KR20190122189A - Model for predicting recovery of stroke patient - Google Patents

Abstract

A method for predicting the recovery of a stroke patient is disclosed. The method includes applying information about a lesion obtained from the brain imaging data of a stroke patient to the dormant fMRI (fMRI) of a normal person and determining the first connection information of the entire brain region, obtaining second connection information corresponding to a connection where impact on the lesion is lower than a predetermined criterion on the basis of the first connection information; generating a recovery prediction model for the lesion based on the initial degree of failure and the second connection information. It is possible to improve the accuracy of recovery prediction.

Description

MODEL FOR PREDICTING RECOVERY OF STROKE PATIENT}

The disclosed embodiment relates to a recording medium having recorded thereon a program for executing a method for predicting the degree of recovery of a stroke patient, a device for predicting the degree of recovery of a stroke patient, and a method for predicting the degree of recovery of a stroke patient on a computer.

Stroke is the cause of acquired disorder. Stroke-related disorders drastically reduce a patient's daily life and quality of life. Thus, an effective rehabilitation plan can be important for the future life of the patient. In particular, rehabilitation predictions can help clinicians develop rehabilitation plans that are tailored to each individual and help patients set more realistic goals. Brain tissue is characterized by a complex network. Therefore, stroke damage spreads through brain tissue, and brain structures are damaged from major lesions, but they can also affect the function of distant brain areas.

Recent rehabilitation predictions have been studied through lesion and connectivity analyzes, and several important factors have been identified. However, prediction is still a difficult task because of the diversity between individuals. Accordingly, there is a need for a more accurate prediction model that can predict the degree of recovery of stroke patients regardless of individual diversity.

The disclosed embodiment uses a second connection information obtained through the lesion analysis network in addition to the initial disability of the stroke patient to predict the degree of recovery of the stroke patient, thereby predicting the degree of recovery to increase the accuracy of recovery prediction It is about.

According to an embodiment of the present invention, a method for predicting a degree of recovery of a stroke patient may include applying information about a lesion obtained from brain structural image data of a stroke patient to a dormant fMRI (functional MRI) of a normal person, thereby providing a primary connection of the entire brain region. Determining information; Based on the primary connection information, obtaining secondary connection information corresponding to a connection whose impact on the lesion is lower than a predetermined criterion; Based on the secondary connection information of the lesion and the degree of initial motor dysfunction, a recovery prediction model may be generated.

According to an embodiment, in the method of predicting a recovery degree of a stroke patient, the obtaining of the secondary connection information may include: secondary connection of one lesion based on an average value of secondary connection information of a plurality of normal persons for one lesion. Information can be obtained.

According to an embodiment, the method for predicting the degree of recovery of a stroke patient may further include obtaining age and size of the patient, and generating the final recovery predictive model may include an initial degree of disability and secondary connection information. Together with the age of the patient and the size of the lesion may be generated to predict the recovery.

According to an embodiment, a method for predicting a recovery degree of a stroke patient may include obtaining brain image data of a stroke patient through an MRI technique; And correcting head movement of the patient on the acquired brain image data.

According to an embodiment, in the method of predicting a recovery degree of a stroke patient, the secondary connection information extracts connection information that is not affected by the lesion or is less than a predetermined criterion. Secondary linkage information for a lesion was obtained by comparing the baseline linkage information without lesions with the size of each linkage value to determine the number of lower linkages, and this quantitative figure can predict the extent of recovery in stroke patients. .

According to an embodiment, the apparatus for predicting the degree of recovery of a stroke patient may determine an initial degree of disability from brain image data of a stroke patient, and may provide information about a lesion obtained from brain image data to a dormant state fMRI (functional MRI) of a normal person. Determine the primary connection information of the whole area of the brain, obtain secondary connection information corresponding to the connection with a lower impact on the lesion based on the primary connection information, and obtain the initial degree of disability and secondary connection information. Based on, the processor generating a recovery prediction model for the lesion; And a memory for storing the recovery prediction model.

