNI standard space. The second gray matter images of the template are superimposed, and a standardized normal gray matter image template is created by averaging the image brightness. Step 310: Register each second gray matter image to the standardized normal gray matter image template. Step 320: Match Perform smoothing processing on each second gray matter image that is aligned to the standardized normal gray matter image template. Step 330: Perform the smoothing of the second gray matter images according to the general linear model and integrate the age factor and gender factor to estimate the weight coefficient of the age factor And the weight coefficient of the sex factor, and obtain the residual image corresponding to each smoothed second gray matter image. Step 340: Calculate the standard deviation of the volume size of the i-th voxel of each residual image to obtain the estimated residual The volume standard deviation of the i-th voxel of the image, and then build the database

FIG. 1 is a method flowchart of an embodiment of the method for personalized brain image evaluation of the present invention. Fig. 2 is a flowchart of an embodiment of the superimposing procedure described in step 130 of Fig. 1. FIG. 3 is a flowchart of an embodiment of the method for creating a database described in step 140 in FIG. 1. Figure 4 is a block diagram of an embodiment of a non-transitory computer-readable medium for personalized brain image evaluation of the present invention. Figure 5 is a block diagram of an embodiment of the device for personalized brain image evaluation of the present invention. Figure 6 is the first gray matter image of the evaluation report output after the method of personalized brain imaging evaluation on the same patient in a database established with different sample numbers. Figures 7A and 7B are schematic diagrams of the computer simulation assessment of hippocampus atrophy of the same patient using the method of personalized brain imaging assessment in Figure 1 and the traditional T test statistical method.

Step 110: Receive the first T1-weighted image of a patient's brain

Step 120: Perform a tissue segmentation procedure on the first T1-weighted image to obtain the first gray matter image

Step 130: Register the first gray matter image to the standardized normal gray matter image template created by the overlay process

，TW為第i個體素對應的評分值，x*為配准至標準化正常灰質影像模板的第一灰質影像之第i個體素的體積大小，

為依據該病人的年齡與性別於資料庫取得 預期影像之第i個體素的體積大小，s為依據資料庫取得估計殘差影像之第i個體素的體積標準差，

為T檢定的比例因子，n為建立資料庫的樣本數，i為大於或等於1的正整數 Step 140: Obtain the score value corresponding to each voxel of the first gray matter image registered to the standardized normal gray matter image template according to the voxel analysis formula, where the voxel analysis formula is

, TW is the score value corresponding to the i-th voxel, x* is the volume of the i-th voxel of the first gray matter image registered to the standardized normal gray matter image template,

To obtain the volume of the i-th voxel of the expected image from the database based on the patient’s age and gender, s is the volume standard deviation of the i-th voxel of the estimated residual image obtained from the database,

Is the scale factor of the T test, n is the number of samples to establish the database, and i is a positive integer greater than or equal to 1

Step 150: Determine whether the score value corresponding to each voxel is greater or less than the expected value

Step 160: According to the voxels larger or smaller than the expected value, push back to the brain area to which it belongs, and output an assessment report

Claims (7)

A method for personalized brain image evaluation, the method includes the following steps: receiving a first T1 weighted image of a patient's brain; performing a tissue segmentation procedure on the first T1 weighted image to obtain a first T1 weighted image A gray matter image; registering the first gray matter image to a standardized normal gray matter image template created by a superimposing process; obtaining the first gray matter image registered to the standardized normal gray matter image template according to an integrated element analysis formula It has a score value corresponding to each voxel, where the voxel analysis formula is

TW is the score value corresponding to the i-th voxel, x* is the volume of the i-th voxel of the first gray matter image registered to the standardized normal gray matter image template,

To obtain the volume size of the i-th voxel of an expected image in a database based on the patient’s age and gender, s is the volume standard deviation of the i-th voxel of an estimated residual image obtained from the database,

