Dementia diagnosis method and system using genetic information data and brain image data

Abstract

One embodiment of the present disclosure provides a dementia diagnosis method, comprising the steps of: generating genetic feature data by comparing and analyzing genetic information of normal individuals and genetic information of dementia patients; encoding the brain image data of the normal individuals and the brain image data of the dementia patients, respectively, and generating brain feature data corresponding to the encoded brain image data of the normal individuals and the dementia patients, respectively; and using data obtained by combining the genetic feature data and the brain feature data in a predetermined manner as training data, generating a dementia diagnosis model trained to determine whether or not a specific individual has dementia based on the genetic information and genetic feature data of the specific individual.

Description

[Technical Field]

[0001] The present invention relates to a method and system for diagnosing dementia that uses genetic information data and brain imaging data, and more specifically to a method and system for diagnosing dementia that analyzes genetic information from normal individuals and genetic information from dementia patients, and brain imaging data from normal individuals and brain imaging data from dementia patients, extracts feature data from each, and combines the feature data to train a model. [Background technology]

[0002] Dementia is a disease in which the accumulation of beta-amyloid causes a decrease in the areas of the brain responsible for memory, the cerebrum or hippocampus.

[0003] According to the "Current Status of Dementia in Korea" statistics released by the Korea National Dementia Center, the number of dementia patients aged 65 and over was counted at 648,223 (prevalence rate 9.8%) in 2015, and is estimated to exceed 1 million (prevalence rate 10.3%) by 2024 and 2 million (prevalence rate 12.3%) by 2041.

[0004] In addition, conventional dementia testing tools require a long testing time of at least 30 minutes, and diagnose mild cognitive impairment or dementia through MRI imaging, memory questionnaires, and a doctor's findings.However, there is currently a shortage of specialized medical personnel, such as dementia specialists or neuropsychologists and clinical psychologists who have completed specialized training, as well as a lack of separate testing locations, resulting in a shortage of hospitals that can treat dementia.

[0005] This has created a need for new methods of diagnosing dementia other than relying on doctor's findings. Summary of the Invention [Problem to be solved by the invention]

[0006] The present disclosure is intended to solve the problems of the conventional technology described above, and aims to provide a method and system for diagnosing dementia based on a model that analyzes genetic information of normal individuals and genetic information of dementia patients, as well as brain image data of normal individuals and brain image data of dementia patients, extracts feature data from each, and combines the feature data to train the model.

[0007] The technical object to be achieved by the present invention is not limited to the above-mentioned technical object, and other technical objects of the present invention may be derived from the following description. [Means for solving the problem]

[0008] As a technical means for solving the above-mentioned technical problems, an embodiment according to a first aspect of the present disclosure provides a dementia diagnosis method, which includes the steps of generating genetic feature data by comparing and analyzing genetic information of normal individuals and genetic information of dementia patients, encoding the brain image data of the normal individuals and the brain image data of the dementia patients, respectively, and generating brain feature data corresponding to the encoded brain image data of the normal individuals and the dementia patients, respectively, and using data obtained by combining the genetic feature data and the brain feature data in a predetermined manner as training data, generating a dementia diagnosis model trained to determine whether or not a specific individual has dementia based on the genetic information and genetic feature data of the specific individual.

[0009] An embodiment according to a second aspect of the present disclosure provides a dementia diagnosis system, the system including a communication module, at least one processor, and a memory electrically connected to the processor and storing at least one code executed by the processor, the memory storing code which, when executed by the processor, causes the processor to compare and analyze genetic information of normal individuals and genetic information of dementia patients to generate genetic feature data, encode the brain image data of the normal individuals and the brain image data of the dementia patients, generate brain feature data corresponding to the encoded brain image data of the normal individuals and the brain image data of the dementia patients, and generate brain feature data corresponding to the encoded brain image data of the normal individuals and the brain image data of the dementia patients, using data obtained by combining the genetic feature data and the brain feature data in a predetermined manner as learning data, to generate a dementia diagnosis model trained to determine whether or not the specific individual has dementia based on the genetic information and genetic feature data of the specific individual. [Effects of the Invention]

[0010] According to the present invention, accuracy can be improved by diagnosing dementia by taking into account both genetic data and brain imaging data.