According to an embodiment, in the apparatus for predicting a recovery degree of a stroke patient, the processor may obtain secondary connection information based on an average value of the plurality of secondary connection information obtained from the primary connection information of the plurality of normal persons.

According to one embodiment, in the apparatus for predicting the degree of recovery of a stroke patient, the processor obtains information about the age and size of the lesion of the patient, the age and lesion size of the patient along with the initial degree of disability and secondary connection information A recovery prediction model may be generated based on the following.

According to an embodiment, in the apparatus for predicting a recovery degree of a stroke patient, the processor may acquire brain image data of a stroke patient through an MRI technique and perform correction of the head movement of the patient on the acquired brain image data. have.

According to an embodiment, in the apparatus for predicting a recovery degree of a stroke patient, the secondary connection information extracts connection information that is not affected by the lesion or is less than a predetermined criterion. Secondary linkage information for a lesion was obtained by comparing the baseline linkage information without lesions with the size of each linkage value to determine the number of lower linkages, and this quantitative figure can predict the extent of recovery in stroke patients. .

1 is a view for explaining the change in population structure due to aging.
2 is a graph for explaining the increase and decrease rate of the stroke treatment personnel.
3 is a view for explaining the damage of the brain of a patient having a stroke.
4 is a diagram for explaining the connectivity of the brain.
5 to 7 are diagrams for explaining an existing study performed on rehabilitation prediction.
8 to 13 are views for explaining a damaged area of the brain due to the lesion.
14 is a view for explaining the result of photographing the lesion area of the patient with ischemic stroke.
15 to 17 are diagrams for explaining the process of extracting the secondary connection of the lesion.
18 to 20 are diagrams for describing a method of representing a secondary connection to a lesion of a patient in a matrix.
21 is a diagram for describing a method of predicting, by a recovery prediction apparatus, an increase in recovery after three months.
22 to 24 are graphs showing the results of modeling by combining an initial degree of failure and a predictor.
FIG. 25 is a diagram illustrating a method of verifying modeling performed by combining an initial level of failure and a predictor, according to an exemplary embodiment.
FIG. 26 is a graph illustrating performance of modeling performed by combining an initial level of failure and a prediction factor, according to an exemplary embodiment.
27 is a block diagram of a recovery prediction apparatus, according to an exemplary embodiment.

Terms used herein will be briefly described and the present invention will be described in detail.

The terms used in the present invention have been selected as widely used general terms as possible in consideration of the functions of the present invention, but may vary according to the intention or precedent of the person skilled in the art, the emergence of new technologies, and the like. In addition, in certain cases, there is also a term arbitrarily selected by the applicant, in which case the meaning will be described in detail in the description of the invention. Therefore, the terms used in the present invention should be defined based on the meanings of the terms and the contents throughout the present invention, rather than the names of the simple terms.

When any part of the specification is to "include" any component, this means that it may further include other components, except to exclude other components unless otherwise stated. In addition, the terms "... unit", "module", etc. described in the specification mean a unit for processing at least one function or operation, which may be implemented in hardware or software or a combination of hardware and software. .

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining the change in population structure due to aging.

Referring to Figure 1, the structure of the aging trend over time and the number of population by age occupying the total population is shown. In the future, as the aging society progresses rapidly, the population over 55 will make up a large part of the population.

Due to population changes such as aging, the number of patients with physical disabilities is gradually increasing. For example, the number of stroke patients may increase, resulting in an increase in the number of patients with physical disabilities. Therefore, the role of rehabilitation therapy for the recovery of stroke patients is increasing.

Rehabilitation therapy is very important for stroke patients to return to their daily lives or to reduce the initial degree of disability as much as possible. In this regard, rehabilitation predictions can help therapists develop personalized rehabilitation plans and help patients set more realistic goals.

2 is a graph for explaining the increase and decrease rate of the stroke treatment personnel.

Referring to FIG. 2, the number of deaths per 100,000 population is decreasing, while the number of medical personnel due to the stroke confirmed in the emergency room is steadily increasing. That is, it can be confirmed that the stroke invention is increasing.

