Alzheimer’s disease (AD) is a dementing disorder and one of the major public health problems in countries with greater longevity. The cerebral cortical thickness and cerebral blood flow (CBF), which are considered as...Alzheimer’s disease (AD) is a dementing disorder and one of the major public health problems in countries with greater longevity. The cerebral cortical thickness and cerebral blood flow (CBF), which are considered as morphological and functional image features, respectively, could be decreased in specific cerebral regions of patients with dementia of Alzheimer type. Therefore, the aim of this study was to develop a computer-aided classification system for AD patients based on machine learning with the morphological and functional image features derived from a magnetic resonance (MR) imaging system. The cortical thicknesses in ten cerebral regions were derived as morphological features by using gradient vector trajectories in fuzzy membership images. Functional CBF maps were measured with an arterial spin labeling technique, and ten regional CBF values were obtained by registration between the CBF map and Talairach atlas using an affine transformation and a free form deformation. We applied two systems based on an arterial neural network (ANN) and a support vector machine (SVM), which were trained with 4 morphological and 6 functional image features, to 15 AD patients and 15 clinically normal (CN) subjects for classification of AD. The area under the receiver operating characteristic curve (AUC) values for the two systems based on the ANN and SVM with both image?features were 0.901 and 0.915, respectively. The AUC values for the ANN-and SVM-based systems with the morphological features were 0.710 and 0.660, respectively, and those with the functional features were 0.878 and 0.903, respectively. Our preliminary results suggest that the proposed method may have potential for assisting radiologists in the differential diagnosis of AD patients by using morphological and functional image features.展开更多
The classification and identification of brain diseases with multimodal information have attracted increasing attention in the domain of computer-aided. Compared with traditional method which use single modal feature ...The classification and identification of brain diseases with multimodal information have attracted increasing attention in the domain of computer-aided. Compared with traditional method which use single modal feature information, multiple modal information fusion can classify and diagnose brain diseases more comprehensively and accurately in patient subjects. Existing multimodal methods require manual extraction of features or additional personal information, which consumes a lot of manual work. Furthermore, the difference between different modal images along with different manual feature extraction make it difficult for models to learn the optimal solution. In this paper, we propose a multimodal 3D convolutional neural networks framework for classification of brain disease diagnosis using MR images data and PET images data of subjects. We demonstrate the performance of the proposed approach for classification of Alzheimer’s disease (AD) versus mild cognitive impairment (MCI) and normal controls (NC) on the Alzheimer’s Disease National Initiative (ADNI) data set of 3D structural MRI brain scans and FDG-PET images. Experimental results show that the performance of the proposed method for AD vs. NC, MCI vs. NC are 93.55% and 78.92% accuracy respectively. And the accuracy of the results of AD, MCI and NC 3-classification experiments is 68.86%.展开更多
Increased physical activity and higher adherence to a Mediterranean-type diet (MeDi) have been independently associated with reduced risk of Alzheimer’s disease (AD). Their association has not been investigated with ...Increased physical activity and higher adherence to a Mediterranean-type diet (MeDi) have been independently associated with reduced risk of Alzheimer’s disease (AD). Their association has not been investigated with the use of biomarkers. This study examines whether, among cognitively normal (NL) individuals, those who are less physically active and show lower MeDi adherence have brain biomarker abnormalities consistent with AD. Methods: Forty-five NL individuals (age 54 ± 11, 71% women) with complete leisure time physical activity (LTA), dietary information, and cross-sectional 3D T1-weigthed MRI, 