CN112767341A - Deep learning-based method for classifying cognitive impairment of brain structure of type 2 diabetes patient - Google Patents
Deep learning-based method for classifying cognitive impairment of brain structure of type 2 diabetes patient Download PDFInfo
- Publication number
- CN112767341A CN112767341A CN202110049893.9A CN202110049893A CN112767341A CN 112767341 A CN112767341 A CN 112767341A CN 202110049893 A CN202110049893 A CN 202110049893A CN 112767341 A CN112767341 A CN 112767341A
- Authority
- CN
- China
- Prior art keywords
- brain
- cognitive impairment
- image
- type
- deep learning
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B20/30—Detection of binding sites or motifs
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B5/00—ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
-
- 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
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Public Health (AREA)
- Biotechnology (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Genetics & Genomics (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a deep learning-based method for classifying cognitive impairment of brain structures of type 2 diabetes patients, which comprises the following steps: extracting a whole brain 3D image for marking the brain cognitive disorder, and carrying out brain peeling treatment to obtain a brain region image corresponding to the brain cognitive disorder; constructing a 3D CNN network model with 11 layers, inputting the brain region image serving as a training set into the 3D CNN network model for training, and adjusting network parameters and functions until an output result is an accurate classification result; and inputting the real-time whole brain 3D image into the trained 3DCNN network model, and outputting a result serving as a classification result of whether the input whole brain 3D image has cognitive impairment or not through calculation of the network model. By the method and the device, the influence of the brain structures on cognitive impairment can be accurately identified.
Description
Technical Field
The invention relates to the technical field of deep learning, in particular to a method for classifying cognitive impairment of brain structures of type 2 diabetes patients based on deep learning.
Background
Previous studies have consistently shown an association between diabetes and cognitive decline. Both type 1 and type 2 diabetes are associated with decreased psychological speed and psychological flexibility; type 2 diabetes is also associated with impaired learning and memory.
Based on the results, scientists propose to compare the cognitive function decline of the type 2 diabetes mellitus patients with the cognitive abilities of normal people and people at risk of Alzheimer's disease, and research and evaluate the cognitive function of the diabetes mellitus outpatient. Subjects first received a simple memory screen and then a comprehensive memory assessment. The subject's memory, attention, language fluency and performance are assessed using the NACC unified dataset, and a specific cognitive diagnosis is given to the patient by a team of neuropsychologists and geriatric physicians through these results. Subjects were compared to normal controls and patients with mild cognitive impairment from amnesic (aMCI) in the ADRC database.
The results showed that 30 patients were confirmed in the group and were aged (64.4. + -. 7.4). Diabetic patients performed significantly worse on neuropsychological testing compared to normal cognitive functioning populations.
Type 2 diabetes patients develop cognitive impairment earlier than their peers as the disease progresses and are associated with susceptibility to gene polymorphisms, and the brain also shows aging phenomena.
There are many documents that show that the existence of brain cognitive disorder is closely related to brain structure, but it is still a problem to be solved that structural changes in which part of the brain can seriously affect the cognitive function of a human to form cognitive disorder.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method for classifying the cognitive impairment of the brain structure of type 2 diabetes patients based on deep learning, aiming at the defects of the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: constructing a classification method of cognitive impairment of brain structures of type 2 diabetes patients based on deep learning, comprising the following steps:
extracting a whole brain 3D image for marking the brain cognitive disorder, carrying out brain peeling treatment, obtaining a brain region image corresponding to the brain cognitive disorder, and dividing a training set and a test set;
constructing 11 layers of 3D CNN network models, inputting the brain region images serving as training sets into the 3D CNN network models for training, adjusting network parameters and functions until the output results are accurate classification results, inputting the brain region images serving as test sets into the 3D CNN network models after training is finished, and verifying the accuracy of the 3D CNN network models;
and inputting the real-time whole brain 3D image into the trained 3D CNN network model, and outputting a result serving as a classification result of whether the input whole brain 3D image has cognitive disorder or not through calculation of the network model.
