Assessing Functional Brain Network Dynamics in Dyslexia from fNIRS Data

Developmental dyslexia is characterized by a deficit of phonological awareness whose origin is related to atypical neural processing of speech streams. This can lead to differences in the neural networks that encode audio information for dyslexics. In this work, we investigate whether such differences exist using functional near-infrared spectroscopy (fNIRS) and complex network analysis. We have explored functional brain networks derived from low-level auditory processing of nonspeech stimuli related to speech units such as stress, syllables or phonemes of skilled and dyslexic seven-year-old readers. A complex network analysis was performed to examine the properties of functional brain networks and their temporal evolution. We characterized aspects of brain connectivity such as functional segregation, functional integration or small-worldness. These properties are used as features to extract differential patterns in controls and dyslexic subjects. The results corroborate the presence of discrepancies in the topological organizations of functional brain networks and their dynamics that differentiate between control and dyslexic subjects, reaching an Area Under ROC Curve (AUC) up to 0.89 in classification experiments.

Assisted Diagnosis of Parkinsonism Based on the Striatal Morphology

Parkinsonism is a clinical syndrome characterized by the progressive loss of striatal dopamine. Its diagnosis is usually corroborated by neuroimaging data such as DaTSCAN neuroimages that allow visualizing the possible dopamine deficiency. During the last decade, a number of computer systems have been proposed to automatically analyze DaTSCAN neuroimages, eliminating the subjectivity inherent to the visual examination of the data. In this work, we propose a computer system based on machine learning to separate Parkinsonian patients and control subjects using the size and shape of the striatal region, modeled from DaTSCAN data. First, an algorithm based on adaptative thresholding is used to parcel the striatum. This region is then divided into two according to the brain hemisphere division and characterized with 152 measures, extracted from the volume and its three possible 2-dimensional projections. Afterwards, the Bhattacharyya distance is used to discard the least discriminative measures and, finally, the neuroimage category is estimated by means of a Support Vector Machine classifier. This method was evaluated using a dataset with 189 DaTSCAN neuroimages, obtaining an accuracy rate over 94%. This rate outperforms those obtained by previous approaches that use the intensity of each striatal voxel as a feature.

Empirical Functional PCA for 3D Image Feature Extraction Through Fractal Sampling

Medical image classification is currently a challenging task that can be used to aid the diagnosis of different brain diseases. Thus, exploratory and discriminative analysis techniques aiming to obtain representative features from the images play a decisive role in the design of effective Computer Aided Diagnosis (CAD) systems, which is especially important in the early diagnosis of dementia. In this work, we present a technique that allows using specific time series analysis techniques with 3D images. This is achieved by sampling the image using a fractal-based method which preserves the spatial relationship among voxels. In addition, a method called Empirical functional PCA (EfPCA) is presented, which combines Empirical Mode Decomposition (EMD) with functional PCA to express an image in the space spanned by a basis of empirical functions, instead of using components computed by a predefined basis as in Fourier or Wavelet analysis. The devised technique has been used to classify images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Parkinson Progression Markers Initiative (PPMI), achieving accuracies up to 93% and 92% differential diagnosis tasks (AD versus controls and PD versus Controls, respectively). The results obtained validate the method, proving that the information retrieved by our methodology is significantly linked to the diseases.

Robust Ensemble Classification Methodology for I123-Ioflupane SPECT Images and Multiple Heterogeneous Biomarkers in the Diagnosis of Parkinson's Disease

In last years, several approaches to develop an effective Computer-Aided-Diagnosis (CAD) system for Parkinson's Disease (PD) have been proposed. Most of these methods have focused almost exclusively on brain images through the use of Machine-Learning algorithms suitable to characterize structural or functional patterns. Those patterns provide enough information about the status and/or the progression at intermediate and advanced stages of Parkinson's Disease. Nevertheless this information could be insufficient at early stages of the pathology. The Parkinson's Progression Markers Initiative (PPMI) database includes neurological images along with multiple biomedical tests. This information opens up the possibility of comparing different biomarker classification results. As data come from heterogeneous sources, it is expected that we could include some of these biomarkers in order to obtain new information about the pathology. Based on that idea, this work presents an Ensemble Classification model with Performance Weighting. This proposal has been tested comparing Healthy Control subjects (HC) vs. patients with PD (considering both PD and SWEDD labeled subjects as the same class). This model combines several Support-Vector-Machine (SVM) with linear kernel classifiers for different biomedical group of tests—including CerebroSpinal Fluid (CSF), RNA, and Serum tests—and pre-processed neuroimages features (Voxels-As-Features and a list of defined Morphological Features) from PPMI database subjects. The proposed methodology makes use of all data sources and selects the most discriminant features (mainly from neuroimages). Using this performance-weighted ensemble classification model, classification results up to 96% were obtained.

