WO2025005388A1 - 뇌 ct에서 예측한 부피를 이용한 치매 관련 정보 산출 방법 및 분석장치 - Google Patents
뇌 ct에서 예측한 부피를 이용한 치매 관련 정보 산출 방법 및 분석장치 Download PDFInfo
- Publication number
- WO2025005388A1 WO2025005388A1 PCT/KR2024/003074 KR2024003074W WO2025005388A1 WO 2025005388 A1 WO2025005388 A1 WO 2025005388A1 KR 2024003074 W KR2024003074 W KR 2024003074W WO 2025005388 A1 WO2025005388 A1 WO 2025005388A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- dementia
- brain
- region
- interest
- related information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/032—Transmission computed tomography [CT]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/501—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of the head, e.g. neuroimaging or craniography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5294—Devices using data or image processing specially adapted for radiation diagnosis involving using additional data, e.g. patient information, image labeling, acquisition parameters
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
Definitions
- the technology described below is a method for predicting dementia-related information of a subject using brain CT images.
- Dementia is a syndrome that causes cognitive functions such as memory, language, and judgment to deteriorate in the future.
- Alzheimer's disease is the most common type of dementia.
- Brain imaging such as MRI (Magnetic Resonance Imaging) and PET are used to diagnose Alzheimer's disease.
- 3D(dimensional) MRI and PET-CT(positron emission tomography-Computed Tomography) take a lot of time and money to take pictures.
- CT has no restrictions such as the presence of metal substances in the human body, can be obtained much faster than MRI, and is relatively inexpensive.
- the technology described below is intended to provide a method for producing dementia-related information, such as dementia presence, dementia risk, and brain atrophy, using only brain CT images.
- a method for producing dementia-related information using a volume predicted from a brain CT includes a step of an analysis device receiving a brain CT image of a subject, a step of the analysis device inputting the brain CT image into a learned segmentation model to extract regions of interest, a step of the analysis device inputting pixel information of the regions of interest into a first learned model to predict the volume of at least one region among the regions of interest, and a step of the analysis device inputting the volume of the at least one region into a second learned model to produce dementia-related information of the subject.
- An analysis device for calculating dementia-related information using a volume predicted from a brain CT includes an interface device for receiving a brain CT image of a subject, a segmentation model for extracting a region of interest from the brain CT image, a storage device for storing a first learning model for receiving information on a region of interest of the brain and predicting a volume, and a second learning model for calculating dementia-related information, and a calculation device for inputting the received brain CT image into the segmentation model to extract regions of interest, inputting pixel information of the extracted regions of interest into the first learning model to predict a volume of at least one region among the regions of interest, and inputting the volume of the at least one region into the second learning model to calculate dementia-related information of the subject.
- the technology described below extracts regions of interest from CT images and derives dementia-related information based on the volume of the region of interest.
- the technology described below can quickly and inexpensively derive significant dementia-related information using only CT images.
- Figure 1 is an example of a system that produces dementia-related information based on CT images.
- Figure 2 is an example of a process for producing dementia-related information using brain CT images.
- Figure 3 is an example of the process of learning a segmentation model that extracts a region of interest from a brain CT image.
- Figure 4 is an example of the learning process of a learning model that predicts the volume of a region of interest based on the extracted region of interest.
- Figure 5 is an example of the learning process of a learning model that produces dementia-related information based on the volume of a brain region of interest.
- Figure 6 is an example of an analysis device that produces dementia-related information of a subject using a brain CT image.
- first, second, A, B, etc. may be used to describe various components, these components are not limited by these terms, and are only used to distinguish one component from another.
- first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.
- the term and/or includes any combination of a plurality of related described items or any item among a plurality of related described items.
- each process constituting the method may occur in a different order from the stated order unless the context clearly states a specific order. That is, each process may occur in the same order as the stated order, may be performed substantially simultaneously, or may be performed in the opposite order.
- the technology described below is a technology that produces dementia-related information from brain CT.
- Dementia below includes Alzheimer's dementia.
- Dementia-related information refers to information related to dementia diagnosis or dementia prediction.
- dementia-related information may be at least one of the following information: dementia onset, dementia risk, dementia possibility, dementia-related score, dementia prognosis prediction, brain atrophy degree, beta amyloid (amyloid-ß, Aß) positivity, tau protein positivity, brain age, etc.
- the analysis device can take the form of a computer device such as a PC, a smart device, a network server, a data processing-dedicated chipset, etc.
- the analysis device can use multiple learning models to derive dementia-related information based on brain images.
- the analysis device can use a segmentation model to extract regions of interest from the CT.
- the analysis device can use a classification model to derive dementia-related information from the CT or regions of interest.
- Fig. 1 is an example of a system (100) that produces dementia-related information based on CT images.
- an example of an analysis device being a computer terminal (130) and a server (140) is illustrated.
- the CT imaging device (110) captures a CT image of a subject.
- the CT image is an image of a brain region (brain CT image).
- the brain CT image generated by the CT imaging device (110) can be stored in a separate database such as an Electronic Medical Record (EMR, 120).
- EMR Electronic Medical Record
- the computer terminal (130) can receive a brain CT image of a subject from a CT imaging device (110) or EMR (120) through a wired or wireless network. In some cases, the computer terminal (130) may be a device physically connected to the CT imaging device (110). The computer terminal (130) can preprocess the brain CT image in a predetermined manner.
- the computer terminal (130) extracts regions of interest (areas) from a brain CT image.
- the computer terminal (130) can extract regions of interest (areas) from a brain CT image using a learned segmentation model.
- the computer terminal (130) can estimate the volume of the regions of interest (areas) using the learned model.
- the computer terminal (130) can produce dementia-related information about the subject based on the volume of the regions of interest (areas) using the learned model.
- User A can check dementia-related information through the computer terminal (130).
- the server (140) can receive a brain CT image of a subject from a CT imaging device (110) or EMR (120) via a wireless network.
- the server (140) can preprocess the brain CT image on a regular basis.
- the server (140) extracts regions of interest (areas of interest) from a brain CT image.
- the server (140) can extract regions of interest (areas of interest) from a brain CT image using a learned segmentation model.
- the server (140) can estimate the volume of the regions of interest (areas of interest) using the learned model.