Wherein, in the step of acquiring the brain regional image corresponding to the brain cognitive impairment, the method comprises the following steps:
acquiring the gravity center position of a brain structure in a whole brain 3D image through an image processing means;
taking the gravity center position of the brain structure as a coordinate origin, constructing a space three-dimensional coordinate system, wherein the Z axis is the center position of the left half brain and the right half brain, and establishing an X axis and a Y axis according to the Z axis;
after the barycenter and the coordinate system are determined, in the range of 64 voxels from 32 voxels before the barycenter to 31 voxels after the barycenter in the X-axis direction, in the range of 10 voxels from 30 voxels below the barycenter to 39 voxels below the barycenter in the Y-axis direction, and in the range of 64 voxels left and right of the barycenter in the Z-axis direction, an image of 64X 10 is extracted as a brain region image.
After the step of obtaining the brain regional image corresponding to the brain cognitive disorder, the method further comprises a step of enhancing data of the training set; amplification was performed by a 3D rotation operation to 10 times the original data amount.
After the step of acquiring the brain regional image corresponding to the brain cognitive impairment, the method further comprises the step of image preprocessing, and the method comprises the following steps of:
grayscale normalization, including window width, window level and pixel normalization.
And observing the loss curves of the training set and the testing set through the training curve, wherein if the loss curves show a descending trend, the learning success rate of the 3D CNN network model generally shows an ascending trend.
Wherein, in the step of judging the accuracy of the trained network, the degree of development of cognitive impairment of type 2 diabetic patients is assessed by LDH and FA values.
In the step of obtaining the brain region image corresponding to the brain cognitive disorder, 13 brain image markers of the cognitive disorder caused by type 2 diabetes brain aging comprise cingulate gyrus, right frontal lobe, left parietal lobe, lumbricus, bilateral thalamus, right temporal gyrus which are positioned in the brain region with abnormal change of white matter microstructure, and frontal lobe, parietal lobe, temporal lobe, thalamus, basal ganglia, cerebellar hemisphere and brainstem which are positioned in the brain region with weakened functional connection.
The invention provides a deep learning-based method for classifying cognitive impairment of brain structures of type 2 diabetes patients, which comprises the following steps: extracting a whole brain 3D image for marking the brain cognitive disorder, carrying out brain peeling treatment, obtaining a brain region image corresponding to the brain cognitive disorder, and dividing a training set and a test set; constructing 11 layers of 3D CNN network models, inputting brain region images serving as training sets into the 3D CNN network models for training, adjusting network parameters and functions until output results are accurate classification results, inputting the brain region images serving as test sets into the 3D CNN network models after training is finished, and verifying the accuracy of the 3D CNN network models; and inputting the real-time whole brain 3D image into the trained 3D CNN network model, and outputting a result as a classification result of whether the input brain 3D image has cognitive disorder or not through calculation of the network model. By the method and the device, the influence of the brain structures on cognitive impairment can be accurately identified.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a method for classifying cognitive impairment of brain structures of type 2 diabetic patients based on deep learning according to the present invention.
Fig. 2 is a curve diagram of classification results and losses for a training set and a test set in a deep learning-based method for classifying cognitive impairment of brain structures of type 2 diabetic patients according to the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
As shown in fig. 1, the present invention provides a method for classifying brain structure recognition disorders of type 2 diabetic patients based on deep learning, comprising:
extracting a whole brain 3D image for marking the brain cognitive disorder, carrying out brain peeling treatment, obtaining a brain region image corresponding to the brain cognitive disorder, and dividing a training set and a test set;
constructing 11 layers of 3D CNN network models, inputting the brain region images serving as training sets into the 3D CNN network models for training, adjusting network parameters and functions until the output results are accurate classification results, inputting the brain region images serving as test sets into the 3D CNN network models after training is finished, and verifying the accuracy of the 3D CNN network models;
and inputting the real-time whole brain 3D image into the trained 3D CNN network model, and outputting a result serving as a classification result of whether the input whole brain 3D image has cognitive disorder or not through calculation of the network model.
Wherein, in the step of acquiring the brain regional image corresponding to the brain cognitive impairment, the method comprises the following steps:
acquiring the gravity center position of a brain structure in a whole brain 3D image through an image processing means;
taking the gravity center position of the brain structure as a coordinate origin, constructing a space three-dimensional coordinate system, wherein the Z axis is the center position of the left half brain and the right half brain, and establishing an X axis and a Y axis according to the Z axis;
after the barycenter and the coordinate system are determined, in the range of 64 voxels from 32 voxels before the barycenter to 31 voxels after the barycenter in the X-axis direction, in the range of 10 voxels from 30 voxels below the barycenter to 39 voxels below the barycenter in the Y-axis direction, and in the range of 64 voxels left and right of the barycenter in the Z-axis direction, an image of 64X 10 is extracted as a brain region image.