Ensemble of random forests One vs. Rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares

BACKGROUND

Alzheimer's disease (AD) is the most common cause of dementia in the elderly and affects approximately 30 million individuals worldwide. Mild cognitive impairment (MCI) is very frequently a prodromal phase of AD, and existing studies have suggested that people with MCI tend to progress to AD at a rate of about 10-15% per year. However, the ability of clinicians and machine learning systems to predict AD based on MRI biomarkers at an early stage is still a challenging problem that can have a great impact in improving treatments.

METHOD

The proposed system, developed by the SiPBA-UGR team for this challenge, is based on feature standardization, ANOVA feature selection, partial least squares feature dimension reduction and an ensemble of One vs. Rest random forest classifiers. With the aim of improving its performance when discriminating healthy controls (HC) from MCI, a second binary classification level was introduced that reconsiders the HC and MCI predictions of the first level.

RESULTS

The system was trained and evaluated on an ADNI datasets that consist of T1-weighted MRI morphological measurements from HC, stable MCI, converter MCI and AD subjects. The proposed system yields a 56.25% classification score on the test subset which consists of 160 real subjects.

COMPARISON WITH EXISTING METHOD(S)

The classifier yielded the best performance when compared to: (i) One vs. One (OvO), One vs. Rest (OvR) and error correcting output codes (ECOC) as strategies for reducing the multiclass classification task to multiple binary classification problems, (ii) support vector machines, gradient boosting classifier and random forest as base binary classifiers, and (iii) bagging ensemble learning.

CONCLUSIONS

A robust method has been proposed for the international challenge on MCI prediction based on MRI data. The system yielded the second best performance during the competition with an accuracy rate of 56.25% when evaluated on the real subjects of the test set.

A Heavy Tailed Expectation Maximization Hidden Markov Random Field Model with Applications to Segmentation of MRI

A wide range of segmentation approaches assumes that intensity histograms extracted from magnetic resonance images (MRI) have a distribution for each brain tissue that can be modeled by a Gaussian distribution or a mixture of them. Nevertheless, intensity histograms of White Matter and Gray Matter are not symmetric and they exhibit heavy tails. In this work, we present a hidden Markov random field model with expectation maximization (EM-HMRF) modeling the components using the α-stable distribution. The proposed model is a generalization of the widely used EM-HMRF algorithm with Gaussian distributions. We test the α-stable EM-HMRF model in synthetic data and brain MRI data. The proposed methodology presents two main advantages: Firstly, it is more robust to outliers. Secondly, we obtain similar results than using Gaussian when the Gaussian assumption holds. This approach is able to model the spatial dependence between neighboring voxels in tomographic brain MRI.

Preprocessing of 18F-DMFP-PET Data Based on Hidden Markov Random Fields and the Gaussian Distribution

¹⁸F-DMFP-PET is an emerging neuroimaging modality used to diagnose Parkinson's disease (PD) that allows us to examine postsynaptic dopamine D_2/3 receptors. Like other neuroimaging modalities used for PD diagnosis, most of the total intensity of ¹⁸F-DMFP-PET images is concentrated in the striatum. However, other regions can also be useful for diagnostic purposes. An appropriate delimitation of the regions of interest contained in ¹⁸F-DMFP-PET data is crucial to improve the automatic diagnosis of PD. In this manuscript we propose a novel methodology to preprocess ¹⁸F-DMFP-PET data that improves the accuracy of computer aided diagnosis systems for PD. First, the data were segmented using an algorithm based on Hidden Markov Random Field. As a result, each neuroimage was divided into 4 maps according to the intensity and the neighborhood of the voxels. The maps were then individually normalized so that the shape of their histograms could be modeled by a Gaussian distribution with equal parameters for all the neuroimages. This approach was evaluated using a dataset with neuroimaging data from 87 parkinsonian patients. After these preprocessing steps, a Support Vector Machine classifier was used to separate idiopathic and non-idiopathic PD. Data preprocessed by the proposed method provided higher accuracy results than the ones preprocessed with previous approaches.

