Hierarchical based classification method based on fusion of Gaussian map descriptors for Alzheimer diagnosis using T1-weighted magnetic resonance imaging.

Alzheimer's disease (AD) is considered one of the most spouting elderly diseases. In 2015, AD is reported the US's sixth cause of death. Substantially, non-invasive imaging is widely employed to provide biomarkers supporting AD screening, diagnosis, and progression. In this study, Gaussian descriptors-based features are proposed to be efficient new biomarkers using Magnetic Resonance Imaging (MRI) T1-weighted images to differentiate between Alzheimer's disease (AD), Mild Cognitive Impairment (MCI), and Normal controls (NC). Several Gaussian map-based features are extracted such as Gaussian shape operator, Gaussian curvature, and mean curvature. The aforementioned features are then introduced to the Support Vector Machine (SVM). They were, first, calculated separately for the Hippocampus and Amygdala. Followed by the fusion of the features. Moreover, Fusion of the regions before feature extraction was also employed. Alzheimer's disease Neuroimaging Initiative (ADNI) dataset, formed of 45, 55, and 65 cases for AD, MCI, and NC respectively, is appointed in this study. The shape operator feature outperformed the other features, with 74.6%, and 98.9% accuracy in the case of normal vs. abnormal, and AD vs. MCI classification respectively.

Correlation transfer function analysis as a biomarker for Alzheimer brain plasticity using longitudinal resting-state fMRI data.

Neural plasticity is the ability of the brain to alter itself functionally and structurally as a result of its experience. However, longitudinal changes in functional connectivity of the brain are still unrevealed in Alzheimer's disease (AD). This study aims to discover the significant connections (SCs) between brain regions for AD stages longitudinally using correlation transfer function (CorrTF) as a new biomarker for the disease progression. The dataset consists of: 29 normal controls (NC), and 23, 24, and 23 for early, late mild cognitive impairments (EMCI, LMCI), and ADs, respectively, along three distant visits. The brain was divided into 116 regions using the automated anatomical labeling atlas, where the intensity time series is calculated, and the CorrTF connections are extracted for each region. Finally, the standard t-test and ANOVA test were employed to investigate the SCs for each subject's visit. No SCs, along three visits, were found For NC subjects. The most SCs were mainly directed from cerebellum in case of EMCI and LMCI. Furthermore, the hippocampus connectivity increased in LMCI compared to EMCI whereas missed in AD. Additionally, the patterns of longitudinal changes among the different AD stages compared to Pearson Correlation were similar, for SMC, VC, DMN, and Cereb networks, while differed for EAN and SN networks. Our findings define how brain changes over time, which could help detect functional changes linked to each AD stage and better understand the disease behavior.

Alzheimer disease stages identification based on correlation transfer function system using resting-state functional magnetic resonance imaging.

Alzheimer's disease (AD) affects the quality of life as it causes; memory loss, difficulty in thinking, learning, and performing familiar tasks. Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used to investigate and analyze different brain regions for AD identification. This study investigates the effectiveness of using correlated transfer function (CorrTF) as a new biomarker to extract the essential features from rs-fMRI, along with support vector machine (SVM) ordered hierarchically, in order to distinguish between the different AD stages. Additionally, we explored the regions, showing significant changes based on the CorrTF extracted features' strength among different AD stages. First, the process was initialized by applying the preprocessing on rs-fMRI data samples to reduce noise and retain the essential information. Then, the automated anatomical labeling (AAL) atlas was employed to divide the brain into 116 regions, where the intensity time series was calculated, and the CorrTF features were extracted for each region. The proposed framework employed the SVM classifier in two different methodologies, hierarchical and flat multi-classification schemes, to differentiate between the different AD stages for early detection purposes. The ADNI rs-fMRI dataset, employed in this study, consists of 167, 102, 129, and 114 normal, early, late mild cognitive impairment (MCI), and AD subjects, respectively. The proposed schemes achieved an average accuracy of 98.2% and 95.5% for hierarchical and flat multi-classification tasks, respectively, calculated using ten folds cross-validation. Therefore, CorrTF is considered a promising biomarker for AD early-stage identification. Moreover, the significant changes in the strengths of CorrTF connections among the different AD stages can help us identify and explore the affected brain regions and their latent associations during the progression of AD.

Feature and decision-level fusion for schizophrenia detection based on resting-state fMRI data.