- the server (140) can produce dementia-related information about the subject based on the volume of the regions of interest (areas of interest) using the learned model.
- the server (140) can transmit the dementia-related information to a user terminal. User A can check the dementia-related information through the user terminal.
- Figure 2 is an example of a process (200) for producing dementia-related information using a brain CT image.
- the analysis device can produce dementia-related information about a subject based on a brain CT image.
- the analysis device receives a brain CT image of the subject (210).
- the brain CT may be composed of multiple slices.
- the subject analyzed by the analysis device may be all of the multiple slices or at least one slice among the multiple slices.
- the analysis device can preprocess brain CT images in a uniform manner.
- the analysis device can extract the entire brain region from the brain CT image.
- the analysis device can use a pre-trained segmentation model.
- the analysis device can extract the entire brain region from the brain MRI image using the CIVET pipeline to generate an answer, and the segmentation model can be trained to extract the entire brain region from the brain CT image based on the answer (the entire brain region of the brain MRI image).
- the analysis device can extract the entire brain region from the brain CT image using the trained segmentation model.
- the analysis device can normalize the size or resolution of the subject's brain CT image to a certain size.
- the analysis device extracts a region of interest from the input brain CT image (220).
- the analysis device can extract a region of interest using a segmentation model learned in advance.
- the analysis device can extract a plurality of regions of interest using the segmentation model.
- the regions of interest correspond to regions for calculating the volume of the corresponding region.
- the region of interest can include at least one of a cerebrospinal fluid (CSF) region and a ventricle region.
- CSF cerebrospinal fluid
- the region of interest can include at least one of a frontal CSF region, a temporal CSF region, a parietal CSF region, an occipital CSF region, an anterior lateral ventricle region, a posterior lateral ventricle region, and an around hippocampal CSF region.
- CSF cerebrospinal fluid
- the analysis device can estimate the volume of the extracted region(s) of interest (230).
- the analysis device can estimate the volume of the specific region of interest by using a learning model (e.g., a regression analysis model) that has learned in advance the relationship between the number of pixels for the specific region of interest and the volume of the region.
- a learning model e.g., a regression analysis model
- the analysis device needs to uniformly normalize the size of the brain CT image or the region of interest.
- the analysis device can estimate the volume of the specific region of interest based on the uniformly normalized brain CT image.
- the learning model can be prepared in advance for each of a plurality of regions of interest.
- the analysis device can individually estimate the volume of the corresponding region by using learning models for each of the frontal cerebrospinal fluid region, the temporal cerebrospinal fluid region, the parietal cerebrospinal fluid region, the occipital cerebrospinal fluid region, the anterior lateral ventricle region, the posterior lateral ventricle region, and the cerebrospinal fluid region around the hippocampus.
- the analysis device can also estimate the volume of the region of interest by additionally using the subject's clinical information (gender, age, etc.) in addition to the brain CT image.
- the analysis device can produce dementia-related information about the subject based on the volume of the region(s) of interest (240).
- the analysis device can produce dementia-related information based on the volume of the region(s) of interest using a learning model.
- the analysis device can produce dementia-related information about the subject using additional clinical information (age, gender, APOE4 genotype, etc.) in addition to the volume of the region(s) of interest.
- the researcher constructed the aforementioned learning models using data from the population that visited the affiliated medical institution (Samsung Seoul Hospital).
- the population consisted of dementia patients (Alzheimer's disease dementia, ADD) and normal controls (NC).
- the population was selected as subjects who had both MRI and CT scans within a certain period (1 year).
- the population excluded young normal subjects and dementia patients with cardiovascular disease.
- the population data included MRI, CT, clinical information (gender, age, APOE4 phenotype), and dementia (label value).
- the total number of subjects in the population was 895. Table 1 below shows the population information.
- the researcher used 716 data (80%) of the 895 subjects as training data and 179 data (20%) as test data. Verification was performed using 5-fold cross validation.
- Figure 3 is an example of a process (300) for learning a segmentation model that extracts a region of interest from a brain CT image.
- the researcher normalized the brain CT images used as learning data to a certain size.
- the researcher enhanced the learning data through brightness adjustment, image flipping (horizontal flip), etc. for the learning data.
- a learning device refers to a computer device capable of processing image data and performing the learning process of a machine learning model.
- the learning device learns a segmentation model using medical images of multiple subjects.
- Fig. 3 illustrates an example of a process of learning a segmentation model using data of subject i.
- the learning device constructs learning data for learning the learning model (310).
- the learning data can be constructed from brain images of a population (including dementia patients and normal people).
- the CT image DB (database) stores brain CT images of the population.
- the MRI image DB stores brain MRI images of the population.
- the MRI image DB includes information on regions of interest in brain images. The information on regions of interest can be regions of interest labeled automatically or manually by an expert.
- the learning device constructs learning data by extracting CT images and MRI images (including information on regions of interest) of the same subject.
- the learning device performs a process of learning a segmentation model that extracts a region of interest using learning data (320).
- the learning device performs learning based on data about a specific patient among the learning data.
- the learning device can repeatedly perform the learning process using data about a number of patients in the learning data.
- the learning device receives a 3D MRI image (including information on a region of interest) of subject i (311).
- the learning device receives a 2D or 3D CT image of subject i (312).
- the region of interest may be a ROI in a 2D image or a VOI (Volume of Interest) in a 3D image.
- the learning device aligns a brain MRI image and a brain CT image (320). The learning device aligns images of the same brain region of the same subject.
- the learning device builds a segmentation model using aligned brain CT and brain MRI.
- the segmentation model can be a semantic segmentation model.
- the segmentation model can be a fully convolutional network (FCN)-based model such as U-net.
- FCN fully convolutional network
- the segmentation model predicts the region of interest based on the brain CT image.
- the segmentation model is trained to extract the same region of interest from the brain CT image by referencing the region of interest in the brain MRI image, which is the correct answer.
- the regions of interest can be multiple regions as described above.
- the regions of interest can include frontal cerebrospinal fluid regions, temporal cerebrospinal fluid regions, parietal cerebrospinal fluid regions, occipital cerebrospinal fluid regions, anterior lateral ventricle regions, posterior lateral ventricle regions, and perihippocampal cerebrospinal fluid regions.
- the learning device can build a segmentation model for each region of interest.
- the researcher also constructed multiple segmentation models for each area of interest.
- the researcher constructed a U-net-based segmentation model.
- the researcher constructed a segmentation model (2D image-based segmentation model) using each axial slice in the training data.
- the researcher constructed a segmentation model (3D image-based segmentation model) using 3D CT of the training data.
- Table 2 shows the results of evaluating the performance of the constructed segmentation models.
- the researcher performed 5-fold cross-validation on the validation data to evaluate the performance of the 2D image-based segmentation model and the 3D image-based segmentation model.
- Fig. 4 is an example of a learning process (400) of a learning model that predicts the volume of a region of interest based on an extracted region of interest.
- the learning model predicts the volume of an interest potion based on the aforementioned region of interest.
- the learning in Fig. 4 assumes that the region of interest described above has been extracted from a brain CT image of a subject belonging to the population. That is, the learning device can use the region of interest calculated using the segmentation model of Fig. 3.
- the learning device extracts input data based on regions of interest extracted from a brain CT image (410).
- the input data includes regions of interest(s) extracted by the segmentation model.
- the input data includes the actual volume (correct value) of a specific region of interest.
- the actual volume can be derived from MRI.
- the input data may include clinical information (gender, age) about the subject.
- the learning device performs a process of learning a learning model by utilizing the extracted input data (420).
- the learning device repeats the learning process of the learning model by utilizing input data extracted from brain CT images of multiple subjects.
- the learning device can build a learning model that predicts volume by region of interest.
- the learning device calculates the total number of pixels for the region of interest.
- the regions of interest can be, as described above, the frontal cerebrospinal fluid region, the temporal cerebrospinal fluid region, the parietal cerebrospinal fluid region, the occipital cerebrospinal fluid region, the anterior lateral ventricle region, the posterior lateral ventricle region, and the cerebrospinal fluid region around the hippocampus.
- the learning device builds a learning model by comparing the number of pixels in the region of interest with the volume (correct answer) of the region of interest. Through this process, the learning model learns to predict the volume of the region of interest.
- the correct answer is the volume of a specific region of interest derived from brain MRI of subjects belonging to the population.
- the learning model can be constructed as an individual model depending on the information to be predicted.
- the learning model is a machine learning model and can be implemented as one of various types of models.
- the researcher used a regression model.
- the researcher individually constructed a model for predicting the volume of the anterior CSF (anterior CSF model), a model for predicting the volume of the temporal CSF (temporal CSF model), a model for predicting the volume of the parietal CSF (parietal CSF model), a model for predicting the volume of the occipital CSF (occipital CSF model), a model for predicting the volume of the anterior lateral ventricle (lateral ventricle model), a model for predicting the volume of the posterior lateral ventricle (posterior lateral ventricle model), and a model for predicting the volume of the cerebrospinal fluid region around the hippocampus (hippocampal CSF model).
- the learning model can be trained using clinical information (age and gender) in addition to the size of the region of interest.
- the researcher compared the predicted volume of the region of interest extracted from the brain CT image with the correct value measured from the 3D MRI using the segmentation model described above.
- the researcher segmented the region of interest using each of the two segmentation models constructed, and compared the predicted volume with the correct value based on this result.
- the performance evaluation results of the volume prediction model are shown in Table 3 below.
- the performance index is the Pearson Correlation Coefficient.
- the researcher repeated 10 cross validations 10 times (permutations).
- the volume of the region of interest predicted by the learning model showed a significant correlation with the actual correct value.
- Correlation r (Volume prediction of segmented regions of interest based on 2D images) Correlation r (Volume prediction of segmented regions of interest based on 3D images) Frontal cerebrospinal fluid area 0.838 0.868 Temporal cerebrospinal fluid area 0.827 0.878 Cerebrospinal fluid area of the parietal region 0.868 0.905 Occipital cerebrospinal fluid area 0.761 0.824 anterior lateral ventricular area 0.984 0.984 Posterior lateral ventricular area 0.981 0.981 Cerebrospinal fluid area around the hippocampus 0.945 0.944
- Figure 5 is an example of a learning process (500) of a learning model that produces dementia-related information based on the volume of a brain region of interest.
- the learning model that produces dementia-related information can be implemented as any one of various types of machine learning models.
- the researcher implemented a model that produces dementia-related information using a deep learning model.
- the learning in Fig. 5 assumes that the volume of the brain region of interest and clinical information for the subjects belonging to the population have been acquired.
- the learning device can use the volume of each region of interest of the subjects calculated using the learning model in Fig. 4.
- the learning device acquires input data, which is learning data (510).
- the learning device extracts the volume of a specific region of interest extracted from the brain CT images of subjects belonging to the population.
- the brain region volume may include the volume of the frontal cerebrospinal fluid region, the temporal cerebrospinal fluid region, the parietal cerebrospinal fluid region, the occipital cerebrospinal fluid region, the anterior lateral ventricle region, the posterior lateral ventricle region, and the cerebrospinal fluid region around the hippocampus.
- the learning device may construct a learning model to produce dementia-related information based on some of the regions of interest among the multiple regions of interest.
- the learning device acquires clinical information of the subjects.
- the clinical information may include age, gender, and APOE4 phenotype.
- the learning device may construct a learning model to derive dementia-related information by using some of the clinical information in addition to the volume of the region(s) of interest.
- the learning data may include the volume of a specific brain region calculated using the learning model of Fig. 3.
- the learning data may include the cerebral cortex thickness and the volume of a specific brain region calculated from brain images of actual subjects. The researcher used the volume of a region of interest calculated from the results of 3D MRI analysis of an actual subject as the learning data.
- the learning device performs a process of learning a learning model by utilizing the extracted input data (520).
- the learning device repeats the learning process of the learning model by utilizing input data extracted from a number of subjects.
- the learning device performs learning by inputting the extracted input data into the learning model and comparing the value (predicted value) output by the learning model with the correct answer.
- the learning model is trained to predict dementia-related information of the subject.
- the correct answer is dementia-related information of the subject.
- the researcher constructed a learning model to classify dementia patients or normal people.
- the researcher used 90% of the population data as learning data and 10% of the data as verification data.
- the multiple learning models constructed by the researcher are shown in Table 3 below.
- the learning models were largely constructed as a model that uses only the volume of regions of interest (Model A), a model that uses the volume of regions of interest and clinical information (age and gender) (Model B), and a model that uses the volume of regions of interest and clinical information (age, gender, and APOE4 phenotype) (Model C).
- Each model group was constructed by dividing it into models that use 1, 2, 3, 4, 6, and 7 (total) regions of interest among the total regions of interest.
- Table 4 shows the model groups using four different ROIs and the training data used to build different models in each group.
- the model in Table 4 below is a model that predicts whether the subject has dementia (dementia or normal).
- the training model in Figure 4 corresponds to a model that binary classifies whether the subject has dementia or is normal.
- Model classification model name Input Features Model A Model A1 3 ROIs (aLV/pLV/HippCSF) Model A2 4 ROIs (F/T/P/O) Model A3 6 ROIs (F/T/P/O/aLV/pLV) Model A4 7 ROIs (F/T/P/O/aLV/pLV/HippCSF) Model A5 2 ROIs (aLV/pLV) Model A6 1 ROIs (HippCSF) Model B Model B1 3 ROIs (aLV/pLV/HippCSF)+(age, sex) Model B2 4 ROIs (F/T/P/O)+(Age, Gender) Model B3 6 ROIs (F/T/P/O/aLV/pLV)+(age, gender) Model B4 7ROIs (F/T/P/O/aLV/pLV/HippCSF)+(age, sex) Model B5 2 ROIs (aLV/pLV)+(age, sex, APOE4) Model B
- F frontal CSF
- T temporal CSF
- P parietal CSF
- O occipital CSF
- aLV anterior lateral ventricle
- pLV posterior lateral ventricle
- HippCSF perihippocampal CSF
- the researcher verified the constructed learning model. Meanwhile, in the verification process, the researcher used the cerebral cortex thickness and brain region volume predicted by the learning model of Fig. 4 as input data for the learning model of Fig. 5. The researcher performed 10-fold cross-validation.
- the verification results are as shown in Table 5 below.
- 3D CIVET is the classification result using the volume value obtained from CIVET.
- Table 5 shows the classification result using the region of interest segmented by the 2D image-based segmentation model and the classification result using the region of interest segmented by the 3D image-based segmentation model.
- the verification compared the result predicted by the learning model with the correct answer.
- the performance indices used were the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUPRC).
- Model Type 3D CIVET Classification performance using 2D image-based segmentation model Classification performance using 3D image-based segmentation model AUC AUPRC AUC AUPRC AUC AUPRC Model A1 0.791 0.772 0.783 0.767 0.784 0.769 Model A2 0.767 0.737 0.738 0.730 0.772 0.735 Model A3 0.779 0.744 0.746 0.737 0.779 0.738 Model A4 0.780 0.746 0.746 0.738 0.773 0.734 Model A5 0.805 0.772 0.801 0.776 0.800 0.776 Model A6 0.800 0.784 0.766 0.766 0.777 0.763 Model B1 0.924 0.903 0.894 0.893 0.900 0.892 Model B2 0.882 0.870 0.838 0.837 0.884 0.881 Model B3 0.910 0.897 0.872 0.866 0.902 0.899 Model B4 0.930 0.913 0.908 0.899 0.916 0.907 Model B5 0.8
- Fig. 6 is an example of an analysis device (600) that uses brain CT images to derive dementia-related information for a subject.
- the analysis device (600) may be implemented in various physical forms.
- the analysis device (600) may take the form of a computer device such as a PC, a smart device, a network server, a data processing-dedicated chipset, etc.
- the analysis device (600) may be connected to brain imaging equipment or may be an integrated device.
- the analysis device (600) may include a storage device (610), a memory (620), a computational device (630), an interface device (640), a communication device (650), and an output device (660).
- the storage device (610) can store a brain CT image of a subject generated by CT scanning equipment.
- the storage device (610) can store clinical information of the subject.
- the clinical information can include at least one of age, gender, and APOE4 genotype.
- the storage device (610) can store a segmentation model for extracting a region of interest from a brain CT image (slice).
- the storage device (610) can store a learning model that predicts the volume of a region of interest based on information of the region of interest.
- the learning model that predicts the volume of a specific brain region of interest is called a first learning model.
- the region of interest includes at least one of a frontal cerebrospinal fluid region, a temporal cerebrospinal fluid region, a parietal cerebrospinal fluid region, an occipital cerebrospinal fluid region, an anterior lateral ventricle region, a posterior lateral ventricle region, and a cerebrospinal fluid region around the hippocampus.
- the first learning model can be prepared for each region of interest.
- the storage device (610) can store a learning model that calculates dementia-related information using the volume of the region of interest.
- the learning model that calculates dementia-related information is called the second learning model.
- the second learning model can be implemented as various models depending on the type of input data as described above.
- the second learning model can be at least one of various types, such as (i) a model that uses only the volume of the region of interest as input data (Model A), (ii) a model that uses the volume of the region of interest and clinical information (age, gender) as input data (Model B), or (iii) a model that uses the volume of the region of interest and clinical information (age, gender, and APEO4) as input data (Model C).
- the region of interest used by the learning model can be all or a part of the seven regions of interest as described in Table 3.
- the dementia-related information inferred by the second learning model may be at least one of the following information: dementia onset, dementia risk, dementia possibility, dementia-related score, dementia prognosis prediction, brain atrophy degree, beta amyloid-ß (Aß) positivity, tau protein positivity, brain age, etc.
- the dementia-related information may vary depending on the type of learning data (correct answer value) used by the second learning model.
- the memory (620) can store data and information generated during the process in which the analysis device (600) derives dementia-related information from a brain CT image.
- the interface device (640) is a device that receives certain commands and data from the outside.
- the interface device (640) can receive a brain CT image of a subject from a physically connected input device or an external storage device.
- the interface device (640) can also transmit dementia-related information predicted based on the brain CT image to an external object.
- the communication device (650) refers to a configuration that receives and transmits certain information through a wired or wireless network.
- the communication device (650) can receive a brain CT image of a subject from an external object.
- the communication device (650) can also transmit dementia-related information predicted based on the brain CT image to an external object such as a user terminal.
- the interface device (640) may be a device that internally transmits data received from a communication device (650).
- the output device (660) is a device that outputs certain information.
- the output device (660) can output interfaces required for data processing, brain images, regions of interest distinguished from brain images, dementia-related information calculated based on regions of interest, etc.
- the computational device (630) can preprocess the brain CT image of the subject in a predetermined manner. For example, the computational device (630) can normalize the brain CT image to a predetermined size or resolution.
- the computational device (630) can input the subject's brain CT image into the learned segmentation model to extract the region of interest.
- the computational device (630) can input the subject's brain CT image into the learned segmentation model in slice units to extract the region of interest.
- the region of interest may be at least one of the frontal cerebrospinal fluid region, temporal cerebrospinal fluid region, parietal cerebrospinal fluid region, occipital cerebrospinal fluid region, anterior lateral ventricle region, posterior lateral ventricle region, and parahippocampal cerebrospinal fluid region.
- the computational device (630) can extract size information for the region(s) of interest.
- the computational device (630) can calculate the sum of pixels for each region of interest.
- the computational device (630) can estimate the volume of the region of interest based on the number of pixels of the region of interest.
- the computational device (630) can calculate the volume of the region of interest based on the number of pixels of the region of interest using the first learning model described above.
- the computational device (630) can estimate the volume of each of the plurality of regions of interest using the first learning model constructed for each region of interest.
- the computational device (630) can input the volume of the region of interest predicted by the first learning model into the second learning model to produce dementia-related information of the subject.
- the computational device (630) can input the volume of at least one region among the frontal cerebrospinal fluid region, the temporal cerebrospinal fluid region, the parietal cerebrospinal fluid region, the occipital cerebrospinal fluid region, the anterior lateral ventricle region, the posterior lateral ventricle region, and the cerebrospinal fluid region around the hippocampus into the second learning model to produce dementia-related information of the subject.
- the computational device (630) can input clinical information (at least one of age, gender, and APOE4 genotype) in addition to the volume of the region of interest into the second learning model to produce dementia-related information of the subject. This process is as described in FIG. 5.
- the computational device (630) may be a device such as a processor, AP, or chip embedded with a program that processes data and performs certain operations.
- the brain CT image analysis method or dementia-related information generation method as described above may be implemented as a program (or application) including an executable algorithm that can be executed on a computer.
- the program may be provided by being stored in a temporary or non-transitory computer readable medium.
- a non-transitory readable medium refers to a medium that semi-permanently stores data and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory.
- the various applications or programs described above may be stored and provided in a non-transitory readable medium, such as a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM (read-only memory), PROM (programmable read only memory), EPROM (Erasable PROM, EPROM), EEPROM (Electrically EPROM), or flash memory.
- Temporarily readable media refers to various types of RAM such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synclink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM).
- SRAM Static RAM
- DRAM Dynamic RAM
- SDRAM Synchronous DRAM
- DDR SDRAM Double Data Rate SDRAM
- ESDRAM Enhanced SDRAM
- SLDRAM Synclink DRAM
- DRRAM Direct Rambus RAM
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- General Physics & Mathematics (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Optics & Photonics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- High Energy & Nuclear Physics (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physiology (AREA)
- Neurology (AREA)
- Dentistry (AREA)
- Pulmonology (AREA)
- Neurosurgery (AREA)
- Multimedia (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
Description
| Total | NC | ADD | |
| Subjects, N (%) | 895 (100.0) | 457 (51.1) | 438 (48.9) |
| Age, mean years (SD,표준편차) | 67.4 (11.4) | 66.8 (12.5) | 68.0 (10.2) |
| Female, N (%) | 541 (60.4) | 279 (60.9) | 262 (59.8) |
| APOEε4 carriers, N(%) | 322 (36.0) | 86 (18.8) | 236 (51.5) |
| 전두부 뇌척수액 영역, 평균 부피(mm3) | 61052.5 | 50380.9 | 72187.0 |
| 측두부 뇌척수액 영역, 평균 부피 (mm3) | 36534.9 | 31169.5 | 42133.0 |
| 두정부 뇌척수액 영역, 평균 부피 (mm3) | 36045.5 | 29592.5 | 42778.3 |
| 후두부 뇌척수액 영역, 평균 부피 (mm3) | 14828.4 | 13150.0 | 16579.6 |
| 전 측뇌실 영역, 평균 부피 (mm3) | 17687.3 | 13955.5 | 21581.1 |
| 후 측뇌실 영역, 평균 부피(mm3) | 20476.3 | 14904.4 | 26289.8 |
| 해마 주변 뇌척수액 영역, 평균 부피 (mm3) | 7577.0 | 5562.8 | 9678.6 |
| 2D 영상 기반 세그멘테이션 모델 2D (n=179) | |||||||
| 전두부 뇌척수액 영역 |
측두부 뇌척수액 영역 |
두정부 뇌척수액 영역 |
후두부 뇌척수액 영역 |
전 측뇌실 영역 | 후 측뇌실 영역 | 해마 주변 뇌척수액 영역 |
|
| 1 Fold | 0.5686 | 0.4832 | 0.5711 | 0.4294 | 0.8848 | 0.8573 | 0.6511 |
| 2 Fold | 0.5682 | 0.4786 | 0.5686 | 0.4246 | 0.8833 | 0.8563 | 0.6476 |
| 3 Fold | 0.5815 | 0.4949 | 0.5813 | 0.4443 | 0.8816 | 0.8557 | 0.6442 |
| 4 Fold | 0.5836 | 0.4938 | 0.5835 | 0.4434 | 0.8822 | 0.8548 | 0.6435 |
| 5 Fold | 0.5711 | 0.4872 | 0.5714 | 0.4311 | 0.8849 | 0.8584 | 0.6613 |
| 3D 영상 기반 세그멘테이션 모델 (n=179) | |||||||
| 전두부 뇌척수액 영역 | 측두부 뇌척수액 영역 | 두정부 뇌척수액 영역 | 후두부 뇌척수액 영역 | 전 측뇌실 영역 | 후 측뇌실 영역 | 해마 주변 뇌척수액 영역 | |
| 1 Fold | 0.5827 | 0.4885 | 0.5903 | 0.4449 | 0.8851 | 0.8603 | 0.6278 |
| 2 Fold | 0.5865 | 0.4907 | 0.5922 | 0.448 | 0.8837 | 0.859 | 0.6273 |
| 3 Fold | 0.594 | 0.4967 | 0.6037 | 0.4608 | 0.8832 | 0.8593 | 0.6201 |
| 4 Fold | 0.6026 | 0.5023 | 0.6063 | 0.4613 | 0.8823 | 0.8563 | 0.6181 |
| 5 Fold | 0.5864 | 0.4907 | 0.594 | 0.4494 | 0.8862 | 0.8611 | 0.6357 |
| 관심 영역 |
Correlation r
(2D 영상 기반 구분한 관심 영역의 부피 예측) |
Correlation r
(3D 영상 기반 구분한 관심 영역의 부피 예측) |
| 전두부 뇌척수액 영역 | 0.838 | 0.868 |
| 측두부 뇌척수액 영역 | 0.827 | 0.878 |
| 두정부 뇌척수액 영역 | 0.868 | 0.905 |
| 후두부 뇌척수액 영역 | 0.761 | 0.824 |
| 전 측뇌실 영역 | 0.984 | 0.984 |
| 후 측뇌실 영역 | 0.981 | 0.981 |
| 해마 주변 뇌척수액 영역 | 0.945 | 0.944 |
| 모델분류 | 모델명 | 입력 특징 |
| 모델 A |
모델 A1 | 3 ROIs (aLV/pLV/HippCSF) |
| 모델 A2 | 4 ROIs (F/T/P/O) | |
| 모델 A3 | 6 ROIs (F/T/P/O/aLV/pLV) | |
| 모델 A4 | 7 ROIs (F/T/P/O/aLV/pLV/HippCSF) | |
| 모델 A5 | 2 ROIs (aLV/pLV) | |
| 모델 A6 | 1 ROIs (HippCSF) | |
| 모델 B |
모델 B1 | 3 ROIs (aLV/pLV/HippCSF)+(나이, 성별) |
| 모델 B2 | 4 ROIs (F/T/P/O)+(나이, 성별) | |
| 모델 B3 | 6 ROIs (F/T/P/O/aLV/pLV)+(나이, 성별) | |
| 모델 B4 | 7ROIs (F/T/P/O/aLV/pLV/HippCSF)+(나이, 성별) | |
| 모델 B5 | 2 ROIs (aLV/pLV)+(나이, 성별, APOE4) | |
| 모델 B6 | 1 ROIs (HippCSF)+(나이, 성별, APOE4) | |
| 모델 C |
모델 C1 | 3 ROIs (aLV/pLV/HippCSF)+(나이, 성별, APOE4) |
| 모델 C2 | 4 ROIs (F/T/P/O)+(나이, 성별, APOE4) | |
| 모델 C3 | 6 ROIs (F/T/P/O/aLV/pLV)+(나이, 성별, APOE4) | |
| 모델 C4 | 7 ROIs (F/T/P/O/aLV/pLV/HippCSF)+(나이, 성별, APOE4) | |
| 모델 C5 | 2 ROIs (aLV/pLV)+(나이, 성별, APOE4) | |
| 모델 C6 | 1 ROIs (HippCSF)+(나이, 성별, APOE4) |
| 모델종류 | 3D CIVET | 2D영상 기반 세그멘테이션 모델 이용한 분류 성능 | 3D영상 기반 세그멘테이션 모델 이용한 분류 성능 | |||
| AUC | AUPRC | AUC | AUPRC | AUC | AUPRC | |
| 모델 A1 | 0.791 | 0.772 | 0.783 | 0.767 | 0.784 | 0.769 |
| 모델 A2 | 0.767 | 0.737 | 0.738 | 0.730 | 0.772 | 0.735 |
| 모델 A3 | 0.779 | 0.744 | 0.746 | 0.737 | 0.779 | 0.738 |
| 모델 A4 | 0.780 | 0.746 | 0.746 | 0.738 | 0.773 | 0.734 |
| 모델 A5 | 0.805 | 0.772 | 0.801 | 0.776 | 0.800 | 0.776 |
| 모델 A6 | 0.800 | 0.784 | 0.766 | 0.766 | 0.777 | 0.763 |
| 모델 B1 | 0.924 | 0.903 | 0.894 | 0.893 | 0.900 | 0.892 |
| 모델 B2 | 0.882 | 0.870 | 0.838 | 0.837 | 0.884 | 0.881 |
| 모델 B3 | 0.910 | 0.897 | 0.872 | 0.866 | 0.902 | 0.899 |
| 모델 B4 | 0.930 | 0.913 | 0.908 | 0.899 | 0.916 | 0.907 |
| 모델 B5 | 0.863 | 0.870 | 0.854 | 0.865 | 0.862 | 0.874 |
| 모델 B6 | 0.912 | 0.882 | 0.885 | 0.879 | 0.885 | 0.872 |
| 모델 C1 | 0.945 | 0.903 | 0.920 | 0.897 | 0.934 | 0.899 |
| 모델 C2 | 0.926 | 0.899 | 0.877 | 0.869 | 0.937 | 0.927 |
| 모델 C3 | 0.935 | 0.915 | 0.893 | 0.886 | 0.937 | 0.929 |
| 모델 C4 | 0.944 | 0.913 | 0.919 | 0.905 | 0.942 | 0.917 |
| 모델 C5 | 0.903 | 0.910 | 0.905 | 0.914 | 0.904 | 0.915 |
| 모델 C6 | 0.935 | 0.893 | 0.907 | 0.889 | 0.921 | 0.887 |
Claims (10)
- 분석장치가 대상자의 뇌 CT(Computed Tomography) 영상을 입력받는 단계;상기 분석장치가 상기 뇌 CT 영상을 학습된 세그멘테이션 모델에 입력하여 관심 영역들을 추출하는 단계;상기 분석장치가 상기 관심 영역들의 픽셀 정보를 사전에 학습된 제1 학습모델에 입력하여 상기 관심 영역들 중 적어도 하나의 영역의 부피를 예측하는 단계; 및상기 분석장치가 상기 적어도 하나의 영역의 부피를 사전에 학습된 제2 학습 모델에 입력하여 상기 대상자의 치매 관련 정보를 산출하는 단계를 포함하되,상기 관심 영역들은 전두부 뇌척수액 영역, 측두부 뇌척수액 영역, 두정부 뇌척수액 영역, 후두부 뇌척수액 영역, 전 측뇌실 영역, 후 측뇌실 영역 및 해마 주변 뇌척수액 영역 중 복수의 영역들을 포함하는 뇌 CT에서 예측한 부피를 이용한 치매 관련 정보 산출 방법.
- 제1항에 있어서,상기 제1 학습모델은 상기 관심 영역들별로 사전에 마련된 복수의 학습모델들을 포함하는 뇌 CT에서 예측한 부피를 이용한 치매 관련 정보 산출 방법.
- 제1항에 있어서,상기 제2 학습모델은 상기 대상자의 나이, 상기 대상자의 성별 및 상기 대상자의 APOE4 유전자형 중 적어도 하나의 정보를 더 입력받아 상기 대상자의 치매 관련 정보를 산출하는 뇌 CT에서 예측한 부피를 이용한 치매 관련 정보 산출 방법.
- 제1항에 있어서,상기 치매 관련 정보는 치매 발병 여부, 치매 위험도, 치매 가능성, 치매 관련 점수, 치매 예후 예측, 뇌 위축 정도, 베타 아밀로이드(amyloid-ß, Aß) 양성 여부, 타우(tau) 단백질 양성 여부 및 뇌 연령 중 하나인 뇌 CT에서 예측한 부피를 이용한 치매 관련 정보 산출 방법.
- 제1항에 있어서,상기 세그멘테이션 모델은 상기 관심 영역들별로 사전에 마련된 복수의 모델들을 포함하는 뇌 CT에서 예측한 부피를 이용한 치매 관련 정보 산출 방법.
- 대상자의 뇌 CT(Computed Tomography) 영상을 입력받는 인터페이스 장치;뇌 CT 영상에서 관심 영역을 추출하는 세그멘테이션 모델, 뇌의 관심 영역 정보를 입력받아 부피를 예측하는 제1 학습모델 및 치매 관련 정보를 산출하는 제2 학습모델을 저장하는 저장장치; 및상기 입력받은 뇌 CT 영상을 상기 세그멘테이션 모델에 입력하여 관심 영역들을 추출하고, 상기 추출한 관심 영역들의 픽셀 정보를 상기 제1 학습모델에 입력하여 상기 관심 영역들 중 적어도 하나의 영역의 부피를 예측하고, 상기 적어도 하나의 영역의 부피를 상기 제2 학습 모델에 입력하여 상기 대상자의 치매 관련 정보를 산출하는 연산장치를 포함하되,상기 관심 영역들은 전두부 뇌척수액 영역, 측두부 뇌척수액 영역, 두정부 뇌척수액 영역, 후두부 뇌척수액 영역, 전 측뇌실 영역, 후 측뇌실 영역 및 해마 주변 뇌척수액 영역 중 복수의 영역들을 포함하는 뇌 CT에서 예측한 부피를 이용하여 치매 관련 정보를 산출하는 분석장치.
- 제6항에 있어서,상기 세그멘테이션 모델은 상기 관심 영역들별로 사전에 마련된 복수의 모델들을 포함하는 뇌 CT에서 예측한 부피를 이용하여 치매 관련 정보를 산출하는 분석장치.
- 제6항에 있어서,상기 제1 학습모델은 상기 관심 영역들별로 사전에 마련된 복수의 학습모델들을 포함하는 뇌 CT에서 예측한 부피를 이용하여 치매 관련 정보를 산출하는 분석장치.
- 제6항에 있어서,상기 제2 학습모델은 상기 대상자의 나이, 상기 대상자의 성별 및 상기 대상자의 APOE4 유전자형 중 적어도 하나의 정보를 더 입력받아 상기 대상자의 치매 관련 정보를 산출하는 뇌 CT에서 예측한 부피를 이용하여 치매 관련 정보를 산출하는 분석장치.
- 제6항에 있어서,상기 치매 관련 정보는 치매 발병 여부, 치매 위험도, 치매 가능성, 치매 관련 점수, 치매 예후 예측, 뇌 위축 정도, 베타 아밀로이드(amyloid-ß, Aß) 양성 여부, 타우(tau) 단백질 양성 여부 및 뇌 연령 중 하나인 뇌 CT에서 예측한 부피를 이용하여 치매 관련 정보를 산출하는 분석장치.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP24832176.2A EP4736769A1 (en) | 2023-06-27 | 2024-03-11 | Method for calculating dementia-related information using volume predicted by brain ct and analysis device thereof |
| US19/398,339 US20260080535A1 (en) | 2023-06-27 | 2025-11-24 | Method for calculating dementia-related information using volume predicted by brain ct and analysis device thereof |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020230082852A KR102712064B1 (ko) | 2023-06-27 | 2023-06-27 | 뇌 ct에서 예측한 부피를 이용한 치매 관련 정보 산출 방법 및 분석장치 |
| KR10-2023-0082852 | 2023-06-27 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2025005388A1 true WO2025005388A1 (ko) | 2025-01-02 |
Family
ID=92912992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2024/003074 Ceased WO2025005388A1 (ko) | 2023-06-27 | 2024-03-11 | 뇌 ct에서 예측한 부피를 이용한 치매 관련 정보 산출 방법 및 분석장치 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20260080535A1 (ko) |
| EP (1) | EP4736769A1 (ko) |
| KR (2) | KR102712064B1 (ko) |
| WO (1) | WO2025005388A1 (ko) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101957811B1 (ko) * | 2018-08-07 | 2019-03-13 | 주식회사 뷰노 | 의료 영상에 기반하여 피검체의 치매에 대한 중증도를 산출하는 방법 및 이를 이용한 장치 |
| KR20190030151A (ko) * | 2017-09-13 | 2019-03-21 | 이재준 | 영상 분석 방법, 장치 및 컴퓨터 프로그램 |
| KR20200062589A (ko) * | 2018-11-27 | 2020-06-04 | 재단법인 아산사회복지재단 | 뇌 mri 영상의 뇌 영역별 분할을 통한 치매 예측 장치 및 방법 |
| KR20210029318A (ko) * | 2019-09-05 | 2021-03-16 | 고려대학교 산학협력단 | Ct 영상 기반 부위별 대뇌 피질 수축율 예측 방법 및 장치 |
| KR20230056825A (ko) * | 2021-10-20 | 2023-04-28 | 경북대학교 산학협력단 | Pet/ct 영상의 자동 정량화를 이용한 알츠하이머병 예측 방법 및 이를 수행하는 알츠하이머병 예측 장치 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102680579B1 (ko) * | 2021-10-18 | 2024-07-01 | 사회복지법인 삼성생명공익재단 | 3d ct 영상에서 추출한 2d 영상들을 이용하여 병변을 예측하는 방법 및 분석장치 |
-
2023
- 2023-06-27 KR KR1020230082852A patent/KR102712064B1/ko active Active
-
2024
- 2024-03-11 WO PCT/KR2024/003074 patent/WO2025005388A1/ko not_active Ceased
- 2024-03-11 EP EP24832176.2A patent/EP4736769A1/en active Pending
- 2024-09-23 KR KR1020240128056A patent/KR20250000910A/ko active Pending
-
2025
- 2025-11-24 US US19/398,339 patent/US20260080535A1/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190030151A (ko) * | 2017-09-13 | 2019-03-21 | 이재준 | 영상 분석 방법, 장치 및 컴퓨터 프로그램 |
