Evaluation of Functional Decline in Alzheimer's Dementia Using 3D Deep Learning and Group ICA for rs-fMRI Measurements.
ABSTRACT: Purpose: To perform automatic assessment of dementia severity using a deep learning framework applied to resting-state functional magnetic resonance imaging (rs-fMRI) data. Method: We divided 133 Alzheimer's disease (AD) patients with clinical dementia rating (CDR) scores from 0.5 to 3 into two groups based on dementia severity; the groups with very mild/mild (CDR: 0.5-1) and moderate to severe (CDR: 2-3) dementia consisted of 77 and 56 subjects, respectively. We used rs-fMRI to extract functional connectivity features, calculated using independent component analysis (ICA), and performed automated severity classification with three-dimensional convolutional neural networks (3D-CNNs) based on deep learning. Results: The mean balanced classification accuracy was 0.923 ± 0.042 (p < 0.001) with a specificity of 0.946 ± 0.019 and sensitivity of 0.896 ± 0.077. The rs-fMRI data indicated that the medial frontal, sensorimotor, executive control, dorsal attention, and visual related networks mainly correlated with dementia severity. Conclusions: Our CDR-based novel classification using rs-fMRI is an acceptable objective severity indicator. In the absence of trained neuropsychologists, dementia severity can be objectively and accurately classified using a 3D-deep learning framework with rs-fMRI independent components.
Project description:Resting-state functional magnetic resonance imaging (rs-fMRI) data are 4-dimensional volumes (3-space + 1-time) that have been posited to reflect the underlying mechanisms of information exchange between brain regions, thus making it an attractive modality to develop diagnostic biomarkers of brain dysfunction. The enormous success of deep learning in computer vision has sparked recent interest in applying deep learning in neuroimaging. But the dimensionality of rs-fMRI data is too high (~20 M), making it difficult to meaningfully process the data in its raw form for deep learning experiments. It is currently not clear how the data should be engineered to optimally extract the time information, and whether combining different representations of time could provide better results. In this paper, we explored various transformations that retain the full spatial resolution by summarizing the temporal dimension of the rs-fMRI data, therefore making it possible to train a full three-dimensional convolutional neural network (3D-CNN) even on a moderately sized [~2,000 from Autism Brain Imaging Data Exchange (ABIDE)-I and II] data set. These transformations summarize the activity in each voxel of the rs-fMRI or that of the voxel and its neighbors to a single number. For each brain volume, we calculated regional homogeneity, the amplitude of low-frequency fluctuations, the fractional amplitude of low-frequency fluctuations, degree centrality, eigenvector centrality, local functional connectivity density, entropy, voxel-mirrored homotopic connectivity, and auto-correlation lag. We trained the 3D-CNN on a publically available autism dataset to classify the rs-fMRI images as being from individuals with autism spectrum disorder (ASD) or from healthy controls (CON) at an individual level. We attained results competitive on this task for a combined ABIDE-I and II datasets of ~66%. When all summary measures were combined the result was still only as good as that of the best single measure which was regional homogeneity (ReHo). In addition, we also applied the support vector machine (SVM) algorithm on the same dataset and achieved comparable results, suggesting that 3D-CNNs could not learn additional information from these temporal transformations that were more useful to differentiate ASD from CON.
Project description:The specificity and sensitivity of resting state functional MRI (rs-fMRI) measurements depend on preprocessing choices, such as the parcellation scheme used to define regions of interest (ROIs). In this study, we critically evaluate the effect of brain parcellations on machine learning models applied to rs-fMRI data. Our experiments reveal an intriguing trend: On average, models with stochastic parcellations consistently perform as well as models with widely used atlases at the same spatial scale. We thus propose an ensemble learning strategy to combine the predictions from models trained on connectivity data extracted using different (e.g., stochastic) parcellations. We further present an implementation of our ensemble learning strategy with a novel 3D Convolutional Neural Network (CNN) approach. The proposed CNN approach takes advantage of the full-resolution 3D spatial structure of rs-fMRI data and fits non-linear predictive models. Our ensemble CNN framework overcomes the limitations of traditional machine learning models for connectomes that often rely on region-based summary statistics and/or linear models. We showcase our approach on a classification (autism patients versus healthy controls) and a regression problem (prediction of subject's age), and report promising results.
Project description:BACKGROUND:Recently, deep learning technologies have rapidly expanded into medical image analysis, including both disease detection and classification. As far as we know, migraine is a disabling and common neurological disorder, typically characterized by unilateral, throbbing and pulsating headaches. Unfortunately, a large number of migraineurs do not receive the accurate diagnosis when using traditional diagnostic criteria based on the guidelines of the International Headache Society. As such, there is substantial interest in developing automated methods to assist in the diagnosis of migraine. METHODS:To the best of our knowledge, no studies have evaluated the potential of deep learning technologies in assisting with the classification of migraine patients. Here, we used deep learning methods in combination with three functional measures (the amplitude of low-frequency fluctuations, regional homogeneity and regional functional correlation strength) based on rs-fMRI data to distinguish not only between migraineurs and healthy controls, but also between the two subtypes of migraine. We employed 21 migraine patients without aura, 15 migraineurs with aura, and 28 healthy controls. RESULTS:Compared with the traditional support vector machine classifier, which has an accuracy of 83.67%, our Inception module-based convolutional neural network approach showed a significant improvement in classification output (over 86.18%). Our data also indicate that the Inception module-based CNN performs better than the AlexNet-based CNN (Inception module-based CNN reached an accuracy of 99.25%). Finally, we also found that regional functional correlation strength (RFCS) could be regarded as the optimum input out of the three indices (ALFF, ReHo, RFCS). CONCLUSIONS:Overall, our study shows that combining the three functional measures of rs-fMRI with deep learning classification is a powerful method to distinguish between migraineurs and healthy individuals. Our data also highlight that deep learning-based frameworks could be used to develop more complicated models or systems to aid in clinical decision making in the future.
Project description:From molecular mechanisms to global brain networks, atypical fluctuations are the hallmark of neurodegeneration. Yet, traditional fMRI research on resting-state networks (RSNs) has favored static and average connectivity methods, which by overlooking the fluctuation dynamics triggered by neurodegeneration, have yielded inconsistent results. The present multicenter study introduces a data-driven machine learning pipeline based on dynamic connectivity fluctuation analysis (DCFA) on RS-fMRI data from 300 participants belonging to three groups: behavioral variant frontotemporal dementia (bvFTD) patients, Alzheimer's disease (AD) patients, and healthy controls. We considered non-linear oscillatory patterns across combined and individual resting-state networks (RSNs), namely: the salience network (SN), mostly affected in bvFTD; the default mode network (DMN), mostly affected in AD; the executive network (EN), partially compromised in both conditions; the motor network (MN); and the visual network (VN). These RSNs were entered as features for dementia classification using a recent robust machine learning approach (a Bayesian hyperparameter tuned Gradient Boosting Machines (GBM) algorithm), across four independent datasets with different MR scanners and recording parameters. The machine learning classification accuracy analysis revealed a systematic and unique tailored architecture of RSN disruption. The classification accuracy ranking showed that the most affected networks for bvFTD were the SN + EN network pair (mean accuracy = 86.43%, AUC = 0.91, sensitivity = 86.45%, specificity = 87.54%); for AD, the DMN + EN network pair (mean accuracy = 86.63%, AUC = 0.89, sensitivity = 88.37%, specificity = 84.62%); and for the bvFTD vs. AD classification, the DMN + SN network pair (mean accuracy = 82.67%, AUC = 0.86, sensitivity = 81.27%, specificity = 83.01%). Moreover, the DFCA classification systematically outperformed canonical connectivity approaches (including both static and linear dynamic connectivity). Our findings suggest that non-linear dynamical fluctuations surpass two traditional seed-based functional connectivity approaches and provide a pathophysiological characterization of global brain networks in neurodegenerative conditions (AD and bvFTD) across multicenter data.
Project description:Among dementia-like diseases, Alzheimer disease (AD) and vascular dementia (VD) are two of the most frequent. AD and VD may share multiple neurological symptoms that may lead to controversial diagnoses when using conventional clinical and MRI criteria. Therefore, other approaches are needed to overcome this issue. Machine learning (ML) combined with magnetic resonance imaging (MRI) has been shown to improve the diagnostic accuracy of several neurodegenerative diseases, including dementia. To this end, in this study, we investigated, first, whether different kinds of ML algorithms, combined with advanced MRI features, could be supportive in classifying VD from AD and, second, whether the developed approach might help in predicting the prevalent disease in subjects with an unclear profile of AD or VD. Three ML categories of algorithms were tested: artificial neural network (ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS). Multiple regional metrics from resting-state fMRI (rs-fMRI) and diffusion tensor imaging (DTI) of 60 subjects (33 AD, 27 VD) were used as input features to train the algorithms and find the best feature pattern to classify VD from AD. We then used the identified VD-AD discriminant feature pattern as input for the most performant ML algorithm to predict the disease prevalence in 15 dementia patients with a "mixed VD-AD dementia" (MXD) clinical profile using their baseline MRI data. ML predictions were compared with the diagnosis evidence from a 3-year clinical follow-up. ANFIS emerged as the most efficient algorithm in discriminating AD from VD, reaching a classification accuracy greater than 84% using a small feature pattern. Moreover, ANFIS showed improved classification accuracy when trained with a multimodal input feature data set (e.g., DTI + rs-fMRI metrics) rather than a unimodal feature data set. When applying the best discriminant pattern to the MXD group, ANFIS achieved a correct prediction rate of 77.33%. Overall, results showed that our approach has a high discriminant power to classify AD and VD profiles. Moreover, the same approach also showed potential in predicting earlier the prevalent underlying disease in dementia patients whose clinical profile is uncertain between AD and VD, therefore suggesting its usefulness in supporting physicians' diagnostic evaluations.
Project description:BACKGROUND:Few studies have examined how dementia and comorbidities may interact to affect healthcare expenditures. OBJECTIVE:To examine whether effects of dementia severity on Medicare expenditures differed for individuals with different levels of comorbidities. METHODS:Data are drawn from the Washington Heights-Inwood Columbia Aging Project (WHICAP). Comprehensive clinical assessments of dementia severity were systematically carried out at ?18 month intervals. Dementia severity was measured by Clinical Dementia Rating (CDR). Comorbidities were measured by a modified Elixhauser comorbidities index. Generalized linear models examined effects of dementia severity, comorbidities, and their interactions on Medicare expenditures (1999-2010). RESULTS:At baseline, 1,280 subjects were dementia free (CDR?=?0, 66.4%), 490 had very mild dementia (CDR?=?0.5, 25.4%), 108 had mild dementia (CDR?=?1, 5.6%), and 49 had moderate/severe dementia (CDR?=?2/3, 2.5%). Average annual Medicare expenditures for individuals with moderate/severe dementia were more than twice as high as those who were dementia free (CDR?=?0: $9,108, CDR?=?0.5/1: $11,664, CDR?2: $19,604, p?<?0.01). Expenditures were approximately 10 times higher among those with?3 comorbidities than among those with no comorbidities ($2,612 for those with no comorbidities, to $6,109 for those with 1, $10,656 for those with 2, and $30,244 for those with?3 comorbidities, p?<?0.001). Dementia severity was associated with higher expenditures, but comorbidities were the most important predictor of expenditures. We did not find strong interaction effects between number of comorbidities and dementia severity. CONCLUSIONS:Increasing dementia severity and higher comorbidities are associated with higher Medicare expenditures. Care of individuals with dementia should focus on management of comorbidities.
Project description:fMRI data decomposition techniques have advanced significantly from shallow models such as Independent Component Analysis (ICA) and Sparse Coding and Dictionary Learning (SCDL) to deep learning models such Deep Belief Networks (DBN) and Convolutional Autoencoder (DCAE). However, interpretations of those decomposed networks are still open questions due to the lack of functional brain atlases, no correspondence across decomposed or reconstructed networks across different subjects, and significant individual variabilities. Recent studies showed that deep learning, especially deep convolutional neural networks (CNN), has extraordinary ability of accommodating spatial object patterns, e.g., our recent works using 3D CNN for fMRI-derived network classifications achieved high accuracy with a remarkable tolerance for mistakenly labelled training brain networks. However, the training data preparation is one of the biggest obstacles in these supervised deep learning models for functional brain network map recognitions, since manual labelling requires tedious and time-consuming labours which will sometimes even introduce label mistakes. Especially for mapping functional networks in large scale datasets such as hundreds of thousands of brain networks used in this paper, the manual labelling method will become almost infeasible. In response, in this work, we tackled both the network recognition and training data labelling tasks by proposing a new iteratively optimized deep learning CNN (IO-CNN) framework with an automatic weak label initialization, which enables the functional brain networks recognition task to a fully automatic large-scale classification procedure. Our extensive experiments based on ABIDE-II 1099 brains' fMRI data showed the great promise of our IO-CNN framework.
Project description:The ε4 allele of the Apolipoprotein E gene (APOE-ε4) is a potent genetic risk factor for sporadic Alzheimer's disease (AD). Amnestic mild cognitive impairment (aMCI) is an intermediate state between normal cognitive aging and dementia, which is easy to convert to AD dementia. It is an urgent problem in the field of cognitive neuroscience to reveal the conversion of aMCI-ε4 to AD. Based on our preliminary work, we will study the neuroimaging features in the special group of aMCI-ε4 with multi-modality magnetic resonance imaging (structural MRI, resting state-fMRI and diffusion tensor imaging) longitudinally.In this study, 200 right-handed subjects who are diagnosed as aMCI with APOE-ε4 will be recruited at the memory clinic of the Neurology Department, XuanWu Hospital, Capital Medical University, Beijing, China. All subjects will undergo the neuroimaging and neuropsychological evaluation at a 1 year-interval for 3 years. The primary outcome measures are 1) Microstructural alterations revealed with multimodal MRI scans including structure MRI (sMRI), resting state functional MRI (rs-fMRI), diffusion tensor imaging (DTI); 2) neuropsychological evaluation, including the World Health Organization-University of California-LosAngeles Auditory Verbal Learning Test (WHO-UCLA AVLT), Addenbrook's cognitive examination-revised (ACE-R), mini-mental state examination (MMSE), Montreal Cognitive Assessment (MoCA), Clinical Dementia Rating scale (CDR).This study is to find out the neuroimaging biomarker and the changing laws of the marker during the progress of aMCI-ε4 to AD, and the final purpose is to provide scientific evidence for new prevention, diagnosis and treatment of AD.This study has been registered to ClinicalTrials.gov (NCT02225964, https://www.clinicaltrials.gov/ ) in August 24, 2014.
Project description:High-grade gliomas are the most aggressive malignant brain tumors. Accurate pre-operative prognosis for this cohort can lead to better treatment planning. Conventional survival prediction based on clinical information is subjective and could be inaccurate. Recent radiomics studies have shown better prognosis by using carefully-engineered image features from magnetic resonance images (MRI). However, feature engineering is usually time consuming, laborious and subjective. Most importantly, the engineered features cannot effectively encode other predictive but implicit information provided by multi-modal neuroimages. We propose a two-stage learning-based method to predict the overall survival (OS) time of high-grade gliomas patient. At the first stage, we adopt deep learning, a recently dominant technique of artificial intelligence, to automatically extract implicit and high-level features from multi-modal, multi-channel preoperative MRI such that the features are competent of predicting survival time. Specifically, we utilize not only contrast-enhanced T1 MRI, but also diffusion tensor imaging (DTI) and resting-state functional MRI (rs-fMRI), for computing multiple metric maps (including various diffusivity metric maps derived from DTI, and also the frequency-specific brain fluctuation amplitude maps and local functional connectivity anisotropy-related metric maps derived from rs-fMRI) from 68 high-grade glioma patients with different survival time. We propose a multi-channel architecture of 3D convolutional neural networks (CNNs) for deep learning upon those metric maps, from which high-level predictive features are extracted for each individual patch of these maps. At the second stage, those deeply learned features along with the pivotal limited demographic and tumor-related features (such as age, tumor size and histological type) are fed into a support vector machine (SVM) to generate the final prediction result (i.e., long or short overall survival time). The experimental results demonstrate that this multi-model, multi-channel deep survival prediction framework achieves an accuracy of 90.66%, outperforming all the competing methods. This study indicates highly demanded effectiveness on prognosis of deep learning technique in neuro-oncological applications for better individualized treatment planning towards precision medicine.
Project description:OBJECTIVES:Autism spectrum disorders (ASD) are diagnosed based on early-manifesting clinical symptoms, including markedly impaired social communication. We assessed the viability of resting-state functional MRI (rs-fMRI) connectivity measures as diagnostic biomarkers for ASD and investigated which connectivity features are predictive of a diagnosis. METHODS:Rs-fMRI scans from 59 high functioning males with ASD and 59 age- and IQ-matched typically developing (TD) males were used to build a series of machine learning classifiers. Classification features were obtained using 3 sets of brain regions. Another set of classifiers was built from participants' scores on behavioral metrics. An additional age and IQ-matched cohort of 178 individuals (89 ASD; 89 TD) from the Autism Brain Imaging Data Exchange (ABIDE) open-access dataset (http://fcon_1000.projects.nitrc.org/indi/abide/) were included for replication. RESULTS:High classification accuracy was achieved through several rs-fMRI methods (peak accuracy 76.67%). However, classification via behavioral measures consistently surpassed rs-fMRI classifiers (peak accuracy 95.19%). The class probability estimates, P(ASD|fMRI data), from brain-based classifiers significantly correlated with scores on a measure of social functioning, the Social Responsiveness Scale (SRS), as did the most informative features from 2 of the 3 sets of brain-based features. The most informative connections predominantly originated from regions strongly associated with social functioning. CONCLUSIONS:While individuals can be classified as having ASD with statistically significant accuracy from their rs-fMRI scans alone, this method falls short of biomarker standards. Classification methods provided further evidence that ASD functional connectivity is characterized by dysfunction of large-scale functional networks, particularly those involved in social information processing.