Mental disorders, especially schizophrenia, still pose a great challenge for diagnosis in early stages. Recently, computer-aided diagnosis techniques based on resting-state functional magnetic resonance imaging (Rs-fMRI) have been developed to tackle this challenge. In this work, we investigate different decision-level and feature-level fusion schemes for discriminating between schizophrenic and normal subjects. Four types of fMRI features are investigated, namely the regional homogeneity, voxel-mirrored homotopic connectivity, fractional amplitude of low-frequency fluctuations and amplitude of low-frequency fluctuations. Data denoising and preprocessing were first applied, followed by the feature extraction module. Four different feature selection algorithms were applied, and the best discriminative features were selected using the algorithm of feature selection via concave minimization (FSV). Support vector machine classifiers were trained and tested on the COBRE dataset formed of 70 schizophrenic subjects and 70 healthy subjects. The decision-level fusion method outperformed the single-feature-type approaches and achieved a 97.85% accuracy, a 98.33% sensitivity, a 96.83% specificity. Moreover, feature-fusion scheme resulted in a 98.57% accuracy, a 99.71% sensitivity, a 97.66% specificity, and an area under the ROC curve of 0.9984. In general, decision-level and feature-level fusion schemes boosted the performance of schizophrenia detectors based on fMRI features.

Native-resolution myocardial principal Eulerian strain mapping using convolutional neural networks and Tagged Magnetic Resonance Imaging.

BACKGROUND: Assessment of regional myocardial function at native pixel-level resolution can play a crucial role in recognizing the early signs of the decline in regional myocardial function. Extensive data processing in existing techniques limits the effective resolution and accuracy of the generated strain maps. The purpose of this study is to compute myocardial principal strain maps εp1 and εp2 from tagged MRI (tMRI) at the native image resolution using deep-learning local patch convolutional neural network (CNN) models (DeepStrain). METHODS: For network training, validation, and testing, realistic tMRI datasets were generated and consisted of 53,606 cine images simulating the heart, the liver, blood pool, and backgrounds, including ranges of shapes, positions, motion patterns, noise, and strain. In addition, 102 in-vivo image datasets from three healthy subjects, and three Pulmonary Arterial Hypertension patients, were acquired and used to assess the network's in-vivo performance. Four convolutional neural networks were trained for mapping input tagging patterns to corresponding ground-truth principal strains using different cost functions. Strain maps using harmonic phase analysis (HARP) were obtained with various spectral filtering settings for comparison. CNN and HARP strain maps were compared at the pixel level versus the ground-truth and versus the least-loss in-vivo maps using Pearson correlation coefficients (R) and the median error and Inter-Quartile Range (IQR) histograms. RESULTS: CNN-based local patch DeepStrain maps at a phantom resolution of 1.1mm × 1.1 mm and in-vivo resolution of 2.1mm × 1.6 mm were artifact-free with multiple fold improvement with εp1 ground-truth median error of 0.009(0.007) vs. 0.32(0.385) using HARP and εp2 ground-truth error of 0.016(0.021) vs. 0.181(0.08) using HARP. CNN-based strain maps showed substantially higher agreement with the ground-truth maps with correlation coefficients R > 0.91 for εp1 and εp2 compared to R < 0.21 and R < 0.82 for HARP-generated maps, respectively. CONCLUSION: CNN-generated Eulerian strain mapping permits artifact-free visualization of myocardial function at the native image resolution.

Direct pixel to pixel principal strain mapping from tagging MRI using end to end deep convolutional neural network (DeepStrain).

Regional soft tissue mechanical strain offers crucial insights into tissue's mechanical function and vital indicators for different related disorders. Tagging magnetic resonance imaging (tMRI) has been the standard method for assessing the mechanical characteristics of organs such as the heart, the liver, and the brain. However, constructing accurate artifact-free pixelwise strain maps at the native resolution of the tagged images has for decades been a challenging unsolved task. In this work, we developed an end-to-end deep-learning framework for pixel-to-pixel mapping of the two-dimensional Eulerian principal strains [Formula: see text] and [Formula: see text] directly from 1-1 spatial modulation of magnetization (SPAMM) tMRI at native image resolution using convolutional neural network (CNN). Four different deep learning conditional generative adversarial network (cGAN) approaches were examined. Validations were performed using Monte Carlo computational model simulations, and in-vivo datasets, and compared to the harmonic phase (HARP) method, a conventional and validated method for tMRI analysis, with six different filter settings. Principal strain maps of Monte Carlo tMRI simulations with various anatomical, functional, and imaging parameters demonstrate artifact-free solid agreements with the corresponding ground-truth maps. Correlations with the ground-truth strain maps were R = 0.90 and 0.92 for the best-proposed cGAN approach compared to R = 0.12 and 0.73 for the best HARP method for [Formula: see text] and [Formula: see text], respectively. The proposed cGAN approach's error was substantially lower than the error in the best HARP method at all strain ranges. In-vivo results are presented for both healthy subjects and patients with cardiac conditions (Pulmonary Hypertension). Strain maps, obtained directly from their corresponding tagged MR images, depict for the first time anatomical, functional, and temporal details at pixelwise native high resolution with unprecedented clarity. This work demonstrates the feasibility of using the deep learning cGAN for direct myocardial and liver Eulerian strain mapping from tMRI at native image resolution with minimal artifacts.

Alzheimer's disease diagnosis from diffusion tensor images using convolutional neural networks.

Machine learning algorithms are currently being implemented in an escalating manner to classify and/or predict the onset of some neurodegenerative diseases; including Alzheimer's Disease (AD); this could be attributed to the fact of the abundance of data and powerful computers. The objective of this work was to deliver a robust classification system for AD and Mild Cognitive Impairment (MCI) against healthy controls (HC) in a low-cost network in terms of shallow architecture and processing. In this study, the dataset included was downloaded from the Alzheimer's disease neuroimaging initiative (ADNI). The classification methodology implemented was the convolutional neural network (CNN), where the diffusion maps, and gray-matter (GM) volumes were the input images. The number of scans included was 185, 106, and 115 for HC, MCI and AD respectively. Ten-fold cross-validation scheme was adopted and the stacked mean diffusivity (MD) and GM volume produced an AUC of 0.94 and 0.84, an accuracy of 93.5% and 79.6%, a sensitivity of 92.5% and 62.7%, and a specificity of 93.9% and 89% for AD/HC and MCI/HC classification respectively. This work elucidates the impact of incorporating data from different imaging modalities; i.e. structural Magnetic Resonance Imaging (MRI) and Diffusion Tensor Imaging (DTI), where deep learning was employed for the aim of classification. To the best of our knowledge, this is the first study assessing the impact of having more than one scan per subject and propose the proper maneuver to confirm the robustness of the system. The results were competitive among the existing literature, which paves the way for improving medications that could slow down the progress of the AD or prevent it.

Alzheimer'S Disease Classification Using Bag-Of-Words Based On Visual Pattern Of Diffusion Anisotropy For DTI Imaging.

Diffusion tensor imaging (DTI) has recently been added to the large scale of studies for Alzheimer's Disease (AD) to investigate the White Matter (WM) defects that are not detectable using structural MRI. In this paper, we extracted Speeded Up Robust Features (SURF) and Scale Invariant Feature Transform (SIFT) features, based on the visual diffusion patterns of Fractional Anisotropy (FA), and Mean Diffusivity (MD) maps, to build bag-of-words AD-signature for the hippocampal area. The experiments were accomplished with a subset of participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset formed of AD patients (n = 35), Early Mild Cognitive Impairment (EMCI) (n=6), Late Mild Cognitive Impairment (LMCI) (n=24) and cognitively healthy elderly Normal Controls (NC) (n=31). The preliminary studied experiments give promising results that would consider the proposed system as an accurate and useful tool to capture the AD leanness with accuracy of 87% and 89% for FA and MD maps respectively.

Automatic localization of the left ventricle in cardiac MRI images using deep learning.

Automatic localization of the left ventricle (LV) in cardiac MRI images is an essential step for automatic segmentation, functional analysis, and content based retrieval of cardiac images. In this paper, we introduce a new approach based on deep Convolutional Neural Network (CNN) to localize the LV in cardiac MRI in short axis views. A six-layer CNN with different kernel sizes was employed for feature extraction, followed by Softmax fully connected layer for classification. The pyramids of scales analysis was introduced in order to take account of the different sizes of the heart. A publically-available database of 33 patients was used for learning and testing. The proposed method was able it localize the LV with 98.66%, 83.91% and 99.07% for accuracy, sensitivity and specificity respectively.

Image features of spectral correlation function for arrhythmia classification.

Recently, computerized arrhythmia classification tools have been intensively used to aid physicians to recognize different irregular heartbeats. In this paper, we introduce arrhythmia CAD system exploiting cyclostationary signal analysis through estimation of the spectral correlation function for 5 different beat types. Two experiments were performed. Raw spectral correlation data were used as features in the first experiment while the other experiment which dealt with the spectral correlation coefficients as image included extraction of wavelet and shape features followed by fisher score for dimensionality reduction. As for the classification task, Support Vector Machine (SVM) with linear kernel was used for both experiments. The experimental results showed that both proposed approaches are superior compared to several state of the art methods. This approach achieved sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of 99.20%, 99.70%, 98.60%, 99.90% and 97.60% respectively.