Brain image data analysis device, brain image data analysis method, and brain image data analysis program

Abstract

The present invention provides a brain image data analysis device that minimizes the influence of non-uniformity of imaging conditions seen in a brain checkup, measures the atrophy of a part in the brain with good reproducibility, and analyzes the risk of developing dementia.　This brain image data analysis device for analyzing the risk of developing dementia from a brain MRI image has: a segmentation unit 12 for performing segmentation in which division into structural units is performed; a brain structure volume calculation unit 13 for calculating the brain volume for each divided structural unit; an imaging condition difference calibration unit 15 for performing calibration for minimizing the influence of the difference in imaging conditions according to the imaging conditions at the time of imaging performed by an MRI scanner, and a same-age-group ratio calculator 16 for calculating the same-age-group ratio of each structural unit of each subject from each item of structural unit data for each age in a database.

Description

Brain image data analysis device, brain image data analysis method, and brain image data analysis program

[0001] The present invention relates to a brain image data analysis device, and in particular to a brain image data analysis device, a brain image data analysis method, and a brain image data analysis program that are suitable for reducing the influence of uneven imaging conditions in brain checkups and performing highly reproducible brain atrophy measurements.

[0002] Conventionally, a brain checkup is a brain health checkup that checks for brain diseases that cannot be detected in a general health checkup. By performing a head MRI or CT scan, a doctor can interpret and diagnose MRI (Magnetic Resonance Imaging) images or CT (Computed Tomography) images, which are tomographic images of the brain obtained from the MRI or CT device, and can detect cerebrovascular diseases such as cerebral infarction, subarachnoid hemorrhage, and cerebral hemorrhage, as well as Alzheimer's disease, at an early stage.

[0003] Dementia has become one of the most serious social issues in an aging society. To illustrate this point, as shown in Figure 24, Alzheimer's disease accounts for 67.6% of cases and vascular dementia accounts for 19.5%, accounting for approximately 90% of all dementia cases. These cases are expected to be detected using brain tomography images.

[0004] According to the medical journal "Lancet," as shown in Figure 25, as people age, their susceptibility to dementia changes depending on their past lifestyle habits. For example, education (1.6 times), high blood pressure (1.6 times), excessive drinking (1.2 times), obesity (1.6 times), smoking (1.6 times), depression (1.9 times), social isolation (1.6 times), lack of exercise (1.4 times), and diabetes (1.5 times).

[0005] Brain health is directly linked to quality of life (QOL). Figure 26 shows the factors that led to the need for nursing care in the "2016 Comprehensive Survey on Living Conditions of the People (Ministry of Health, Labour and Welfare)." As Figure 26 clearly shows, dementia and cerebrovascular disease (cerebral infarction and cerebral hemorrhage) are the overwhelming causes. For those requiring nursing care level 5, dementia and cerebrovascular disease together account for over 50%. Figure 27 shows the main causes of the need for nursing care over the past 20 years (for those requiring nursing care levels 1-5 / for both men and women) ("2016 Comprehensive Survey on Living Conditions of the People (Ministry of Health, Labour and Welfare)." As Figure 27 clearly shows, when examining the factors that led to the need for nursing care over the past 20 years, dementia has shown a significant increase, and although cerebrovascular disease is on the decline, it remains a major factor. In 2016 data, dementia was the leading cause of the need for nursing care for both men and women. Cerebrovascular disease (cerebral infarction and cerebral hemorrhage) has long been considered a lifestyle factor. As dementia research progresses, it is beginning to be understood that lifestyle is a much greater risk factor for dementia than genetic factors.

[0006] Figure 28 shows the relationship between susceptibility to dementia and risk factors. Figure 28 shows that the susceptibility to dementia increases by 40% to 90% depending on the risk factor. Once dementia develops, it is difficult to treat the underlying condition, so early detection and prevention are the best measures (see Non-Patent Document 1).

[0007] As the number of dementia patients increases, dementia has become a social issue. According to the Brain Checkup Guidelines 2019 (revised, 5th edition), cognitive function testing has been added as a recommended test item to the brain checkup examinations. In particular, cognitive function screening tests (e.g., MMSE, HDS-R, MoCA, CADi2) are recommended as mandatory tests. Because these cognitive function tests must be administered to each brain checkup patient, they impose a burden on patients and also on physicians, resulting in an increased number of test items. This approach is difficult to adopt in health checkup centers that screen many patients per day. Furthermore, even if the results of a brain checkup show no abnormalities, healthy individuals (including those with potential mild cognitive impairment and asymptomatic symptoms) may be reluctant to undergo a brain checkup if it takes too long.

[0008] If a doctor detects atrophy of the hippocampus in an MRI image diagnosis, it can lead to early detection of Alzheimer's disease.

[0009] Recently, a brain checkup program (Brain Suite) using image analysis AI (artificial intelligence) technology has been put into practical use (a product of CogSmart Inc., a startup company spun off from Tohoku University, see "Non-Patent Document 2"). Brain Suite detects the risk of cognitive decline and calculates brain health levels using hippocampal volume measured with "Hippodeep," a brain MRI image analysis AI developed at the Tohoku University Institute of Aging, a dataset of healthy individuals obtained from the Tohoku University database, and the FDA-approved cognitive function test "Cantab."

[0010] In addition, an AI program for brain checkups (Brain Life Imaging (registered trademark)) has been put into practical use, which uses AI (artificial intelligence) to analyze head MRI images, measure and visualize the volume of the hippocampus, and deliver an analysis report to the patient (a product of Splink, Inc., a medical AI startup company; see Non-Patent Document 3).

[0011] MRI equipment manufacturers include Siemens Healthineers, Fujifilm Healthcare, Philips Japan, Canon Medical Systems, and GE Healthcare, and there is no compatibility between manufacturers. There are also various types of MRI equipment, including 0.25T MRI, 0.3T MRI, 0.4T MRI, 1.5T MRI, and 3.0T MRI, but performance varies depending on the equipment. Here, T stands for Tesla, a unit of magnetic field strength.

[0012] The images taken at medical institutions (hospitals, clinics, health checkup centers, etc.) where patients undergo brain checkups vary in resolution due to differences in imaging conditions. Due to these circumstances, even though there are many MRI images obtained during brain checkups, it is generally difficult to use them for brain image analysis.

[0013] Examples of the above-described brain image analysis device include related patent documents such as Japanese Patent Application Laid-Open No. 2021-97988 (Patent Document 1) and Japanese Patent Application Laid-Open No. 2021-97910 (Patent Document 2).

[0014] JP 2021-97988 A JP 2021-97910 A

[0015] Deborah E Barnes, Kristine Yaffe, “The projected effect of risk factor reduction on Alzheimer's disease prevalence”, Lancet Neurol 2011; 10: 819-28, www.thelancet.com / neurology Vol 13 August 2014https: / / www.innervision.co.jp / report / usual / 20210506https: / / sitelp.brain-life-imaging.com / index.html

[0016] The above-mentioned Patent Document 1 measures hippocampal volume using brain MRI images and performs AI brain image analysis, which leads to the detection of cognitive dysfunction such as hippocampal memory function, but because the hippocampus accounts for about 0.3% of the entire brain, high-resolution imaging is required, and there is a problem that sufficient measurement accuracy cannot be obtained with the low-resolution MRI images commonly used in brain checkups. Non-Patent Documents 1 and 2 also have similar problems because they measure hippocampal volume using brain MRI images and perform AI brain image analysis.

[0017] As described in paragraph

[0041] of the specification of Patent Document 2, a plurality of medical images (MRI images) are analyzed, and from the viewpoint of a plurality of contrasts to be input, the contrast is adjusted to match the input image of the detection unit of the selected image, taking into consideration the vendor of the medical image acquisition device, the magnetic field strength (in the case of an MRI device), the imaging conditions, etc., so that the influence of differences in contrast of the original image can be eliminated. However, differences in resolution, such as high resolution and low resolution, of the MRI images are not taken into consideration.

[0018] In order to solve the problems described above, the object of the present invention is to provide a brain image data analysis device, a brain image data analysis method, and a brain image data analysis program that minimize the effects of uneven imaging conditions seen in brain checkups, enable accurate and reproducible measurement of atrophy in various parts of the brain, and analyze the risk of developing dementia.

[0019] According to one aspect of the present invention, there is provided a brain image data analysis device that receives input of brain tomographic images of an evaluation subject captured by a tomographic image scanner device and three-dimensionally analyzes the degree of atrophy of a predetermined region of interest in the brain, the device comprising: a segmentation unit that performs segmentation to divide the entire brain tomographic image into structural units; an identification unit that identifies a structural unit related to the region of interest from the divided structural units; a volume calculation unit that calculates the brain volume of each identified structural unit; a calibration unit that calibrates the brain volume based on the input brain cross-sectional images in accordance with the imaging conditions of the tomographic image scanner device; and a calibration unit that performs calibration of the brain volume based on the input brain cross-sectional images in accordance with the imaging conditions of the tomographic image scanner device. and a same-age ratio calculation unit that calculates the same-age ratio of the structural units of the subject to be evaluated from the data of each structural unit at each age in the database. The calibration unit calibrates the brain volume, for example, by photographing the same person under different shooting conditions or based on the age-related change data in the database. After calibration, the same-age ratio calculation unit calculates the same-age ratio of the brain volumes of the structural units of the subject to be evaluated for multiple subjects based on the data of the structural units at each age in the database, thereby analyzing the degree of atrophy of the specified brain region of interest.

[0020] Preferably, the system further includes a structural unit selection unit that selects, based on brain volume data stored in the database, a structural unit that is associated with atrophy of the region of interest, that has greater age-related changes than other structural units, and that has less change due to the influence of shooting conditions than other structural units, and the identification unit identifies the structural unit selected by the structural unit selection unit.

[0021] Preferably, the specified brain region of interest is a structure known to change in dementia in the limbic system or medial temporal lobe, including the hippocampus, and the structural unit selected by the structural unit selection unit is a structure selected based on the degree of age-related change and robustness to the effects of imaging conditions, including the ventricles.

[0022] Preferably, the tomographic image scanner device is an X-ray CT scanner device.

[0023] Preferably, the tomographic image scanner device is an MRI scanner device.

[0024] Preferably, the same-age ratio calculation unit analyzes the degree of atrophy of a predetermined brain region of interest by independently or collectively analyzing multiple structural units for each age in the database and calculating a same-age ratio, where the multiple structural units are multiple structural units within a single image or multiple structural units obtained from different types of images.

[0025] Preferably, the plurality of structural units include the hippocampus and the ventricles, and the same-age ratio calculation unit i) generates data displaying the volume of the hippocampus as a first axis and the volume of the ventricles as a second axis perpendicular to the first axis, and ii) analyzes the degree of atrophy of a specified region of interest in the brain depending on which quadrant of the coordinates represented by the first axis and the second axis the calculated value of the brain volume of the subject belongs to.

[0026] Preferably, the peer ratio calculation unit evaluates the dementia risk of the subject by analyzing the degree of atrophy of a predetermined region of interest in the brain.

[0027] Preferably, the system further includes a signal intensity calculation unit that calculates the signal intensity of each identified structural unit, and the age-related change data in the database is obtained by previously imaging multiple subjects and includes signal intensity data for each structural unit at each age under various imaging conditions, and the calibration unit calibrates the signal intensity based on the age-related change data in the database, and the same-age ratio calculation unit, after calibration, analyzes the risk of cerebrovascular disease of the structural unit by comparing the signal intensity of the structural unit of the subject being evaluated for the multiple subjects with that of the same age based on the data on the structural unit at each age in the database.

[0028] Preferably, the apparatus further comprises a calibration coefficient determination means, which includes correlation creation means for creating volume-age correlation curves for structural units of a plurality of subjects of different ages based on age-related change data, parameter extraction means for extracting correlation parameters from the created correlation curves, and matching means for determining a calibration coefficient for brain volume so as to reduce differences in the extracted correlation parameters, and the calibration unit calibrates the brain volume based on the determined calibration coefficient.

[0029] Preferably, the same age ratio calculation unit calculates the position of the subject in the population distribution of the structural unit based on the age of the subject, based on the population distribution of the volume of the structural unit at each age.

[0030] According to another aspect of the present invention, there is provided a method for analyzing brain image data using an analysis device that receives input of a brain tomographic image of a subject taken by a tomographic image scanner and three-dimensionally analyzes the degree of atrophy of a predetermined region of interest in the brain, the analysis device having a database containing age-related change data obtained by previously image-taking images of a plurality of subjects, the age-related change data including brain volume data of each structural unit at each age under various imaging conditions, and the method comprising the steps of: segmenting the entire brain tomographic image into each structural unit; identifying structural units related to the region of interest from among the divided structural units; calculating the brain volume of each identified structural unit; calibrating the brain volume based on the input brain cross-sectional image in accordance with the imaging conditions of the tomographic image scanner based on the age-related change data in the database; and calculating a same-age ratio of the structural unit of the subject to be evaluated at each age in the database, wherein the step of calculating the same-age ratio includes a step of analyzing the degree of atrophy of the predetermined region of interest in the brain after calibration by calculating a same-age ratio of the brain volume of the structural unit of the subject to be evaluated compared to the plurality of subjects based on the data of the structural unit at each age in the database.

[0031] Preferably, the method further includes a step of determining a calibration coefficient, the step of determining the calibration coefficient including the steps of creating a volume-age correlation curve for structural units of subjects of different ages based on photographs of the same person taken under different photographing conditions or on age-related change data, extracting correlation parameters from the created correlation curve, and determining a calibration coefficient for brain volume so as to reduce the difference between the extracted correlation parameters, and the step of calibrating the brain volume based on the determined calibration coefficient.

[0032] Preferably, the step of calculating the same age ratio includes a step of calculating the position of the subject in the population distribution of the structural unit based on the age of the subject, based on the population distribution of the volume of the structural unit at each age.

[0033] Preferably, the step of calculating the peer ratio includes the step of assessing the dementia risk of the subject by analyzing the degree of atrophy of a predetermined region of interest in the brain.

[0034] According to yet another aspect of the present invention, there is provided a brain image data analysis program for causing a computer having a storage device and an arithmetic unit to execute processing as an analysis device that receives input of a brain tomographic image of an evaluation subject captured by a tomographic image scanner and three-dimensionally analyzes the degree of atrophy of a predetermined region of interest in the brain, the storage device comprising a database containing age-related change data including brain volume data of each structural unit at each age under various imaging conditions, the data having been captured in advance for a plurality of subjects, the brain volume data being obtained by the arithmetic unit performing segmentation to divide the entire brain tomographic image into each structural unit, and the arithmetic unit identifying a structural unit related to the region of interest from the divided structural units. The method includes the steps of: a calculation device calculating the brain volume of each identified structural unit; a calculation device calibrating the brain volume based on the input brain cross-sectional image in accordance with the imaging conditions of the tomographic image scanner device, based on the age-related change data in the database; and a calculation device calculating the same-age ratio of the structural unit of the subject to be evaluated from the data of each structural unit at each age in the database, wherein the step of calculating the same-age ratio includes a step of analyzing the degree of atrophy of a specified region of interest in the brain by calculating the same-age ratio of the brain volume of the structural unit of the subject to be evaluated for multiple subjects, based on the data of the structural unit at each age in the database after calibration.

[0035] In this specification, "brain checkup" refers to the examination of the health condition of the brain by taking cross-sectional images of the subject's head using diagnostic imaging equipment (including MRI equipment and X-ray CT equipment) installed in clinics, hospitals, etc. For the analysis of brain structure, it is desirable to take images that can reproduce the three-dimensional structure of the brain.