11C-Pittsburgh Compound B (PiB) and 18F-fluorodeoxyglucose (FDG) Positron Emission Tomography (PET) scans were examined. Voxel-wise multivariate partial least square (PLS) regression was used to examine the effects of LTA, MeDi and their interaction on brain biomarkers. Age, gender, ethnicity, education, caloric intake, BMI, family history of AD, Apolipoprotein E (APOE) genotype, presence of hypertension and insulin resistance were examined as confounds. Subjects were dichotomized into more and less physically active (LTA+ vs. LTA-;n = 21 vs. 24), and into higher vs. lower MeDi adherence groups (n = 18 vs. 27) using published scoring methods. Spatial patterns of brain biomarkers that represented the optimal association between the images and the groups were generated for all modalities using voxel-wise multivariate Partial Least Squares (PLS) regression. Results: Groups were comparable for clinical and neuropsychological measures. Independent effects of LTA and MeDi factors were observed in AD-vulnerable brain regions for all modalities (p β load and lower glucose metabolism) were observed in LTA- compared to LTA+ subjects, and in MeDi- as compared to MeDi+ subjects. A gradient effect was observed for all modalities so that LTA+/MeDi+ subjects had the highest and LTA+/MeDi+ subjects had the lowest AD-burden (p < 0.001), although the LTA × MeDi interaction was significant only for FDG measures (p < 0.03). Adjusting for covariates did not attenuate these relationships. Conclusion: Lower physical activity and MeDi adherence were associated with increased brain AD-burden among NL individuals, in-dicating that lifestyle factors may modulate AD risk. Studies with larger samples and longitudinal evaluations are needed to determine the predictive power of the observed associations.展开更多
Alzheimer’s Disease (AD), the most common form of dementia, is an incurable neurological condition that results in a progressive mental deterioration. Although definitive diagnosis of AD is difficult, in practice, AD...Alzheimer’s Disease (AD), the most common form of dementia, is an incurable neurological condition that results in a progressive mental deterioration. Although definitive diagnosis of AD is difficult, in practice, AD diagnosis is largely based on clinical history and neuropsychological data including magnetic resource imaging (MRI). Increasing research has been reported on applying machine learning to AD recognition in recent years. This paper presents our latest contribution to the advance. It describes an automatic AD recognition algorithm that is based on deep learning on 3D brain MRI. The algorithm uses a convolutional neural network (CNN) to fulfil AD recognition. It is unique in that the three dimensional topology of brain is considered as a whole in AD recognition, resulting in an accurate recognition. The CNN used in this study consists of three consecutive groups of processing layers, two fully connected layers and a classification layer. In the structure, every one of the three groups is made up of three layers, including a convolutional layer, a pooling layer and a normalization layer. The algorithm was trained and tested using the MRI data from Alzheimer’s Disease Neuroimaging Initiative. The data used include the MRI scanning of about 47 AD patients and 34 normal controls. The experiment had shown that the proposed algorithm delivered a high AD recognition accuracy with a sensitivity of 1 and a specificity of 0.93.展开更多
Electrical impedance tomography(EIT)image reconstruction is a non-linear problem.In general,finite element model is the critical basis of EIT image reconstruction.A 3D human thorax modeling method for EIT image recons...Electrical impedance tomography(EIT)image reconstruction is a non-linear problem.In general,finite element model is the critical basis of EIT image reconstruction.A 3D human thorax modeling method for EIT image reconstruction is proposed herein to improve the accuracy and reduce the complexity of existing finite element modeling methods.The contours of human thorax and lungs are extracted from the layers of magnetic resonance imaging(MRI)images by an optimized Otsu’s method for the construction of the 3D human thorax model including the lung models.Furthermore,the GMSH tool is used for finite element subdivision to generate the 3D finite element model of human thorax.The proposed modeling method is fast and accurate,and it is universal for different types of MRI images.The effectiveness of the proposed method is validated by extensive numerical simulation in MATLAB.The results show that the individually oriented 3D finite element model can improve the reconstruction quality of the EIT images more effectively than the cylindrical model,the 2.5D model and other human chest models.展开更多
Fast and accurate MRI reconstruction is a key concern in modern clinical practice.Recently,numerous Deep-Learning methods have been proposed for MRI reconstruction,however,they usually fail to reconstruct sharp detail...Fast and accurate MRI reconstruction is a key concern in modern clinical practice.Recently,numerous Deep-Learning methods have been proposed for MRI reconstruction,however,they usually fail to reconstruct sharp details from the subsampled k-space data.To solve this problem,we propose a lightweight and accurate Edge Attention MRI Reconstruction Network(EAMRI)to reconstruct images with edge guidance.Specifically,we design an efficient Edge Prediction Network to directly predict accurate edges from the blurred image.Meanwhile,we propose a novel Edge Attention Module(EAM)to guide the image reconstruction utilizing the extracted edge priors,as inspired by the popular self-attention mechanism.EAM first projects the input image and edges into Q_(image),K_(edge),and V_(image),respectively.Then EAM pairs the Q_(image)with K_(edge)along the channel dimension,such that 1)it can search globally for the high-frequency image features that are activated by the edge priors;2)the overall computation burdens are largely reduced compared with the traditional spatial-wise attention.With the help of EAM,the predicted edge priors can effectively guide the model to reconstruct high-quality MR images with accurate edges.Extensive experiments show that our proposed EAMRI outperforms other methods with fewer parameters and can recover more accurate edges.展开更多
目的:三维重建女性盆底组织闭孔内肌、骨盆和肛提肌的复杂几何结构,为从力学角度进一步认识女性盆底组织的力学特性和盆底功能障碍性疾病的发病机理做前期准备.方法:选取一系列层厚为0.8 mm MRI图像,运用三维图像重建软件MIMICS进行图...目的:三维重建女性盆底组织闭孔内肌、骨盆和肛提肌的复杂几何结构,为从力学角度进一步认识女性盆底组织的力学特性和盆底功能障碍性疾病的发病机理做前期准备.方法:选取一系列层厚为0.8 mm MRI图像,运用三维图像重建软件MIMICS进行图像重建,建立其三维几何结构.结果:获得了闭孔内肌、骨盆和肛提肌的独立三维几何结构,从解剖结构上完全还原其相对位置.结论:所获得的三维模型真实地反映了其解剖构型和几何外形,且通过有限元软件验证了本模型力学分析的可行性.展开更多
基金Manuscript received February 13, 2016 accepted December 7, 2016. This work was supported by the National Natural Science Foundation of China （61362001, 61661031）, Jiangxi Province Innovation Projects for Postgraduate Funds （YC2016-S006）, the International Postdoctoral Exchange Fellowship Program, and Jiangxi Advanced Project for Post-Doctoral Research Fund （2014KY02）.
文摘Alzheimer’s disease (AD) is a dementing disorder and one of the major public health problems in countries with greater longevity. The cerebral cortical thickness and cerebral blood flow (CBF), which are considered as morphological and functional image features, respectively, could be decreased in specific cerebral regions of patients with dementia of Alzheimer type. Therefore, the aim of this study was to develop a computer-aided classification system for AD patients based on machine learning with the morphological and functional image features derived from a magnetic resonance (MR) imaging system. The cortical thicknesses in ten cerebral regions were derived as morphological features by using gradient vector trajectories in fuzzy membership images. Functional CBF maps were measured with an arterial spin labeling technique, and ten regional CBF values were obtained by registration between the CBF map and Talairach atlas using an affine transformation and a free form deformation. We applied two systems based on an arterial neural network (ANN) and a support vector machine (SVM), which were trained with 4 morphological and 6 functional image features, to 15 AD patients and 15 clinically normal (CN) subjects for classification of AD. The area under the receiver operating characteristic curve (AUC) values for the two systems based on the ANN and SVM with both image?features were 0.901 and 0.915, respectively. The AUC values for the ANN-and SVM-based systems with the morphological features were 0.710 and 0.660, respectively, and those with the functional features were 0.878 and 0.903, respectively. Our preliminary results suggest that the proposed method may have potential for assisting radiologists in the differential diagnosis of AD patients by using morphological and functional image features.
基金the National Natural Science Foundation of China under Grant No. 61672181, No. 51679058Natural Science Foundation of Heilongjiang Province under Grant No. F2016005. We would like to thank our teacher for guiding this paper. We would also like to thank classmates for their encouragement and help.
文摘The classification and identification of brain diseases with multimodal information have attracted increasing attention in the domain of computer-aided. Compared with traditional method which use single modal feature information, multiple modal information fusion can classify and diagnose brain diseases more comprehensively and accurately in patient subjects. Existing multimodal methods require manual extraction of features or additional personal information, which consumes a lot of manual work. Furthermore, the difference between different modal images along with different manual feature extraction make it difficult for models to learn the optimal solution. In this paper, we propose a multimodal 3D convolutional neural networks framework for classification of brain disease diagnosis using MR images data and PET images data of subjects. We demonstrate the performance of the proposed approach for classification of Alzheimer’s disease (AD) versus mild cognitive impairment (MCI) and normal controls (NC) on the Alzheimer’s Disease National Initiative (ADNI) data set of 3D structural MRI brain scans and FDG-PET images. Experimental results show that the performance of the proposed method for AD vs. NC, MCI vs. NC are 93.55% and 78.92% accuracy respectively. And the accuracy of the results of AD, MCI and NC 3-classification experiments is 68.86%.
文摘Increased physical activity and higher adherence to a Mediterranean-type diet (MeDi) have been independently associated with reduced risk of Alzheimer’s disease (AD). Their association has not been investigated with the use of biomarkers. This study examines whether, among cognitively normal (NL) individuals, those who are less physically active and show lower MeDi adherence have brain biomarker abnormalities consistent with AD. Methods: Forty-five NL individuals (age 54 ± 11, 71% women) with complete leisure time physical activity (LTA), dietary information, and cross-sectional 3D T1-weigthed MRI, 11C-Pittsburgh Compound B (PiB) and 18F-fluorodeoxyglucose (FDG) Positron Emission Tomography (PET) scans were examined. Voxel-wise multivariate partial least square (PLS) regression was used to examine the effects of LTA, MeDi and their interaction on brain biomarkers. Age, gender, ethnicity, education, caloric intake, BMI, family history of AD, Apolipoprotein E (APOE) genotype, presence of hypertension and insulin resistance were examined as confounds. Subjects were dichotomized into more and less physically active (LTA+ vs. LTA-;n = 21 vs. 24), and into higher vs. lower MeDi adherence groups (n = 18 vs. 27) using published scoring methods. Spatial patterns of brain biomarkers that represented the optimal association between the images and the groups were generated for all modalities using voxel-wise multivariate Partial Least Squares (PLS) regression. Results: Groups were comparable for clinical and neuropsychological measures. Independent effects of LTA and MeDi factors were observed in AD-vulnerable brain regions for all modalities (p β load and lower glucose metabolism) were observed in LTA- compared to LTA+ subjects, and in MeDi- as compared to MeDi+ subjects. A gradient effect was observed for all modalities so that LTA+/MeDi+ subjects had the highest and LTA+/MeDi+ subjects had the lowest AD-burden (p < 0.001), although the LTA × MeDi interaction was significant only for FDG measures (p < 0.03). Adjusting for covariates did not attenuate these relationships. Conclusion: Lower physical activity and MeDi adherence were associated with increased brain AD-burden among NL individuals, in-dicating that lifestyle factors may modulate AD risk. Studies with larger samples and longitudinal evaluations are needed to determine the predictive power of the observed associations.
文摘Alzheimer’s Disease (AD), the most common form of dementia, is an incurable neurological condition that results in a progressive mental deterioration. Although definitive diagnosis of AD is difficult, in practice, AD diagnosis is largely based on clinical history and neuropsychological data including magnetic resource imaging (MRI). Increasing research has been reported on applying machine learning to AD recognition in recent years. This paper presents our latest contribution to the advance. It describes an automatic AD recognition algorithm that is based on deep learning on 3D brain MRI. The algorithm uses a convolutional neural network (CNN) to fulfil AD recognition. It is unique in that the three dimensional topology of brain is considered as a whole in AD recognition, resulting in an accurate recognition. The CNN used in this study consists of three consecutive groups of processing layers, two fully connected layers and a classification layer. In the structure, every one of the three groups is made up of three layers, including a convolutional layer, a pooling layer and a normalization layer. The algorithm was trained and tested using the MRI data from Alzheimer’s Disease Neuroimaging Initiative. The data used include the MRI scanning of about 47 AD patients and 34 normal controls. The experiment had shown that the proposed algorithm delivered a high AD recognition accuracy with a sensitivity of 1 and a specificity of 0.93.
基金the National Natural Science Foundation of China(No.61371017)。
文摘Electrical impedance tomography(EIT)image reconstruction is a non-linear problem.In general,finite element model is the critical basis of EIT image reconstruction.A 3D human thorax modeling method for EIT image reconstruction is proposed herein to improve the accuracy and reduce the complexity of existing finite element modeling methods.The contours of human thorax and lungs are extracted from the layers of magnetic resonance imaging(MRI)images by an optimized Otsu’s method for the construction of the 3D human thorax model including the lung models.Furthermore,the GMSH tool is used for finite element subdivision to generate the 3D finite element model of human thorax.The proposed modeling method is fast and accurate,and it is universal for different types of MRI images.The effectiveness of the proposed method is validated by extensive numerical simulation in MATLAB.The results show that the individually oriented 3D finite element model can improve the reconstruction quality of the EIT images more effectively than the cylindrical model,the 2.5D model and other human chest models.
基金This work is supported in part by the National Key R&D Program of China under Grant 2021YFE0203700 and 2021YFA1003004in part by the Natural Science Foundation of Shanghai under Grand 23ZR1422200+1 种基金in part by the Shanghai Sailing Program under Grant 23YF1412800in part by the NSFC/RGC N CUHK 415/19,Grant ITF MHP/038/20,Grant CRF 8730063,Grant RGC 14300219,14302920,14301121,and CUHK Direct Grant for Research.
文摘Fast and accurate MRI reconstruction is a key concern in modern clinical practice.Recently,numerous Deep-Learning methods have been proposed for MRI reconstruction,however,they usually fail to reconstruct sharp details from the subsampled k-space data.To solve this problem,we propose a lightweight and accurate Edge Attention MRI Reconstruction Network(EAMRI)to reconstruct images with edge guidance.Specifically,we design an efficient Edge Prediction Network to directly predict accurate edges from the blurred image.Meanwhile,we propose a novel Edge Attention Module(EAM)to guide the image reconstruction utilizing the extracted edge priors,as inspired by the popular self-attention mechanism.EAM first projects the input image and edges into Q_(image),K_(edge),and V_(image),respectively.Then EAM pairs the Q_(image)with K_(edge)along the channel dimension,such that 1)it can search globally for the high-frequency image features that are activated by the edge priors;2)the overall computation burdens are largely reduced compared with the traditional spatial-wise attention.With the help of EAM,the predicted edge priors can effectively guide the model to reconstruct high-quality MR images with accurate edges.Extensive experiments show that our proposed EAMRI outperforms other methods with fewer parameters and can recover more accurate edges.
文摘目的:三维重建女性盆底组织闭孔内肌、骨盆和肛提肌的复杂几何结构,为从力学角度进一步认识女性盆底组织的力学特性和盆底功能障碍性疾病的发病机理做前期准备.方法:选取一系列层厚为0.8 mm MRI图像,运用三维图像重建软件MIMICS进行图像重建,建立其三维几何结构.结果:获得了闭孔内肌、骨盆和肛提肌的独立三维几何结构,从解剖结构上完全还原其相对位置.结论:所获得的三维模型真实地反映了其解剖构型和几何外形,且通过有限元软件验证了本模型力学分析的可行性.