| KR101957811B1 (ko) * | 2018-08-07 | 2019-03-13 | 주식회사 뷰노 | 의료 영상에 기반하여 피검체의 치매에 대한 중증도를 산출하는 방법 및 이를 이용한 장치 |
| KR20200062589A (ko) * | 2018-11-27 | 2020-06-04 | 재단법인 아산사회복지재단 | 뇌 mri 영상의 뇌 영역별 분할을 통한 치매 예측 장치 및 방법 |
| KR20210029318A (ko) * | 2019-09-05 | 2021-03-16 | 고려대학교 산학협력단 | Ct 영상 기반 부위별 대뇌 피질 수축율 예측 방법 및 장치 |
| KR20230056825A (ko) * | 2021-10-20 | 2023-04-28 | 경북대학교 산학협력단 | Pet/ct 영상의 자동 정량화를 이용한 알츠하이머병 예측 방법 및 이를 수행하는 알츠하이머병 예측 장치 |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20250000910A (ko) | 2025-01-03 |
| EP4736769A1 (en) | 2026-05-06 |
| US20260080535A1 (en) | 2026-03-19 |
| KR102712064B1 (ko) | 2024-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tufail et al. | Binary classification of Alzheimer’s disease using sMRI imaging modality and deep learning | |
| Liu et al. | Anatomical landmark based deep feature representation for MR images in brain disease diagnosis | |
| Cheng et al. | Multimodal manifold-regularized transfer learning for MCI conversion prediction | |
| Miao et al. | MMTFN: Multi‐modal multi‐scale transformer fusion network for Alzheimer's disease diagnosis | |
| WO2023095989A1 (ko) | 뇌질환 진단을 위한 다중 모달리티 의료 영상 분석 방법 및 장치 | |
| Jia et al. | Deep learning and multimodal feature fusion for the aided diagnosis of Alzheimer's disease | |
| Ragab et al. | [Retracted] Multiclass Classification of Chest X‐Ray Images for the Prediction of COVID‐19 Using Capsule Network | |
| Balboni et al. | The impact of transfer learning on 3D deep learning convolutional neural network segmentation of the hippocampus in mild cognitive impairment and Alzheimer disease subjects | |
| Bhatele et al. | Neurodegenerative diseases-Caps: a capsule network based early screening system for the classification of neurodegenerative diseases | |
| Kato et al. | Machine/deep learning‐assisted hemoglobin level prediction using palpebral conjunctival images | |
| Lyu et al. | Classification of mild cognitive impairment by fusing neuroimaging and gene expression data: classification of mild cognitive impairment by fusing neuroimaging and gene expression data | |
| WO2015085319A1 (en) | Gross feature recognition of anatomical images based on atlas grid | |
| Liu et al. | A bag of semantic words model for medical content-based retrieval | |
| WO2025005388A1 (ko) | 뇌 ct에서 예측한 부피를 이용한 치매 관련 정보 산출 방법 및 분석장치 | |
| KR102608205B1 (ko) | 2차원 mri에서 예측한 부피를 이용한 치매 정보 산출 방법 및 분석장치 | |
| CN120707940A (zh) | 一种基于个体差异结构协变网络与机器学习的精神疾病分类方法和系统 | |
| Yashodhar et al. | Classification and feature selection of Alzheimer’s disease for MRI data utilizing convolutional neural network and support vector machine | |
| WO2025075244A1 (ko) | 인공지능모델 구축을 위한 라디오믹스 특징 선별 방법 및 분석장치 | |
| Gadewar et al. | Synthesizing study-specific controls using generative models on open access datasets for harmonized multi-study analyses | |
| Sheriff et al. | Retracted: An enhanced ensemble machine learning classification method to detect attention deficit hyperactivity for various artificial intelligence and telecommunication applications | |
| Shibata et al. | Deep-learning assessment of hippocampal magnetic susceptibility in Alzheimer's disease | |
| WO2023153839A1 (ko) | 2차원 mri를 이용한 치매 정보 산출 방법 및 분석장치 | |
| WO2024090677A1 (ko) | 대뇌외 뇌척수액 영역의 부피에 기반한 치매 관련 지표 산출 방법 및 분석장치 | |
| WO2024128681A1 (ko) | Tau-PET에서 치매 예측을 위한 관심 영역 추출 방법, CT와 Tau-PET을 이용한 치매 단계 예측 방법 및 분석장치 | |
| WO2024167062A1 (ko) | 비디오 프레임 보간 모델을 이용하여 mri를 증강하는 방법 및 영상처리장치 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24832176 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024832176 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2024832176 Country of ref document: EP Effective date: 20260127 |
|
| ENP | Entry into the national phase |
Ref document number: 2024832176 Country of ref document: EP Effective date: 20260127 |