After the step of obtaining the brain regional image corresponding to the brain cognitive disorder, the method further comprises a step of enhancing data of the training set; amplification was performed by a 3D rotation operation to 10 times the original data amount.
After the step of acquiring the brain regional image corresponding to the brain cognitive impairment, the method further comprises the step of image preprocessing, and the method comprises the following steps of:
grayscale normalization, including window width, window level and pixel normalization.
And observing the loss curves of the training set and the testing set through the training curve, wherein if the loss curves show a descending trend, the learning success rate of the 3D CNN network model generally shows an ascending trend.
Wherein, in the step of judging the accuracy of the trained network, the degree of development of cognitive impairment of type 2 diabetic patients is assessed by LDH and FA values.
In the step of obtaining the brain region image corresponding to the brain cognitive disorder, 13 brain image markers of the cognitive disorder caused by type 2 diabetes brain aging comprise cingulate gyrus, right frontal lobe, left parietal lobe, lumbricus, bilateral thalamus, right temporal gyrus which are positioned in the brain region with abnormal change of white matter microstructure, and frontal lobe, parietal lobe, temporal lobe, thalamus, basal ganglia, cerebellar hemisphere and brainstem which are positioned in the brain region with weakened functional connection.
An 11-layer 3d CNN network is constructed, and the network structure is as follows:
Layer 1 | 64x 64x 10 | input |
Layer 2 | 11 | conv |
Layer 3 | 11 | batchNorm |
Layer 4 | 17 | conv |
Layer 5 | 17 | batchNorm |
Layer 6 | 34 | conv |
Layer 7 | 34 | batchNorm |
Layer 8 | 1024 | fc |
Layer 9 | 2 | |
Layer | ||
10 | 2 | softmax |
Layer 11 | 2 | output |
and observing the loss curves of the training set and the testing set through the training curve, wherein if the loss curves show a descending trend, the learning success rate of the 3D CNN network model generally shows an ascending trend. As shown in fig. 2.
The invention firstly discloses a T2DM susceptibility gene locus for brain aging. The neuroimaging and genetic mechanism of cognitive dysfunction of a T2DM patient is researched by adopting an advanced concept of imaging genetics and a brain network analysis frontier technology, susceptible gene loci of the cognitive dysfunction of the T2DM patient are extracted, and the occurrence of the cognitive dysfunction of the type 2 diabetic patient is closely related to the polymorphism of transmembrane protein 106B (TMEM106B), plasminogen activator and urokinase (PLAU) genes. The discovery of the susceptible gene locus can provide a biological marker for the diagnosis and the curative effect monitoring of early cognitive impairment of a T2DM patient, and is beneficial to the construction of a prediction model, so that the development of dementia is prevented or delayed, and the life quality of the patient is improved.
Different from the prior art, the invention provides a method for classifying the cognitive disorder of the brain structure of a type 2 diabetic patient based on deep learning, which comprises the following steps: extracting a brain 3D image for marking the cognitive disorder of the brain, carrying out brain peeling treatment, obtaining a brain region image corresponding to the cognitive disorder of the brain, and dividing a training set and a test set; constructing 11 layers of 3D CNN network models, inputting the brain region images serving as training sets into the 3D CNN network models for training, adjusting network parameters and functions until the output results are accurate classification results, inputting the brain region images serving as test sets into the 3D CNN network models after training is finished, and verifying the accuracy of the 3D CNN network models; and inputting the real-time brain 3D image into the trained 3D CNN network model, and outputting a result serving as a classification result of whether the input brain 3D image has cognitive impairment through calculation of the network model. By the method and the device, the influence of the brain structures on the cognitive disorder can be accurately identified.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (7)
1. A method for classifying cognitive impairment of brain structures of type 2 diabetes patients based on deep learning is characterized by comprising the following steps:
extracting a whole brain 3D image for marking the brain cognitive disorder, carrying out brain peeling treatment, obtaining a brain region image corresponding to the brain cognitive disorder, and dividing a training set and a test set;
constructing 11 layers of 3D CNN network models, inputting the brain region images serving as training sets into the 3D CNN network models for training, adjusting network parameters and functions until the output results are accurate classification results, inputting the brain region images serving as test sets into the 3D CNN network models after training is finished, and verifying the accuracy of the 3D CNN network models;
and inputting the real-time whole brain 3D image into the trained 3D CNN network model, and outputting a result serving as a classification result of whether the input whole brain 3D image has cognitive disorder or not through calculation of the network model.