[0036] According to the 11th revision of the International Classification of Diseases (ICD-11), which came into effect in January 2022, dementia is defined as "an acquired syndrome characterized by a decline from previous levels in two or more of the following cognitive domains: (1) memory, (2) executive function, (3) attention, (4) language, (5) social cognition and judgment, (6) psychomotor speed, and (7) visual or visuospatial cognition." With the revision from ICD-10 to ICD-11, memory impairment is no longer a mandatory requirement. Additionally, new cognitive impairments, "social cognition impairment" and "psychomotor speed delay," have been added.

[0037] According to the present invention, it is possible to realize a brain image data analysis device, a brain image data analysis method, and a brain image data analysis program that minimize the effects of uneven imaging conditions seen in brain checkups, enable accurate and reproducible measurement of atrophy in various parts of the brain, and analyze the risk of developing dementia.

[0038] The drawings show specific embodiments of the present invention according to the present disclosure, and include not only essential components of the invention but also optional and preferred embodiments.

[0023] FIG. 1 is a functional block diagram of a brain image data analysis device according to an embodiment.

[0024] FIG. 2 is a block diagram for explaining the hardware configuration of the brain image data analysis device 1 shown in FIG. 1.

[0025] FIG. 3 is a flowchart of brain image data analysis processing by the brain image data analysis device of FIG. 1.

[0026] FIG. 4 is a functional block diagram of a brain image data analysis device according to an embodiment.

[0027] FIG. 5 is a diagram showing examples of segmentation training data at various structural levels.

[0028] FIG. 6 is a flowchart showing pre-analysis of brain image data analysis processing by the brain image data analysis device.

[0029] FIG. 7 is a flowchart showing analysis of a subject's brain image data analysis processing by the brain image data analysis device of FIG. 1.

[0029] FIG. 8 is a functional block diagram of an imaging condition calibration unit in the brain image data analysis device according to the present embodiment shown in FIG. 1 or FIG. 4.

[0029] FIG. 9 is a processing flowchart of the imaging condition calibration unit in the brain image data analysis device according to the present embodiment shown in FIG. 1 or FIG. 4.

[0029] FIG. 9 is a diagram comparing before and after calibration using ventricular volume-age correlation.

[0030] FIG. 9(a) is a diagram showing an example before calibration, and FIG. 9(b) is a diagram showing an example after calibration.

[0031] FIG. 9 is a functional block diagram of a peer age ratio calculation unit in the brain image data analysis device according to the embodiment shown in FIG. 1 or FIG. 4. 1 is a processing flowchart of the same-age ratio calculation unit in the brain image data analysis device of the embodiment of FIG. 1 or FIG. 4. A diagram showing normal distribution (by age) using a logarithmic scale of ventricular volume. (a) shows the 30s, (b) the 40s, (c) the 50s, and (d) the 60s. A diagram showing a histogram of ventricular volume by age for women using a linear scale. (a) shows the 30s, (b) the 40s, (c) the 50s, and (d) the 60s. A diagram showing a histogram of ventricular volume by age for men using a linear scale. (a) shows the 30s, (b) the 40s, (c) the 50s, and (d) the 60s. A diagram showing Z-scores of ventricular volume based on a normal distribution model (solid line) and gradient boosting regression (dotted line) for pooled data. This is a functional block diagram of the cerebrovascular disorder degree calculation unit in the brain image data analysis device of the embodiment of FIG. 1 or FIG. 4. 5 is a processing flowchart of a cerebrovascular disorder degree calculation unit in the brain image data analysis device of the embodiment of FIG. 1 or FIG. 4 .1 is a diagram showing training data defining regions of brain white matter with abnormal signals. 2 is a diagram showing the correlation between age and the volume of regions of white matter with abnormal signals. 3 is a diagram showing an example of a monitor display screen for a comprehensive evaluation, "global brain atrophy evaluation," in the brain image data analysis device of this embodiment. 4 is a diagram showing an example of a comprehensive evaluation of brain atrophy and vascular lesions in the brain image data analysis device of this embodiment. 5 is a diagram showing the results of an analysis report created from past MRI images. 6 is a diagram showing an example of a monitor display screen for "vascular lesion evaluation." 7 is a diagram showing the proportion of dementia by type. 8 is a diagram showing examples of dementia risk. 9 is a diagram showing example statistical data showing an overview of the 2016 Comprehensive Survey on Living Conditions of the People. 10 is a diagram showing examples of the main causes of the need for nursing care. 11 is a diagram showing lifestyle risk factors for the onset of dementia. 12 is a diagram showing a comparison of the volume of brain structures (left hemisphere) between patients with Alzheimer's disease (AD) and healthy individuals. 13 is a diagram showing a comparison of the volume of brain structures (ventricles) between patients with Alzheimer's disease (AD) and healthy individuals. 14 is a diagram showing the correlation between age and ventricular volume calculated from a normal distribution model. 15 (a) is a diagram showing a lateral view of the brain. 16 (b) is a diagram showing a posterior view of the brain. 1 is a diagram showing the degree of dilation of the anterior and lateral lateral ventricles with age. A diagram showing the relationship between ventricular volume and blood pressure (men and women in their 50s). A diagram showing the relationship between ventricular volume and drinking frequency (number of times per week) (men and women in their 50s). A diagram showing a comparison of signal intensity changes between normal cases and cases with vascular lesions. A diagram showing the relationship between the volume of the signal change area and age (vascular lesions). A diagram for explaining the flow of lifestyle habits and brain disease detection using M-vision measurement (brain MRI). A diagram showing the configuration of a workstation and a medical image management system (PACS) using the brain image data analysis device of this embodiment. A diagram showing an example in which the brain image data analysis device of this embodiment is applied to a cloud server. A diagram showing an example in which the brain image data analysis device of this embodiment is applied to a cloud server. A diagram for comparing the correlation between limbic system volume and hippocampal volume in patients with Alzheimer's disease (AD) and healthy subjects. A diagram for comparing the correlation between ventricular volume and hippocampal volume in patients with Alzheimer's disease (AD) and healthy subjects. A diagram showing brain structures that show significant age-related changes in the brain image data analysis device of this embodiment. A diagram showing the cerebral hemispheres. 1 shows gray matter, ventricles, and the Sylvian sulcus. 2 shows areas with abnormal signals in the anterior ventricular horn.1A is a diagram showing the relationship between examinee age and atrophy level (ventricular volume) in low-resolution imaging (2.5 mm data). (b) is a diagram showing the relationship between examinee age and atrophy level (ventricular volume) in high-resolution imaging (1.2 mm data). (a) is a diagram showing the frequency of atrophy of ventricular volume in female examinees (by age: 30s, 40s, 50s, 60s, 70s). (b) is a diagram showing the frequency of atrophy of ventricular volume in male examinees (by age: 30s, 40s, 50s, 60s, 70s). (c) is a diagram showing a histogram and log-normal distribution of atrophy level (logarithmic value of ventricular volume) by age. (d) is a diagram showing the difference between population analysis obtained from a normal distribution model and the AD patient region. (e) is a diagram showing example images of the ventricles. (a) is a diagram showing an actual example of ventricular enlargement in a typical normal case (40s). (b) is a diagram showing an actual example of ventricular enlargement in an atrophic case without atrophy findings (40s). 1A and 1B are diagrams showing example images of the ventricles. (a) is a diagram showing an actual example of ventricular enlargement in a typical normal case (in their 40s). (b) is a diagram showing an actual example of ventricular enlargement in an atrophic case without atrophy findings (in their 40s). (c) is a diagram showing an example of ventricle images. (a) is a diagram showing an actual example of ventricular enlargement in a typical normal case (in their 30s). (b) is a diagram showing an actual example of ventricular enlargement in an atrophic case with mild bilateral lateral ventricle enlargement (in their 30s). (d) is a diagram showing the correlation between blood glucose levels and ventricular volume. (a) is a diagram showing the correlation between blood glucose levels and ventricular volume in men and women in their 40s (low-resolution data 2.5 mm). (b) is a diagram showing the correlation between blood glucose levels and ventricular volume in men and women in their 50s (low-resolution data 2.5 mm). (c) is a diagram showing the correlation between blood glucose levels and ventricular volume in men and women in their 40s (high-resolution data 1-1.2 mm). (d) is a diagram showing the correlation between blood glucose levels and ventricular volume for men and women in their 50s (high resolution data 1-1.2 mm). A diagram showing the correlation between blood pressure values ​​and ventricular volume. (a) is a diagram showing the correlation between blood pressure values ​​and ventricular volume for men and women in their 40s (low resolution data 2.5 mm). (b) is a diagram showing the correlation between blood pressure values ​​and ventricular volume for men and women in their 50s (low resolution data 2.5 mm). (c) is a diagram showing the correlation between blood pressure values ​​and ventricular volume for men and women in their 40s (high resolution data 1-1.2 mm). (d) is a diagram showing the correlation between blood pressure values ​​and ventricular volume for men and women in their 50s (high resolution data 1-1.2 mm). A diagram showing the correlation between visceral fat mass and ventricular volume.(a) is a diagram showing the correlation between visceral fat mass and ventricular volume for men and women in their 40s (low-resolution data 2.5 mm); (b) is a diagram showing the correlation between visceral fat mass and ventricular volume for men and women in their 50s (low-resolution data 2.5 mm); (c) is a diagram showing the correlation between visceral fat mass and ventricular volume for men and women in their 40s (high-resolution data 1-1.2 mm); (d) is a diagram showing the correlation between visceral fat mass and ventricular volume for men and women in their 50s (high-resolution data 1-1.2 mm); and (a) is a diagram showing the correlation between alcohol consumption (times / week) and ventricular volume for men and women in their 40s (low-resolution data 2.5 mm). (b) is a diagram showing the correlation between alcohol consumption (times / week) and ventricular volume for men and women in their 50s (low-resolution data 2.5 mm). 1-1.2mm。 (c) is a diagram showing the correlation between drinking (times / week) and ventricular volume for men and women in their 40s (high-resolution data 1-1.2mm). (d) is a diagram showing the correlation between drinking (times / week) and ventricular volume for men and women in their 50s (high-resolution data 1-1.2mm). Figure 1 shows the results of analysis for simultaneously estimating atrophy risk and vascular lesion (white matter organization) risk. Figure 1 shows the results of initial analysis of time-series data. (a) is a diagram showing the results of initial analysis of time-series data using low-resolution data (2.5mm). (b) is a diagram showing the results of initial analysis of time-series data using high-resolution data (1-1.2mm). Figure 1 shows the relationship between ventricular volume and ventricular expansion rate. (a) is a diagram showing the relationship between ventricular volume and ventricular expansion rate using low-resolution data (2.5mm). (b) is a diagram showing the relationship between ventricular volume and ventricular expansion rate using high-resolution data (1-1.2mm). Figure 1 shows an example of a detailed cerebral atrophy pattern evaluation monitor display screen. 1 is a diagram showing an example of an analytical evaluation monitor display screen for the four major lifestyle factors that affect brain atrophy.

[0023] FIG. 1 is a diagram showing (a) the influence of blood glucose level, (b) the influence of visceral fat mass, (c) the influence of blood pressure level, and (d) the influence of drinking frequency.

[0024] FIG. 1 is a diagram showing examples of brain structures related to dementia risk.

[0025] FIG. 1 is a diagram showing cross-sectional brain images of a subject in his 50s and a subject in his 70s.

[0026] FIG. 1 is a conceptual diagram showing an example of combined analysis when the hippocampus and ventricles are the measurement targets.

[0027] FIG. 1 is a diagram showing an example of measured values ​​of the hippocampus and ventricles plotted on a graph with hippocampal volume on the horizontal axis and ventricular volume on the vertical axis.

[0028] FIG. 1 is a diagram showing an example of measured values ​​of the amygdala and ventricles plotted on a graph with amygdala volume on the horizontal axis and ventricular volume on the vertical axis.1 is a diagram showing a flowchart of a process for evaluating atrophy of brain structures using composite indicators. 2 is a diagram showing the concept of data flow from data acquisition to achieve both pseudonymization of data and usability as longitudinal data, to the joint use of data. 3 is a conceptual diagram showing a configuration that enables pseudonymized information to be used by both system operators and data users. 4 is a flowchart for explaining the operation of the system.

[0039] The details of the brain image data analysis device according to the present invention will be described below with reference to the accompanying drawings. The following embodiments include not only essential features of the present invention, but also features that can be selectively adopted and features that can be combined as appropriate.

[0040] [Embodiment 1]

[0041] The brain imaging data analysis device of this embodiment utilizes AI technology from Johns Hopkins University in the United States, and is based on software developed to use AI to analyze big data on 30,000 MRI brain images stored in Japan, thereby comprehensively evaluating brain atrophy and vascular changes, which are characteristics observed in patients with dementia and cerebral infarction.

[0042] Such brain image analysis technology developed by Johns Hopkins University in the United States is disclosed in the following documents, for example: Reference 1: U.S. Patent No. 10,074,173 Reference 2: U.S. Patent No. 10,535,133

[0043] In particular, Reference 1 discloses an automatic segmentation technique that can flexibly change the granularity level of the whole brain based on the hierarchical relationship of 254 structures defined in a brain atlas. Reference 2 discloses a technique that performs automatic segmentation of brain images and labels each structure using a generative model technique based on multiple atlases.

[0044] However, other segmentation methods and other labeling techniques may be used for segmenting brain images and labeling each structure.

[0045] In this specification, a "structural unit" of a brain image is described as referring to each of a plurality of structures (e.g., 505 structures) that have been automatically segmented based on one or more known brain atlases (brain maps), for example, using the method defined in Reference 1. However, as will be described later, the number of structures to be segmented is not limited to 505 structures, and for example, several segments may be integrated and considered as one "structural unit."

[0046] However, it is known that the structure of the brain is hierarchical and that its functions are localized, and the "structural units" obtained from brain images are not limited to those obtained using the method in Reference 1, but other divisions that can be distinguished from the information of the acquired images depending on the performance, type, imaging principle, imaging conditions, etc. of the scanner may also be used as "structural units."

[0047] As will be described later, a combination of multiple automatically segmented "structural units" may correspond to a single "brain structure." For example, the "brain structure" called the "ventricle" may consist of the lateral ventricle, the third ventricle, and the fourth ventricle, and the lateral ventricle may further have a hierarchical relationship consisting of an anterior portion, a posterior portion, and a lateral portion.

[0048] The brain image data analysis device of this embodiment utilizes the above-mentioned technology to quantify and evaluate ventricular expansion and the volume of the cerebral cortex in each part of the brain, and outputs reports such as the following: 1) "Comprehensive brain atrophy assessment" that evaluates the aging progression of the degree of brain atrophy by comparing with subjects of the same age.

[0049] 2) "Vascular lesion assessment" involves quantifying the volume of white matter lesion areas and comparing them with patients of the same age to assess the progression of vascular lesions in the brain over time.

[0050] The program that runs on the brain image data analysis device is a program for brain checkups and health centers that uses AI analysis of lesions or deviations from the average value based on these evaluations to measure analytical values ​​that serve as supplementary information or reference information for brain health risks and obtain information on the analytical results.

[0051] <Principle of the analysis device>

[0052] First, the technical background and principles of the brain image data analysis device will be explained using FIGS. 29 to 37.

[0053] Brain image data analysis devices automatically quantify the degree of brain atrophy and vascular lesions from MRI images, enabling the extraction of information related to dementia. Conventional brain checkups have used brain MRI to detect and diagnose aneurysms, brain tumors, cerebral infarction, and intracerebral inflammation. However, they have not yet been able to predict the risk of developing dementia as a lifestyle-related disease and help reduce or prevent the onset of dementia. While existing technology includes programs for measuring the volume of the hippocampus, which plays a major role in cognitive function, the hippocampus accounts for only 0.3% of the human brain's volume. Volumetric measurements of the brain's parenchymal structure are prone to variability depending on the type of MRI equipment, resolution, and imaging method, making it difficult to accumulate useful information as stable tracking data. Furthermore, as discussed below, much of the remaining 99.7% of brain structure is important for estimating dementia risk, limiting the value of measuring the hippocampus alone.

[0054] Furthermore, measuring hippocampal atrophy requires a high-resolution brain MRI, but taking MRI images takes time, so high-resolution images are often not taken during brain checkups. Brain checkups in Japan have a long history of over 20 years, with over 1 million pieces of data already in existence, and some locations even having time-series data going back more than 15 years. However, for the reasons mentioned above, they are not necessarily able to reduce the risk of developing dementia or address risk management for dementia, which will become increasingly important in the future.

[0055] Analysis using the brain image data analysis device of this embodiment makes it possible to accumulate large amounts of big data and perform automatic AI analysis, which will greatly contribute to future dementia risk management. Analysis using this brain image data analysis device is already being conducted using existing data from brain checkup centers and research institutions. This analysis is a technology that is expected to lead to world-class big data analysis in the future, with existing data alone exceeding one million items.

[0056] This analysis of brain image data aims to increase the stability of measurements by measuring structures such as ventricular volume, which are less affected by MRI image acquisition conditions and sensitively reflect brain atrophy, thereby simplifying the analysis of brain atrophy data from brain checkups.

[0057] Figure 32 is a conceptual diagram showing the structure of the ventricles in the brain, where Figure 32(a) is a sagittal cross-sectional view of the ventricles, and Figure 32(b) is a horizontal cross-sectional view of the ventricles.

[0058] As shown in Figure 32(a) and (b), the ventricles are divided into the lateral, third, and fourth ventricles based on their shape. In young brains, most of these ventricles are closed and undetectable, but as brain atrophy progresses, gaps appear. Comparing people aged 30 to 60, the cerebral cortex shrinks by an average of about 4%, while the ventricles expand by more than 50%. This brain image data analysis device can examine or diagnose the degree of brain atrophy by evaluating the volumetric measurements of the ventricles, which are sensitive to brain atrophy. It can also detect atrophy in various regions by dividing the lateral ventricles into anterior, posterior, and lateral portions and measuring them (Figure 32(a) and (b)).

[0059] FIG. 33 is a diagram showing the degree of dilation of the anterior and lateral ventricles with age.

[0060] As shown in Figure 33, the anterior part of the lateral ventricle, which is strongly affected by frontal lobe atrophy, begins to expand in people in their late 30s, whereas the lateral part of the lateral ventricle, which is affected by limbic atrophy including the hippocampus, begins to expand after people reach their 60s. The brain image data analysis device of this embodiment makes it possible to measure the degree of brain atrophy by age and region in such a detailed manner.

[0061] 29 and 30 are diagrams showing the degree of brain atrophy in Alzheimer's disease patients (AD) compared with that in healthy individuals who have not developed dementia.

[0062] Figures 29 and 30 show the results of an investigation into the actual extent of brain atrophy in Alzheimer's disease patients (AD) and healthy individuals who have not developed dementia, using the segmentation function of the brain image data analysis device of this embodiment.

[0063] As shown in FIG. 29, it can be seen that the hippocampus of AD patients is more atrophied than that of healthy individuals.

[0064] Furthermore, as shown in Figure 30, since the ventricles are fluid-filled spaces, their volume expands as brain atrophy progresses, and therefore the area in AD patients is shifted to the right (the expanding side) compared to healthy individuals.

[0065] As brain atrophy progresses, the volume of the ventricles expands, but atrophy also occurs widely in other parts of the brain. However, there is also some overlap in the proportion of the brain occupied by the ventricles between AD patients and healthy individuals. In other words, some AD patients appear to have little atrophy, while others appear to have atrophy. While people with advanced brain atrophy are more likely to have dementia, diagnosing dementia by measuring brain atrophy alone can be difficult. Furthermore, such comparisons of Alzheimer's disease patients and healthy individuals can only be conducted on individuals aged 70 or older. The pattern of brain atrophy with age follows a reverse evolutionary process, first progressing to atrophy of primitive areas: the frontal, parietal, and temporal lobes, followed by the occipital lobe and the limbic system, including the hippocampus. Once atrophy reaches these primitive areas, a person loses important functions as a living being, reaching the level of dementia, which is defined as "impairing daily life." Conversely, it can be said that significant atrophy of the limbic system, including the hippocampus, is rare in the pre-illness stage of middle age.

[0066] Therefore, in order to provide auxiliary or reference information for diagnosing the risk of developing dementia, with dementia considered a lifestyle-related disease, it is essential to build a database of brain MRIs of people in their 40s to 60s in the pre-disease stage and to understand the atrophy of structures that act as precursors to dementia in the pre-disease stage.

[0067] Figure 31 shows the results of measuring the ventricular volume of over 30,000 people aged from their 20s to 90s using a brain image data analysis device of this embodiment (for example, a device that uses M-Vision Brain (registered trademark) or M-Vision health (registered trademark) as software), and quantifying the brain health status.

[0068] The results shown in Figure 31 are based on data provided by Midtown Clinic. For example, the degree to which a subject's ventricular volume differs from the average for the same age can be used as an indicator of suspected brain atrophy. These results also revealed the existence of middle-aged individuals whose atrophy rate is rapid. Experiments and analyses are already underway at other brain checkup centers and research institutions using the brain image data analysis device of this embodiment (M-Vision Brain (registered trademark): brain image data analysis program). These analyses are expected to eventually lead to world-class big data analysis involving hundreds of thousands of data sets. Brain checkups in Japan have a history of over 20 years, with existing data exceeding one million records, and some locations even holding time-series data spanning over 15 years. If big data created by combining these conventional brain checkups with the brain image data analysis device of the present invention could be used for automated AI analysis, it could significantly contribute to future dementia risk management.

[0069] In reality, to prove that these middle-aged brain characteristics can predict future Alzheimer's disease, it would be necessary to follow a huge number of people for over 40 years. Therefore, it is currently difficult to directly observe the causal relationship between middle age and old age. However, the current medical community believes that the relationship between middle-aged brain atrophy and dementia is strongly influenced by lifestyle factors, and that it progresses gradually over the years.

[0070] The above-mentioned trends have been confirmed in previous studies using this brain imaging data analysis device.

[0071] Figure 34 shows the relationship between ventricular volume and blood pressure, and Figure 35 shows the relationship between ventricular volume and drinking frequency (number of times per week). These results suggest that brain atrophy that begins in middle age can be managed through improvements in lifestyle factors, and it is thought that dementia can be prevented by identifying people at high dementia risk early and encouraging them to improve lifestyle factors such as blood pressure, drinking, obesity, and blood sugar.

[0072] Furthermore, in addition to analyzing atrophy due to dementia, the brain image data analysis device of this embodiment can also be used to analyze vascular lesions in the brain.

[0073] Figure 36 shows the signal intensity changes specific to normal cases and vascular lesion cases, and Figure 37 shows the relationship between the volume ratio of the detected signal change area (shown as "cerebral vascular aging degree" in the figure) and age. Cerebrovascular aging degree is evaluated into three levels: "average zone," "cautionary zone," and "alert zone."

[0074] Figure 38 shows the relationship between lifestyle-related diseases and brain diseases when this brain image data analysis program is used. This allows risk assessment of dementia and cerebrovascular disease, which are brain diseases.

[0075] The configuration and operation of the brain image data analysis device described above will now be described in detail.

[0076] <Configuration>

[0077] FIG. 1 is a functional block diagram of the brain image data analysis device according to the first embodiment.

[0078] As shown in Figure 1, the brain image data analysis device 1 of this embodiment has an image input unit 11, a segmentation unit 12, a brain structure volume calculation unit 13, a brain signal intensity calculation unit 14, an imaging condition calibration unit 15, a peer ratio calculation unit 16, a cerebrovascular disorder degree calculation unit 17, an analysis report creation unit 18, and an analysis report output unit 19.

[0079] Database 2 is a big data database, and includes brain volume data for each structural unit at each age under various imaging conditions (including resolution, slice thickness, slice angle, slice direction, and sequence parameters (echo time, repetition time, flip angle, etc.)), age-structural unit volume data including brain signal intensity data, age-structural unit signal intensity data, etc. This database may be stored in a storage device such as a server in the analysis center, or in a storage device installed on a cloud server. Note that the data referred to as "big data" here may include not only existing data captured and integrated at multiple imaging sites, but also data that is newly acquired at multiple imaging sites, including non-existent ones, and is accumulated sequentially. <Configuration Description>

[0080] The "image input unit 11" accepts input of brain images (brain MRI images) acquired by an MRI scanner or brain images and imaging condition data transmitted from a PACS (Picture Archiving and Communication System), as well as attribute data of the imaged subject. The image input unit 11 corresponds to a communication interface that allows the brain image data analysis device 1, which is realized as a computer, to exchange data with the outside. The PACS may be a server on the cloud, and the brain image data analysis device itself may also be a server on the cloud.

[0081] The "segmentation unit 12" performs segmentation to divide the entire brain MRI image into structural units. Although not particularly limited, this segmentation can utilize the techniques described in the above-mentioned references 1 and 2, for example.

[0082] The "brain structure volume calculation unit 13" calculates the brain volume for each divided structural unit.

[0083] The "brain signal intensity calculation unit 14" calculates the brain signal intensity for each divided structural unit. Although the brain structural volume calculation unit 13 and the brain signal intensity calculation unit 14 are separated into separate functions, they may be configured as a single integrated function.

[0084] The 'imaging condition calibration unit 15' performs calibration in accordance with the imaging conditions when an image is captured by the MRI scanner, in order to minimize the influence of differences in the imaging conditions.

[0085] The 'same age ratio calculation unit 16' calculates the same age ratio of each structural unit of each subject from the structural unit data for each age in the database 2.

[0086] The 'cerebrovascular disorder degree calculation unit 17' calculates the degree of cerebrovascular disorder.

[0087] The analysis report creation unit 18 creates an analysis report based on the analysis results obtained.

[0088] As described above, the brain image data analysis device 1 is realized by executing arithmetic processing on a computer. Therefore, the segmentation unit 12, brain structure volume calculation unit 13, brain signal intensity calculation unit 14, imaging condition calibration unit 15, peer ratio calculation unit 16, cerebrovascular disorder degree calculation unit 17, and analysis report creation unit 18 correspond to functions executed by a CPU (Central Processing Unit) based on a program stored in memory, and this program includes modules that execute each function. In addition, information to be included in a report corresponding to the analysis results is also stored as data in the database 2.

[0089] FIG. 20 shows an example of a monitor display screen for a comprehensive evaluation of overall brain atrophy, which is created by the analysis report creation unit 18.

[0090] In the example of Figure 20, the entire brain is roughly divided into five regions: the frontal lobe, parietal lobe, occipital lobe, temporal lobe, and deep brain, and each region is divided into left and right regions, and displayed as a map in a spider chart, with an explanation (not shown) displayed on the right. The state of brain atrophy is evaluated based on the ranking of people of the same age group.

[0091] Brain atrophy is classified into the following four health zones based on the ranking of people of the same age. Warning group: Values ​​within the top 5%. Caution group: Values ​​within the top 20%. Average group: Values ​​within the top 20 to 80%.

[0092] Relatively good group: Values ​​in the top 80% or higher.

[0093] However, the classification of health status zones is not limited to this, and as mentioned above, different classifications may be possible as brain imaging data, clinical data, and health data are further accumulated.

[0094] Furthermore, without being limited to this, for example, an analysis report displayed on such a monitor screen may have the following commentary (annotation) added to the right side: "EEG is broadly divided into five areas, and each area is said to have a different function. While atrophy with age is a natural process, excessive atrophy is considered one of the greatest risks of dementia. The areas where atrophy progresses tend to differ depending on the type of dementia. The functions of each area and the areas that doctors consider to be important for different types of dementia are as follows: Frontal lobe: Higher-level functions such as planning and executing actions Parietal and occipital lobes: Sensation, vision, environmental awareness Temporal lobe: Language, hearing Limbic system: Memory, emotions Areas where atrophy is seen in major dementias Alzheimer's disease: Limbic system, temporal lobe, parietal lobe, frontal lobe Temporal lobe dementia: Frontal lobe, temporal lobe Dementia with Leppy bodies: Overall brain function"

[0095] Figure 21 shows an example of a monitor screen for the overall evaluation of cerebral atrophy and vascular lesions. The left column shows an example of an overall evaluation map for cerebral atrophy and vascular lesions, and the right column shows an evaluation commentary (not shown). The evaluation map uses the same-age ranking described above. The horizontal axis shows cerebral atrophy, and the vertical axis shows vascular lesions. In the evaluation map, "☆" indicates the date of the subject's examination. In the example of Figure 21, this indicates that the subject underwent a brain checkup on December 6, 2021, and that cerebral atrophy is in the caution category, but vascular lesions are in the average category.

[0096] Furthermore, although not particularly limited, for example, the analysis report displayed on such a monitor display screen may have the following commentary (annotation) added to the right column:

[0097] This comprehensive assessment determines your brain health type based on two of the biggest risk factors for dementia: cerebral atrophy and vascular lesions. The further to the right on the chart, the more heterogeneous the type, and the higher up, the more severe the vascular lesions. It is said that vascular dementia is on the decline in Japan due to increased awareness of vascular disease and improved lifestyle habits in recent years. However, if you have the vascular lesion type, we recommend that you increase your awareness of your vascular health. It is said that 30 to 50 percent of dementia cases are caused by lifestyle habits, and high blood pressure, high blood sugar, middle-aged obesity, and alcohol use are cited as risk factors. These factors are used to assess your health, so if you have been determined to require caution for cerebral atrophy or cerebrovascular lesions, please refer to the next page.

[0098] FIG. 22 shows an example of an analysis report created for a subject in comparison with past MRI image data.

[0099] FIG. 23 shows an example of a monitor screen of an analysis report of vascular lesion evaluation, similar to FIG. 22.

[0100] Here, as an example, we consider a situation in which the brain image data analysis device 1 shown in Figure 1 is operated on a server on the cloud and receives "brain image data," "imaging condition data," and "subject attribute information" from each imaging site (health checkup center, hospital, etc.).

[0101] In this case, the brain image data analysis device 1 creates an analysis report such as those shown in Figures 20 to 23, and outputs the analysis report from the analysis report output unit 19 to a health checkup center, hospital, individual, etc. via a network.

[0102] 1, the analysis report output unit 19 outputs the analysis report created by the analysis report creation unit 18. The analysis report is in the form of a combination of text and images, and can be provided to the client as electronic data or paper media. If the client is an individual, the request for the creation of the analysis report from the client may be made via access via the Internet, or may be an online request from a health checkup center or hospital.

[0103] The analysis report output unit 19 can output the report in PDF format, which combines text and images, or as paper output. In the case of a medical examination center, for example, many brain MRI images may be analyzed. In addition to these formats, images may be sent in the DICOM (Digital Imaging and Communications in Medicine) standard, and text may be provided in Excel (registered trademark) or CSV file format. Since the analysis report contains personal information, it is desirable to implement security measures, such as compressing, encrypting, or password-protecting the file before transmission.

[0104] 1, the imaging condition calibration unit 15 performs calibration using the age-structural unit volume data and age-structural unit signal intensity data in the database 2. After the calibration, the same-age ratio calculation unit 16 calculates the same-age ratio of each structural unit of each subject from the structural unit data for each age in the database 2, thereby analyzing the risk of developing dementia and obtaining auxiliary information or reference information.

[0105] FIG. 2 is a block diagram for explaining the hardware configuration of the brain image data analysis device 1 shown in FIG.

[0106] In the following description, the brain image data analysis device 1 is assumed to operate on a server 3000 that operates on the cloud. However, the brain image data analysis device 1 may also operate on an on-premise server, or may be installed at the location where the device that captures brain images is installed, such as a workstation.

[0107] As described above, the server 3000 may be configured such that a computing device (CPU: Central Processing Unit) within its own housing executes the arithmetic processing, or such that part of the program processing is executed on another server. In the following description, it is assumed that the arithmetic device within its own housing executes the arithmetic processing.

[0108] Referring to FIG. 2, the server 3000 comprises a computer device 3010, a network communication unit 3300 for communicating with a network, and a recording medium (e.g., a memory card) 3210 for recording data from the outside and providing the data to the computer device 3010.

[0109] For example, a USB memory, a memory card, or an external storage device can be used as the recording medium 3210. Furthermore, for example, a wired LAN or wireless LAN communication function can be used as the network communication unit 3300.

[0110] As shown in FIG. 2 , the computer main body constituting this computer device 3010 includes, in addition to a disk drive 3030 and a memory drive 3020, a CPU (Central Processing Unit) 3040, memory including a ROM (Read Only Memory) 3060 and a RAM (Random Access Memory) 3070, each connected to a bus 3050, a nonvolatile rewritable storage device 3080, and an input / output interface 3090 for communication via a network and for sending and receiving data with external devices. The nonvolatile storage device 3080 may be, for example, a hard disk drive (HDD) or a solid state drive (SSD). An optical disk can be inserted into the disk drive 3030. A memory card 3210 can be inserted into the memory drive 3020.

[0111] When the programs of the computer device 3010 operate, the data and programs that store the information that is the basis for the operation of the computer will be described as being stored in the SSD 3080.

[0112] 2, the medium capable of recording information such as a program to be installed in the computer main body may be, for example, a DVD-ROM (Digital Versatile Disc), a memory card, a USB memory, etc. In such cases, the computer main body is provided with a drive device (memory drive 3020, disk drive 3030) capable of reading these media.

[0113] The main components of the computer device 3010 are computer hardware and software executed by the CPU 3040. Generally, such software is stored in a storage medium and distributed or distributed via a network, and is obtained via the disk drive 3030 or the network communication unit 3300 and temporarily stored in the SSD 3080. The software is then read from the SSD 3080 into the RAM 3070 in the memory and executed by the CPU 3040. Note that when connected to a network, the software may be directly loaded into the RAM and executed without being stored in the SSD 3080.

[0114] When distributed, the program for functioning as computer device 3010 does not necessarily have to include an operating system (OS) that causes computer main body 3010 to execute functions of an information processing device, etc. The program only needs to include an instruction portion that calls appropriate functions (modules) in a controlled manner and achieves the desired results. How computer system 3010 operates is well known, and a detailed description will be omitted.

[0115] Furthermore, the CPU 3040 may be a single-core processor or a multi-core processor. That is, it may be a single-core processor or a multi-core processor. The server 3000 may also be configured with multiple servers to execute distributed processing.

[0116] Fig. 3 is a flowchart of the brain image data analysis process performed by the brain image data analysis device of Fig. 1. The brain image data analysis process will be described below with reference to the flowchart of Fig. 3.

[0117] First, the image input unit 11 executes an image input step for receiving a brain image of a subject to be evaluated into the system (step S201). The segmentation unit 12 executes a segmentation step for the image input in the image input step S201 (step S202). The segmentation process in the segmentation step S202 divides the brain image into multiple structural units.

[0118] Next, the brain structure volume calculation unit 13 and the brain signal intensity calculation unit 14 execute a brain structure volume / signal intensity calculation step (step S203). For each structural unit divided in step S202, calculation processing of the brain structure volume and calculation processing of the detected brain signal intensity are executed.

[0119] Next, the imaging condition calibration unit 15 executes an imaging calibration step (step S204). In the imaging calibration step S204, the brain structural volume and brain signal intensity calculated for each structural unit are calibrated to minimize the influence of differences in imaging conditions during image capture. The database used for calibration to minimize the influence of differences in imaging conditions includes various imaging condition data (including, for example, resolution, slice thickness, slice angle, slice direction, sequence parameters, echo time, repetition time, flip angle, etc.) and the structural volume (age-structural unit volume data) and signal intensity (age-structural unit signal intensity data) of each structural unit at each age under various imaging conditions.

[0120] After the calibration, the same-age ratio calculation unit 16 executes a same-age ratio calculation step (step S205). In the same-age ratio calculation step S205, the same-age ratio of each structural unit of each subject is calculated using the age-structural unit volume data and age-structural unit signal intensity data in the database (step S205).

[0121] [First Modification of First Embodiment] <Configuration>

[0122] 4 is a functional block diagram of a first modification of the brain image data analysis device of this embodiment. While the first embodiment of the brain image data analysis device 1 is primarily configured to analyze imaging data of a subject currently being evaluated, the first modification of the first embodiment of the brain image data analysis device 1 also includes a configuration for setting analysis parameters, conditions, and the like in advance based on existing big data in order to analyze the subject currently being evaluated, as will be described later.

[0123] As shown in Figure 4, the brain image data analysis device 1 of variant 1 of embodiment 1 has an image input unit 11, a segmentation unit 12, a brain structure volume / brain signal intensity calculation unit 31, an imaging condition calibration unit 15, a peer age ratio calculation unit 16, a cerebrovascular disorder degree calculation unit 17, an analysis report creation unit 18, and an analysis report output unit 19.

[0124] The brain structure volume / brain signal intensity calculation unit 31 is an integrated configuration of the brain structure volume calculation unit 13 and the brain signal intensity calculation unit 14 of Fig. 1. The brain structure volume / signal intensity calculation unit 31 has a brain structure selection unit 32, an imaging condition influence evaluation unit 33, a brain structure identification unit 34, and a brain structure volume / signal intensity calculation unit 35. The brain image data analysis device 1 of Fig. 4 has the same configuration as Fig. 1 except for the brain structure volume / signal intensity calculation unit 31, so a description thereof will be omitted and only the brain structure volume / signal intensity calculation unit 31 will be described below.

[0125] As in the first embodiment, the brain structure volume / signal intensity calculation unit 31 corresponds to a function in which the CPU executes a corresponding module in a program stored in memory when the computer operates as the brain image data analysis device 1. The brain structure selection unit 32, the imaging condition influence evaluation unit 33, the brain structure identification unit 34, and the brain structure volume / signal intensity calculation unit 35 are implemented as submodules in the module of the brain structure volume / signal intensity calculation unit 31, each of whose functions is executed by the CPU.

[0126] The database 2a is a database of big data, and includes brain volume data for each structural unit at each age under various imaging conditions (including resolution, slice thickness, slice angle, slice direction, and sequence parameters (echo time, repetition time, flip angle, etc.)), age-structural unit volume data including brain signal intensity data, age-structural unit signal intensity data, etc. This database may be stored in the analysis center, or may be installed on a cloud server. <Configuration Description>

[0127] The "brain structure volume / signal intensity calculation unit 31" first includes an imaging condition influence evaluation unit 33 that evaluates the influence of the imaging conditions of brain MRI images on brain structures based on big data before analyzing the current subject, and a brain structure selection unit 32 that, based on the evaluation results, selects brain structures that are highly effective in terms of being able to accurately calculate the volume of brain structures, etc. from an engineering perspective even if there are variations in imaging conditions and subject attributes (age, gender, etc.), and that exhibit large changes due to aging and disease. The "brain structure volume / signal intensity calculation unit 31" further includes a brain structure identification unit 34 that identifies brain structures that are less affected by the imaging conditions from the imaging data from the subject currently being evaluated, and a brain structure volume / signal intensity calculation unit 35 that calculates the volume and signal intensity of large structures, such as ventricles and lobar structures, from among the identified brain structures.

[0128] Figures 6A and 6B are flowcharts of the brain image data analysis process by the brain image data analysis device 1 of Figure 1 or 4. Figure 6A is a flowchart showing the pre-analysis of the brain image data analysis process, and Figure 6B is a flowchart showing the analysis of the brain image data analysis process on a subject by the brain image data analysis device.

[0129] (Preliminary analysis using big data)

[0130] 6A , prior to analysis of the current subject, the image input unit 11 executes an image input step of reading image data from the database 2a based on big data (step S501). The segmentation unit 12 executes a segmentation step for the image input in the image input step S501 (step S502). The segmentation in the segmentation step S502 divides the brain image into multiple structural units. Segmentation can also be performed by preparing, for example, training data that has already been segmented in the database 2a (which stores imaging condition data, age-structural unit volume data, and age-structural unit signal intensity data).

[0131] For example, by using training data such as that shown in US Pat. No. 10,074,173 in Reference 1, the structure of the brain can be defined at multiple structural levels.

[0132] Figure 5 shows segmentation training data at various structural levels. In the example of Figure 5, the coarseness (granularity) of the brain structure definition is defined in five levels: 287 structures, 137 structures, 54 structures, 19 structures, and 8 structures. Finer structure definitions increase the amount of information about brain regions, but reduce data reproducibility and increase dependency on imaging conditions. On the other hand, coarser structure definitions decrease the amount of information about brain regions, but increase data reproducibility and reduce dependency on imaging conditions. As a result of segmentation, all of the defined structures can serve as indicators (volume values, signal intensity values) for measuring the brain's health. The brain image data analysis device 1 can select structures that are more suitable as health indicators from these many structures, and by performing preprocessing, it is possible to obtain a final indicator with high suitability.

[0133] Here, the correspondence between the "structural units" and the "brain structures" used in the analysis is as follows:

[0134] That is, for example, segmentation can be performed in the smallest unit, and a larger structure can be defined by combining multiple units.

[0135] 6A, next, the brain structure volume / signal intensity calculation unit 31 executes an imaging condition influence evaluation step S503 and a brain structure selection step S504. Each processing step executed by the brain structure volume / signal intensity calculation unit 31 will be described in detail below.

[0136] First, as a module of the imaging condition influence evaluation program, the imaging condition influence evaluation unit 33 executes an imaging condition influence evaluation step (step S503). The imaging condition influence evaluation step S503 is a step for evaluating the influence of various imaging conditions from an engineering perspective. The imaging condition influence evaluation unit 33 selects structures that are highly robust from an engineering perspective and evaluates them based on the data in the database 2a. In this step S503, the influence of brain MRI images taken under various conditions on the definition of the structure (e.g., volume) is evaluated. This is because, for example, when MRI images are taken at different resolutions, the volume of a specific structure may be measured as being larger.

[0137] For example, there are nearly 100 parameters for MRI imaging conditions, and it cannot be assumed that imaging conditions are the same between imaging sites (e.g., hospitals). All of these parameters have the potential to affect the volume.

[0138] As a result, strictly speaking, it is impossible to compare data between facilities as it is, and each hospital must collect hundreds or thousands of data points before it is possible to make an assessment such as, "The average hippocampal volume of a 50-year-old is XX, and this person's hippocampus is smaller in comparison." This process must be repeated even if one imaging condition is changed.

[0139] Therefore, when, for example, 505 brain structures are divided by segmentation, the imaging condition influence evaluation unit 33 performs a process of evaluating and separating those that are sensitive to differences in these parameters, with their volume values ​​changing when the parameters are changed, from those that are insensitive, with their volume values ​​remaining almost unchanged regardless of the parameters. The latter is an excellent index from an engineering perspective. Therefore, the imaging condition influence evaluation unit 33 evaluates "how much the volume values ​​change depending on the imaging parameters" based on, for example, changes in the CV (Coefficient of Variation) value or the volume-age correlation curve due to the imaging conditions.

[0140] Next, as a module of the brain structure selection program, the brain structure selection unit 32 executes a brain structure selection step (step S504). In the brain structure selection step S504, brain structures with high suitability for brain structure volume and signal calculation processing are selected. The brain structures selected here include structures with known medical and biological functions, or structures known to be medically important for the disease risk being evaluated. For example, the hippocampus, which is known to be important for memory. Furthermore, from an engineering perspective, structures suitable as indicators require different suitabilities, and in the brain structure selection step 504, brain structures with a large effect on variability from an engineering perspective are selected.

[0141] Below, we will explain the significance of "brain structures with a large effect despite variability." From an engineering perspective, the three most important suitability factors are good reproducibility (small variability when multiple measurements are taken under the same conditions), small influence from imaging conditions (robustness; similar values ​​are obtained even when measurements are taken under different conditions), and high sensitivity to the biological changes we want to detect. In this context, "sensitivity" refers to the ratio of the biological change (effect), its magnitude, and reproducibility; even if the effect is high, if the variability is large, it cannot be considered an excellent indicator from an engineering perspective.

[0142] Therefore, if the risk of dementia is to be evaluated, for example, the brain structure selection unit 32 will determine, from the standpoints of sensitivity and reproducibility, as will be described later, to use only the volume of the ventricles as an index from the 505 structures obtained by segmentation from the imaging data of the subject, or to use an index that is a combination of the ventricles and other brain structures. The brain structure selection unit 32 stores the brain structures selected in this way, for example, in database 2a, in association with the disease to be evaluated, as selected brain structure data.

[0143] The method of defining the brain structure at multiple levels using the training data described above, as shown in Figure 5, is extremely effective in finding robust structures.

[0144] Thereafter, the brain image data analysis device 1 of the first modification of the first embodiment executes processing by the brain structure volume / signal intensity calculation unit 35 (S505) and processing by the imaging condition calibration unit 15 (step S506).

[0145] FIG. 7 is a functional block diagram of the imaging condition calibration unit 15 in the brain image data analysis device of FIG. 1 or FIG.

[0146] The imaging condition calibration unit 15 includes a “calibration unit for imaging condition differences” as shown in FIG. 7 , and the calibration unit for imaging condition differences has a brain structure volume-age correlation creation unit 151, a brain structure volume-age correlation parameter extraction unit 152, and an imaging condition parameter matching unit 153.

[0147] Here again, the imaging condition calibration unit 15 corresponds to a function in which the CPU executes the corresponding module in the program stored in the memory when the computer operates as the brain image data analysis device 1. The brain structure volume-age correlation creation unit 151, the brain structure volume-age correlation parameter extraction unit 152, and the imaging condition parameter matching unit 153 are implemented as sub-modules in the module of the imaging condition calibration unit 15, each of which is executed by the CPU. <Configuration Description>

[0148] The "brain structure volume-age correlation creation unit 151" creates a volume-age correlation curve for the measurement results of brain structures of multiple people of different ages (each subject) based on existing big data, before analyzing the current subject.

[0149] The "brain structure volume-age correlation parameter extraction unit 152" extracts volume-age correlation parameters that define the correlation curve created by the brain structure volume-age correlation creation unit 151 and statistical parameters (such as average values) for each imaging condition.

[0150] The "imaging condition parameter matching unit 153" determines calibration coefficients to match or minimize the volume and signal intensity of each brain structure so that the differences in the parameters of the volume-age correlation curves and statistical parameters extracted by the brain structure volume-age correlation parameter extraction unit 152 are small even when the imaging conditions are different. Here, the "calibration coefficient" is not particularly limited, but refers to, for example, a coefficient used to calibrate the volume of a specific brain structure so that it matches between imaging conditions A and B. Similarly, the "calibration coefficient" refers to a coefficient used to calibrate the signal intensity so that it matches between imaging conditions A and B. Note that, for example, the "brain structure volume-age correlation parameter" can be the average value and standard deviation of the structure at each age. Therefore, calibration is a correction between group A and group B (for example, two groups imaged using MRI devices with different resolutions). If we assume that the average for Group A is 10% larger than the average for Group B at age 30, and Group A is considered the standard, then by reducing the volume of the 30-year-old patients in Group B by 10%, the data from Group B can be compared with the data from Group A.

[0151] Fig. 8 is a processing flowchart of the imaging condition calibration unit 15 in the brain image data analysis device of Fig. 1 or 4. The processing for determining the imaging condition calibration coefficients will be described below with reference to the flowchart of Fig. 8.

[0152] First, the imaging condition calibration unit 15 executes the imaging condition calibration step 204. Each step of the imaging condition calibration step 204 will be described in detail below.

[0153] In order to determine a calibration coefficient for the difference in volume values ​​due to differences in imaging conditions, the imaging condition calibration unit 15 executes the following steps: brain structure volume-age correlation creation step S701, in which brain structures of a plurality of people (subjects) of different ages are measured and a volume-age correlation curve is created for each imaging condition; brain structure volume-age correlation parameter extraction step S702, in which volume-age correlation parameters are extracted for each imaging condition from the created correlation curve and statistical parameters are extracted for each imaging condition; and brain structure volume-age correlation matching (correction) step S703, in which a calibration coefficient is determined so that the differences in the extracted volume-age correlation parameters and statistical parameters are small.

[0154] To calibrate the difference in volume values ​​due to different shooting conditions, the shooting condition calibration unit 15 can also take images of the same person under different shooting conditions and measure the influence of each shooting condition (for example, resolution) to perform calibration. Steps S701 to S703 show one method of calibrating the difference in volume values ​​due to different shooting conditions (when not using the same person).

[0155] In the brain structure volume-age correlation creation step S701, the imaging condition calibration unit 15 creates (draws) a volume-age correlation curve for the measurement results of multiple people (subjects) of different ages, thereby obtaining a correlation equation. In the brain structure volume-age correlation parameter extraction step S702, the imaging condition calibration unit 15 extracts volume-age correlation parameters and statistical parameters for each imaging condition from the created correlation curve. For example, extracting statistical parameters includes extracting the mean and standard deviation at each age for each imaging condition, and extracting parameters that add the imaging condition as a covariate using polynomial regression or the like as parameters for the correlation curve for each imaging condition. In the brain structure volume-age correlation parameter extraction step S702, structures that are robust to differences in imaging conditions (with small differences in the equations) can be identified based on the differences in the obtained correlation equations. Therefore, if these results are obtained in advance, they can also be used in evaluating the effects of imaging conditions (S503).

[0156] Next, in step S703, volume values ​​obtained under different imaging conditions are matched. When the imaging conditions are different, calibration coefficients for volume values ​​and signal intensities are determined. That is, calibration is performed so that differences in correlation equations and statistical parameters are eliminated.

[0157] For example, there are two methods for determining the calibration coefficients:

[0158] In the first method, for example, if the average value and standard deviation of a 30-year-old person under condition A are average AA and deviation SA, and under condition B they are average AB and deviation SB, then by setting volume data B of the person photographed under condition B to B+(average AA-average AB), the average value of data B photographed under condition B can be compared with condition A. In other words, (average AA-average AB) becomes the calibration coefficient for B→A conversion. In this case, it is assumed that there is a certain amount of measurement data under conditions A and B, and that the averages of each can be calculated.

[0159] The statistical parameters of both conditions may be matched based on either condition A or condition B. For example, if the condition is the strength of the measurement magnetic field, the statistical parameters may be matched to the measurement data under the condition of the highest magnetic field strength, which is thought to provide the highest resolution. Alternatively, if the slice thickness is different between condition A and condition B, the statistical parameters may be matched to the measurement data under the condition of a thinner slice pressure, which allows for the observation of a finer structure.

[0160] The second method is to use the statistical value of A as prior information when there is a large amount of data for condition A and a small amount of data for condition B.

[0161] A more rigorous implementation of this concept can be achieved using so-called Bayesian estimation.

[0162] In the above explanation, calibration is performed by comparing the average value and standard deviation for each age group to achieve a match. However, for example, when the average value is in the 20s to 80s range, the average values ​​for ages 20 to 80 under conditions A and B may be applied to a polynomial, and the calibration coefficients may be calculated so that the polynomials match. In this case, differences in imaging conditions may be added as covariates.

[0163] The above-mentioned Bayesian estimation will be explained in more detail below.

[0164] That is, for example, let us say that the average of structure X at age 30, found from 30,000 cases under imaging condition A, is θ, and the standard deviation is γ. Let us say that under imaging condition B, the results of volume measurement of structure X for n people are average μ and standard deviation σ. A Bayesian model can be used to estimate the posterior distribution. f(θ|data) ∝ f(θ)f(d|θ) For example, if both the prior distribution f(θ) and likelihood f(d|θ) follow normal distributions, the posterior distribution (estimation of the average under imaging condition B) is: Mean: θγ 2 / (nγ 2 +σ 2 ) + μnγ / (nγ 2 +σ 2 ) Variance: γ2 σ 2 / (nγ 2 +σ 2 ) is normally distributed.

[0165] Figures 9(a) and (b) show examples of pre- and post-calibration results using the ventricular volume-age correlation. Figure 9(a) shows the logarithmic representation of ventricular volume obtained from raw data as a function of age, while Figure 9(b) shows the average ventricular volume (logarithmic scale percentage) at each age after calibration based on the 1.2 mm slice data. For data obtained at the same resolution from two different sites, the correlation between protocol, age, and sex was not statistically significant. Therefore, data at the same slice resolution were pooled for analysis. As shown in Figure 9(a), the protocol effect was highly significant across the three different slice thicknesses (1.2 mm, 2.0 mm, and 2.5 mm). This indicates that the difference was greater in younger subjects with smaller ventricular volumes, whereas it decreased with age and increased ventricular volumes. This suggests that low-resolution images are difficult to distinguish between ventricular volumes in younger subjects and are therefore not suitable for characterizing age-dependent changes in younger subjects. Figure 9(b) shows the mean ventricular volume (logarithmic scale) at each age after calibration based on the 1.2-m-thick data, demonstrating that calibration can effectively reduce the effect of image resolution.

[0166] In the examples of Figures 9(a) and 9(b), the vertical axis shows the logarithmic scale ratio of ventricular volume, and the horizontal axis shows age. The subjects were males and females in their 30s to 70s, and the results were obtained by performing calibration with slice thicknesses of 1.2 mm, 2.0 mm, and 2.5 mm. As is clear from the results of Figures 9(a) and 9(b), calibration of the image resolution imaging conditions results in consistent parameters, enabling analysis of brain image data that is not affected by the performance of the MRI equipment.

[0167] (Analysis of current subjects)

[0168] Returning to FIG. 6B, the process of analysis performed by the brain structure volume / signal intensity calculation unit 31 based on the brain image data and imaging condition data of the subject currently being evaluated will now be described.

[0169] After the image input step (step S510) and the segmentation step (step S512), the brain structure volume / signal intensity calculation unit 31 executes a brain structure identification step S514, a brain structure volume / signal intensity calculation step S516, processing by the imaging condition calibration unit 15 (step S518), and processing by the same age ratio calculation unit 16 (step S520).

[0170] First, for analysis of the current subject, the image input unit 11 executes an image input step in which it reads brain image data and imaging condition data of the subject to be evaluated, transmitted from the imaging site (step S510). The segmentation unit 12 executes a segmentation step for the image input in the image input step S510 (step S512). The segmentation in the segmentation step S512 divides the brain image into multiple structural units (e.g., 505 structural units). Again, the segmentation can be performed with reference to the segmentation training data in the database 2a described above.

[0171] Next, as a module of the brain structure identification program, the brain structure identification unit 34 performs labeling of brain structures for the structural units divided by segmentation, and executes a brain structure identification step of identifying structures that are less affected by the imaging conditions according to the prior evaluation by the imaging condition influence evaluation unit 33 (step S514). In the brain structure identification step S514, structures are identified that are robust and less affected by the imaging conditions, and that can be minimized by calibration, and that are selected taking into account their sensitivity to the disease risk of the evaluation target. As described above, examples of robust structures include the ventricles and large lobe structures (e.g., the frontal lobe) when dementia risk is the target.

[0172] Next, as a module of the brain structure volume / signal intensity calculation program, the brain structure volume / signal intensity calculation unit 35 calculates the volume and signal intensity for each brain structure (step S516). That is, the volume and signal intensity of the brain structure are calculated from the structures with large volumes, such as the ventricles and lobe structures, identified in step S514.

[0173] Here, for example, the volume value of the identified brain structure is calculated by multiplying the number of voxels contained in the structure by the volume of one voxel. Furthermore, the signal intensity calculation is equivalent to the average value of the signal intensities of all voxels contained in the structure. In this case, the signal intensity calculation is not limited to the average value, and may be a median, moment, or histogram.

[0174] The method of defining the brain structure at multiple levels using the training data described above, as shown in Figure 5, is extremely effective in finding robust structures.

[0175] Thereafter, the brain image data analysis device 1 of the first modification of the first embodiment executes the processing of the imaging condition calibration unit 15 (step S518) and the processing of the same age ratio calculation unit 16 (step S520).

[0176] <Configuration>

[0177] FIG. 10 is a functional block diagram of the same-age ratio calculation unit 16 in the brain image data analysis device 1 of FIG. 1 or FIG.

[0178] As shown in FIG. 10, the peer ratio calculation unit 16 includes an age-brain volume distribution creation unit 161, an age-brain volume distribution parameterization unit 162, and an age percentile calculation unit 163.

[0179] Here again, the peer age ratio calculation unit 16 corresponds to a function in which the CPU executes a corresponding module in a program stored in memory when the computer operates as the brain image data analysis device 1. The age-brain volume distribution creation unit 161, the age-brain volume distribution parameterization unit 162, and the age percentile calculation unit 163 are implemented as submodules in the module of the peer age ratio calculation unit 16, each of which is executed by the CPU. <Configuration Description>

[0180] The "age-brain volume distribution creation unit" 161 creates a population distribution of the volume of the selected brain structure at each age. Here, "population distribution" means the distribution of the average value and standard deviation of the volume obtained from three or more subjects.

[0181] The 'age-brain volume distribution parameterization unit' 162 calculates parameters of the volume distribution of brain structures.

[0182] The "age percentile calculation unit" 163 uses the calculated parameters to calculate an age percentile based on the age of each subject.

[0183] Fig. 11 is a processing flowchart of the same age calculation unit 16 in the brain image data analysis device of Fig. 1 or Fig. 4. The same age calculation processing will be described below with reference to the flowchart of Fig. 11.

[0184] The same age calculation unit 16 executes the same age ratio calculation step S205 or S520. Each step of the same age ratio calculation step S520 will be described in detail below.

[0185] The peer ratio calculation step S520 includes an age-brain volume distribution creation step S1001 for creating a population distribution of the volume of the selected brain structure at each age, an age-brain volume distribution parameterization step S1002 for calculating parameters of the volume distribution of the brain structure, and an age percentile calculation step S1003 for calculating an age percentile based on the age of each subject using the calculated parameters.

[0186] 13 and 14 are diagrams showing the distribution of ventricular volume ratios according to age and sex.

[0187] In the age-brain volume distribution creating step S1001, the age-brain volume distribution creating unit 161 creates a population distribution of the volume of the selected structure at each age, as shown in FIGS.

[0188] FIG. 12 is a diagram showing the distribution of ventricular volume by age group.

[0189] Next, in the age-brain volume distribution parameterization step S1002, the age-brain volume distribution parameterization unit 162 parameterizes the population distribution. As a result of experiments, it was found that using the logarithmic value of the ventricle volume on the horizontal axis approaches a normal distribution, as shown in Figure 12. Therefore, for example, if a normal distribution model is used, parameterization can be achieved using two values: the distribution, the mean, and the standard deviation.

[0190] FIG. 15 is a diagram showing age-dependent changes in the mean value of ventricular volume and a predetermined variance value.

[0191] As an alternative to the parameterization shown in FIG. 12, a method (e.g., Bayesian statistics) can be used to directly calculate percentiles from raw data, as shown by the dashed line in FIG. 15, without using a distribution model such as a normal distribution.

[0192] Next, in an age percentile calculation step S1003, the age percentile calculation unit 163 can use the obtained parameters to obtain a percentile based on the age of each individual.

[0193] <Configuration>

[0194] FIG. 16 is a functional block diagram of the cerebrovascular disorder degree calculation unit 17 in the brain image data analysis device of FIG. 1 or FIG.

[0195] As shown in FIG. 16 , the cerebrovascular disorder degree calculation unit 17 includes a cerebral white matter signal abnormal region-containing volume calculation unit 171, a peer ratio calculation unit 172, and a cerebral atrophy / cerebral white matter signal abnormal region simultaneous calculation unit 173.

[0196] Here, too, the cerebrovascular disorder degree calculation unit 17 corresponds to a function in which the CPU executes the corresponding module in a program stored in memory when the computer operates as the brain image data analysis device 1. The cerebral white matter signal abnormal region-containing volume calculation unit 171, peer age ratio calculation unit 172, and cerebral atrophy / cerebral white matter signal abnormal region simultaneous calculation unit 173 are implemented as submodules in the cerebrovascular disorder degree calculation unit 17 module, each of which is executed by the CPU.

[0197] <Configuration explanation>

[0198] Referring to FIG. 16, the 'cerebrovascular disorder degree calculation unit 17' calculates the degree of cerebrovascular disorder.

[0199] The “cerebral white matter signal abnormal region-containing volume calculation unit” 171 calculates the volume of brain structures by incorporating cerebral white matter signal abnormal regions into the segmentation training data.

[0200] The "peer age ratio calculation unit" 172 calculates the peer age ratio from the age correlation of the brain white matter signal abnormality areas in the database 2, 2a (see FIG. 1 or FIG. 4).

[0201] The 'cerebral atrophy / cerebral white matter signal abnormality region simultaneous calculation unit' 173 simultaneously calculates the degree of cerebral atrophy and cerebrovascular disease from the same MRI image.

[0202] Fig. 17 is a processing flowchart of the cerebrovascular disorder degree calculation unit 17 in the brain image data analysis device 1 of Fig. 1 or 4. The cerebrovascular disorder degree calculation processing will be described below with reference to the flowchart of Fig. 17.

[0203] The cerebrovascular disorder degree calculation unit 17 executes the cerebrovascular disorder degree calculation step in the same age ratio calculation step S205 or S520. Each step of the cerebrovascular disorder degree calculation step will be described in detail below.

[0204] The "cerebrovascular disorder degree calculation step" includes a step S1601 of calculating the contained volume of abnormal cerebral white matter signal regions, which calculates the volume of brain structures by incorporating the volume of abnormal cerebral white matter signal regions into the segmentation training data; a step S1602 of calculating the same-age ratio from the age correlation of abnormal cerebral white matter signal regions in the database; and a step S1603 of simultaneously calculating cerebral atrophy and abnormal cerebral white matter signal regions, which simultaneously calculates the degree of cerebral atrophy and cerebrovascular disease from the same MRI image.

[0205] FIG. 18 shows an MRI image in which there is an area with abnormal signal intensity in the white matter of the brain due to a cerebrovascular disorder.

[0206] In Figure 18, the small area surrounded by a thick black line at the tip of the arrow corresponds to the abnormal signal intensity region. Specifically, the abnormal signal region has a lower signal intensity than the surrounding area. This region is defined in the training data, and when a similar dark region appears in the subject, it can be segmented and its volume measured. Note that in this example, the image used to measure the abnormal signal region was the same as the image used to measure the volume of other brain structures. However, it is also possible to measure the abnormal signal region using different images, for example, using T1-weighted images to measure the brain structure volume and using FLAIR (Fluid Attenuated Inversion Recovery) images to measure the abnormal signal region.

[0207] As described above, the volume of each structure can be used to determine the shape of the brain and the degree of atrophy. Meanwhile, the degree of cerebrovascular damage can also be measured using the structural definitions provided in the training data. For example, by defining abnormal signal intensity regions in the white matter of a specific brain structure using training data such as that shown in FIG. 18 , the cerebral white matter signal abnormality region volume calculation unit 171 can automatically calculate the volume of the signal abnormality region for each individual in the step S1601 for calculating the volume of the cerebral white matter signal abnormality region (containment).

[0208] FIG. 19 shows the age dependency of the ratio of the volume of vascular lesions to the volume of the whole brain.

[0209] Furthermore, in the same-age ratio calculation step 1602, the same-age ratio calculation unit 172 can calculate the same-age ratio from the age correlation of this signal abnormality region based on a large amount of data, as in the case of measuring cerebral atrophy based on the above-mentioned brain parenchymal structure and ventricular volume, as shown in Figure 19. Therefore, by combining this method, in the simultaneous calculation step 1603 of cerebral atrophy / cerebral white matter signal abnormality region, the cerebral atrophy / cerebral white matter signal simultaneous calculation unit 173 can estimate both the degree of cerebral atrophy and cerebrovascular disease from a single MRI image.

[0210] FIG. 21 is a diagram showing an example of output of information on the comprehensive evaluation of both the degree of cerebral atrophy and cerebrovascular disease.

[0211] The "alert group," "caution group," "average group," and "relatively good group" in the example of FIG. 21 are the same as those described in FIG. 20, and therefore will not be described again.

[0212] Other Embodiments Picture Archiving and Communication Systems (PACS) or Workstations

[0213] Figure 39 is a diagram showing an example of a configuration in which a brain image data analysis program is implemented on an on-premise server at an imaging site.

[0214] FIG. 39 shows an example in which the functions of the brain image data device are realized by software in the system of a brain checkup institution or health checkup center, and a brain image data analysis program is installed.

[0215] A medical image communication system (PACS) 40 is a system that acquires brain image data (MRI images) from an MRI scanner 38, stores them in storage 42, and allows them to be viewed and displayed on a monitor terminal 43. The example in Fig. 39 shows an example in which a brain image data analysis program 41 is implemented in an on-premise server 40, and an example in which a brain image data analysis program 45 is implemented in a dedicated data analysis workstation 44. In this case, the brain image data analysis program can be installed in either the server or the workstation, or both.

[0216] The functions of the brain image data analysis program are the same as those of the brain image data analysis device described above, so detailed explanations will be omitted.

[0217] <Cloud System> FIG. 40 is a diagram showing an example of a configuration in which a brain image data analysis program is implemented on a server on the cloud that is accessed from the imaging site.

[0218] Figure 40 shows an example in which the functions of the brain image data device are realized by software on a cloud system, and a brain image data analysis program is implemented. In the example of Figure 40, a server 51 running the brain image data analysis program is connected to multiple health checkup centers 47-50 via a cloud system network. This example shows a brain image data analysis program 52 implemented within the cloud system (cloud server) 51. When the cloud system 51 receives image data 53 or 54 from each health checkup center 47, 48, 49, or 50, it performs image analysis using the brain image data analysis program 52 and returns analysis results (numerical data or PDF reports) 55 and 56 to the health checkup center. The functions of the brain image data analysis program are the same as those of the brain image data analysis device described above, and therefore a detailed description thereof will be omitted.

[0219] <Other cloud systems>

[0220] Figure 41 is a diagram showing another example of a configuration in which the brain image data analysis program is realized on a server on the cloud that is accessed from the imaging site.

[0221] Figure 41 shows an example in which the functions of this brain image data device are realized by software on a cloud system, and a brain image data analysis program is implemented.

[0222] In the example of Figure 41, one health checkup center (or multiple health checkup centers) is connected via a cloud system via a network. This example shows a brain image data analysis program 59 implemented in a cloud system (cloud server) 58. When the cloud system 58 automatically transfers image data, lifestyle habits, and clinical data 60 from each health checkup center 57, it analyzes the images using the brain image data analysis program 59 and returns the analysis results (numerical data and PDF reports) 61 to the health checkup center 57, which then automatically inserts them into an existing output terminal. This allows the health checkup center to receive the analysis results without an operator, thereby contributing to a reduction in labor costs at the health checkup center. The functions of the brain image data analysis program are similar to those of the brain image data analysis device described above, so a detailed description will be omitted.

[0223] FIG. 42 is a diagram for comparing the correlation between limbic system volume and hippocampal volume in Alzheimer's disease (AD) patients and healthy individuals.

[0224] FIG. 43 is a diagram for comparing the correlation between ventricular volume and hippocampal volume between Alzheimer's disease (AD) patients and healthy individuals.

[0225] It is clear that there is a strong positive correlation between the volumetric atrophy of the hippocampus, which has been reported to shrink in patients with Alzheimer's disease, and the volumetric atrophy of the limbic system. It is also clear that the volume of the ventricles tends to expand in accordance with the volumetric atrophy of the hippocampus.

[0226] Here, the limbic system is a collective term for the paleocortex (hippocampus, fornix, dentate gyrus), paleocortex (olfactory lobe, piriform lobe), intermediate cortex (cingulate gyrus, hippocampal gyrus), and subcortical nuclei (amygdala, septum, mammillary bodies).

[0227] The ventricles are cavities within the brain where cerebrospinal fluid is produced. In humans, there are four ventricles in total: a pair of lateral ventricles on the left and right, and one third and one fourth ventricle in the midline.

[0228] FIG. 44 is a diagram showing brain structures that undergo significant age-related changes in the brain image data analysis device of this embodiment.

[0229] The rate of change in the ventricles due to aging from the 30s to the 60s is significantly greater than that of other parts of the brain. Furthermore, within the ventricles, the anterior ventricles account for 0.5% of the total volume, and the rate of change due to age exceeds 70%.

[0230] FIG. 45 is a diagram showing the cerebral hemispheres.

[0231] FIG. 46 is a diagram showing gray matter, ventricles, and Sylvian sulcus.

[0232] FIG. 47 shows an area of ​​abnormal signal in the anterior ventricular horn.

[0233] FIG. 48 is a diagram showing the relationship between examinee age and ventricular atrophy when imaging is performed at different resolutions.

[0234] Figure 48(a) shows the relationship between examinee age and atrophy level (ventricular volume) in low-resolution imaging (2.5 mm data), and Figure 48(b) shows the relationship between examinee age and atrophy level (ventricular volume) in high-resolution imaging (1.2 mm data).

[0235] It can be seen that the changes in atrophy of the ventricles with age show similar trends, even when the resolution is different.

[0236] FIG. 49 is a graph showing the frequency of ventricular atrophy in examinees by age group.

[0237] Figure 49(a) shows the frequency of ventricular volume atrophy in male examinees (by age group: 30s, 40s, 50s, 60s, and 70s), and Figure 49(b) shows the frequency of ventricular volume atrophy in female examinees (by age group: 30s, 40s, 50s, 60s, and 70s).

[0238] FIG. 50 shows a histogram of age-specific atrophy (logarithmic ventricular volume) and a log-normal distribution.

[0239] The left side of Figure 50 shows a histogram of the degree of atrophy (logarithmic value of ventricular volume) by age, and the right side of Figure 50 shows a log-normal distribution. In the log-normal distribution, for example, the average degree of atrophy for people in their 70s and the position where atrophy has progressed by one standard deviation from the average degree of atrophy are also shown in the figure. 68.2% of people in their 70s belong to the "average of people in their 70s + 1 standard deviation."

[0240] Conversely, for example, if a person in their 60s falls into the range exceeding the "average for people in their 70s plus one standard deviation," it is highly likely that their atrophy is more severe than that of people of the same age.

[0241] FIG. 51 is a diagram showing the difference between population analysis obtained from a normal distribution model and the AD patient region.

[0242] As shown in the figure, population analysis can identify the AD patient region by comparing the degree of ventricular atrophy with the average value for the same age. If the degree of ventricular atrophy falls within this AD patient region, supplementary information can be provided indicating a high risk of dementia.

[0243] 52, 53 and 54 show example MRI images illustrating the implementation of ventriculomegaly.

[0244] Fig. 52(a) is a diagram showing an actual example of ventricular enlargement in a typical normal case (in his 40s), and Fig. 52(b) is a diagram showing an actual example of ventricular enlargement in an atrophic case (in his 40s) without atrophy findings.

[0245] Fig. 53(a) is a diagram showing an actual example of ventricular enlargement in a typical normal case (in his 40s), and Fig. 53(b) is a diagram showing an actual example of ventricular enlargement in an atrophic case (in his 40s) without atrophy findings.

[0246] Fig. 54(a) is a diagram showing an actual example of ventricular enlargement in a normal typical case (in his 30s), and Fig. 54(b) is a diagram showing an actual example of ventricular enlargement in a case of mild atrophy of bilateral lateral ventricles (in his 30s).

[0247] FIG. 55 is a diagram showing the correlation between blood glucose levels and ventricular volume.

[0248] Figure 55(a) is a graph showing the correlation between blood glucose levels and ventricular volume for men and women in their 40s (low-resolution data 2.5 mm). Figure 55(b) is a graph showing the correlation between blood glucose levels and ventricular volume for men and women in their 50s (low-resolution data 2.5 mm). Figure 55(c) is a graph showing the correlation between blood glucose levels and ventricular volume for men and women in their 40s (high-resolution data 1-1.2 mm). Figure 55(d) is a graph showing the correlation between blood glucose levels and ventricular volume for men and women in their 50s (high-resolution data 1-1.2 mm).

[0249] FIG. 56 is a diagram showing the correlation between blood pressure values ​​and ventricular volume.

[0250] Figure 56(a) is a graph showing the correlation between blood pressure values ​​and ventricular volume for men and women in their 40s (low-resolution data 2.5 mm). Figure 56(b) is a graph showing the correlation between blood pressure values ​​and ventricular volume for men and women in their 50s (low-resolution data 2.5 mm). Figure 56(c) is a graph showing the correlation between blood pressure values ​​and ventricular volume for men and women in their 40s (high-resolution data 1-1.2 mm). Figure 56(d) is a graph showing the correlation between blood pressure values ​​and ventricular volume for men and women in their 50s (high-resolution data 1-1.2 mm).

[0251] FIG. 57 is a graph showing the correlation between visceral fat mass and ventricle volume.

[0252] Figure 57(a) is a diagram showing the correlation between visceral fat mass and ventricular volume for men and women in their 40s (low-resolution data 2.5 mm). Figure 57(b) is a diagram showing the correlation between visceral fat mass and ventricular volume for men and women in their 50s (low-resolution data 2.5 mm). Figure 57(c) is a diagram showing the correlation between visceral fat mass and ventricular volume for men and women in their 40s (high-resolution data 1-1.2 mm). Figure 57(d) is a diagram showing the correlation between visceral fat mass and ventricular volume for men and women in their 50s (high-resolution data 1-1.2 mm).

[0253] FIG. 58 is a graph showing the correlation between the number of times alcohol was consumed per week and ventricular volume.

[0254] Figure 58(a) is a graph showing the correlation between alcohol consumption (times / week) and ventricular volume for men and women in their 40s (low-resolution data 2.5 mm). Figure 58(b) is a graph showing the correlation between alcohol consumption (times / week) and ventricular volume for men and women in their 50s (low-resolution data 2.5 mm). Figure 58(c) is a graph showing the correlation between alcohol consumption (times / week) and ventricular volume for men and women in their 40s (high-resolution data 1-1.2 mm). Figure 58(d) is a graph showing the correlation between alcohol consumption (times / week) and ventricular volume for men and women in their 50s (high-resolution data 1-1.2 mm).

[0255] According to Figures 55 to 58, for example, when high-resolution data is referenced, it can be seen that there is a certain correlation between risk factors for so-called lifestyle-related diseases (blood sugar levels, blood pressure, obesity, and alcohol consumption) and ventricular atrophy (i.e., the risk of dementia).

[0256] FIG. 59 shows the results of analysis for simultaneously estimating atrophy risk and vascular lesion (white matter lesion) risk.

[0257] MRI imaging makes it possible to simultaneously assess both the risk of ventricular atrophy (which correlates with ventricular enlargement, i.e., hippocampal atrophy), which are indicators for assessing the risk of dementia, and the proportion of areas with abnormal brain white matter signals (risk due to vascular lesions).

[0258] FIG. 60 shows the tendency of increase in ventricular volume (ventricular atrophy) with age for the same person.

[0259] 60(a) shows the results of initial analysis of time-series data for low-resolution data (2.5 mm), and FIG. 60(b) shows the results of initial analysis of time-series data for high-resolution data (1-1.2 mm).

[0260] Both high-resolution and low-resolution data show the same general trend of ventricular volume increasing with age for the same individual, although this trend is more clearly evident in the high-resolution data.

[0261] Figure 61(a) shows the relationship between ventricular volume and ventricular expansion rate using low-resolution data (2.5 mm), and Figure 61(b) shows the relationship between ventricular volume and ventricular expansion rate using high-resolution data (1-1.2 mm).

[0262] Here, the ventricular enlargement rate for a subject means the following, assuming that the years of measurement are T1 and T2 (T1<T2): {(ventricular volume at T2) - (ventricular volume at T1)} / (T2-T1)

[0263] FIG. 62 is a diagram showing an example of a detailed pattern evaluation monitor display screen of cerebral atrophy.

[0264] Figure 62 lists the functions performed by each area in the brain, the names of areas that tend to show atrophy in dementia, as well as findings and recommended actions for the subject.

[0265] In FIG. 62, the degree of atrophy is divided into four stages for each brain region, and is displayed separately for the right and left hemispheres.

[0266] Fig. 63 shows an example of the display screen of the analysis and evaluation monitor for the four major lifestyle factors that affect brain atrophy. Fig. 63 shows (a) the influence of blood glucose level, (b) the influence of visceral fat mass, (c) the influence of blood pressure, and (d) the influence of drinking frequency.

[0267] This type of display allows the subject to see how their risk factors (blood sugar level, blood pressure level, visceral fat mass, drinking frequency) compare to the overall data of other subjects in the past. Also, by displaying the subject's atrophy level, it is expected to encourage behavioral change in the subject.

[0268] [Modification 2 of Embodiment 1]

[0269] In the above description, the image data to be analyzed is an MRI image, but the present invention can be applied to CT or PET images as well.

[0270] For example, the following describes a case where brain images taken by an X-ray CT (Computed Tomography) device are used. As is well known, it is possible to reconstruct a three-dimensional image by taking tomographic images using a CT device, just like MRI imaging.

[0271] Imaging with an X-ray CT device generally lacks contrast to separate structures within the brain parenchyma, making it difficult to measure the volume of, for example, the hippocampus alone.

[0272] However, as mentioned above, if "ventricular volume," which is a large brain structure and has contrast that allows the brain parenchyma and ventricles to be distinguished even with an X-ray CT scanner, is used as an evaluation index, it will be possible to indirectly evaluate the degree of hippocampal atrophy even through imaging with an X-ray CT scanner.

[0273] However, in this case too, the following measures will be taken.

[0274] 1) A calibration coefficient between the ventricle volume when imaged with an MRI device and the ventricle volume when imaged with an X-ray CT device is evaluated in advance.

[0275] 2) The evaluated ventricular volume is compared with the average value (and the range of standard deviations, if necessary) for each age group of the subjects, and presented to the subjects who underwent the test as a graph or chart. This report is then prepared and sent back to the hospital, clinic, etc.

[0276] In this case, too, when determining the calibration coefficients, in order to calibrate the difference in volume values ​​due to differences in imaging conditions (imaging using an MRI device and imaging using an X-ray CT device), the imaging condition calibration unit 15 can take images of the same person under different imaging conditions and measure the influence of each imaging condition (for example, resolution) to perform calibration.

[0277] Alternatively, the imaging condition calibration unit 15 creates (draws) a volume-age correlation curve for the measurement results of a plurality of people (subjects) of different ages for each imaging condition (imaging using an MRI device and imaging using an X-ray CT device), and obtains a correlation equation.

[0278] When the imaging conditions are different, calibration coefficients for volume values ​​and signal intensities are determined. That is, calibration is performed so that differences in correlation equations and statistical parameters are eliminated.

[0279] For example, there are two methods for determining the calibration coefficients:

[0280] In the first method, when imaging with an MRI device, for example, the average value and standard deviation of a 30-year-old person are taken as the average MAA and deviation MSA, and when imaging with an X-ray CT device, they are taken as the average CAB and deviation CSB, and when volume data B of a person imaged with the X-ray CT device is taken as B + (average MAA - average CAB), the average value of data B imaged with the X-ray CT device can be compared with that of imaging with an MRI device. In other words, (average MAA - average CAB) becomes the calibration coefficient for converting the volume imaged with the X-ray CT device to the volume imaged with the MRI device.

[0281] The statistical parameters of both may be matched based on either condition A or condition B, but for example, they may be matched to the measurement data of an image taken by an MRI apparatus under the highest magnetic field strength condition, which is thought to result in higher resolution.

[0282] A second method is to use the statistical values ​​of the imaging data obtained by the MRI device as prior information, for example, when there is a large amount of imaging data obtained by the MRI device and a small amount of imaging data obtained by the X-ray CT device.

[0283] A more rigorous implementation of this concept can use Bayesian inference as described above.

[0284] In this way, by using the ventricles, it becomes possible to apply the dementia risk assessment method described in the first embodiment to not only various imaging conditions of the MRI device (including the magnetic field strength of the MRI device), but also to imaging methods of tomographic images other than those of the MRI device (for example, imaging with an X-ray CT device).

[0285] In the first embodiment, a configuration has been described in which the risk of dementia is evaluated using ventricle volume as an index in imaging by an MRI apparatus.

[0286] In the following, in the second embodiment, an apparatus and an evaluation method for more accurately evaluating dementia risk by performing a combined analysis of multiple brain structures including the ventricles will be described.

[0287] As mentioned above, there are already existing services that calculate the volume of brain structures. However, these services are limited to measuring the volume of a single structure, and the information obtained may be limited, or there may be a high possibility that the evaluation may contain errors depending on the situation.

[0288] FIG. 64 is a diagram showing examples of brain structures associated with dementia risk.

[0289] FIG. 64 shows an MRI image of a brain cross section.

[0290] For example, the hippocampus and amygdala are known to frequently shrink in patients with Alzheimer's disease. However, because their volumes show little age-related change until old age, they are largely influenced by their birth size (i.e., unrelated to the progression of the disease), making it difficult to determine whether atrophy is the cause based on measurements taken at a single point in time.

[0291] On the other hand, other existing services that are said to evaluate the degree of hippocampal atrophy often attempt to evaluate the presence and degree of atrophy using i) the volume of the hippocampus alone or ii) the hippocampal to intracranial volume ratio. However, because there is a large amount of individual variability in either i) or ii), evaluating atrophy based solely on these values ​​may lead to erroneous conclusions.

[0292] FIG. 65 shows cross-sectional brain images of a subject in his 50s and a subject in his 70s.

[0293] FIG. 65(a) is an average brain cross-sectional image of a subject in his 50s, and FIG. 65(b) is a brain cross-sectional image of a subject in his 70s showing atrophy.

[0294] For example, when brain parenchyma such as the hippocampus shrinks, the surrounding space between the brain and skull (the space filled with cerebrospinal fluid, not the brain parenchyma such as the ventricles or sulci) always expands. Even if the volume of the hippocampus is small, if the cerebrospinal fluid space around the hippocampus is not open, it is unlikely to be atrophy. Also, even if the space is open, if the hippocampal volume is not small, it may be due to atrophy of brain tissue other than the hippocampus.

[0295] In this way, atrophy can be more accurately judged by considering both a decrease in substance and an expansion of space as a set.

[0296] FIG. 66 is a conceptual diagram showing an example of performing a combined analysis when the hippocampus and ventricles are the measurement targets.

[0297] In FIG. 66, the horizontal axis represents the volume of the hippocampus, and the vertical axis represents the volume of the ventricles.

[0298] To standardize the subjects' ventricular and hippocampal volumes, they were converted into z-values ​​(z-scores).

[0299] Here, the z-value is a value obtained by performing the following processes: i) subtracting the mean from the data value x; and ii) dividing the value obtained by subtracting the mean from the data value x by the standard deviation.

[0300] In Figure 66, the subject's measurement values ​​are located in the lower left quadrant (both the z-values ​​of the ventricle volume and the hippocampus volume are negative).

[0301] As mentioned above, as brain atrophy progresses with age, the volume of the hippocampus decreases and the volume of the ventricles increases.

[0302] Therefore, in FIG. 66, a straight line with a slope of (-1) is used as the standard so that a larger composite index value is obtained as the volume of the hippocampus decreases and as the volume of the ventricle increases.

[0303] However, more generally, any other curve can be used as the reference, as long as it is a monotonically decreasing function whose slope is always negative in the graph.

[0304] Let the point where the observed volume is expressed as a z-value be (pa, pb). A simple calculation will give the point of intersection of a perpendicular line drawn to this line as follows: [(pa-pb) / 2, (pb-pa) / 2]

[0305] The composite index value CI is expressed by the following formula, where the distance from the origin to this intersection point is given a sign: CI=(pa-pb) / sqrt(2)

[0306] FIG. 67 shows an example of the hippocampus and ventricle measurements for a certain subject, plotted on a graph with hippocampal volume on the horizontal axis and ventricular volume on the vertical axis.

[0307] In Figure 67, the upper left quadrant, i.e., the region with smaller-than-average hippocampi and larger-than-average ventricles, is an area where hippocampal atrophy is likely to occur, regardless of the subject's natural size of these brain structures.

[0308] In this case, the greater the absolute value of the composite index, the greater the possibility of hippocampal atrophy.

[0309] On the other hand, the upper right quadrant in Figure 67 corresponds to an area where the hippocampus is larger than average and the ventricles are larger than average, and therefore is an area where there is a possibility of age-related atrophy of nearby structures other than the hippocampus.

[0310] Furthermore, the lower left quadrant in Figure 67 corresponds to an area where the hippocampus is smaller than average and the ventricles are smaller than average, so it is an area where the smaller-than-average hippocampus is likely to be congenital.

[0311] Therefore, as shown in Figure 67, if the measured volumes of two brain structures, the hippocampus and the ventricles, are plotted on a graph with the average value for the subject's age (or generation) as the origin, it becomes possible to identify the risk of dementia depending on which of the four quadrants the subject belongs to.

[0312] In this case, the graph may be converted into z values ​​as shown in FIG.

[0313] It is also possible to measure the volume of the hippocampus and amygdala in combination with the volume of the adjacent ventricles.

[0314] FIG. 68 shows an example of a graph plotting the measured values ​​of the amygdala and ventricles for a certain subject, with amygdala volume on the horizontal axis and ventricle volume on the vertical axis.

[0315] In Figure 68, as in the case of the hippocampus, it is possible to distinguish whether the volume of the amygdala has atrophied due to aging, whether a nearby structure other than the amygdala has atrophied due to aging, or whether the amygdala is naturally small in size.

[0316] Here, too, the graph may be converted into z values ​​as shown in FIG.

[0317] Furthermore, by evaluating Figures 67 and 68 together, if the volumes of the hippocampus and amygdala are small and the ventricles are enlarged, it can be determined that there is a high possibility that this is due to atrophy caused by aging.

[0318] In other words, by two-dimensionally plotting the volume of each hippocampus and amygdala in comparison with the volume of the adjacent ventricles, as shown in Figures 67 and 68, it is possible to determine whether these structures are due to individual differences or atrophy.

[0319] More generally, the above-mentioned identification and assessment becomes possible by dividing the pattern of brain atrophy into four quadrants based on a combination of brain parenchyma volumes belonging to the limbic system, such as the hippocampus, entorhinal cortex, and amygdala, and the adjacent ventricles (inferior lateral ventricles, medial temporal lobe).

[0320] FIG. 69 is a flowchart showing a process for evaluating the atrophy of brain structures using the composite index described above.

[0321] Apart from the difference in the processing performed by the computer, the hardware configuration is the same as that of the first embodiment.

[0322] Referring to Figure 69, the process of analysis performed by the brain structure volume / signal intensity calculation unit 31 based on the brain image data and imaging condition data of the subject currently being evaluated will be described.

[0323] After the image input step (step S810) and the segmentation step (step S812), the brain structure volume / signal intensity calculation unit 31 executes a brain structure identification step S814, a brain structure volume / signal intensity calculation step S816, and processing by the imaging condition calibration unit 15 (step S818).

[0324] Here, too, first, for the analysis of the current subject, the image input unit 11 executes an image input step in which it reads brain image data and imaging condition data of the subject to be evaluated, transmitted from the imaging site (step S810). The segmentation unit 12 executes a segmentation step for the image input in the image input step S810 (step S812). The segmentation in the segmentation step S812 divides the brain image into multiple structural units (e.g., 505 structural units). Again, the segmentation can be performed with reference to the segmentation training data in the database 2a described above.

[0325] Next, as a module of the brain structure identification program, the brain structure identification unit 34 performs brain structure labeling for the structural units divided by segmentation, and executes a brain structure identification step of identifying structures previously selected to be used in calculating the composite index according to the prior evaluation by the imaging condition influence evaluation unit 33 (step S814). In the brain structure identification step S814, at least two brain structures such as those described in Figures 66 to 68 are identified. Note that, although not particularly limited, it is desirable that at least one brain structure be a robust structure that is little affected by imaging conditions and that can be minimized by calibration, and that is selected taking into consideration sensitivity to the disease risk of the evaluation target, such as a ventricle or a nearby ventricle.

[0326] Next, as a module of the brain structure volume / signal intensity calculation program, the brain structure volume / signal intensity calculation unit 35 executes calculation of the volume and signal intensity for each identified brain structure (step S816).

[0327] Then, in the brain image data analysis device 1 of embodiment 2, after processing by the imaging condition calibration unit 15 (step S818), the same-age ratio calculation unit 16 calculates a composite index using multiple brain structures (S820), and further generates display data for displaying a graph (four quadrants) such as those shown in Figures 66 to 68 for the volumes of the two brain structures used in calculating the composite index (S822), and outputs it as report information.

[0328] As explained above, when the brain is divided into multiple regions and each region is evaluated, it is found that each region exhibits characteristic age-related changes. For example, there is almost no age-related change in hippocampal volume until the age of 60, but the frontal lobe begins to atrophy in the 30s. By understanding normal age-related changes in each region of the brain, it is possible to detect pathological atrophy localized to a particular region. Therefore, by knowing the atrophy of multiple regions in combination, it is more likely that we can identify the signs of a specific disease (for example, in addition to the above, frontotemporal dementia causes atrophy in a combination of the frontal lobe and temporal lobe).

[0329] Therefore, by combining information on multiple structures in addition to the total brain volume and ventricular volume, it is possible to more accurately depict the state of brain atrophy. This improves the accuracy of determining the state of the brain to be evaluated (risk of dementia, dementia class, causative disease of dementia, etc.). [Embodiment 3] (Configuration of data sharing using temporary IDs)

[0330] In the first and second embodiments, a system and method for evaluating "disease risk," such as "risk of dementia," by evaluating the volume of specific brain structures using a device capable of capturing cross-sectional images of the human body, such as an MRI device or an X-ray CT device, has been described.

[0331] However, the imaging data acquired by such imaging devices, the disease risk assessed from the imaging data, and other clinical information about the subject are extremely valuable "medical data" and "healthcare data."

[0332] Therefore, in the third embodiment, a configuration for making such "medical data" and "healthcare data" available for sharing with third parties will be described.

[0333] The following are prerequisites:

[0334] 1) Both "medical data" and "healthcare data" are personal information that requires particular care in handling. In particular, information related to a subject's disease history is required to be handled with the strictest of care under the Personal Information Protection Act.

[0335] 2) On the other hand, from the perspective of effective use of valuable data, progress is being made in establishing a system that allows data to be provided to third parties by "anonymizing" each piece of data. However, while the true significance of "medical data" and "healthcare data" lies in the time series data (longitudinal data) of a specific individual, "data that is longitudinally related to the same person" is not necessarily desirable from the perspective of "anonymization."

[0336] 3) Therefore, one possible way to achieve both the protection of personal information and the use of data is to pseudonymize the data, process it so that it cannot easily identify a specific individual, notify the subject himself / herself of the purpose of use, etc., and use the data with his / her consent.

[0337] Figure 70 shows the concept of data flow from data acquisition to data joint use, in order to achieve both kana processing of data and usability as longitudinal data.

[0338] First, as will be described later, it is assumed that the system operator who provides the platform for shared data use issues identification information CP-ID as a shared temporary ID to each subject. The shared temporary ID is used in both health checkups for healthy individuals and diagnosis and treatment for patients.

[0339] Although not particularly limited, for example, the identification information CP-ID is converted into a two-dimensional code and stored in the subject's smartphone, and is configured to be displayed on the smartphone screen only when the user performs special access.

[0340] For example, a subject who has been issued such a shared temporary ID is to present this shared temporary ID to a hospital or clinic when undergoing imaging at an imaging site.

[0341] In the system operator's system, the shared temporary ID and the subject's personal information are associated and stored in a secure manner for security reasons.

[0342] Then, at the imaging site that is the data provider (for example, a data provider such as a hospital or clinic), the subject's name, a pseudonymized ID issued to each subject for the operation of the imaging site, information indicating whether consent has been obtained from the subject for data sharing, and information indicating whether the subject has requested the deletion of their data are associated with the shared temporary ID and stored in a storage device as a "personal identification information DB."

[0343] On the other hand, the data provider deletes information that can identify individuals, such as names and health insurance card numbers (including MAN numbers in Japan and Social Security numbers in the United States), and stores the subject's gender, age (coarse-grained to years, etc., as necessary), test results (imaging data, disease risk assessment indicators based on imaging), drug prescription information, and other clinical data in a storage device separate from the personal identification information DB, associated with the pseudonymized ID and shared temporary ID as a "pseudonymized processed information DB."

[0344] In this case, i) personally identifiable information will be stored separately from pseudonymized information, ii) it will be managed so that it cannot be compared with the personally identifiable information database unless certain requirements are met, and iii) only data for which the individual has given consent for data sharing will be registered in the pseudonymized information database.

[0345] When data is used for its intended purpose at the time of acquisition, such as health checkups or medical treatment, within a hospital or other facility, it will be permitted to be used as personal information, provided that certain requirements are met and matching with a pseudonymized ID is possible.

[0346] On the other hand, for joint purposes with the consent of the individual, only pseudonymized information will be shared.

[0347] With the above configuration, it is possible to share data in a manner that makes it difficult for anyone other than the data source to easily identify the subject, and within the scope of the subject's consent.

[0348] In the following, the operation of the system will be described on the assumption that imaging data and clinical data are stored from the imaging site in a PACS on the cloud.

[0349] FIG. 71 is a conceptual diagram showing a configuration that enables the kana-processed information described in FIG. 70 to be used by both system operators and data users.

[0350] Here, it is assumed that the system operator manages and operates the service page operation server 1000 and the analysis service providing server 2000 .

[0351] Here, the service page management server 1000 provides a service such as authenticating the request as being from a registered member subject 100 on a smartphone 200, and then providing a service page containing the results of the health checkup, imaging data related to the results of the diagnosis, clinical data, and recommended information for the subject, etc., and displaying them on the screen of the smartphone 200.

[0352] Furthermore, the service page operation server 1000 issues identification information CP-ID as a shared temporary ID as described in FIG. 70 to the subject who is a member.

[0353] FIG. 72 is a flowchart for explaining the operation of the system shown in FIG.

[0354] The imaging site 5000 where health checkups and medical examinations are performed is, for example, a hospital or a clinic.

[0355] 71 and 72, first, user 100 accesses service page operation server 1000 and performs user registration (S900). Then, service page operation server 1100 issues a CP-ID, which is a shared temporary ID that can be used both for health checkups and medical treatment at medical institutions (S902).

[0356] The storage device 1100 connected to the service page operation server 1000 receives data from the service page operation server 1100 and stores the shared temporary ID in association with personal information such as the member's name. As will be described later, if the member himself / herself gives consent, and within the scope of that consent, the storage device 1100 also stores information about the captured images, the contents of the analysis report, other related health care information, clinical information, and the like after the member's health checkup or medical examination.

[0357] The smartphone 200 of the member 100 that receives the shared temporary ID stores the shared temporary ID as, for example, a two-dimensional code, although this is not particularly limited.

[0358] When member 100 visits imaging site 5000 (hospital or clinic) for a health check (brain checkup) or medical treatment, member 100 displays a two-dimensional code of the shared temporary ID on the screen of his / her smartphone 200 and has it read into the system of imaging site 5000 (S904).

[0359] However, the method for passing the shared temporary ID to the system of the imaging site 5000 is not limited to using such a two-dimensional code, and may also be configured to transmit it via encrypted wireless communication using technology such as short-range communication.

[0360] Then, the member 100 is photographed at the imaging site 5000 (S906).

[0361] Image data captured at the imaging site 5000 is stored and registered in, for example, the cloud PACS 2100 (S908).

[0362] At this time, although not limited to this, for example, when storing in the cloud PACS 2100, personal identification information may be managed separately at the imaging site 5000, or if the cloud PACS is managed with the same level of security as the in-hospital system, the data registered in the cloud PACS 2100 is associated with information on the shared temporary ID and in-hospital ID, as well as image information, personal information such as patient names, and information on the member 100's consent to the shared use of the data.

[0363] Although not limited to this, data stored in cloud PACS 2100 may be encrypted to ensure stricter security, and furthermore, the data may be divided and stored on multiple servers, and the data stored on each server may be divided and stored using technology such as electronic tallying, thereby further improving security.

[0364] After the image data is stored in the cloud PACS 2100, the analysis service providing server 2000 executes an analysis process on the data in the cloud PACS 2100 (S910) and creates an analysis report (S912).

[0365] Here, "analysis processing" refers to the analysis as explained in the first and second embodiments, and includes analysis for "assessing the risk of dementia."

[0366] The analysis service providing server 2000 returns the analysis report to the system of the imaging site 5000 (S920), and the report is displayed on the screen of the system's display device (S922). In a hospital, this displayed report can be viewed by a doctor and used as auxiliary diagnostic information. In addition, in the case of a health checkup, the analysis report can be printed out and provided to the member 100.

[0367] Meanwhile, the analysis service providing server 2000 transmits the analysis report to the data sharing server 3000 , and the data sharing server 3000 stores the analysis report in a shared database (hereinafter, shared DB) 3100 .

[0368] The shared DB 3100 stores image information, clinical information, analysis reports, etc. in association with the shared temporary ID, within the scope of the consent of the member 100. As a result, the shared DB 3100 does not store any personally identifying information.

[0369] The shared DB 3100 also stores, as a recommended behavior database, behaviors recommended to the member 100 as behavioral changes in accordance with the results of the clinical information and analysis reports.

[0370] Therefore, when returning the analysis report to the member 100, the service page operation server 1000 may refer to the recommended action database and include the recommended action in the analysis report returned to the member 100.

[0371] In addition, in response to access from a member, the service page management server 1000 may display the member's analysis report, brain images, etc. in chronological order or selectively on the display screen of the member's 100 smartphone 200.

[0372] By accessing the shared DB 3100, the data user server 4000 stores in the user data server 4100, in association with the shared temporary ID, the temporary subscriber ID for the user's service (for example, insurance), and "healthcare information" of clinical information and analysis reports to the extent that the member 100 has agreed to the data user's use. The data user separately manages a correspondence table between personal identification information and temporary subscriber IDs. As a result, the personal identification information is not stored in the user data server 4100.

[0373] With the above configuration, brain image data, clinical information, and analysis report data captured at the imaging site 5000 can be shared within the scope of the member's 100 consent, and in a manner that makes it difficult to identify individuals without directly associating them with personal identification information.

[0374] As a result, as the data stored in the shared DB 3100 accumulates, not only will the accuracy of assessing the risk of dementia and other conditions improve, but data users will also be able to provide healthcare services based on the subject's healthcare information.

[0375] Thus, according to this embodiment and other embodiments, it is possible to realize a brain image data analysis device, a brain image data analysis method, and a brain image data analysis program that minimize the effects of uneven imaging conditions seen in brain checkups, enable accurate and reproducible measurement of atrophy in various parts of the brain, and analyze the risk of developing dementia.

[0376] Brain imaging data can also be used to assess a subject's risk of disease and provide information for behavioral modification.

[0377] The embodiments disclosed herein are merely examples of configurations for specifically implementing the present invention, and do not limit the technical scope of the present invention. The technical scope of the present invention is defined by the claims, not by the description of the embodiments, and is intended to include modifications within the literal scope of the claims and within the scope of equivalent meanings.

[0378] REFERENCE SIGNS LIST 1 Brain image data analysis device 2, 2a Database 11 Image input unit 12 Segmentation unit 13 Brain structure volume calculation unit 14 Brain signal intensity calculation unit 15 Shooting condition calibration unit 16 Peer age ratio calculation unit 17 Cerebrovascular disorder degree calculation unit 18 Analysis report creation unit 19 Analysis report output unit 201 Image input step 202 Segmentation step 203 Brain structure volume / signal intensity calculation step 204 Shooting condition calibration step 205 Peer age ratio calculation step

Claims

1. A brain image data analysis device that receives input of brain tomography images of a subject being evaluated, acquired by a tomography scanner, and analyzes the degree of atrophy of a predetermined region of interest in the brain in three dimensions, A segmentation unit that performs segmentation to divide the entire brain tomographic image into individual structural units, An identification unit for identifying structural units related to the region of interest from among the divided structural units, A volume calculation unit that calculates the brain volume of each identified structural unit, A calibration unit for calibrating the brain volume based on the input brain tomography image, according to the imaging conditions of the tomography scanner device, A database containing age-related change data, including brain volume data of each structural unit at each age under various imaging conditions, obtained by imaging multiple subjects in advance, The system includes a same-age ratio calculation unit that calculates the same-age ratio of the structural units of the person being evaluated from the data of each structural unit at each age in the database, The calibration unit performs calibration of the brain volume based on the age-related change data in the database. Brain image data analysis device, wherein the age-group ratio calculation unit analyzes the degree of atrophy of a predetermined brain region of interest by calculating the age-group ratio of the brain volume of the structural units of the subject to be evaluated to the plurality of subjects, based on the structural unit data for each age in the database after calibration.

2. The system further comprises a structural unit selection unit that, based on the brain volume data stored in the database, selects structural units that are related to atrophy of the region of interest, exhibit age-related changes greater than other structural units, and show changes less than other structural units due to the effects of imaging conditions. The brain image data analysis apparatus according to claim 1, wherein the identification unit targets the structural unit selected by the structural unit selection unit for identification.

3. The aforementioned specified brain regions of interest are structures known to change in dementias of the limbic system, including the hippocampus, or the medial temporal lobe. The brain image data analysis apparatus according to claim 2, wherein the structural unit selected by the structural unit selection unit is a structure selected based on the degree of the magnitude of the age-related change and robustness to the influence of the imaging conditions, and includes a ventricle.

4. The brain image data analysis apparatus according to claim 3, wherein the tomographic image scanner apparatus is an X-ray CT scanner apparatus.

5. The brain image data analysis apparatus according to claim 3, wherein the tomographic image scanner apparatus is an MRI scanner apparatus.

6. The brain image data analysis device according to claim 3 or 5, wherein the age-group ratio calculation unit analyzes a plurality of structural units in the database for each age and calculates the age-group ratio to analyze the degree of atrophy of the predetermined brain region of interest.

7. The plurality of structural units include the hippocampus and the ventricles, The aforementioned age ratio calculation unit, i) Generate data that displays the volume of the hippocampus on a first axis and the volume of the ventricles on a second axis perpendicular to the first axis, ii) The brain image data analysis device according to claim 6, which analyzes the degree of atrophy of a predetermined region of interest in the brain according to which quadrant of the coordinates represented by the first axis and the second axis the calculated value of the brain volume of the person being evaluated belongs to.

8. The brain image data analysis device according to claim 1 or 2, wherein the age-comparison calculation unit evaluates the dementia risk of the person being evaluated by analyzing the degree of atrophy of a predetermined brain region of interest.

9. The system further comprises a signal intensity calculation unit that calculates the signal intensity of each identified structural unit, The age-related change data in the database includes signal intensity data of each structural unit at each age under various imaging conditions, which has been imaged in advance for the multiple subjects. The calibration unit performs calibration of the signal intensity based on the age-related change data in the database. The brain image data analysis device according to claim 8, wherein the age-group ratio calculation unit, after calibration, analyzes the risk of cerebrovascular disease of the structural units by comparing the signal intensity of the structural units of the evaluated subjects with that of the same age group for the plurality of subjects, based on the data of the structural units at each age in the database.

10. Further comprising means for determining the calibration coefficient, The calibration coefficient determination means is A correlation generation means for creating a volume-age correlation curve for structural units of multiple subjects of different ages based on the aforementioned age-related change data, A parameter extraction means for extracting correlation parameters from the created correlation curve, The system includes matching means for determining a calibration coefficient for brain volume in order to reduce the difference in the extracted correlation parameters, The brain image data analysis apparatus according to claim 1, wherein the calibration unit performs calibration of the brain volume based on the determined calibration coefficient.

11. The aforementioned age ratio calculation unit, The brain image data analysis device according to claim 1, which calculates the position of the structural units of the person being evaluated in the population distribution based on the population distribution of the volume of the structural units at each age, and based on the age of the person being evaluated.

12. A method for analyzing brain image data of an analysis device that receives input of brain tomography images of a subject being evaluated, acquired by a tomography scanner, and analyzes the degree of atrophy of a predetermined region of interest in the brain in three dimensions, The analysis device includes a database containing age-related change data, which includes brain volume data of each structural unit at each age under various imaging conditions, obtained by imaging multiple subjects in advance. The steps include: performing segmentation to divide the entire brain tomographic image into individual structural units; The steps include identifying structural units related to the region of interest from among the divided structural units, A step of calculating the brain volume of each identified structural unit, The steps include: Calibrating the brain volume based on the input brain tomography image according to the imaging conditions of the tomography scanner device, based on the age-related change data in the database; The system comprises the step of calculating the age-group ratio of the structural units of the person being evaluated from the data of each structural unit at each age in the database, A method for analyzing brain imaging data, wherein the step of calculating the age-group ratio includes, after calibration, the step of analyzing the degree of atrophy of a predetermined region of interest in the brain by calculating the age-group ratio of the brain volume of the structural units of the subject to be evaluated to the plurality of subjects based on the structural unit data for each age in the database.

13. The step further includes determining the calibration coefficient, The step of determining the calibration coefficient is: Based on the aforementioned age-related change data, the steps include creating a volume-age correlation curve for the structural units of multiple subjects of different ages, The steps include extracting correlation parameters from the created correlation curve, The process includes the step of determining a calibration coefficient for brain volume so as to reduce the difference in the extracted correlation parameters, The method for analyzing brain image data according to claim 12, wherein the calibration step involves performing a calibration of the brain volume based on the determined calibration coefficient.

14. The step of calculating the ratio of people of the same age group is, A method for analyzing brain image data according to claim 12, comprising the step of calculating the position of the structural units of the person being evaluated in the population distribution based on the age of the person being evaluated, based on the population distribution of the volume of the structural units at each age.

15. The brain image data analysis method according to claim 12, wherein the step of calculating the age ratio includes a step of evaluating the dementia risk of the person being evaluated by analyzing the degree of atrophy of the predetermined brain region of interest.

16. A brain image data analysis program that causes a computer having a processing unit to receive input of brain tomography images of a subject being evaluated, captured by a tomography scanner, and to perform processing as an analysis device that analyzes the degree of atrophy of a predetermined region of interest in the brain in three dimensions, The storage device includes a database containing age-related change data, which includes brain volume data of each structural unit at each age under various imaging conditions, obtained by imaging multiple subjects in advance. The computing device performs a segmentation step, dividing the entire brain tomography image into individual structural units. The calculation device includes the steps of identifying structural units related to the region of interest from among the divided structural units, The calculation device performs the steps of calculating the brain volume of each identified structural unit, The calculation device performs the following steps: Based on the age-related change data in the database, it performs the calibration of the brain volume based on the input brain tomography image according to the shooting conditions of the tomography scanner device; The calculation device includes the step of calculating the age-group ratio of the structural units of the person being evaluated from the data of each structural unit for each age in the database, Brain imaging data analysis program, the step of calculating the age-group ratio after calibration, includes the step of analyzing the degree of atrophy of a predetermined region of interest in the brain by calculating the age-group ratio of the brain volume of the structural units of the evaluated subject to the number of subjects based on the structural unit data for each age in the database.

17. A workstation incorporating the brain image data analysis device described in claim 1.

18. A medical image management system incorporating the brain image data analysis device described in claim 1.

19. A cloud server system incorporating the brain image data analysis device described in claim 1.