Multimodal MRI-Based Classification of Trauma Survivors with and without Post-Traumatic Stress Disorder.
ABSTRACT: Post-traumatic stress disorder (PTSD) is a debilitating psychiatric disorder. It can be difficult to discern the symptoms of PTSD and obtain an accurate diagnosis. Different magnetic resonance imaging (MRI) modalities focus on different aspects, which may provide complementary information for PTSD discrimination. However, none of the published studies assessed the diagnostic potential of multimodal MRI in identifying individuals with and without PTSD. In the current study, we investigated whether the complementary information conveyed by multimodal MRI scans could be combined to improve PTSD classification performance. Structural and resting-state functional MRI (rs-fMRI) scans were conducted on 17 PTSD patients, 20 trauma-exposed controls without PTSD (TEC) and 20 non-traumatized healthy controls (HC). Gray matter volume (GMV), amplitude of low-frequency fluctuations (ALFF), and regional homogeneity were extracted as classification features, and in order to integrate the information of structural and functional MRI data, the extracted features were combined by a multi-kernel combination strategy. Then a support vector machine (SVM) classifier was trained to distinguish the subjects at individual level. The performance of the classifier was evaluated using the leave-one-out cross-validation (LOOCV) method. In the pairwise comparison of PTSD, TEC, and HC groups, classification accuracies obtained by the proposed approach were 2.70, 2.50, and 2.71% higher than the best single feature way, with the accuracies of 89.19, 90.00, and 67.57% for PTSD vs. HC, TEC vs. HC, and PTSD vs. TEC respectively. The proposed approach could improve PTSD identification at individual level. Additionally, it provides preliminary support to develop the multimodal MRI method as a clinical diagnostic aid.
Project description:The early diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI) is very important for treatment research and patient care purposes. Few biomarkers are currently considered in clinical settings, and their use is still optional. The objective of this work was to determine whether multimodal and nonpreviously AD associated features could improve the classification accuracy between AD, MCI, and healthy controls, which may impact future AD biomarkers. For this, Alzheimer's Disease Neuroimaging Initiative database was mined for case-control candidates. At least 652 baseline features extracted from MRI and PET analyses, biological samples, and clinical data up to February 2014 were used. A feature selection methodology that includes a genetic algorithm search coupled to a logistic regression classifier and forward and backward selection strategies was used to explore combinations of features. This generated diagnostic models with sizes ranging from 3 to 8, including well documented AD biomarkers, as well as unexplored image, biochemical, and clinical features. Accuracies of 0.85, 0.79, and 0.80 were achieved for HC-AD, HC-MCI, and MCI-AD classifications, respectively, when evaluated using a blind test set. In conclusion, a set of features provided additional and independent information to well-established AD biomarkers, aiding in the classification of MCI and AD.
Project description:Magnetic resonance imaging (MRI) has been proposed as a source of information for automatic prediction of individual diagnosis in schizophrenia. Optimal integration of data from different MRI modalities is an active area of research aimed at increasing diagnostic accuracy. Based on a sample of 96 patients with schizophrenia and a matched sample of 115 healthy controls that had undergone a single multimodal MRI session, we generated individual brain maps of gray matter vbm, 1back, and 2back levels of activation (nback fMRI), maps of amplitude of low-frequency fluctuations (resting-state fMRI), and maps of weighted global brain connectivity (resting-state fMRI). Four unimodal classifiers (Ridge, Lasso, Random Forests, and Gradient boosting) were applied to these maps to evaluate their classification accuracies. Based on the assignments made by the algorithms on test individuals, we quantified the amount of predictive information shared between maps (what we call redundancy analysis). Finally, we explored the added accuracy provided by a set of multimodal strategies that included post-classification integration based on probabilities, two-step sequential integration, and voxel-level multimodal integration through one-dimensional-convolutional neural networks (1D-CNNs). All four unimodal classifiers showed the highest test accuracies with the 2back maps (80% on average) achieving a maximum of 84% with the Lasso. Redundancy levels between brain maps were generally low (overall mean redundancy score of 0.14 in a 0-1 range), indicating that each brain map contained differential predictive information. The highest multimodal accuracy was delivered by the two-step Ridge classifier (87%) followed by the Ridge maximum and mean probability classifiers (both with 85% accuracy) and by the 1D-CNN, which achieved the same accuracy as the best unimodal classifier (84%). From these results, we conclude that from all MRI modalities evaluated task-based fMRI may be the best unimodal diagnostic option in schizophrenia. Low redundancy values point to ample potential for accuracy improvements through multimodal integration, with the two-step Ridge emerging as a suitable strategy.