2. The method for classifying cognitive impairment of brain structures of type 2 diabetes patients based on deep learning according to claim 1, wherein the step of acquiring brain region images corresponding to the cognitive impairment of the brain comprises the steps of:
acquiring the gravity center position of a brain structure in a whole brain 3D image through an image processing means;
taking the gravity center position of the brain structure as a coordinate origin, constructing a space three-dimensional coordinate system, wherein the Z axis is the center position of the left half brain and the right half brain, and establishing an X axis and a Y axis according to the Z axis;
after the barycenter and the coordinate system are determined, in the range of 64 voxels from 32 voxels before the barycenter to 31 voxels after the barycenter in the X-axis direction, in the range of 10 voxels from 30 voxels below the barycenter to 39 voxels below the barycenter in the Y-axis direction, and in the range of 64 voxels left and right of the barycenter in the Z-axis direction, an image of 64X 10 is extracted as a brain region image.
3. The deep learning based type 2 diabetic brain structure cognitive impairment classification method according to claim 1, characterized in that after the step of obtaining brain region images corresponding to brain cognitive impairment, a step of training set data enhancement is further included; amplification was performed by a 3D rotation operation to 10 times the original data amount.
4. The deep learning based classification method for cognitive impairment of brain structures of type 2 diabetic patients according to claim 1, further comprising a step of image preprocessing after the step of obtaining images of brain regions corresponding to cognitive impairment of brain, comprising:
grayscale normalization, including window width, window level and pixel normalization.
5. The method for classifying cognitive impairment of brain structure of type 2 diabetes patients based on deep learning of claim 1, wherein a loss curve of a training set and a testing set is observed through the training curve, and if the loss curve shows a downward trend, the learning success rate of the 3D CNN network model generally shows an upward trend.
6. The deep learning-based classification method for cognitive impairment of brain structure of type 2 diabetes mellitus patients according to claim 1, wherein in the step of judging the accuracy of the trained network, the degree of development of cognitive impairment of type 2 diabetes mellitus patients is evaluated by LDH and FA values.
7. The method for classifying cognitive impairment of brain structure of type 2 diabetes patients based on deep learning according to claim 1, wherein in the step of obtaining the image of the brain region corresponding to the cognitive impairment of brain, 13 brain image markers of cognitive impairment caused by brain aging of type 2 diabetes include cingulate gyrus, right frontal lobe, left parietal lobe, lumbricus, bilateral thalamus, right temporal gyrus, and frontal lobe, parietal lobe, temporal lobe, thalamus, basal ganglia, cerebellar hemisphere and brainstem in the brain region with weakened functional connection, where the abnormal change of white matter microstructure occurs.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110049893.9A CN112767341A (en) | 2021-01-14 | 2021-01-14 | Deep learning-based method for classifying cognitive impairment of brain structure of type 2 diabetes patient |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110049893.9A CN112767341A (en) | 2021-01-14 | 2021-01-14 | Deep learning-based method for classifying cognitive impairment of brain structure of type 2 diabetes patient |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112767341A true CN112767341A (en) | 2021-05-07 |
Family
ID=75700561
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110049893.9A Pending CN112767341A (en) | 2021-01-14 | 2021-01-14 | Deep learning-based method for classifying cognitive impairment of brain structure of type 2 diabetes patient |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112767341A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116417135A (en) * | 2023-02-17 | 2023-07-11 | 中国人民解放军总医院第二医学中心 | Processing method and device for predicting early Alzheimer's disease type based on brain image |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107145727A (en) * | 2017-04-26 | 2017-09-08 | 中国人民解放军总医院 | The medical image processing devices and method of a kind of utilization convolutional neural networks |
WO2018052586A1 (en) * | 2016-09-14 | 2018-03-22 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for multi-scale cell image segmentation using multiple parallel convolutional neural networks |