3 is a view for explaining the damage of the brain of a patient having a stroke.

Referring to Figure 3, the brain damage is spread through the neural network, the brain damage occurs in the brain structure mainly corresponds to the areas where major lesions occurred, the stroke affects the distant brain tissue in addition to the areas where major lesions occurred. Can give

4 is a diagram for explaining the connectivity of the brain.

Referring to FIG. 4, the resting-state fMRI is based on a spontaneous low frequency signal lower than 0.1 Hz in a blood-oxygen level dependent signal. Such spontaneous low-frequency signals can be meaningful brain activity, despite no external stimulation.

In particular, dormant fMRIs may be more suitable for patients with neurological disorders because they have less requirements than specific task-based fMRIs.

5 to 7 are diagrams for explaining an existing study performed on rehabilitation prediction.

Recently, rehabilitation predictions have been conducted using a number of lesion and linkage analyzes, and some predictors have proved it. For example, FIG. 5 is a graph for explaining an approach for predicting recovery of function with lesion data over time. In addition, FIG. 6 describes the study of the effects of lesions based on node removal and edge removal due to an attack. In addition, FIG. 7 describes a study focusing on the lesion connection at the center of the lesion.

8 to 13 are views for explaining a damaged area of the brain due to the lesion.

Referring to Figure 8, it can be seen that the brain is composed of a complex network. On the other hand, as stroke occurs, as shown in FIG. 9, certain regions of the brain may be damaged by major lesions. If certain areas of the brain are damaged by major lesions, the primary neural network may be damaged, as shown in FIG. 10. The damage caused to the primary neural network can spread through the brain network, as shown in FIG. 11. In addition, as the damage spreads through the brain network, the secondary neural network may be affected by the lesion, as shown in FIG. 12. That is, due to the spread of the injury, the secondary neural network may be strongly affected by the lesion as shown in FIG. 13.

Secondary neural networks have a greater number of connections and can cover more brain areas in the transfer of information to network structures. Secondary neural networks are not directly damaged by major lesions.

The recovery prediction apparatus according to one embodiment used the secondary connection of the lesion to predict rehabilitation. The characteristics of the secondary connection are relatively strongly affected by the lesion, and the connection covers a much larger and larger area in terms of information diffusion in the network structure. Secondary connections also represent connections that are not directly damaged.

14 is a view for explaining the result of photographing the lesion area of the patient with ischemic stroke.

FIG. 14 shows the results obtained by performing MRI data collection and behavioral tests for two weeks after stroke expression, except for patients with neuropsychiatric diseases other than stroke.

Motor impairment was measured on the day of obtaining MRI data using a Fulg-Meyer assessment (FMA). It was measured again three months after stroke expression. Participants were instructed to close their eyes and no movement during the resting-state fMRI scan.

 At this time, fMRI data was obtained by Philips ACHIEVA MR scanner.

15 to 17 are diagrams for explaining the process of extracting the secondary connection of the lesion.

Referring to FIG. 15, the recovery predicting apparatus according to an embodiment may determine the connectivity of the entire brain to time series information about the lesion by moving a lesion of a patient onto resting-state fMRI data of a normal person. This connection is the primary connection to the lesion.

The recovery prediction apparatus according to an embodiment first divides the entire brain into 94 regions based on Automated Anatomical Labeling (AAL) template criteria, and if there are voxels connected by primary connection of the lesions of the corresponding regions, there is no time series information and lesions of the voxels. Secondary connections can be identified through correlation analysis between areas where there was no primary connection of the lesion. In this case, a voxel is a three-dimensional meaning of a pixel, and is a minimum unit having one value on MRI data.

The recovery prediction apparatus may input a value relating to the secondary connection into the matrix. The recovery prediction apparatus can perform this process on all 64 healthy individuals. In other words, the recovery prediction device may extract secondary connection information of such lesions from 64 normal persons for a patient's lesion. That is, 64 matrices can be obtained for one lesion.

Referring to FIG. 17, one matrix obtained from a plurality of normal persons and a matrix obtained by averaging the number of the plurality of normal persons is a secondary connection to the lesion.

18 to 20 are views for comparing a secondary connection to a patient's lesion with a reference matrix to obtain a low-impact connection to the lesion and a method for describing the result in a matrix.

Referring to FIG. 18, an area corresponding to an odd number in a matrix may be rearranged to a lesion side area, and an area corresponding to an even number may be rearranged to a healthy side area.

In this case, an asymmetric adjacent matrix can be modified to a symmetric matrix by adding a transpose matrix.

The recovery prediction apparatus according to an embodiment uses a reference network extracted from a normal person without lesions to relatively evaluate the influence of each connection. matrices) into a binary matrix, where we can count the number of connections marked 1 in the half-segment connections and use this as a predictor.

The greater the number of connections, the less the impact of the lesion on the entire brain, which can be a good condition for recovery and better recovery.

19 to 20, as described above, the secondary connection of each lesion is obtained, and the result of changing the small value to 1 and the large value to 0 by dividing the reference network is shown.

In addition, Fig. 21 shows the result of calculating the recovery increase amount at the three month time point by setting the number of ones of the hemisphere connections on the horizontal axis.

21 is a diagram illustrating a result of the recovery prediction apparatus predicting an increase in recovery after three months.

Referring to FIG. 21, it can be seen from the graph (D) that the proposed predictor predicts an increase in recovery after 3 months. In addition, the graph (E) and the graph (F) are divided into supratentorial and infratentorial positions of the lesion, respectively, and it is confirmed that the patients have a strong predictive power, especially in patients with supratentorial lesions.

22 to 24 are graphs showing the results of modeling including the initial degree of disability and predictive factors, including the initial level of disability and predictive factors, and the age and size of the patient.

Referring to FIG. 22, according to an embodiment, the recovery prediction apparatus may combine the initial degree of failure and the predictor through multiple linear regression. The recovery prediction apparatus may increase the predictive power of rehabilitation by generating a model for predicting the motor function score of the patient at 3 months based on the combined result.

The recovery prediction apparatus may perform lesion network analysis to measure the influence of the lesion on the entire brain region through the neural network analysis, and use it as a predictor. The recovery prediction device sequentially acquired the primary and secondary neural networks of the lesions and measured the effects of the lesions on the entire brain area. In particular, the effects of the recovery predictions focused on the secondary neural networks. In addition, this predictive factor, combined with the initial degree of failure, has the characteristics of higher performance and reproducibility than conventional.

23 and 24, according to an embodiment, the recovery prediction apparatus may combine the age of the patient and the size of the lesion through multiple linear regression in addition to the initial degree of failure and the predictive factors. The recovery prediction apparatus may thus create a prediction model with an accuracy of close to 0.8.

FIG. 25 is a diagram illustrating a method of verifying modeling performed by combining an initial level of failure and a predictor, according to an exemplary embodiment.

Referring to FIG. 25, a recovery prediction apparatus may allocate test data to verify a model. The recovery prediction apparatus may train the prediction model through the data. The recovery prediction device performs a k-fold cross-validation using LOOCV and 5 data as test data and using the remaining data as training data. Can be verified.

FIG. 26 is a graph illustrating performance of modeling performed by combining an initial level of failure and a prediction factor, according to an exemplary embodiment.

Referring to FIG. 26, the recovery prediction apparatus may compare a result of performing prediction by modeling based on an initial degree of failure and a result of performing prediction by modeling based on an initial degree of failure and a predictor. As a result of the comparison, it is confirmed that the accuracy of the result of the prediction by combining the initial degree of failure and the predictor is improved.

The recovery prediction apparatus according to an embodiment may finally process the spatially calm standardized image using a 6-mm full-width half-maximum Gaussian kernel. At this time, some of the signal elements to be removed can be removed using 22 linear regressions. The factor may include six head motion factors and six factors derived primarily from the motion factors. Here, each of the five factors is obtained and included through principal component analysis of white matter and cerebrospinal fluid signals. This signal can be included as a disturbing degenerate to extract a significant signal.