Is a scale factor of the T test, n is the number of samples to establish the database, and i is a positive integer greater than or equal to 1; judge whether the score value corresponding to each voxel is greater than or less than an expected value; and the basis is greater than Or, the voxels that are smaller than the expected value push back the brain area they belong to, and output an evaluation report. According to the method for personalized brain image evaluation in the first item of the scope of patent application, the superimposing process includes the following steps: Obtain one of the second T1-weighted images of the brains of n healthy subjects, where n is greater than or equal to 30 A positive integer for each of the second T1-weighted images to obtain a corresponding second gray matter image by performing the tissue segmentation procedure for each second T1-weighted image; respectively registering the second gray matter images to the MNI (Montreal Neurological Institute) standard space template ; And the second gray matter images registered to the MNI standard space template are superimposed, and the standardized normal gray matter image template is established by averaging the image brightness. According to the method for personal brain image evaluation in the second patent application, the method for establishing the database includes the following steps: registering each second gray matter image to the standardized normal gray matter image template; registering to Perform a smoothing process on each of the second gray matter images of the normal image template; perform a smoothing process on the smoothed second gray matter images according to a general linear model and integrate the age factor and gender factor to estimate the weight coefficient of the age factor and the The weight coefficient of the gender factor, and obtain a residual image corresponding to each second gray matter image smoothed; and calculate the standard deviation of the volume size of the i-th voxel of each residual image to obtain the estimate The volume standard deviation of the i-th voxel of the residual image, and then establish the database. A non-transitory computer-readable medium for personalized brain image evaluation, which is configured to store a number of operating instructions, which when executed by one or more processors cause the one or more processors to perform the following operations : Receiving a first T1-weighted image of a patient’s brain; performing a tissue segmentation process on the first T1-weighted image to obtain a first gray matter image; registering the first gray matter image to a superimposed process Established a standardized normal gray matter image template; the first gray matter image registered to the standardized normal gray matter image template obtains a score value corresponding to each voxel it has according to the integrated voxel analysis formula, wherein the voxel analysis formula for

TW is the score value corresponding to the i-th voxel, x* is the volume of the i-th voxel of the first gray matter image registered to the standardized normal gray matter image template,

To obtain the volume size of the i-th voxel of an expected image in a database based on the patient’s age and gender, s is the volume standard deviation of the i-th voxel of an estimated residual image obtained from the database,

Is a scale factor of the T test, n is the number of samples to build the database, and i is a positive integer greater than or equal to 1; judge whether the score value corresponding to each voxel is greater than or less than an expected value; and the basis is greater than or The voxels that are smaller than the expected value push back the brain area they belong to, and output an evaluation report. The non-transitory computer-readable medium for personalized brain image evaluation according to item 4 of the scope of patent application, wherein the overlay procedure includes the following operations: Obtain one of the second T1-weighted images of the brains of n healthy subjects, n Be a positive integer greater than or equal to 30; perform the tissue segmentation procedure for each second T1 weighted image to obtain a corresponding second gray matter image; respectively register the second gray matter images to an MNI standard Spatial template; and superimposing the second gray matter images registered to the MNI standard spatial template, and establishing the standardized normal gray matter image template by averaging the image brightness. According to the non-transitory computer-readable medium for personalized brain image evaluation according to item 5 of the scope of patent application, the method for establishing the database includes the following operations: registering each second gray matter image to the standardized normal gray matter image Template; perform a smoothing process on each of the second gray matter images registered to the standardized normal gray matter image template; calculate the smoothed second gray matter images according to the general linear model and integrate the age factor and gender factor The weight coefficient of the age factor and the weight coefficient of the gender factor are obtained, and a residual image corresponding to each of the second gray matter images that is smoothed is obtained; and the volume size of the i-th voxel of each residual image is calculated The standard deviation is calculated to obtain the volume standard deviation of the i-th voxel of the estimated residual image, and then establish the database. A device for personalized brain image evaluation, the device comprising: one or more processors; a storage unit; and at least one program, wherein the at least one program is stored in the storage unit and configured to be used by the one or more Is executed by a processor, and the at least one program as a whole includes the following operation instructions: receiving a first T1-weighted image of a patient’s brain; performing a tissue segmentation process on the first T1-weighted image to obtain a first gray matter Image; registering the first gray matter image to a standardized normal gray matter image template created by a superimposing procedure; registering the first gray matter image to the standardized normal gray matter image template according to the integral element analysis formula Each voxel corresponds to a score value, where the voxel analysis formula is

TW is the score value corresponding to the i-th voxel, x* is the volume of the i-th voxel of the first gray matter image registered to the standardized normal gray matter image template,

To obtain the volume size of the i-th voxel of an expected image in a database based on the patient’s age and gender, s is the volume standard deviation of the i-th voxel of an estimated residual image obtained from the database,

Is a scale factor of the T test, n is the number of samples to establish the database, and i is a positive integer greater than or equal to 1; judge whether the score value corresponding to each voxel is greater than or less than an expected value; and the basis is greater than Or, the voxels that are smaller than the expected value push back the brain area they belong to, and output an evaluation report.

Images