CN110859624A - Brain age deep learning prediction system based on structural magnetic resonance image - Google Patents
Brain age deep learning prediction system based on structural magnetic resonance image Download PDFInfo
- Publication number
- CN110859624A CN110859624A CN201911266178.XA CN201911266178A CN110859624A CN 110859624 A CN110859624 A CN 110859624A CN 201911266178 A CN201911266178 A CN 201911266178A CN 110859624 A CN110859624 A CN 110859624A
- Authority
- CN
- China
- Prior art keywords
- brain
- age
- densenet
- magnetic resonance
- module
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
- A61B5/004—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
- A61B5/0042—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part for the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/08—Elderly
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2576/00—Medical imaging apparatus involving image processing or analysis
- A61B2576/02—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part
- A61B2576/026—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part for the brain
Abstract
The invention discloses a brain age deep learning prediction system based on structural magnetic resonance images, which comprises: a training set construction module; a data preprocessing module; the deep learning model building module is used for building a convolutional neural network model AGE-DenseNet by utilizing a Keras framework and based on a DenseNet idea; a deep learning model training module; a model verification module; and a brain age prediction module. The invention adopts a convolutional neural network structure AGE-DenseNet based on the DenseNet thought, can extract high-dimensional complex characteristics from a complex brain structure magnetic resonance image, accurately, efficiently and quickly predict the brain AGE, and quantizes the degree of the brain deviating from a healthy brain aging track.
Description
Technical Field
The invention belongs to the field of computers and neuroscience, and particularly relates to a brain age deep learning prediction system based on a structural magnetic resonance image.
Background
With the growing problem of aging of the global population, aging-related brain diseases are placing an increasing burden on society. The human brain undergoes subtle changes in structure with the aging, and the changes can cause the brain to degenerate in normal functions and show significant relevance to brain diseases such as neurodegeneration and the like. Genetic, environmental, disease or injury may lead to a significant increase in the rate of brain aging, and methods are needed to quantify this abnormal rate of brain aging and assess the current aging stage of the brain.
The artificial intelligence method can utilize the magnetic resonance image of the brain structure to establish a prediction model of brain aging so as to predict the age of the old, and the age predicted by the model is called the brain age. The age of the brain may indicate the age stage of the current brain and even predict the risk of future related diseases. The prediction model established by the image data of the healthy old people actually describes a normal aging track of the brain of the old people, and the difference between the age of the brain and the real age of the old people can reflect the degree of deviation of a person from the aging track of the healthy brain and reflect the degree of advance or delay of the aging of the brain of the person. It has been shown that the greater the difference between the age of the brain and the actual age of an elderly person, the higher the risk of mental or physical problems and the easier it is to become. Clinically, doctors can use the index to evaluate the aging degree of the brain of the old and take corresponding intervention measures.
At present, the method for predicting the brain age by using the structural magnetic resonance image mainly takes the traditional machine learning method as a main method. When a prediction model is established, a large amount of preprocessing and feature extraction work needs to be carried out on the magnetic resonance image of the brain structure. Currently, the features commonly used for brain age prediction are: gray matter density map (GMD), White matter density map (WMD), White matter volume, cortical thickness, network characteristic parameters, and the like. The feature dimensions extracted may range from tens to hundreds of dimensions. Therefore, in the process of establishing a brain age prediction model by using a traditional machine learning method, steps such as feature selection or feature dimension reduction are often required. For example, based on GMD features, machine learning models such as gaussian regression process, support vector machine, etc. can be used to predict brain age, but since GMD-based models have the disadvantage of high feature dimensionality, the constructed models are easily over-fitted and have poor generalization capability. In addition, the extraction of image features is susceptible to many factors, such as: optional parameters such as image smoothing, voxel size and the like are involved in the GMD feature generation process, and the parameters have great influence on feature extraction and even the result of brain age prediction.
In addition, convolutional neural networks are being attempted for brain age prediction, but unlike natural images, structural mri images are three-dimensional images, and the amount of training samples is much smaller than that of natural images, so that it poses a high challenge to the structure of convolutional neural network structures, and the convolutional neural networks are required to fully extract and utilize the information contained in the mri images. At present, the convolutional neural networks applied to the brain age prediction task are too traditional, only a structure of convolution, pooling and full connection is used, and the extraction and utilization efficiency of the features needs to be improved.
Disclosure of Invention
The invention aims to provide a brain age deep learning prediction system based on a structural magnetic resonance image, which predicts the brain age of the old based on the structural magnetic resonance image through a convolutional neural network. The invention regards the convolution network as a high-dimensional feature extractor, performs hierarchical representation description on the feature information of the magnetic resonance image of the complex brain structure, firstly expresses the features of the bottom layer, then combines the low-layer features to obtain more detailed and rich high-layer features for expression, and efficiently extracts effective features so as to evaluate the aging stage of the current brain, namely the 'brain age'. The invention provides an AGE-DenseNet network structure on the basis of the traditional convolution network, which can greatly improve the utilization efficiency of characteristics and obtain excellent brain AGE prediction effect. The invention has the advantages of high analysis speed, strong generalization capability, practicability and easy use.
The invention provides a brain age deep learning prediction system based on a structural magnetic resonance image, which comprises:
the training set constructing module is used for constructing a training set by using original structure magnetic resonance images from different sources;
the data preprocessing module is used for preprocessing the magnetic resonance images of the original structures, and the preprocessing operation comprises image registration, skull stripping and image data standardization;
the deep learning model building module is used for building a convolutional neural network model AGE-DenseNet by utilizing a Keras framework and based on a DenseNet idea;
the deep learning model training module is used for carrying out supervised learning on the constructed convolutional neural network model AGE-DenseNet by utilizing the constructed training set through a back propagation and gradient descent algorithm;
the model verification module is used for verifying the convolutional neural network model AGE-DenseNet by using a cross verification method and adjusting the hyper-parameters in the training of the convolutional neural network model AGE-DenseNet;
and the brain AGE prediction module is used for sending the magnetic resonance image of the original structure after the preprocessing operation into a convolution neural network model AGE-DenseNet with accurate verification to predict the brain AGE, obtaining a brain AGE prediction value, calculating the difference value between the brain AGE prediction value and the actual AGE, and evaluating the aging degree of the brain.
Further, the convolutional neural network model AGE-DenseNet comprises five repeated convolutional blocks, each convolutional block comprising two identical convolutional units and a 2 × 2 × 2 max pooling layer with step size of 2, each convolutional unit comprising a 3 × 3 × 3 convolutional layer with step size of 1, a ReLU activation and a 3D batch normalization layer,
during learning and training, downsampling the feature mapping output by each rolling block in a maximum pooling mode, changing the size of the feature mapping, and then serially connecting the feature mapping output by each rolling block with the feature mapping output by other rolling blocks to form a single tensor which is used as the input of the current rolling block; and after the last convolution block is ended, using a Global averaging pooling layer (Global averaging pooling), to map and vectorize the features into a feature vector. When the brain age is predicted, a unary full-link layer plus a ReLU activation function is used, and the feature vector obtained by global average pooling is mapped to a single output value.
Further, the image registration comprises performing a non-linear registration operation on the original structure magnetic resonance image;
the skull stripping comprises the step of obtaining a skull stripping image of the registered structural magnetic resonance image through a preset threshold value;
the image data normalization includes calculating the mean and standard deviation of voxels within the brain contour after the skull stripping, and performing a gaussian normalization of the voxels within the brain contour.
The invention has the beneficial effects that:
1) the invention adopts a convolutional neural network structure, AGE-DenseNet, based on the DenseNet thought. Compared with the traditional machine learning prediction model, the method can directly analyze and process the whole brain structure magnetic resonance image without manually extracting the structural features of the brain (such as a gray density map, a white matter volume, a cortical thickness and the like), and can avoid the complicated processes of feature extraction, feature selection/dimension reduction and the like. In addition, compared with a general convolutional neural network, in the deep learning model design process, the invention adopts a structure of convolution plus tight connection (Dense connection) plus global average pooling, namely, tight short circuit connection is added between convolutional layers, so that the utilization efficiency of characteristics can be effectively improved, the problem of gradient disappearance is obviously relieved in the gradient back propagation process, and meanwhile, the global average pooling layer is used for replacing the traditional full connection layer, so that the overfitting phenomenon is slowed down to a certain extent while more space information is kept.
2) The method can accurately, efficiently and quickly predict the age of the brain of the old through the magnetic resonance image of the brain structure, so as to quantify the degree of the brain deviating from the aging track of the healthy brain, and provide important basis for early diagnosis and prevention of diseases of the old in particular.
Drawings
Fig. 1 is a flowchart of a brain age deep learning prediction method based on structural magnetic resonance imaging according to the present invention;
FIG. 2 is a block diagram of the convolutional neural network model AGE-DenseNet of the present invention;
fig. 3 is a schematic diagram of brain age deep learning prediction based on structural magnetic resonance imaging according to an embodiment of the present invention.
Detailed Description
Brain aging is a common biological phenomenon that occurs with age, resulting in subtle changes in brain structure. Even healthy elderly people have a normal aging course, in which cognitive ability is reduced to some extent and the risk of disease is increased with the increase of age. But there are some people who deviate from this normal aging trajectory by being genetically, environmentally or diseased, the present invention aims to quantify the early or late aging of the brain and thereby predict the future development trajectory and the consequent risk of aging-related health deterioration of an individual. The invention is further described below with reference to the accompanying drawings and examples, it being understood that the examples described below are intended to facilitate the understanding of the invention, and are not intended to limit it in any way.
It should be noted that the present invention is preferably applied to mr images of brain structures that have undergone non-linear registration and skull stripping, and the preprocessing uses the FSL5.0 FSL _ anat command. Firstly, preprocessing an image to meet the input requirements of the convolutional neural network model AGE-DenseNet, such as the image size and the like; performing feature extraction operations such as convolution, pooling and the like on the image through a convolution neural network model AGE-DenseNet; and finally, fusing the extracted high-dimensional features to obtain the predicted brain age.
As shown in fig. 1, the method for deep learning and predicting brain age based on structural magnetic resonance image of the present invention includes the following steps:
s1, constructing an original input image;
the original input image is a brain T1 magnetic resonance image.
S2: preprocessing an original input image and constructing a training set by using the preprocessed original input image;
the preprocessing operations include image non-linear registration, skull stripping, and image data normalization. Specifically, the image registration includes: performing a non-linear registration operation on the input image; the skull stripping comprises the following steps: acquiring a skull stripping image of the registered T1 image through a preset threshold; image data normalization includes: calculating the average value and the standard deviation of voxels in the brain contour after the skull stripping, performing Gaussian normalization on the voxels in the brain contour, and setting the background outside the brain contour to be 0. The method has the advantages that the original input image is preprocessed, so that the prediction accuracy of the brain age prediction by the depth method can be improved, the processing and analyzing speed is increased, and the method is efficient and easy to use.
S3, constructing a convolutional neural network model AGE-DenseNet;
the convolutional neural network architecture of the present invention uses three-dimensional brain T1 structural magnetic resonance image data of fixed size as input. This CNN architecture contains five repeated convolution blocks (volumetric blocks), each containing two identical convolution units (volumetric units) and one 2 × 2 × 2 max pooling layer of step size 2. The convolution unit contains a 3 × 3 × 3 convolution layer with step size 1, a ReLU activation and a 3D bulk normalization layer. In the first volume block, the number of feature channels is set to 8 and doubled after entering the next volume block to deduce a sufficiently rich representation of the brain information.
In addition, in order to relieve the problem of gradient disappearance and improve the utilization efficiency of the features, the invention connects the feature maps learned by different volume blocks in series based on DenseNet, increases the variables input by the subsequent layer, and improves the feature utilization efficiency and the learning effect of the network. Each convolution block will integrate the information of all previous convolution block output feature maps as input. Since the sizes of the feature maps output by different convolution blocks are different, the feature maps are downsampled by using a maximum pooling mode to change the sizes of the feature maps, and then the feature maps output by different convolution blocks are connected in series to form a single tensor which is used as the input of the current convolution block. And after the last convolution block is ended, using a global average pooling layer (global averaging pooling), and vectorizing the feature mapping into a feature vector. The final age prediction uses a unary fully-connected layer plus the ReLU activation function, which maps the feature vectors from the global average pooling to a single output value. The structure of the convolutional neural network model AGE-DenseNet is shown in FIG. 2.
And S4, training and learning the constructed convolutional neural network model AGE-DenseNet by utilizing the training set through a back propagation and gradient descent algorithm, and selecting a model with high prediction precision and strong generalization performance for storage, thereby facilitating the calling of a user.
And S5, verifying the convolutional neural network model AGE-DenseNet by using a cross-validation method, and adjusting the hyper-parameters in the training of the convolutional neural network model AGE-DenseNet.
And S6, sending the magnetic resonance image of the preprocessed original structure into a convolution neural network model AGE-DenseNet with accurate verification to predict the brain AGE to obtain a predicted value of the brain AGE, and calculating the difference between the predicted value of the brain AGE and the actual AGE to evaluate the degree of the current brain deviating from the aging track of the healthy brain.
The invention will be more clearly understood and more precisely understood and applied by the following specific examples.
As shown in fig. 3, the original input, i.e., the T1 magnetic resonance image of the brain, is first constructed as the original input. Then, carrying out image preprocessing, and carrying out nonlinear registration on the original input image to an MNI152-2mm template, wherein the data size after registration is 91 multiplied by 109 multiplied by 91;
according to a set threshold value, stripping the skull in the registered image, and only preserving brain tissues;
the data standardization is carried out, and because a large amount of black backgrounds exist in an MRI image and the data standardization effect can be greatly influenced, a rough brain contour is obtained by setting a threshold value, then the average value and the standard deviation of voxels in the brain contour are calculated, and the brain voxels are subjected to Gaussian standardization;
selecting an early trained convolutional neural network model AGE-DenseNet, predicting the brain AGE according to an input image to obtain a brain AGE predicted value, and subtracting the brain AGE from the actual AGE to obtain a quantized value of the current brain deviating from the healthy aging track.
It will be apparent to those skilled in the art that various modifications and improvements can be made to the embodiments of the present invention without departing from the inventive concept thereof, and these modifications and improvements are intended to be within the scope of the invention.
Claims (3)
1. A brain age deep learning prediction system based on structural magnetic resonance images is characterized by comprising:
the training set constructing module is used for constructing a training set by using original structure magnetic resonance images from different sources;
the data preprocessing module is used for preprocessing the magnetic resonance images of the original structures, and the preprocessing operation comprises image registration, skull stripping and image data standardization;
the deep learning model building module is used for building a convolutional neural network model AGE-DenseNet by utilizing a Keras framework and based on a DenseNet idea;
the deep learning model training module is used for carrying out supervised learning on the constructed convolutional neural network model AGE-DenseNet by utilizing the constructed training set through a back propagation and gradient descent algorithm;
the model verification module is used for verifying the convolutional neural network model AGE-DenseNet by using a cross verification method and adjusting the hyper-parameters in the training of the convolutional neural network model AGE-DenseNet;
and the brain AGE prediction module is used for sending the magnetic resonance image of the original structure after the preprocessing operation into a convolution neural network model AGE-DenseNet with accurate verification to predict the brain AGE, obtaining a brain AGE prediction value, calculating the difference value between the brain AGE prediction value and the actual AGE, and evaluating the aging degree of the brain.
2. The system of claim 1, wherein the convolutional neural network model AGE-DenseNet comprises five repeating convolutional blocks, each convolutional block comprising two identical convolutional units and a 2 x 2 max pooling layer of step size 2, each convolutional unit comprising a 3 x 3 convolutional layer of step size 1, a ReLU activation, and a 3D batch normalization layer,
during learning and training, downsampling the feature mapping output by each convolution block in a maximum pooling mode, changing the size of the feature mapping, then connecting the feature mapping output by each convolution block with the feature mapping output by other convolution blocks in series to form a single tensor which is used as the input of the current convolution block, and after the last convolution block is finished, using a global average pooling layer to vectorize the feature mapping into a feature vector;
when the brain age is predicted, a unary full-link layer plus a ReLU activation function is used, and the feature vector obtained by global average pooling is mapped to a single output value.
3. The system of claim 1 or 2, wherein the image registration comprises performing a non-linear registration operation on the original structural magnetic resonance image;
the skull stripping comprises the step of obtaining a skull stripping image of the registered structural magnetic resonance image through a preset threshold value;
the image data normalization includes calculating the mean and standard deviation of voxels within the brain contour after the skull stripping, and performing a gaussian normalization of the voxels within the brain contour.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911266178.XA CN110859624A (en) | 2019-12-11 | 2019-12-11 | Brain age deep learning prediction system based on structural magnetic resonance image |
| PCT/CN2020/130073 WO2021115084A1 (en) | 2019-12-11 | 2020-11-19 | Structural magnetic resonance image-based brain age deep learning prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911266178.XA CN110859624A (en) | 2019-12-11 | 2019-12-11 | Brain age deep learning prediction system based on structural magnetic resonance image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110859624A true CN110859624A (en) | 2020-03-06 |
Family
ID=69656759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911266178.XA Pending CN110859624A (en) | 2019-12-11 | 2019-12-11 | Brain age deep learning prediction system based on structural magnetic resonance image |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110859624A (en) |
| WO (1) | WO2021115084A1 (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582215A (en) * | 2020-05-17 | 2020-08-25 | 华中科技大学同济医学院附属协和医院 | Scanning identification system and method for normal anatomical structure of biliary-pancreatic system |
| CN111863247A (en) * | 2020-08-03 | 2020-10-30 | 北京航空航天大学 | Brain age cascade refining prediction method and system based on structural magnetic resonance image |
| CN111968113A (en) * | 2020-09-02 | 2020-11-20 | 中国人民解放军国防科技大学 | Brain image two-dimensional convolution depth learning method based on optimal transmission mapping |
| CN112568872A (en) * | 2020-12-30 | 2021-03-30 | 深圳大学 | Brain age fusion prediction method based on MRI (magnetic resonance imaging) image and blood biochemical indexes |
| CN112690774A (en) * | 2020-09-29 | 2021-04-23 | 首都医科大学附属北京天坛医院 | Magnetic resonance image-based stroke recurrence prediction method and system |
| WO2021115084A1 (en) * | 2019-12-11 | 2021-06-17 | 北京航空航天大学 | Structural magnetic resonance image-based brain age deep learning prediction system |
| CN113158913A (en) * | 2021-04-25 | 2021-07-23 | 安徽科大擎天科技有限公司 | Face mask wearing identification method, system and terminal |
| CN113378898A (en) * | 2021-05-28 | 2021-09-10 | 南通大学 | Brain age prediction method based on relative entropy loss function convolution neural network |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875624A (en) * | 2018-06-13 | 2018-11-23 | 华南理工大学 | Method for detecting human face based on the multiple dimensioned dense Connection Neural Network of cascade |
| CN109145920A (en) * | 2018-08-21 | 2019-01-04 | 电子科技大学 | A kind of image, semantic dividing method based on deep neural network |
| CN109523522A (en) * | 2018-10-30 | 2019-03-26 | 腾讯科技（深圳）有限公司 | Processing method, device, system and the storage medium of endoscopic images |
| CN109543623A (en) * | 2018-11-26 | 2019-03-29 | 微医云(杭州)控股有限公司 | A kind of development of fetus condition predicting device based on Magnetic resonance imaging |
| CN109635862A (en) * | 2018-12-05 | 2019-04-16 | 合肥奥比斯科技有限公司 | Retinopathy of prematurity plus lesion classification method |
| CN109712119A (en) * | 2018-12-13 | 2019-05-03 | 深圳先进技术研究院 | A kind of magnetic resonance imaging and patch recognition methods and device |
| CN109816612A (en) * | 2019-02-18 | 2019-05-28 | 京东方科技集团股份有限公司 | Image enchancing method and device, computer readable storage medium |
| CN109859189A (en) * | 2019-01-31 | 2019-06-07 | 长安大学 | A kind of age estimation method based on deep learning |
| CN109949824A (en) * | 2019-01-24 | 2019-06-28 | 江南大学 | City sound event classification method based on N-DenseNet and higher-dimension mfcc feature |
| CN109993210A (en) * | 2019-03-05 | 2019-07-09 | 北京工业大学 | A kind of brain age estimation method based on neuroimaging |
| CN110555828A (en) * | 2019-08-08 | 2019-12-10 | 北京深睿博联科技有限责任公司 | Brain age prediction method and device based on 3D convolutional neural network |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107067395B (en) * | 2017-04-26 | 2022-01-25 | 中国人民解放军总医院 | Nuclear magnetic resonance image processing device and method based on convolutional neural network |
| WO2019125026A1 (en) * | 2017-12-20 | 2019-06-27 | 주식회사 메디웨일 | Method and apparatus for assisting in diagnosis of cardiovascular disease |
| CN109222902A (en) * | 2018-08-27 | 2019-01-18 | 上海铱硙医疗科技有限公司 | Parkinson's prediction technique, system, storage medium and equipment based on nuclear magnetic resonance |
| CN110859624A (en) * | 2019-12-11 | 2020-03-06 | 北京航空航天大学 | Brain age deep learning prediction system based on structural magnetic resonance image |
-
2019
- 2019-12-11 CN CN201911266178.XA patent/CN110859624A/en active Pending
-
2020
- 2020-11-19 WO PCT/CN2020/130073 patent/WO2021115084A1/en active Application Filing
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875624A (en) * | 2018-06-13 | 2018-11-23 | 华南理工大学 | Method for detecting human face based on the multiple dimensioned dense Connection Neural Network of cascade |
| CN109145920A (en) * | 2018-08-21 | 2019-01-04 | 电子科技大学 | A kind of image, semantic dividing method based on deep neural network |
| CN109523522A (en) * | 2018-10-30 | 2019-03-26 | 腾讯科技（深圳）有限公司 | Processing method, device, system and the storage medium of endoscopic images |
| CN109543623A (en) * | 2018-11-26 | 2019-03-29 | 微医云(杭州)控股有限公司 | A kind of development of fetus condition predicting device based on Magnetic resonance imaging |
| CN109635862A (en) * | 2018-12-05 | 2019-04-16 | 合肥奥比斯科技有限公司 | Retinopathy of prematurity plus lesion classification method |
| CN109712119A (en) * | 2018-12-13 | 2019-05-03 | 深圳先进技术研究院 | A kind of magnetic resonance imaging and patch recognition methods and device |
| CN109949824A (en) * | 2019-01-24 | 2019-06-28 | 江南大学 | City sound event classification method based on N-DenseNet and higher-dimension mfcc feature |
| CN109859189A (en) * | 2019-01-31 | 2019-06-07 | 长安大学 | A kind of age estimation method based on deep learning |
| CN109816612A (en) * | 2019-02-18 | 2019-05-28 | 京东方科技集团股份有限公司 | Image enchancing method and device, computer readable storage medium |
| CN109993210A (en) * | 2019-03-05 | 2019-07-09 | 北京工业大学 | A kind of brain age estimation method based on neuroimaging |
| CN110555828A (en) * | 2019-08-08 | 2019-12-10 | 北京深睿博联科技有限责任公司 | Brain age prediction method and device based on 3D convolutional neural network |
Non-Patent Citations (1)
| Title |
|---|
| 唐明轩: "基于DenseNet的医学图像分割研究与应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021115084A1 (en) * | 2019-12-11 | 2021-06-17 | 北京航空航天大学 | Structural magnetic resonance image-based brain age deep learning prediction system |
| CN111582215A (en) * | 2020-05-17 | 2020-08-25 | 华中科技大学同济医学院附属协和医院 | Scanning identification system and method for normal anatomical structure of biliary-pancreatic system |
| CN111863247A (en) * | 2020-08-03 | 2020-10-30 | 北京航空航天大学 | Brain age cascade refining prediction method and system based on structural magnetic resonance image |
| CN111863247B (en) * | 2020-08-03 | 2022-04-15 | 北京航空航天大学 | Brain age cascade refining prediction method and system based on structural magnetic resonance image |
| CN111968113A (en) * | 2020-09-02 | 2020-11-20 | 中国人民解放军国防科技大学 | Brain image two-dimensional convolution depth learning method based on optimal transmission mapping |
| CN111968113B (en) * | 2020-09-02 | 2024-01-19 | 中国人民解放军国防科技大学 | Brain image two-dimensional convolution deep learning method based on optimal transmission mapping |
| CN112690774A (en) * | 2020-09-29 | 2021-04-23 | 首都医科大学附属北京天坛医院 | Magnetic resonance image-based stroke recurrence prediction method and system |
| CN112690774B (en) * | 2020-09-29 | 2022-07-19 | 首都医科大学附属北京天坛医院 | Magnetic resonance image-based stroke recurrence prediction method and system |
| CN112568872A (en) * | 2020-12-30 | 2021-03-30 | 深圳大学 | Brain age fusion prediction method based on MRI (magnetic resonance imaging) image and blood biochemical indexes |
| CN112568872B (en) * | 2020-12-30 | 2021-11-02 | 深圳大学 | Brain age fusion prediction method based on MRI (magnetic resonance imaging) image and blood biochemical indexes |
| CN113158913A (en) * | 2021-04-25 | 2021-07-23 | 安徽科大擎天科技有限公司 | Face mask wearing identification method, system and terminal |
| CN113378898A (en) * | 2021-05-28 | 2021-09-10 | 南通大学 | Brain age prediction method based on relative entropy loss function convolution neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021115084A1 (en) | 2021-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110859624A (en) | Brain age deep learning prediction system based on structural magnetic resonance image | |
| EP3916674B1 (en) | Brain image segmentation method, apparatus, network device and storage medium | |
| CN108898175B (en) | Computer-aided model construction method based on deep learning gastric cancer pathological section | |
| US10706333B2 (en) | Medical image analysis method, medical image analysis system and storage medium | |
| CN106815481B (en) | Lifetime prediction method and device based on image omics | |
| CN108898160B (en) | Breast cancer histopathology grading method based on CNN and imaging omics feature fusion | |
| CN109272048B (en) | Pattern recognition method based on deep convolutional neural network | |
| CN109544518B (en) | Method and system applied to bone maturity assessment | |
| CN111798462A (en) | Automatic delineation method for nasopharyngeal carcinoma radiotherapy target area based on CT image | |
| CN113421652A (en) | Method for analyzing medical data, method for training model and analyzer | |
| Aranguren et al. | Improving the segmentation of magnetic resonance brain images using the LSHADE optimization algorithm | |
| CN109003270B (en) | Image processing method, electronic device and storage medium | |
| CN111863247B (en) | Brain age cascade refining prediction method and system based on structural magnetic resonance image | |
| CN112674720B (en) | Alzheimer disease pre-judgment method based on 3D convolutional neural network | |
| WO2022127500A1 (en) | Multiple neural networks-based mri image segmentation method and apparatus, and device | |
| CN116884623B (en) | Medical rehabilitation prediction system based on laser scanning imaging | |
| CN115147600A (en) | GBM multi-mode MR image segmentation method based on classifier weight converter | |
| CN102521832B (en) | Image analysis method and system | |
| CN114943721A (en) | Neck ultrasonic image segmentation method based on improved U-Net network | |
| CN116205915B (en) | Brain age assessment method and system based on mask and electronic equipment | |
| CN112489048B (en) | Automatic optic nerve segmentation method based on depth network | |
| CN113456031A (en) | Training device and prediction device of brain state prediction model and electronic equipment | |
| CN111612739A (en) | Deep learning-based cerebral infarction classification method | |
| CN116797817A (en) | Autism disease prediction technology based on self-supervision graph convolution model | |
| CN116433679A (en) | Inner ear labyrinth multi-level labeling pseudo tag generation and segmentation method based on spatial position structure priori |
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 |