 In addition, the recovery prediction apparatus may perform band-pass filtering at a frequency in a range of 0.009 Hz to 0.08 Hz to eliminate integer cancellation and linear trend. In addition, the recovery prediction apparatus calculates the statistical dependencies using the Pearson's correlation coefficient, and ascertains the connectivity as the progress of time is calculated. In this case, only a positive correlation coefficient may be used as the correlation coefficient.

The recovery prediction apparatus may use a Seed-based approach for analyzing connectivity for voxels. In this case, the reference point of the connectivity map may be a t-value.

In addition, the recovery prediction apparatus may separate the brain into 116 regions by using automated anatomical labeling (AAL) to cover the entire brain. At this time, 116 zones may include 90 zones in the cerebrum and 26 zones in the cerebellum. The recovery predictor averaged nine zones in the left cerebellum and the right cerebellum, respectively and averaged eight zones in the palate. The brainstem area can be passively drawn on the AAL atlas.

Thus, a modified AAL atlas consisting of 94 regions can be registered and analyzed together using SPM12 in the normalized fMRI data space.

Each lesion from the patient can be distinguished over a T1 weighted structure image associated with the high signal intensity diffusion-weighted image (DWI) obtained at the patient's first neuropathic examination.

The recovery prediction apparatus according to an embodiment may use the region obtained from the lesion-seeded functional connectivity analysis to configure the next seeds, that is, the second link-step connectivity, to use the secondary connection as the exercise recovery predictor. Each step for obtaining a secondary connection may be as follows.

 (i) Transfer the lesion to a normal object.

 (ii) Acquire lesion-seeded functional connectivity of normal subjects through a seed-based approach. (first link-step, voxel-wise connectivity, p <0.00005).

(iii) The Lesion-seeded connected to the voxel is divided into seven areas based on the modified AAL atlas.

(iv) Set each region to the next seed region and perform region-wise connectivity analysis in the modified AAL space (second link-step, region-wise connectivity, p <0.01). At this time, the lesion-seeded connected to the lesion and the voxel may be masked.

(v) Calculate the correlation between the seeded region and the modified AAL regions. You can construct an adjacency matrix by inserting the values for the correlation into the columns that match the next seed region. In this case, the matrix may change the odd-numbered region from the left region to the same damage region, and the even-numbered region from the right region to the contralesional region.

(vi) The asymmetric contiguous matrix obtained in step (v) can be modified to a symmetric matrix by adding a transpose matrix (A_P1Hi = A_P1Hi + A_P1Hi ') if seeds are located in region 1 and region 2, region 1 And region 2 can be seen to have two different correlation coefficient values. Here, assume that the coefficient reflects the effect of the lesion. If the next seed is located in region 1 and region 2, the effects of the lesion between region 1 and region 2 can be summed. By making an asymmetric matrix, the recovery prediction apparatus can express the effects of the lesions in region 1 and region 2 as summed values.

(vii) Adjacent matrices can be obtained from a healthy object, and all matrices can be averaged. The averaged matrix corresponds to the secondary connection obtained from one lesion. Secondary connection matrix for stroke patients can be defined as follows.

[Equation 1]

는 i번째 정상 객체로부터 획득된 2차 연결 행렬을 나타내고, n은 정상 객체의 수를 나타낸다. In Equation 1 above

Denotes a secondary connection matrix obtained from the i-th normal object, and n denotes the number of normal objects.

The recovery prediction device may compare the unlinked or weak linkage with the reference reference linkage as a predictor for motor recovery to determine the effect on the brain from the lesion.

As a result, the recovery predictor is not connected, or the greater the number of weak connections, the less the lesion affects the brain nerves, and the brain nerves are better at repairing the damage from stroke, which is good for the recovery of motor nerves. It can be determined to influence.

[Equation 2]

는 환자의 2차 연결 행렬을 나타내고,

는 참조 기준 연결 행렬을 나타내며, m은 영역의 개수를 나타낸다. 참조 연결 행렬은 병변 볼륨에 의해 마스킹 된 모든 정상 객체의 AAL 연결 행렬을 평균하여 획득될 수 있다. 참조 연결 세기 보다 강도가 낮은 연결은 병변의 약한 부분으로 정의될 수 있고, 세기가 없는 연결은 병변에 영향을 받지 않는 연결로 정의될 수 있다. 그러므로 회복 예측 장치는 강도가 낮은 연결 및 병변에 영향을 받지 않는 연결의 개수에 대응되는 예측 인자를 이용할 수 있다. In Equation 2 above,

Represents the secondary connection matrix of the patient,

Denotes a reference criterion connection matrix and m denotes the number of regions. The reference connection matrix may be obtained by averaging the AAL connection matrices of all normal objects masked by the lesion volume. Links that are less intense than the reference link strength may be defined as weak portions of the lesion, and links without strength may be defined as links that are not affected by the lesion. Therefore, the recovery prediction apparatus may use a prediction factor corresponding to the number of low-strength connections and connections that are not affected by the lesion.

According to an embodiment, the recovery prediction apparatus may perform univariate analysis through a linear regression model. The recovery predictor examines the relationship between various variables (patient age, lesion size, baseline, expected factors) and recovery of motor performance and, depending on the findings, the relationship between age, lesion size and predictive factors and recovery of motor performance. Can be determined.

In addition, the recovery predicting device may classify the patient into an upper tent and a lower tent lesion to investigate a relationship between the predictive factor and the recovery of exercise ability. As a result, it was confirmed that the predictor was high in accuracy, especially for patients with lesions on the tent. In addition, the recovery prediction device may examine tent-like lesions through multivariate analysis. The recovery prediction device combines the initial level of disability and the predictive factors, and as a result of the analysis, it is confirmed that the accuracy of the motor performance prediction is improved. In addition, the analysis was performed using multiple linear regression models, including factors such as age and lesion size, as well as the initial degree of disability and predictive factors. On the other hand, according to the results of the multivariate analysis, it was confirmed that the initial degree of disorder had a strong influence on the rehabilitation prediction, and the predictor also maintained the significance in the multivariate analysis, indicating that the influence factor was high.

The recovery prediction apparatus according to an embodiment may apply leave-one-out cross validation (LOOCV) and k-fold cross validation to confirm the utility of the multivariate analysis using the initial degree of failure and the proposed predictor.

The relationship between the predicted FMA score and the actual FMA score three months after cerebral hemorrhage occurred. As a result of comparing the change of the sum of the combined model, the multivariate model, and the two models to compare the accuracy of the prediction, it can be seen that the determination constant of the combined model is higher than the determination constant of the multivariate model. In particular, it can be seen that the decision constants of the two models are much greater for patients with large initial damage. It was also confirmed that the combined model prediction accuracy was greater than univariate analysis.

27 is a block diagram of a recovery prediction apparatus 2700, according to an exemplary embodiment.

Referring to FIG. 27, the recovery prediction apparatus 2700 may include a processor 2710 and a memory 2720. According to the recovery prediction method proposed in the above embodiments, the processor 2710 and the memory 2720 may operate. However, the components of the recovery prediction apparatus 2700 according to an embodiment are not limited to the above-described example. According to another embodiment, the recovery prediction apparatus 2700 may include more components or fewer components than the aforementioned components.

The processor 2710 may apply the information about the lesion obtained from the brain image data to a dormant state fMRI (functional MRI) of a normal person to determine primary connection information of the entire brain region. The processor 2710 may obtain secondary connection information corresponding to a connection whose influence on the lesion is lower than a predetermined criterion based on the primary connection information. The processor 2710 may generate a recovery prediction model for the lesion based on the initial degree of failure and the secondary connection information.

The processor 2710 may obtain secondary connection information based on an average value of the plurality of secondary connection information obtained from the primary connection information of the plurality of normal persons. The processor 2710 may obtain information about the age of the patient and the size of the lesion. The processor 2710 may generate a recovery prediction model based on the age of the patient and the size of the lesion along with the initial degree of failure and the secondary connection information.

The processor 2710 may acquire brain neural network data of a stroke patient through an MRI brain imaging technique. The processor 2710 may perform correction of the head movement of the patient on the acquired brain image data.

The memory 2720 may store information necessary for the processor 2710 to predict the degree of recovery of the stroke patient. For example, the memory 2720 may store brain image data of a stroke patient. In addition, the memory 2720 may store a recovery prediction model.

The device according to the invention comprises a processor, a memory for storing and executing program data, a permanent storage such as a disk drive, a communication port for communicating with an external device, a user interface such as a touch panel, a key, a button and the like. Device and the like. Methods implemented by software modules or algorithms may be stored on a computer readable recording medium as computer readable codes or program instructions executable on the processor. The computer-readable recording medium may be a magnetic storage medium (eg, read-only memory (ROM), random-access memory (RAM), floppy disk, hard disk, etc.) and an optical reading medium (eg, CD-ROM). ) And DVD (Digital Versatile Disc). The computer readable recording medium can be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion. The medium is readable by the computer, stored in the memory, and can be executed by the processor.

All documents, including publications, patent applications, patents, and the like, cited in the present invention, may be incorporated into the present invention as if each cited document were individually and specifically shown as merged or as totally merged in the present invention. .

For the understanding of the present invention, reference numerals have been set forth in the preferred embodiments illustrated in the drawings, and specific terms are used to describe the embodiments of the present invention, but the present invention is not limited to the specific terms, and the present invention. May include all components conventionally conceivable to a person skilled in the art.

The invention can be represented by functional block configurations and various processing steps. Such functional blocks may be implemented in various numbers of hardware or / and software configurations that perform particular functions. For example, the present invention relates to integrated circuit configurations such as memory, processing, logic, look-up table, etc., which may execute various functions by the control of one or more microprocessors or other control devices. It can be adopted. Similar to the components in the present invention may be implemented in software programming or software elements, the present invention includes various algorithms implemented in data structures, processes, routines or other combinations of programming constructs, including C, C ++ It may be implemented in a programming or scripting language such as Java, an assembler, or the like. The functional aspects may be implemented with an algorithm running on one or more processors. In addition, the present invention may employ the prior art for electronic environment setting, signal processing, and / or data processing. Terms such as "mechanism", "element", "means", "configuration" can be used widely and are not limited to mechanical and physical configurations. The term may include the meaning of a series of routines of software in conjunction with a processor or the like.

Particular implementations described in the present invention are embodiments and do not limit the scope of the present invention in any way. For brevity of description, descriptions of conventional electronic configurations, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connection or connection members of the lines between the components shown in the drawings by way of example shows a functional connection and / or physical or circuit connections, in the actual device replaceable or additional various functional connections, physical It may be represented as a connection, or circuit connections. In addition, unless specifically mentioned, such as "essential", "important" may not be a necessary component for the application of the present invention.

In the specification (particularly in the claims) of the present invention, the use of the term “above” and the similar indicating term may be used in the singular and the plural. In addition, in the present invention, when the range is described, it includes the invention to which the individual values belonging to the range are applied (if not stated to the contrary), and each individual value constituting the range is described in the detailed description of the invention. Same as Finally, if there is no explicit order or contrary to the steps constituting the method according to the invention, the steps may be performed in a suitable order. The present invention is not necessarily limited to the order of description of the above steps. The use of all examples or exemplary terms (eg, etc.) in the present invention is merely for the purpose of describing the present invention in detail, and the scope of the present invention is limited by the examples or exemplary terms unless defined by the claims. It doesn't happen. In addition, one of ordinary skill in the art appreciates that various modifications, combinations and changes can be made depending on design conditions and factors within the scope of the appended claims or equivalents thereof.

Claims (11)

Determining, by the processor, an initial degree of disability based on brain image data of the stroke patient;
The processor may apply information about a lesion obtained from the brain image data to a functional state of sleep (fMRI) of a normal person, respectively, to set the lesion of the stroke patient as a first seed in the brain network structure of the normal person. Thereby determining primary connection information of the normal person with respect to a first plurality of regions that are primarily connected to the first seed;
By the processor, secondary to the first seed by setting the first plurality of regions as a second seed in the brain network structure of the normal person based on the primary connection information determined in the brain network structure of the normal person. Obtaining secondary connection information of the normal person relating to a second plurality of regions that are connected and primarily connected to the second seed;
Determining, by the processor, the primary connection information of the normal person and obtaining the secondary connection information of the normal person for the first normal person to the nth normal person to perform the first normal person to the nth normal person Obtaining respective secondary connection information;
Generating, by the processor, a recovery prediction model for the lesion of the stroke patient, using the secondary connection information of each of the first to nth normal persons, and the initial degree of disability of the stroke patient. and,
And n is an integer of 2 or more. The method of claim 1,
Generating the recovery prediction model,
Generating a recovery example model for the lesion, using the average value of the secondary connection information of each of the first normal person to the nth normal person, and the initial degree of disorder. Way. The method of claim 1,
Obtaining, by the processor, information regarding the age of the stroke patient and the size of the lesion of the stroke patient,
Generating the recovery prediction model,
Predicting, by the processor, recovery of the stroke patient for the lesion, using the age of the stroke patient, the size of the lesion, the secondary connectivity information of each of the first to nth normal persons, and the initial degree of disability. Generating a model, the method of predicting the extent of recovery of a stroke patient. The method of claim 1,
Acquiring, by the processor, the brain image data of the stroke patient through an MRI technique; And
And correcting, by the processor, the head movement of the stroke patient on the acquired brain image data. The method of claim 1, wherein the secondary connection information,
A method for predicting the extent of recovery of a stroke patient that is unaffected from, or affected by, the lesion below the predetermined criterion. Determine the extent of the initial disorder based on brain imaging data of the stroke patient,
By applying the information on the lesion obtained from the brain image data to the functional state of sleep (fMRI) of the normal person, respectively, by setting the lesion of the stroke patient as the first seed in the brain network structure of the normal person, Determine primary connection information of the normal person, relating to a first plurality of regions primarily connected to a seed,
Setting the first plurality of regions as a second seed in the brain network structure of the normal person based on the primary connection information determined in the brain network structure of the normal person, thereby being secondarily connected to the first seed and being connected to the second seed. Obtain secondary connection information of the normal person, relating to a second plurality of regions that are primarily connected to a seed,
Determining the primary connection information of the normal person and acquiring the secondary connection information of the normal person for each of the first normal person to the nth normal person to perform secondary connection information of each of the first normal person to the nth normal person; Earned,
A processor configured to generate a recovery prediction model for the lesion of the stroke patient, using the secondary connectivity information of each of the first to nth normal persons, and the initial degree of disability of the stroke patient; And
A memory for storing the recovery prediction model,
Wherein n is an integer of at least 2, predicting the extent of recovery of a stroke patient. The method of claim 6, wherein the processor,
An apparatus for predicting a degree of recovery of a stroke patient further configured to generate the recovery sample model for the lesion using the average value of each secondary connection information of the first normal to nth normal and the initial degree of disability. . The method of claim 6, wherein the processor,
Obtaining information about the age of the stroke patient and the size of the lesion of the stroke patient,
Further using the age of the stroke patient, the size of the lesion, secondary connection information of each of the first to nth normal persons, and the initial degree of disability, to generate a recovery prediction model for the lesion of the stroke patient. Device configured to predict the extent of recovery of a stroke patient. The method of claim 6, wherein the processor,
The brain imaging data of the stroke patient is obtained through MRI technique,
The apparatus for predicting the degree of recovery of the stroke patient further configured to perform correction of the head movements of the stroke patient on the acquired brain image data. The method of claim 6, wherein the secondary connection information,
A device for predicting the extent of recovery of a stroke patient that is not affected by the lesion or is affected by the lesion below the predetermined criterion. A computer-readable recording medium having recorded thereon a program for executing the method of any one of claims 1 to 5.

Images