Project description:In posttraumatic stress disorder (PTSD), functional connectivity (FC) between the thalamus and other brain areas has yet to be comprehensively investigated. The present study explored resting state FC (rsFC) of thalamus and its associations with trauma-related features. The included subjects were North Korean refugees with PTSD (n?=?23), trauma-exposed North Korean refugees without PTSD (trauma-exposed control [TEC] group, n?=?22), and South Korean healthy controls (HCs) without traumatic experiences (HC group, n?=?40). All participants underwent psychiatric evaluation and functional magnetic resonance imaging (fMRI) procedures using the bilateral thalamus as seeds. In the TEC group, the negative rsFC between each thalamus and its contralateral postcentral cortex was stronger relative to the PTSD and HC groups, while positive rsFC between the left thalamus and left precentral cortex was stronger in the HC group compared to the PTSD and TEC groups. Thalamo-postcentral rsFC was positively correlated with the CAPS total score in the TEC group, and with the number of traumatic experiences in the PTSD group. The present study identified the difference of thalamic rsFC alterations among traumatized refugees and HCs. Negative rsFC between the thalamus and somatosensory cortices might be compensatory changes after multiple traumatic events in refugees.
Project description:Magnetic resonance imaging (MRI) methods have been used to detect cerebral anatomical distinction between obsessive-compulsive disorder (OCD) patients and healthy controls (HC). Machine learning approach allows for the possibility of discriminating patients on the individual level. However, few studies have used this automatic technique based on multiple modalities to identify potential biomarkers of OCD. High-resolution structural MRI and diffusion tensor imaging (DTI) data were acquired from 48 OCD patients and 45 well-matched HC. Gray matter volume (GMV), white matter volume (WMV), fractional anisotropy (FA), and mean diffusivity (MD) were extracted as four features were examined using support vector machine (SVM). Ten brain regions of each feature contributed most to the classification were also estimated. Using different algorithms, the classifier achieved accuracies of 72.08, 61.29, 80.65, and 77.42% for GMV, WMV, FA, and MD, respectively. The most discriminative gray matter regions that contributed to the classification were mainly distributed in the orbitofronto-striatal "affective" circuit, the dorsolateral, prefronto-striatal "executive" circuit and the cerebellum. For WMV feature and the two feature sets of DTI, the shared regions contributed the most to the discrimination mainly included the uncinate fasciculus, the cingulum in the hippocampus, corticospinal tract, as well as cerebellar peduncle. Based on whole-brain volumetry and DTI images, SVM algorithm revealed high accuracies for distinguishing OCD patients from healthy subjects at the individual level. Computer-aided method is capable of providing accurate diagnostic information and might provide a new perspective for clinical diagnosis of OCD.
Project description:Graphical, voxel, and region-based analysis has become a popular approach to studying neurodegenerative disorders such as Alzheimer's disease (AD) and its prodromal stage [mild cognitive impairment (MCI)]. These methods have been used previously for classification or discrimination of AD in subjects in a prodromal stage called stable MCI (MCIs), which does not convert to AD but remains stable over a period of time, and converting MCI (MCIc), which converts to AD, but the results reported across similar studies are often inconsistent. Furthermore, the classification accuracy for MCIs vs. MCIc is limited. In this study, we propose combining different neuroimaging modalities (sMRI, FDG-PET, AV45-PET, DTI, and rs-fMRI) with the apolipoprotein-E genotype to form a multimodal system for the discrimination of AD, and to increase the classification accuracy. Initially, we used two well-known analyses to extract features from each neuroimage for the discrimination of AD: whole-brain parcelation analysis (or region-based analysis), and voxel-wise analysis (or voxel-based morphometry). We also investigated graphical analysis (nodal and group) for all six binary classification groups (AD vs. HC, MCIs vs. MCIc, AD vs. MCIc, AD vs. MCIs, HC vs. MCIc, and HC vs. MCIs). Data for a total of 129 subjects (33 AD, 30 MCIs, 31 MCIc, and 35 HCs) for each imaging modality were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) homepage. These data also include two APOE genotype data points for the subjects. Moreover, we used the 2-mm AICHA atlas with the NiftyReg registration toolbox to extract 384 brain regions from each PET (FDG and AV45) and sMRI image. For the rs-fMRI images, we used the DPARSF toolbox in MATLAB for the automatic extraction of data and the results for REHO, ALFF, and fALFF. We also used the pyClusterROI script for the automatic parcelation of each rs-fMRI image into 200 brain regions. For the DTI images, we used the FSL (Version 6.0) toolbox for the extraction of fractional anisotropy (FA) images to calculate a tract-based spatial statistic. Moreover, we used the PANDA toolbox to obtain 50 white-matter-region-parcellated FA images on the basis of the 2-mm JHU-ICBM-labeled template atlas. To integrate the different modalities and different complementary information into one form, and to optimize the classifier, we used the multiple kernel learning (MKL) framework. The obtained results indicated that our multimodal approach yields a significant improvement in accuracy over any single modality alone. The areas under the curve obtained by the proposed method were 97.78, 96.94, 95.56, 96.25, 96.67, and 96.59% for AD vs. HC, MCIs vs. MCIc, AD vs. MCIc, AD vs. MCIs, HC vs. MCIc, and HC vs. MCIs binary classification, respectively. Our proposed multimodal method improved the classification result for MCIs vs. MCIc groups compared with the unimodal classification results. Our study found that the (left/right) precentral region was present in all six binary classification groups (this region can be considered the most significant region). Furthermore, using nodal network topology, we found that FDG, AV45-PET, and rs-fMRI were the most important neuroimages, and showed many affected regions relative to other modalities. We also compared our results with recently published results.
Project description:Different modalities such as structural MRI, FDG-PET, and CSF have complementary information, which is likely to be very useful for diagnosis of AD and MCI. Therefore, it is possible to develop a more effective and accurate AD/MCI automatic diagnosis method by integrating complementary information of different modalities. In this paper, we propose multi-modal sparse hierarchical extreme leaning machine (MSH-ELM). We used volume and mean intensity extracted from 93 regions of interest (ROIs) as features of MRI and FDG-PET, respectively, and used p-tau, t-tau, and A?42 as CSF features. In detail, high-level representation was individually extracted from each of MRI, FDG-PET, and CSF using a stacked sparse extreme learning machine auto-encoder (sELM-AE). Then, another stacked sELM-AE was devised to acquire a joint hierarchical feature representation by fusing the high-level representations obtained from each modality. Finally, we classified joint hierarchical feature representation using a kernel-based extreme learning machine (KELM). The results of MSH-ELM were compared with those of conventional ELM, single kernel support vector machine (SK-SVM), multiple kernel support vector machine (MK-SVM) and stacked auto-encoder (SAE). Performance was evaluated through 10-fold cross-validation. In the classification of AD vs. HC and MCI vs. HC problem, the proposed MSH-ELM method showed mean balanced accuracies of 96.10% and 86.46%, respectively, which is much better than those of competing methods. In summary, the proposed algorithm exhibits consistently better performance than SK-SVM, ELM, MK-SVM and SAE in the two binary classification problems (AD vs. HC and MCI vs. HC).
Project description:Recently, there have been great interests for computer-aided diagnosis of Alzheimer's disease (AD) and its prodromal stage, mild cognitive impairment (MCI). Unlike the previous methods that considered simple low-level features such as gray matter tissue volumes from MRI, and mean signal intensities from PET, in this paper, we propose a deep learning-based latent feature representation with a stacked auto-encoder (SAE). We believe that there exist latent non-linear complicated patterns inherent in the low-level features such as relations among features. Combining the latent information with the original features helps build a robust model in AD/MCI classification, with high diagnostic accuracy. Furthermore, thanks to the unsupervised characteristic of the pre-training in deep learning, we can benefit from the target-unrelated samples to initialize parameters of SAE, thus finding optimal parameters in fine-tuning with the target-related samples, and further enhancing the classification performances across four binary classification problems: AD vs. healthy normal control (HC), MCI vs. HC, AD vs. MCI, and MCI converter (MCI-C) vs. MCI non-converter (MCI-NC). In our experiments on ADNI dataset, we validated the effectiveness of the proposed method, showing the accuracies of 98.8, 90.7, 83.7, and 83.3?% for AD/HC, MCI/HC, AD/MCI, and MCI-C/MCI-NC classification, respectively. We believe that deep learning can shed new light on the neuroimaging data analysis, and our work presented the applicability of this method to brain disease diagnosis.
Project description:Accurate, reliable prediction of risk for Alzheimer's disease (AD) is essential for early, disease-modifying therapeutics. Multimodal MRI, such as structural and diffusion MRI, is likely to contain complementary information of neurodegenerative processes in AD. Here we tested the utility of the multimodal MRI (T1-weighted structure and diffusion MRI), combined with high-throughput brain phenotyping-morphometry and structural connectomics-and machine learning, as a diagnostic tool for AD. We used, firstly, a clinical cohort at a dementia clinic (National Health Insurance Service-Ilsan Hospital [NHIS-IH]; N = 211; 110 AD, 64 mild cognitive impairment [MCI], and 37 cognitively normal with subjective memory complaints [SMC]) to test the diagnostic models; and, secondly, Alzheimer's Disease Neuroimaging Initiative (ADNI)-2 to test the generalizability. Our machine learning models trained on the morphometric and connectome estimates (number of features = 34,646) showed optimal classification accuracy (AD/SMC: 97% accuracy, MCI/SMC: 83% accuracy; AD/MCI: 97% accuracy) in NHIS-IH cohort, outperforming a benchmark model (FLAIR-based white matter hyperintensity volumes). In ADNI-2 data, the combined connectome and morphometry model showed similar or superior accuracies (AD/HC: 96%; MCI/HC: 70%; AD/MCI: 75% accuracy) compared with the CSF biomarker model (t-tau, p-tau, and Amyloid β, and ratios). In predicting MCI to AD progression in a smaller cohort of ADNI-2 (n = 60), the morphometry model showed similar performance with 69% accuracy compared with CSF biomarker model with 70% accuracy. Our comparisons of the classifiers trained on structural MRI, diffusion MRI, FLAIR, and CSF biomarkers showed the promising utility of the white matter structural connectomes in classifying AD and MCI in addition to the widely used structural MRI-based morphometry, when combined with machine learning.
Project description:The abnormal brain activity is a pivotal condition for the occurrence of posttraumatic stress disorder. However, the dynamic time features of intrinsic brain activities still remain unclearly in PTSD patients. Our study aims to perform the resting-state lag analysis (RS-LA) method to explore potential propagated patterns of intrinsic brain activities in PTSD patients. We recruited 27 drug-naive patients with PTSD, 33 trauma-exposed controls (TEC), and 30 demographically matched healthy controls (HC) in the final data statistics. Both RS-LA and conventional voxel-wise functional connectivity strength (FCS) methods were employed on the same dataset. Then, Spearman correlation analysis was conducted on time latency values of those abnormal brain regions with the clinical assessments. Compared with HC group, the time latency patterns of PTSD patients significantly shifted toward later in posterior cingulate cortex/precuneus, middle prefrontal cortex, right angular, and left pre- and post-central cortex. The TEC group tended to have similar time latency in right angular. Additionally, significant time latency in right STG was found in PTSD group relative to TEC group. Spearman correlation analysis revealed that the time latency value of mPFC negatively correlated to the PTSD checklist-civilian version scores (PCL_C) in PTSD group (r = -0.578, P < 0.05). Furthermore, group differences map of FCS exhibited parts of overlapping areas with that of RS-LA, however, less specificity in detecting PTSD patients. In conclusion, apparent alterations of time latency were observed in DMN and primary sensorimotor areas of PTSD patients. These findings provide us with new evidence to explain the neural pathophysiology contributing to PTSD.
Project description:Alzheimer's disease (AD) is one of the most common neurodegenerative illnesses (dementia) among the elderly. Recently, researchers have developed a new method for the instinctive analysis of AD based on machine learning and its subfield, deep learning. Recent state-of-the-art techniques consider multimodal diagnosis, which has been shown to achieve high accuracy compared to a unimodal prognosis. Furthermore, many studies have used structural magnetic resonance imaging (MRI) to measure brain volumes and the volume of subregions, as well as to search for diffuse changes in white/gray matter in the brain. In this study, T1-weighted structural MRI was used for the early classification of AD. MRI results in high-intensity visible features, making preprocessing and segmentation easy. To use this image modality, we acquired four types of datasets from each dataset's server. In this work, we downloaded 326 subjects from the National Research Center for Dementia homepage, 123 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) homepage, 121 subjects from the Alzheimer's Disease Repository Without Borders homepage, and 131 subjects from the National Alzheimer's Coordinating Center homepage. In our experiment, we used the multiatlas label propagation with expectation-maximization-based refinement segmentation method. We segmented the images into 138 anatomical morphometry images (in which 40 features belonged to subcortical volumes and the remaining 98 features belonged to cortical thickness). The entire dataset was split into a 70?:?30 (training and testing) ratio before classifying the data. A principal component analysis was used for dimensionality reduction. Then, the support vector machine radial basis function classifier was used for classification between two groups-AD versus health control (HC) and early mild cognitive impairment (MCI) (EMCI) versus late MCI (LMCI). The proposed method performed very well for all four types of dataset. For instance, for the AD versus HC group, the classifier achieved an area under curve (AUC) of more than 89% for each dataset. For the EMCI versus LMCI group, the classifier achieved an AUC of more than 80% for every dataset. Moreover, we also calculated Cohen kappa and Jaccard index statistical values for all datasets to evaluate the classification reliability. Finally, we compared our results with those of recently published state-of-the-art methods.