|
1
|
Chattopadhyay T, Joshy NA, Ozarkar SS, Buwa K, Feng Y, Laltoo E, Thomopoulos SI, Villalon JE, Joshi H, Venkatasubramanian G, John JP, Thompson PM. Brain Age Analysis and Dementia Classification using Convolutional Neural Networks trained on Diffusion MRI: Tests in Indian and North American Cohorts. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2024; 2024:1-7. [PMID: 40039079 DOI: 10.1109/embc53108.2024.10781599] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/06/2025]
Abstract
Deep learning models based on convolutional neural networks (CNNs) have been used to classify Alzheimer's disease or infer dementia severity from T1-weighted brain MRI scans. Here, we examine the value of adding diffusion-weighted MRI (dMRI) as an input to these models. Much research in this area focuses on specific datasets such as the Alzheimer's Disease Neuroimaging Initiative (ADNI), which assesses people of North American, largely European ancestry, so we examine how models trained on ADNI, generalize to a new population dataset from India (the NIMHANS cohort). We first benchmark our models by predicting "brain age" - the task of predicting a person's chronological age from their MRI scan and proceed to AD classification. We also evaluate the benefit of using a 3D CycleGAN approach to harmonize the imaging datasets before training the CNN models. Our experiments show that classification performance improves after harmonization in most cases, as well as better performance for dMRI as input.
Collapse
|
|
2
|
Chattopadhyay T, Joshy NA, Ozarkar SS, Buwa KS, Feng Y, Laltoo E, Thomopoulos SI, Villalon-Reina JE, Joshi H, Venkatasubramanian G, John JP, Thompson PM. Brain Age Analysis and Dementia Classification using Convolutional Neural Networks trained on Diffusion MRI: Tests in Indian and North American Cohorts. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.02.04.578829. [PMID: 38370641 PMCID: PMC10871286 DOI: 10.1101/2024.02.04.578829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/20/2024]
Abstract
Deep learning models based on convolutional neural networks (CNNs) have been used to classify Alzheimer's disease or infer dementia severity from T1-weighted brain MRI scans. Here, we examine the value of adding diffusion-weighted MRI (dMRI) as an input to these models. Much research in this area focuses on specific datasets such as the Alzheimer's Disease Neuroimaging Initiative (ADNI), which assesses people of North American, largely European ancestry, so we examine how models trained on ADNI, generalize to a new population dataset from India (the NIMHANS cohort). We first benchmark our models by predicting 'brain age' - the task of predicting a person's chronological age from their MRI scan and proceed to AD classification. We also evaluate the benefit of using a 3D CycleGAN approach to harmonize the imaging datasets before training the CNN models. Our experiments show that classification performance improves after harmonization in most cases, as well as better performance for dMRI as input.
Collapse
|
|
3
|
Hao X, Zhang W, Jiao B, Yang Q, Zhang X, Chen R, Wang X, Xiao X, Zhu Y, Liao W, Wang D, Shen L. Correlation between retinal structure and brain multimodal magnetic resonance imaging in patients with Alzheimer's disease. Front Aging Neurosci 2023; 15:1088829. [PMID: 36909943 PMCID: PMC9992546 DOI: 10.3389/fnagi.2023.1088829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2022] [Accepted: 02/06/2023] [Indexed: 02/24/2023] Open
Abstract
Background The retina imaging and brain magnetic resonance imaging (MRI) can both reflect early changes in Alzheimer's disease (AD) and may serve as potential biomarker for early diagnosis, but their correlation and the internal mechanism of retinal structural changes remain unclear. This study aimed to explore the possible correlation between retinal structure and visual pathway, brain structure, intrinsic activity changes in AD patients, as well as to build a classification model to identify AD patients. Methods In the study, 49 AD patients and 48 healthy controls (HCs) were enrolled. Retinal images were obtained by optical coherence tomography (OCT). Multimodal MRI sequences of all subjects were collected. Spearman correlation analysis and multiple linear regression models were used to assess the correlation between OCT parameters and multimodal MRI findings. The diagnostic value of combination of retinal imaging and brain multimodal MRI was assessed by performing a receiver operating characteristic (ROC) curve. Results Compared with HCs, retinal thickness and multimodal MRI findings of AD patients were significantly altered (p < 0.05). Significant correlations were presented between the fractional anisotropy (FA) value of optic tract and mean retinal thickness, macular volume, macular ganglion cell layer (GCL) thickness, inner plexiform layer (IPL) thickness in AD patients (p < 0.01). The fractional amplitude of low frequency fluctuations (fALFF) value of primary visual cortex (V1) was correlated with temporal quadrant peripapillary retinal nerve fiber layer (pRNFL) thickness (p < 0.05). The model combining thickness of GCL and temporal quadrant pRNFL, volume of hippocampus and lateral geniculate nucleus, and age showed the best performance to identify AD patients [area under the curve (AUC) = 0.936, sensitivity = 89.1%, specificity = 87.0%]. Conclusion Our study demonstrated that retinal structure change was related to the loss of integrity of white matter fiber tracts in the visual pathway and the decreased LGN volume and functional metabolism of V1 in AD patients. Trans-synaptic axonal retrograde lesions may be the underlying mechanism. Combining retinal imaging and multimodal MRI may provide new insight into the mechanism of retinal structural changes in AD and may serve as new target for early auxiliary diagnosis of AD.
Collapse
Affiliation(s)
- Xiaoli Hao
- Department of Neurology, Xiangya Hospital of Central South University, Changsha, China
| | - Weiwei Zhang
- Department of Radiology, Xiangya Hospital of Central South University, Changsha, China
| | - Bin Jiao
- Department of Neurology, Xiangya Hospital of Central South University, Changsha, China.,National Clinical Research Center for Geriatric Disorders, Central South University, Changsha, China.,Engineering Research Center of Hunan Province in Cognitive Impairment Disorders, Central South University, Changsha, China.,Hunan International Scientific and Technological Cooperation Base of Neurodegenerative and Neurogenetic Diseases, Changsha, China.,Key Laboratory of Hunan Province in Neurodegenerative Disorders, Central South University, Changsha, China
| | - Qijie Yang
- Department of Neurology, Xiangya Hospital of Central South University, Changsha, China
| | - Xinyue Zhang
- Department of Neurology, Xiangya Hospital of Central South University, Changsha, China
| | - Ruiting Chen
- Department of Radiology, Xiangya Hospital of Central South University, Changsha, China
| | - Xin Wang
- Department of Neurology, Xiangya Hospital of Central South University, Changsha, China
| | - Xuewen Xiao
- Department of Neurology, Xiangya Hospital of Central South University, Changsha, China
| | - Yuan Zhu
- Department of Neurology, Xiangya Hospital of Central South University, Changsha, China
| | - Weihua Liao
- Department of Radiology, Xiangya Hospital of Central South University, Changsha, China
| | - Dongcui Wang
- Department of Radiology, Xiangya Hospital of Central South University, Changsha, China
| | - Lu Shen
- Department of Neurology, Xiangya Hospital of Central South University, Changsha, China.,National Clinical Research Center for Geriatric Disorders, Central South University, Changsha, China.,Engineering Research Center of Hunan Province in Cognitive Impairment Disorders, Central South University, Changsha, China.,Hunan International Scientific and Technological Cooperation Base of Neurodegenerative and Neurogenetic Diseases, Changsha, China.,Key Laboratory of Hunan Province in Neurodegenerative Disorders, Central South University, Changsha, China.,Key Laboratory of Organ Injury, Aging and Regenerative Medicine of Hunan Province, Changsha, China
| |
Collapse
|
|
4
|
Ertl M, Woeckel M, Maurer C. Differentiation Between Ischemic and Hemorrhagic Strokes - A Pilot Study with Transtemporal Investigation of Brain Parenchyma Elasticity Using Ultrasound Shear Wave Elastography. ULTRASCHALL IN DER MEDIZIN (STUTTGART, GERMANY : 1980) 2021; 42:75-83. [PMID: 33036048 DOI: 10.1055/a-1248-2022] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
INTRODUCTION Ultrasound shear wave elastography is well established in diagnostics of several parenchymatous organs and is recommended by respective guidelines. So far, research about applications in relevant neurological conditions is missing, especially in adults. Here we aimed to examine the method for the differentiation of ischemic (IS) and hemorrhagic strokes (HS) and cerebral mass effects. MATERIALS & METHODS 50 patients with a confirmed diagnosis of HS or IS were enrolled in this prospective study. 2D shear wave elastography was performed on the ipsilateral and the contralateral side with a modified acoustic radiation force impulse (ARFI) technique (ElastPQ mode, Philips). Lesion volumetry was conducted based on computed tomography data for correlation with elastography results. RESULTS Elastography measurements (EM) revealed a highly significant difference between IS and HS with mean values of 1.94 and 5.50 kPa, respectively (p < 0.00 001). Mean values of brain tissue on the non-affected side were almost identical (IS 3.38 (SD = 0.63); HS 3.35 (SD = 0.66); p = 0.91). With a sensitivity of 0.98 and a specificity of 0.99, a cut-off value of 3.52 kPa for discrimination could be calculated. There was a significant correlation of mass effect represented by midline shift and EM values on the contralateral side (Pearson correlation coefficient = 0.68, p < 0.0003). CONCLUSION Ultrasound brain parenchyma elastography seems to be a reliable sonographic method for discriminating between large IS and HS and for detecting and tracking conditions of intracerebral mass effects.
Collapse
Affiliation(s)
- Michael Ertl
- Neurology and Clinical Neurophysiology, University Hospital Augsburg, Germany
| | - Margarethe Woeckel
- Institute of Epidemiology, Helmholtz-Zentrum München Deutsches Forschungszentrum für Gesundheit und Umwelt, Neuherberg, Germany
| | - Christoph Maurer
- Diagnostic and interventional Neuroradiology, University Hospital Augsburg, Germany
| |
Collapse
|
|
5
|
Pfeffer A, Munder T, Schreyer S, Klein C, Rasińska J, Winter Y, Steiner B. Behavioral and psychological symptoms of dementia (BPSD) and impaired cognition reflect unsuccessful neuronal compensation in the pre-plaque stage and serve as early markers for Alzheimer's disease in the APP23 mouse model. Behav Brain Res 2018; 347:300-313. [PMID: 29572105 DOI: 10.1016/j.bbr.2018.03.030] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2017] [Revised: 02/28/2018] [Accepted: 03/19/2018] [Indexed: 12/15/2022]
Abstract
Recent research on Alzheimer's disease (AD) focuses on processes prior to amyloid-beta plaque deposition accounting for the progress of the disease. However, early mechanisms of AD are still poorly understood and predictors of the disease in the pre-plaque stage essential for initiating an early therapy are lacking. Behavioral and psychological symptoms of dementia (BPSD) and potentially impaired cognition may serve as predictors and early clinical diagnostic markers for AD. To investigate potential BPSD and cognitive impairments in association with neuronal cell development as such markers for AD in the pre-plaque stage, female APP23 mice at eight, 19 and 31 weeks of age and corresponding control animals were tested for BPSD (elevated zero maze; sucrose preference test), motor coordination (rotarod), spatial memory and reversal learning (Morris water maze) and hippocampal neurogenesis as a neuronal correlate for hippocampus-dependent behavior. To evaluate a potential therapeutic effect of physical, cognitive and social stimulation, animals were exposed to environmental enrichment (EE) for one, twelve or 24 weeks from five weeks of age. In APP23, decreased anxiety accompanied increased agitation from eight weeks of age. Impairment of spatial memory and learning flexibility prior to plaque deposition involved an insufficient use of spatial search strategies associated with an unsuccessful compensatory increase of neurogenesis. EE had an overall beneficial effect on behavior and neurogenesis and thus constitutes a therapeutic tool to slow disease progression. BPSD, cognition and associated impaired neurogenesis complement clinical diagnostic markers for pre-plaque AD and contribute to an early detection essential to halt disease progression.
Collapse
Affiliation(s)
- Anna Pfeffer
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Department of Neurology, Charitéplatz 1, 10117, Berlin, Germany
| | - Tonia Munder
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Department of Neurology, Charitéplatz 1, 10117, Berlin, Germany
| | - Stefanie Schreyer
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Department of Neurology, Charitéplatz 1, 10117, Berlin, Germany
| | - Charlotte Klein
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Department of Neurology, Charitéplatz 1, 10117, Berlin, Germany
| | - Justyna Rasińska
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Department of Neurology, Charitéplatz 1, 10117, Berlin, Germany
| | - York Winter
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, NeuroCure Cluster of Excellence, Charitéplatz 1, 10117, Berlin, Germany
| | - Barbara Steiner
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Department of Neurology, Charitéplatz 1, 10117, Berlin, Germany.
| |
Collapse
|
|
6
|
Sun J, Zhou H, Bai F, Zhang Z, Ren Q. Remyelination: A Potential Therapeutic Strategy for Alzheimer's Disease? J Alzheimers Dis 2018; 58:597-612. [PMID: 28453483 DOI: 10.3233/jad-170036] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
Myelin is a lipid-rich multilamellar membrane that wraps around long segments of neuronal axons and it increases the conduction of action potentials, transports the necessary trophic support to the neuronal axons, and reduces the energy consumed by the neuronal axons. Together with axons, myelin is a prerequisite for the higher functions of the central nervous system and complex forms of network integration. Myelin impairments have been suggested to lead to neuronal dysfunction and cognitive decline. Accumulating evidence, including brain imaging and postmortem and genetic association studies, has implicated myelin impairments in Alzheimer's disease (AD). Increasing data link myelin impairments with amyloid-β (Aβ) plaques and tau hyperphosphorylation, which are both present in patients with AD. Moreover, aging and apolipoprotein E (ApoE) may be involved in the myelin impairments observed in patients with AD. Decreased neuronal activity, increased Aβ levels, and inflammation further damage myelin in patients with AD. Furthermore, treatments that promote myelination contribute to the recovery of neuronal function and improve cognition. Therefore, strategies targeting myelin impairment may provide therapeutic opportunities for patients with AD.
Collapse
|
|
7
|
Ertl M, Raasch N, Hammel G, Harter K, Lang C. Transtemporal Investigation of Brain Parenchyma Elasticity Using 2-D Shear Wave Elastography: Definition of Age-Matched Normal Values. ULTRASOUND IN MEDICINE & BIOLOGY 2018; 44:78-84. [PMID: 28982629 DOI: 10.1016/j.ultrasmedbio.2017.08.1885] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/26/2017] [Revised: 08/23/2017] [Accepted: 08/28/2017] [Indexed: 06/07/2023]
Abstract
The goal of our research was to assess the possibility of reliable investigation of brain tissue stiffness using ultrasonographic brain parenchyma elastography with an intact temporal bone. We enrolled 108 patients after exclusion of intracranial pathology or healthy volunteers. All patients were subdivided by age into groups: 20-40, 40-60 and >60 y. For statistical analysis, the χ2 test and t-test were used. The mean values, regardless of age and other parameters, were 3.34 kPa (SD = 0.59) on the left side and 3.33 kPa (SD = 0.58) on the right side. We found no correlation between the values, body mass index (r = 0.07, p = 0.48) and sex (t = -0.11, p = 0.91), but we observed a highly significant correlation between the values and age (r = 0.43, p <0.0001). We found ultrasonographic brain parenchyma elastography to be a valid, reproducible and investigator-independent method that reliably determines brain parenchyma stiffness. Normal values should serve as a reference for studies on various intracranial lesions.
Collapse
Affiliation(s)
- Michael Ertl
- Clinic for Neurology and Neurophysiology, Klinikum Augsburg, Augsburg, Germany.
| | - Nele Raasch
- Clinic for Neurology and Neurophysiology, Klinikum Augsburg, Augsburg, Germany
| | - Gertrud Hammel
- Chair and Institute of Environmental Medicine, UNIKA-T, Technical University of Munich and Helmholtz Zentrum München, Germany - German Research Center for Environmental Health, Augsburg, Germany; CK-CARE, Christine Kühne - Center for Allergy and Research and Education, Davos, Switzerland
| | - Katharina Harter
- Chair and Institute of Environmental Medicine, UNIKA-T, Technical University of Munich and Helmholtz Zentrum München, Germany - German Research Center for Environmental Health, Augsburg, Germany; CK-CARE, Christine Kühne - Center for Allergy and Research and Education, Davos, Switzerland
| | - Christopher Lang
- Clinic for Neurology and Neurophysiology, Klinikum Augsburg, Augsburg, Germany
| |
Collapse
|
|
8
|
Sun J, Zhou H, Bai F, Ren Q, Zhang Z. Myelin injury induces axonal transport impairment but not AD-like pathology in the hippocampus of cuprizone-fed mice. Oncotarget 2017; 7:30003-17. [PMID: 27129150 PMCID: PMC5058659 DOI: 10.18632/oncotarget.8981] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2015] [Accepted: 04/16/2016] [Indexed: 12/02/2022] Open
Abstract
Both multiple sclerosis (MS) and Alzheimer's disease (AD) are progressive neurological disorders with myelin injury and memory impairment. However, whether myelin impairment could cause AD-like neurological pathology remains unclear. To explore neurological pathology following myelin injury, we assessed cognitive function, the expression of myelin proteins, axonal transport-associated proteins, axonal structural proteins, synapse-associated proteins, tau and beta amyloid and the status of neurons, using the cuprizone mouse model of demyelination. We found the mild impairment of learning ability in cuprizone-fed mice and the decreased expression of myelin basic protein (MBP) in the hippocampus. And anti-LINGO-1 improved learning ability and partly restored MBP level. Furthermore, we also found kinesin light chain (KLC), neurofilament light chain (NFL) and neurofilament heavy chain (NF200) were declined in demyelinated hippocampus, which could be partly improved by treatment with anti-LINGO-1. However, we did not observe the increased expression of beta amyloid, hyperphosphorylation of tau and loss of neurons in demyelinated hippocampus. Our results suggest that demyelination might lead to the impairment of neuronal transport, but not cause increased level of hyperphosphorylated tau and beta amyloid. Our research demonstrates remyelination might be an effective pathway to recover the function of neuronal axons and cognition in MS.
Collapse
Affiliation(s)
- Junjun Sun
- Department of Neuropsychiatry, Affiliated ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Hong Zhou
- Department of Neuropsychiatry, Affiliated ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Feng Bai
- Department of Neuropsychiatry, Affiliated ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Qingguo Ren
- Department of Neuropsychiatry, Affiliated ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Zhijun Zhang
- Department of Neuropsychiatry, Affiliated ZhongDa Hospital, School of Medicine, Southeast University, Nanjing, China
| |
Collapse
|
|
9
|
Zhang T, Wang D, Zhang Q, Wu J, Lv J, Shi L. Supervoxel-based statistical analysis of diffusion tensor imaging in schizotypal personality disorder. Neuroimage 2017; 163:368-378. [DOI: 10.1016/j.neuroimage.2017.07.026] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2017] [Revised: 06/20/2017] [Accepted: 07/13/2017] [Indexed: 01/24/2023] Open
|
|
10
|
Oppedal K, Engan K, Eftestøl T, Beyer M, Aarsland D. Classifying Alzheimer's disease, Lewy body dementia, and normal controls using 3D texture analysis in magnetic resonance images. Biomed Signal Process Control 2017. [DOI: 10.1016/j.bspc.2016.10.007] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/10/2023]
|
|
11
|
Wang T, Shi F, Jin Y, Yap PT, Wee CY, Zhang J, Yang C, Li X, Xiao S, Shen D. Multilevel Deficiency of White Matter Connectivity Networks in Alzheimer's Disease: A Diffusion MRI Study with DTI and HARDI Models. Neural Plast 2016; 2016:2947136. [PMID: 26881100 PMCID: PMC4737469 DOI: 10.1155/2016/2947136] [Citation(s) in RCA: 21] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2015] [Accepted: 11/22/2015] [Indexed: 01/27/2023] Open
Abstract
Alzheimer's disease (AD) is the most common form of dementia in elderly people. It is an irreversible and progressive brain disease. In this paper, we utilized diffusion-weighted imaging (DWI) to detect abnormal topological organization of white matter (WM) structural networks. We compared the differences between WM connectivity characteristics at global, regional, and local levels in 26 patients with probable AD and 16 normal control (NC) elderly subjects, using connectivity networks constructed with the diffusion tensor imaging (DTI) model and the high angular resolution diffusion imaging (HARDI) model, respectively. At the global level, we found that the WM structural networks of both AD and NC groups had a small-world topology; however, the AD group showed a significant decrease in both global and local efficiency, but an increase in clustering coefficient and the average shortest path length. We further found that the AD patients had significantly decreased nodal efficiency at the regional level, as well as weaker connections in multiple local cortical and subcortical regions, such as precuneus, temporal lobe, hippocampus, and thalamus. The HARDI model was found to be more advantageous than the DTI model, as it was more sensitive to the deficiencies in AD at all of the three levels.
Collapse
Affiliation(s)
- Tao Wang
- Department of Geriatric Psychiatry, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- IDEA Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
- Alzheimer's Disease and Related Disorders Center, Shanghai Jiao Tong University, Shanghai, China
| | - Feng Shi
- IDEA Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| | - Yan Jin
- IDEA Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| | - Pew-Thian Yap
- IDEA Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| | - Chong-Yaw Wee
- IDEA Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| | - Jianye Zhang
- Department of Radiology, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Cece Yang
- Department of Geriatric Psychiatry, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Alzheimer's Disease and Related Disorders Center, Shanghai Jiao Tong University, Shanghai, China
| | - Xia Li
- Department of Geriatric Psychiatry, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Alzheimer's Disease and Related Disorders Center, Shanghai Jiao Tong University, Shanghai, China
| | - Shifu Xiao
- Department of Geriatric Psychiatry, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Alzheimer's Disease and Related Disorders Center, Shanghai Jiao Tong University, Shanghai, China
| | - Dinggang Shen
- IDEA Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
- Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea
| |
Collapse
|
|
12
|
Barsanti C, Lenzarini F, Kusmic C. Diagnostic and prognostic utility of non-invasive imaging in diabetes management. World J Diabetes 2015; 6:792-806. [PMID: 26131322 PMCID: PMC4478576 DOI: 10.4239/wjd.v6.i6.792] [Citation(s) in RCA: 18] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/27/2014] [Revised: 12/23/2014] [Accepted: 04/14/2015] [Indexed: 02/05/2023] Open
Abstract
Medical imaging technologies are acquiring an increasing relevance to assist clinicians in diagnosis and to guide management and therapeutic treatment of patients, thanks to their non invasive and high resolution properties. Computed tomography, magnetic resonance imaging, and ultrasonography are the most used imaging modalities to provide detailed morphological reconstructions of tissues and organs. In addition, the use of contrast dyes or radionuclide-labeled tracers permits to get functional and quantitative information about tissue physiology and metabolism in normal and disease state. In recent years, the development of multimodal and hydrid imaging techniques is coming to be the new frontier of medical imaging for the possibility to overcome limitations of single modalities and to obtain physiological and pathophysiological measurements within an accurate anatomical framework. Moreover, the employment of molecular probes, such as ligands or antibodies, allows a selective in vivo targeting of biomolecules involved in specific cellular processes, so expanding the potentialities of imaging techniques for clinical and research applications. This review is aimed to give a survey of characteristics of main diagnostic non-invasive imaging techniques. Current clinical appliances and future perspectives of imaging in the diagnostic and prognostic assessment of diabetic complications affecting different organ systems will be particularly addressed.
Collapse
|
|
13
|
Ouyang X, Chen K, Yao L, Hu B, Wu X, Ye Q, Guo X. Simultaneous changes in gray matter volume and white matter fractional anisotropy in Alzheimer's disease revealed by multimodal CCA and joint ICA. Neuroscience 2015; 301:553-62. [PMID: 26116521 DOI: 10.1016/j.neuroscience.2015.06.031] [Citation(s) in RCA: 24] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2015] [Revised: 06/16/2015] [Accepted: 06/17/2015] [Indexed: 01/30/2023]
Abstract
The prominent morphometric alterations of Alzheimer's disease (AD) occur both in gray matter and in white matter. Multimodal fusion can examine joint information by combining multiple neuroimaging datasets to identify the covariant morphometric alterations in AD in greater detail. In the current study, we conducted a multimodal canonical correlation analysis and joint independent component analysis to identify the covariance patterns of the gray and white matter by fusing structural magnetic resonance imaging and diffusion tensor imaging data of 39 AD patients (23 males and 16 females, mean age: 74.91±8.13years) and 41 normal controls (NCs) (20 males and 21 females, mean age: 73.97±6.34years) derived from the Alzheimer's Disease Neuroimaging Initiative database. The results revealed 25 joint independent components (ICs), of which three joint ICs exhibited strong links between the gray matter volume and the white matter fractional anisotropy (FA) and significant differences between the AD and NC group. The joint IC maps revealed that the simultaneous changes in the gray matter and FA values primarily involved the following areas: (1) the temporal lobe/hippocampus-cingulum, (2) the frontal/cingulate gyrus-corpus callosum, and (3) the temporal/occipital/parietal lobe-corpus callosum/corona radiata. Our findings suggest that gray matter atrophy is associated with reduced white matter fiber integrity in AD and possibly expand the understanding of the neuropathological mechanisms in AD.
Collapse
Affiliation(s)
- X Ouyang
- College of Information Science and Technology, Beijing Normal University, Beijing, China
| | - K Chen
- Banner Alzheimer's Institute and Banner Good Samaritan PET Center, Phoenix, AZ, USA
| | - L Yao
- College of Information Science and Technology, Beijing Normal University, Beijing, China; State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China
| | - B Hu
- College of Information Science and Technology, Beijing Normal University, Beijing, China
| | - X Wu
- College of Information Science and Technology, Beijing Normal University, Beijing, China; State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China
| | - Q Ye
- College of Information Science and Technology, Beijing Normal University, Beijing, China
| | - X Guo
- College of Information Science and Technology, Beijing Normal University, Beijing, China; State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China.
| | | |
Collapse
|
|
14
|
Classifying dementia using local binary patterns from different regions in magnetic resonance images. Int J Biomed Imaging 2015; 2015:572567. [PMID: 25873943 PMCID: PMC4385607 DOI: 10.1155/2015/572567] [Citation(s) in RCA: 25] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2014] [Revised: 02/26/2015] [Accepted: 03/02/2015] [Indexed: 01/10/2023] Open
Abstract
Dementia is an evolving challenge in society, and no disease-modifying treatment exists. Diagnosis can be demanding and MR imaging may aid as a noninvasive method to increase prediction accuracy. We explored the use of 2D local binary pattern (LBP) extracted from FLAIR and T1 MR images of the brain combined with a Random Forest classifier in an attempt to discern patients with Alzheimer's disease (AD), Lewy body dementia (LBD), and normal controls (NC). Analysis was conducted in areas with white matter lesions (WML) and all of white matter (WM). Results from 10-fold nested cross validation are reported as mean accuracy, precision, and recall with standard deviation in brackets. The best result we achieved was in the two-class problem NC versus AD + LBD with total accuracy of 0.98 (0.04). In the three-class problem AD versus LBD versus NC and the two-class problem AD versus LBD, we achieved 0.87 (0.08) and 0.74 (0.16), respectively. The performance using 3DT1 images was notably better than when using FLAIR images. The results from the WM region gave similar results as in the WML region. Our study demonstrates that LBP texture analysis in brain MR images can be successfully used for computer based dementia diagnosis.
Collapse
|