Multivariate Analysis of 18F-DMFP PET Data to Assist the Diagnosis of Parkinsonism

An early and differential diagnosis of parkinsonian syndromes still remains a challenge mainly due to the similarity of their symptoms during the onset of the disease. Recently, ¹⁸F-Desmethoxyfallypride (DMFP) has been suggested to increase the diagnostic precision as it is an effective radioligand that allows us to analyze post-synaptic dopamine D_2/3 receptors. Nevertheless, the analysis of these data is still poorly covered and its use limited. In order to address this challenge, this paper shows a novel model to automatically distinguish idiopathic parkinsonism from non-idiopathic variants using DMFP data. The proposed method is based on a multiple kernel support vector machine and uses the linear version of this classifier to identify some regions of interest: the olfactory bulb, thalamus, and supplementary motor area. We evaluated the proposed model for both, the binary separation of idiopathic and non-idiopathic parkinsonism and the multigroup separation of parkinsonian variants. These systems achieved accuracy rates higher than 70%, outperforming DaTSCAN neuroimages for this purpose. In addition, a system that combined DaTSCAN and DMFP data was assessed.

Building a FP-CIT SPECT Brain Template Using a Posterization Approach

Spatial affine registration of brain images to a common template is usually performed as a preprocessing step in intersubject and intrasubject comparison studies, computer-aided diagnosis, region of interest selection and brain segmentation in tomography. Nevertheless, it is not straightforward to build a template of [123I]FP-CIT SPECT brain images because they exhibit very low intensity values outside the striatum. In this work, we present a procedure to automatically build a [123I]FP-CIT SPECT template in the standard Montreal Neurological Institute (MNI) space. The proposed methodology consists of a head voxel selection using the Otsu's method, followed by a posterization of the source images to three different levels: background, head, and striatum. Analogously, we also design a posterized version of a brain image in the MNI space; subsequently, we perform a spatial affine registration of the posterized source images to this image. The intensity of the transformed images is normalized linearly, assuming that the histogram of the intensity values follows an alpha-stable distribution. Lastly, we build the [123I]FP-CIT SPECT template by means of the transformed and normalized images. The proposed methodology is a fully automatic procedure that has been shown to work accurately even when a high-resolution magnetic resonance image for each subject is not available.

An Optimal Approach for Selecting Discriminant Regions for the Diagnosis of Alzheimer's Disease

In this work, we present a fully automatic computer-aided diagnosis method for the early diagnosis of the Alzheimer's disease. We study the distance between classes (labelled as normal controls and possible Alzheimer's disease) calculated in 116 regions of the brain using the Welchs's t-test. We select the regions with highest Welchs's t-test value as features to perform classification. Furthermore, we also study the less discriminative region according to the t-test (regions with lowest t-test absolute values) in order to use them as reference. We show that the mean and standard deviation of the intensity values in these two regions, the less and most discriminative according to the Welch's ttest, can be combined as a vector. The modulus and phase of this vector reveal statistical differences between groups which can be used to improve the classification task. We show how they can be used as input for a support vector machine classifier. The proposed methodology is tested in a SPECT brain database of 70 SPECT brain images yielding an accuracy up to 91.5% for a wide range of selected voxels.

Affine registration of [123I]FP-CIT SPECT brain images

In this work, we perform a comparison between the spatial normalization of [123I]FP-CIT SPECT brain images when a FP-CIT SPECT and a MRI template are used. A 12-parameters affine registration model is calculated by the optimization of a sum of squares cost function. When the images are registered to a FP-CIT template, the intersubject variation is found to be lower than when the MRI template is used, specially in the striatum, which is the most relevant part of the brain in FP-CIT SPECT brain images.

Multimodal image data fusion for Alzheimer's Disease diagnosis by sparse representation

Alzheimer's Diasese (AD) diagnosis can be carried out by analysing functional or structural changes in the brain. Functional changes associated to neurological disorders can be figured out by positron emission tomography (PET) as it allows to study the activation of certain areas of the brain during specific task development. On the other hand, neurological disorders can also be discovered by analysing structural changes in the brain which are usually assessed by Magnetic Resonance Imaging (MRI). In fact, computer-aided diagnosis tools (CAD) that have been recently devised for the diagnosis of neurological disorders use functional or structural data. However, functional and structural data can be fused out in order to improve the accuracy and to diminish the false positive rate in CAD tools. In this paper we present a method for the diagnosis of AD which fuses multimodal image (PET and MRI) data by combining Sparse Representation Classifiers (SRC). The method presented in this work shows accuracy values up to 95% and clearly outperforms the classification outcomes obtained using single-modality images.