[0011] Furthermore, according to the present invention, dementia can be diagnosed based on genetic data and brain imaging data, thereby making the testing more convenient.

[0012] The effects of the present invention are not limited to the effects described above, but include all effects that can be understood from the following description. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a diagram illustrating a dementia diagnosis system according to an embodiment of the present invention; [Figure 2] 2 is a diagram showing a detailed configuration of a server shown in FIG. 1; [Figure 3] 10 is a diagram illustrating an example of gene characteristic data. [Figure 4]10 is a diagram illustrating an example of gene characteristic data. [Figure 5] 10 is a diagram illustrating an example of extracting brain feature data. [Figure 6] 10 is a diagram illustrating an example of extracting brain feature data. [Figure 7] 10 is a diagram illustrating an example of extracting brain feature data. [Figure 8a] 1 is a diagram illustrating the accuracy of a dementia diagnosis result obtained by a dementia diagnosis model. [Figure 8b] 1 is a diagram illustrating the accuracy of a dementia diagnosis result obtained by a dementia diagnosis model. [Figure 9] 10 is a flowchart showing the sequence of a dementia diagnosis method according to another embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0014] The present disclosure will be described in detail below with reference to the accompanying drawings. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. Furthermore, the accompanying drawings are intended to facilitate understanding of the embodiments disclosed herein and are not intended to limit the technical ideas disclosed herein. All terms, including technical and scientific terms, used herein should be interpreted in the sense commonly understood by those skilled in the art to which the present disclosure belongs. Predefined terms should be interpreted as having a meaning consistent with the relevant technical literature and the content of the present disclosure, and should not be interpreted in an overly ideal or restrictive sense unless otherwise defined.

[0015] In order to clearly explain the present disclosure in the drawings, parts that are not relevant to the description are omitted, and the size, form, and shape of each component shown in the drawings may be variously changed. The same or similar parts are designated by the same or similar reference numerals throughout the specification.

[0016] The suffixes "module" and "section" used in the following description for components are given or used interchangeably solely for the convenience of writing the specification, and do not have any mutually distinguishing meanings or roles. Furthermore, when describing the embodiments disclosed in this specification, if it is determined that a detailed description of related well-known technologies may obscure the gist of the embodiments disclosed in this specification, such a detailed description will be omitted.

[0017] Throughout this specification, when a part is described as being "connected (connected, contacted, or coupled)" to another part, this includes not only when it is "directly connected (connected, contacted, or coupled)" to another part, but also when it is "indirectly connected (connected, contacted, or coupled)" via another member therebetween. Furthermore, when a part is described as "including (comprising or providing)" a certain component, this does not mean that it excludes other components, but that it may further "include (comprise or provide)" other components, unless otherwise specified.

[0018] As used herein, ordinal terms such as "first" and "second" are used only to distinguish one component from another and do not limit the order or relationship of the components. For example, a first component of the present disclosure may be referred to as a second component, and similarly, a second component may be referred to as a first component. As used herein, singular expressions should be construed as including plural expressions unless clearly indicated to the contrary.

[0019] FIG. 1 is a diagram illustrating a dementia diagnosis system according to one embodiment of the present invention. 1, the dementia diagnosis system can include a server 100 and a user terminal 200. The server 100 and the user terminal 200 can be communicatively connected to each other via a communication network.

[0020] The server (100) compares and analyzes the genetic information of normal individuals and the genetic information of dementia patients to generate or extract genetic characteristic data.

[0021] The server (100) encodes the brain image data of normal individuals and the brain image data of dementia patients, respectively. The server (100) generates or extracts brain feature data corresponding to the encoded brain image data of normal individuals and the brain image data of dementia patients, respectively. For example, the brain image data may be MRI images of the brain.

[0022] The server (100) uses data obtained by combining gene feature data and brain feature data according to a predetermined method as learning data, and generates a dementia diagnostic model trained to determine whether or not a specific person has dementia based on the genetic information and gene feature data of the specific person. The server (100) diagnoses dementia in accordance with input genetic information and brain image data based on the generated dementia diagnostic model.

[0023] The user terminal (200) can receive a dementia diagnosis result from the server (100). The user terminal (200) can also transmit genetic information and brain image data to the server (100).

[0024] The user terminal 200 may be communicatively connected to the server 100 through a communication network. The user terminal 200 may be a notebook computer, desktop computer, laptop computer, a portable and mobile wireless communication device equipped with a web browser, or any type of handheld wireless communication device such as a smartphone or tablet PC.

[0025] FIG. 2 is a diagram showing a detailed configuration of the server shown in FIG. Referring to FIG. 2, the server (100) may include a communication module (110), a processor (120), and a memory (130).

[0026] The communications module (110) may include a device containing the necessary hardware and software to send and receive signals, such as control or data signals, over wired or wireless connections with other network devices.

[0027] The communication module (110) can receive genetic information and brain imaging data of normal individuals, mild cognitive impairment patients, and dementia patients from the user terminal, and can also transmit dementia diagnosis results to the user terminal.

[0028] The processor 120 may include various types of devices that control and process data, and may refer to a data processing device built into hardware that has circuitry physically configured to perform the functions expressed in the code or instructions contained in a program.

[0029] As an example, the processor 120 may be implemented in the form of a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or the like, but the scope of the present invention is not limited thereto.

[0030] The processor (120) executes operations according to the code stored in the memory (130).

[0031] The memory (130) can store at least one of information and data input through the communication module (110), information and data required for functions performed by the processor (120), and data generated by the execution of the processor (120).

[0032] The memory 130 should be interpreted as a general term for both non-volatile storage devices that maintain stored information even when power is not supplied and volatile storage devices that require power to maintain stored information. The memory 130 may include magnetic storage media or flash storage media in addition to volatile storage devices that require power to maintain stored information, but the scope of the present invention is not limited thereto.

[0033] The memory 130 is electrically connected to the processor 120 and stores at least one code that is executed by the processor 120. The memory 130 stores code that causes the processor 120 to perform functions and procedures such as:

[0034] The memory 130 stores code for generating genetic feature data by comparatively analyzing genetic information of normal individuals and genetic information of dementia patients. For example, the genetic information may be data representing the composition of the microbiota as bacterial abundance data for each sample through analysis of 16s rRNA sequencing data for fecal samples. The genetic feature data may also be a vector generated based on the frequency of occurrence of each type of bacteria.

[0035] The memory 130 may store code for clustering bacterial information contained in the genetic information of each of normal individuals and dementia patients to generate bacterial data. The memory 130 may store code for converting the generated bacterial data into numerical data and extracting vector-formatted gene feature data. For example, the memory 130 may perform ASV clustering and taxon annotation on the 16s rRNA data based on the stored code.

[0036] For example, the memory 130 may convert the ASV data into numerical data based on the stored codes, perform one-hot encoding on the samples for each ASV, and generate a numerical vector representing the ASV features for each sample, where the ASV may be taxonomic information matched down to species.

[0037] The memory 130 may also store code that causes genetic information of mild cognitive impairment patients to be compared and analyzed to extract genetic characteristic data.

[0038] The memory (130) may also store code that uses CNN to extract features from brain image data and vectorize the brain image data corresponding to normal individuals, mild cognitive impairment patients, and dementia patients.

[0039] The memory 130 stores codes for encoding the brain image data of normal individuals and the brain image data of dementia patients. For example, the memory 130 may store codes for encoding the brain image data of normal individuals and the brain image data of dementia patients by region. Here, the brain image data may be brain MRI images, and the memory 130 may store codes for digitizing the brain MRI images into brain image data based on a dementia diagnosis model.

[0040] The memory 130 stores codes for generating brain feature data corresponding to the coded brain image data of normal individuals and the coded brain image data of dementia patients, and may also store codes for extracting brain feature data corresponding to the coded brain image data of mild cognitive impairment patients.

[0041] For example, the memory (130) may store coded brain image data of a normal person, a dementia patient, and a mild cognitive impairment patient, as well as a code that causes brain feature data in vector format to be generated based on a predetermined feature extraction method.

[0042] The memory 130 stores code for generating a dementia diagnosis model trained to determine whether or not a specific person has dementia based on the genetic information and genetic feature data of the specific person, using data obtained by combining genetic feature data, brain feature data of normal individuals, and brain feature data of dementia patients in a predetermined manner as learning data. For example, the memory 130 may store code for generating an input vector by concatenating the genetic feature data and the brain feature data. For example, the memory 130 may generate an input vector by concatenating the brain feature data acquired by the CNN and the converted genetic feature data based on the stored code.

[0043] The memory 130 may store code for training a dementia diagnosis model using the generated input vectors to generate the dementia diagnosis model. For example, the memory 130 may input the combined input vectors to the dementia diagnosis model based on the stored code, and train and execute the dementia diagnosis model. The memory 130 may calculate a prediction value and loss for dementia or normal. Here, the dementia diagnosis model may be a model generated using Keras.

[0044] The memory 130 stores code that causes a diagnosis of dementia in response to input genetic information and brain image data based on a dementia diagnostic model. For example, the memory 130 stores code that causes a diagnosis of dementia in response to input genetic information and brain image data of a specific person using the dementia diagnostic model, and determines the state of the specific person as at least one of mild cognitive impairment, dementia, and normal.

[0045] 3 and 4 are diagrams shown to explain an example of gene characteristic data. 3 and 4, the gene feature data may include bacteria-specific ASV IDs, taxonomic information data related to ASVs, and sample-specific bacterial information for normal and dementia patient samples. For example, the gene feature data may include information on OUT ID, kingdom, phylum, class, order, family, genus, species, AD01, and C88.

[0046] Gene feature data can be extracted in the form of vectors based on the number of occurrences of each ASV, such as AD1=[1,0,0,1] and C88=[0,1,1,0].

[0047] The dementia diagnosis system can convert each ASV into a vector 410 in which each feature has a unique value. For example, if there are four ASVs, the dementia diagnosis system can perform one-hot encoding as follows: ASV1: [1,0,0,0], ASV2: [0,1,0,0], ASV3: [0,0,1,0], and ASV4: [0,0,0,1].

[0048] The dementia diagnosis system can generate transformation data 420 for the samples. For example, the dementia diagnosis system can generate transformation data for sample 1 in which ASV1 exists and sample 2 in which ASV2 and ASV3 exist, such as sample 1: [1,0,0,0], sample 2: [0,1,1,0].

[0049] The dementia diagnosis system can extract gene feature data 440 in vector format based on the number of times each ASV appears 430. For example, if ASV1 appears 5 times and ASV3 appears 3 times in sample 1, and ASV1 appears 2 times and ASV3 appears 7 times in sample 2, the dementia diagnosis system can extract gene feature data 440 as sample 1: [5, 3, 0, 0] and sample 2: [2, 0, 7, 0].

[0050] 5 to 7 are diagrams shown to explain an example of extracting brain characteristic data. 5 to 7, the dementia diagnosis system can encode MRI images of normal subjects, dementia patients, and mild cognitive impairment patients by region. The dementia diagnosis system can combine the region-coded brain image data (610) and feature extraction data (620) to generate a feature map (710).

[0051] The dementia diagnosis system can generate layers related to the features of the brain image data and extract vector-format brain feature data by repeatedly applying max pooling and flattening to the feature map 710. The dementia diagnosis system can analyze newly input brain image data and genetic information based on the brain feature data, and diagnose the presence or absence of dementia.

[0052] 8a and 8b are diagrams shown to explain the accuracy of dementia diagnosis results according to the dementia diagnosis model. Referring to Figure 8a, we can see that the dementia diagnosis model was generated by combining MRI images and 16s rRNA data, and the dementia diagnosis result was output with a loss of 0.203 and an accuracy of 0.91 on the test set. In this case, the dementia diagnosis model can be trained for 10 epochs.

[0053] On the other hand, referring to Figure 8b, when a dementia diagnosis model was generated using only 16s rRNA data without MRI images, the loss on the test set was 0.356 and the accuracy was 0.80.

[0054] This shows that when a dementia diagnostic model is generated by combining MRI images and 16s rRNA data and used to diagnose dementia, accuracy improves to 0.91 and loss decreases by 0.153 compared to when a dementia diagnostic model is generated using only 16s rRNA data.

[0055] FIG. 9 is a flowchart showing the steps of a dementia diagnosis method according to another embodiment of the present invention. The dementia diagnosis method described below can be performed by the dementia diagnosis system and server described above with reference to Figures 1 to 8. Therefore, the contents related to the embodiments of the present disclosure described above with reference to Figures 1 to 8 can be similarly applied to the embodiments described below, and the contents that overlap with the above description will be omitted below. The steps described below do not necessarily have to be performed in order; the order of the steps can be set in various ways, and the steps may be performed almost simultaneously.

[0056] Referring to FIG. 9, the dementia diagnosis method includes a gene feature data extraction step (S100), a brain feature data extraction step (S200), and a dementia diagnosis step based on the gene feature data and the brain feature data (S300).

[0057] The gene feature data extraction step (S100) is a step of extracting gene feature data by comparatively analyzing the genetic information of normal individuals and the genetic information of dementia patients. For example, in the gene feature data extraction step (S100), the bacterial information of each of the genetic information of normal individuals and the genetic information of dementia patients is clustered to generate bacterial data, and the bacterial data can be converted into numerical data to extract gene feature data in vector format.

[0058] The brain feature data extraction step (S200) is a step of coding the brain image data of normal individuals and the brain image data of dementia patients, and extracting brain feature data corresponding to the coded brain image data of normal individuals and the brain image data of dementia patients, respectively. For example, in the brain feature data extraction step (S200), the brain image data of normal individuals and the brain image data of dementia patients are coded by region, and brain feature data in vector format can be extracted based on the coded brain image data and predetermined feature extraction data.

[0059] The dementia diagnosis step based on gene feature data and brain feature data (S300) is a step of generating a dementia diagnosis model trained to determine whether or not a specific person has dementia based on the genetic information and genetic feature data of a specific person, using data obtained by combining the genetic feature data and the brain feature data according to a predetermined method as learning data. For example, in the dementia diagnosis step based on gene feature data and brain feature data (S300), the genetic feature data and the brain feature data are linked to generate an input vector, and the dementia diagnosis model is trained using the input vector, and dementia can be diagnosed based on the dementia diagnosis model in accordance with the input genetic information and brain image data.

[0060] Those skilled in the art to which the present disclosure pertains will understand that the present disclosure can be easily modified into other specific forms based on the above description without departing from the technical spirit or essential characteristics of the present disclosure. Therefore, the above-described embodiments are illustrative in all respects and should not be construed as limiting. The scope of the present disclosure is defined by the claims set forth below, and all modifications and variations derived from the meaning and scope of the claims and their equivalents should be construed as being within the scope of the present disclosure. The scope of the present application is defined by the claims set forth below, rather than the above detailed description, and all modifications and variations derived from the meaning and scope of the claims and their equivalents should be construed as being within the scope of the present application. [Industrial Applicability]

[0061] The present invention can be used in a technique for diagnosing dementia and has industrial applicability.

Claims

1. A dementia diagnosis method performed by a dementia diagnosis system, a) generating genetic feature data by comparatively analyzing genetic information of normal individuals and genetic information of dementia patients; b) encoding the brain image data of normal individuals and the brain image data of dementia patients, and generating brain feature data corresponding to the encoded brain image data of normal individuals and the brain image data of dementia patients, respectively; c) generating a dementia diagnosis model trained to determine whether or not a specific person has dementia based on the genetic information and genetic feature data of the specific person, using data obtained by combining the genetic feature data and the brain feature data in a predetermined manner as learning data; A method for diagnosing dementia, comprising:

2. The method for diagnosing dementia according to claim 1, In step a), the method for diagnosing dementia comprises clustering the bacterial information of the genetic information of the normal individual and the genetic information of the dementia patient to generate bacterial data, and converting the bacterial data into numerical data to generate the gene characteristic data in vector format.

3. 3. The dementia diagnosis method according to claim 2, wherein the gene characteristic data is vector data generated based on the number of occurrences of each type of bacteria.

4. The method for diagnosing dementia according to claim 1 , wherein the genetic information includes 16s rRNA data.

5. 2. The dementia diagnosis method according to claim 1, wherein in step b), the brain image data of the normal subject and the brain image data of the dementia patient are coded by region, and the brain feature data in vector format is generated based on the coded brain image data and a predetermined feature extraction method.

6. 2. The dementia diagnosis method according to claim 1, wherein in step c), the gene feature data and the brain feature data are concatenated to generate an input vector, and the dementia diagnosis model is trained based on the input vector.

7. 2. The dementia diagnosis method according to claim 1, wherein step a) comprises a step of comparatively analyzing genetic information of a patient with mild cognitive impairment and genetic information of a normal individual to generate the genetic feature data; The method for diagnosing dementia, wherein step b) includes a step of comparatively analyzing brain image data of the mild cognitive impairment patient and brain image data of a normal individual to generate the brain feature data.

8. 2. The dementia diagnosis method according to claim 1, wherein step c) includes using the dementia diagnosis model to receive the genetic information and brain image data of a specific person as input, and determining the condition of the specific person as at least one of mild cognitive impairment, dementia, and normal.

9. a communication module; at least one processor; a memory electrically connected to the processor and storing at least one code to be executed by the processor; The memory stores code that, when executed by the processor, causes the processor to compare and analyze genetic information of normal individuals and genetic information of dementia patients to generate genetic feature data, encode each of the brain image data of normal individuals and the brain image data of dementia patients, generate brain feature data corresponding to each of the encoded brain image data of normal individuals and the brain image data of dementia patients, and use data obtained by combining the genetic feature data and the brain feature data in a predetermined manner as learning data to generate a dementia diagnosis model trained to determine whether or not a specific individual has dementia based on the genetic information and genetic feature data of the specific individual.

10. 10. The dementia diagnosis system according to claim 9, wherein the memory stores code that causes the processor to cluster bacterial information from the genetic information of the normal individual and the genetic information of the dementia patient to generate bacterial data, and convert the bacterial data into numerical data to extract the gene feature data in vector format.

11. 10. The dementia diagnosis system according to claim 9, wherein the gene characteristic data is vector data generated based on the number of occurrences of each type of bacteria.

12. 10. The dementia diagnosis system according to claim 9, wherein the memory stores code that causes the processor to code each of the brain image data of the normal subject and the brain image data of the dementia patient by region, and to extract the brain feature data in vector format based on the coded brain image data and predetermined feature extraction data.

13. 10. The dementia diagnosis system according to claim 9, wherein the memory stores code that causes the processor to concatenate the gene feature data and the brain feature data to generate a single input vector, train the dementia diagnosis model using the input vector, and diagnose the dementia based on the dementia diagnosis model.

14. 10. A dementia diagnosis system according to claim 9, wherein the memory stores code that causes the processor to compare and analyze genetic information of patients with mild cognitive impairment with genetic information of normal individuals to generate the genetic feature data, and to compare and analyze brain image data of patients with mild cognitive impairment with brain image data of normal individuals to generate the brain feature data.

15. 10. A dementia diagnosis system according to claim 9, wherein the memory stores code that causes the processor to use the dementia diagnosis model to receive the genetic information and brain imaging data of a specific person as input and determine the specific person's condition as at least one of mild cognitive impairment, dementia, and normal.

Images