CN109871838A (en) * | 2019-04-18 | 2019-06-11 | 电子科技大学 | The extracting method of Alzheimer's disease lesion brain area based on cascade deep network |
CN111242233A (en) * | 2020-01-18 | 2020-06-05 | 温州大学 | Alzheimer disease classification method based on fusion network |
CN111738363A (en) * | 2020-07-24 | 2020-10-02 | 温州大学 | Alzheimer disease classification method based on improved 3D CNN network |
-
2021
- 2021-01-14 CN CN202110049893.9A patent/CN112767341A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018052586A1 (en) * | 2016-09-14 | 2018-03-22 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for multi-scale cell image segmentation using multiple parallel convolutional neural networks |
CN107145727A (en) * | 2017-04-26 | 2017-09-08 | 中国人民解放军总医院 | The medical image processing devices and method of a kind of utilization convolutional neural networks |
CN109871838A (en) * | 2019-04-18 | 2019-06-11 | 电子科技大学 | The extracting method of Alzheimer's disease lesion brain area based on cascade deep network |
CN111242233A (en) * | 2020-01-18 | 2020-06-05 | 温州大学 | Alzheimer disease classification method based on fusion network |
CN111738363A (en) * | 2020-07-24 | 2020-10-02 | 温州大学 | Alzheimer disease classification method based on improved 3D CNN network |
Non-Patent Citations (1)
Title |
---|
曾安: "基于3D卷积神经网络-感兴趣区域的阿尔茨海默症辅助诊断模型", 《生物医学工程研究》, pages 1 - 7 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116417135A (en) * | 2023-02-17 | 2023-07-11 | 中国人民解放军总医院第二医学中心 | Processing method and device for predicting early Alzheimer's disease type based on brain image |
CN116417135B (en) * | 2023-02-17 | 2024-03-08 | 中国人民解放军总医院第二医学中心 | Processing method and device for predicting early Alzheimer's disease type based on brain image |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Oh et al. | Identifying schizophrenia using structural MRI with a deep learning algorithm | |
Dai et al. | Resting‐state functional MRI: Functional connectivity analysis of the visual cortex in primary open‐angle glaucoma patients | |
Sridhar et al. | Diagnosis of attention deficit hyperactivity disorder using imaging and signal processing techniques | |
Casanova et al. | Reduced brain size and gyrification in the brains of dyslexic patients | |
EP3884862A1 (en) | Method and system for individualized prediction of mental illness on basis of brain function map monkey-human cross-species migration | |
Shan et al. | Mapping the heterogeneous brain structural phenotype of autism spectrum disorder using the normative model | |
Cai et al. | Increased left inferior temporal gyrus was found in both low function autism and high function autism | |
Diniz et al. | Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network | |
Preston et al. | Structural brain differences in school-age children with residual speech sound errors | |
CN112348785B (en) | Epileptic focus positioning method and system | |
Zhan et al. | Network-based statistic show aberrant functional connectivity in Alzheimer's disease | |
CN112927187A (en) | Method for automatically identifying and positioning focal cortical dysplasia epileptic focus | |
CN114970599A (en) | Identification method and identification device for attention defect associated electroencephalogram signals and storage medium | |
CN112767341A (en) | Deep learning-based method for classifying cognitive impairment of brain structure of type 2 diabetes patient | |
Levman et al. | Multivariate analyses applied to fetal, neonatal and pediatric MRI of neurodevelopmental disorders | |
Khadem-Reza et al. | Evaluation of brain structure abnormalities in children with autism spectrum disorder (ASD) using structural magnetic resonance imaging | |
Tang et al. | Comparing different algorithms for the course of Alzheimer’s disease using machine learning | |
CN117275734A (en) | Brain health state assessment method and device | |
DE102017213714A1 (en) | Method for determining a disease prognosis of a motor vehicle occupant and prognosis device | |
CN116386845A (en) | Schizophrenia diagnosis system based on convolutional neural network and facial dynamic video | |
Zonneveld et al. | High-dimensional mapping of cognition to the brain using voxel-based morphometry and subcortical shape analysis | |
CN111583182B (en) | fMRI data processing method for facial paralysis language functional area function connection | |
CN112837807B (en) | Early intelligent high-precision auxiliary diagnosis method for T2DM brain aging cognitive impairment | |
CN109859839B (en) | Alzheimer disease classification method based on layered ensemble learning | |
CN114400086A (en) | Articular disc forward movement auxiliary diagnosis system and method based on deep learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |