Francisco Jesús Martínez-Murcia

LVQ-SVM based CAD tool applied to structural MRI for the diagnosis of the Alzheimer's disease

This paper presents a novel computer-aided diagnosis (CAD) tool for the diagnosis of the Alzheimers disease (AD) using structural Magnetic Resonance Images (MRIs). The proposed method uses information learnt from the tissue distribution of Gray Matter (GM) and White Matter (WM) in the brain, which is previously obtained by an unsupervised segmentation method. The tissue distribution of control (normal) and AD images is modelled by means of Learning Vector Quantization (LVQ) algorithm, generating a set of representative prototypes of each class. The devised method projects new images onto the model vectors space for further classification using Support Vector Machine (SVM). The tool proposed here yields classification results over 90% (accuracy) for controls (normal) and Alzheimers disease (AD) patients and sensitivity up to 95% to AD. Moreover, statistical significance tests have been also performed in order to validate the proposed approach.

Parametrization of textural patterns in 123I‐ioflupane imaging for the automatic detection of Parkinsonism

PURPOSE A novel approach to a computer aided diagnosis system for the Parkinsons disease is proposed. This tool is intended as a supporting tool for physicians, based on fully automated methods that lead to the classification of (123)I-ioflupane SPECT images. METHODS (123)I-ioflupane images from three different databases are used to train the system. The images are intensity and spatially normalized, then subimages are extracted and a 3D gray-level co-occurrence matrix is computed over these subimages, allowing the characterization of the texture using Haralick texture features. Finally, different discrimination estimation methods are used to select a feature vector that can be used to train and test the classifier. RESULTS Using the leave-one-out cross-validation technique over these three databases, the system achieves results up to a 97.4% of accuracy, and 99.1% of sensitivity, with positive likelihood ratios over 27. CONCLUSIONS The system presents a robust feature extraction method that helps physicians in the diagnosis task by providing objective, operator-independent textural information about (123)I-ioflupane images, commonly used in the diagnosis of the Parkinsons disease. Textural features computation has been optimized by using a subimage selection algorithm, and the discrimination estimation methods used here makes the system feature-independent, allowing us to extend it to other databases and diseases.

Automatic ROI Selection in Structural Brain MRI Using SOM 3D Projection

This paper presents a method for selecting Regions of Interest (ROI) in brain Magnetic Resonance Imaging (MRI) for diagnostic purposes, using statistical learning and vector quantization techniques. The proposed method models the distribution of GM and WM tissues grouping the voxels belonging to each tissue in ROIs associated to a specific neurological disorder. Tissue distribution of normal and abnormal images is modelled by a Self-Organizing map (SOM), generating a set of representative prototypes, and the receptive field (RF) of each SOM prototype defines a ROI. Moreover, the proposed method computes the relative importance of each ROI by means of its discriminative power. The devised method has been assessed using 818 images from the Alzheimers disease Neuroimaging Initiative (ADNI) which were previously segmented through Statistical Parametric Mapping (SPM). The proposed algorithm was used over these images to parcel ROIs associated to the Alzheimers Disease (AD). Additionally, this method can be used to extract a reduced set of discriminative features for classification, since it compresses discriminative information contained in the brain. Voxels marked by ROIs which were computed using the proposed method, yield classification results up to 90% of accuracy for controls (CN) and Alzheimers disease (AD) patients, and 84% of accuracy for Mild Cognitive Impairment (MCI) and AD patients.

A Structural Parametrization of the Brain Using Hidden Markov Models Based Paths in Alzheimer's Disease

The usage of biomedical imaging in the diagnosis of dementia is increasingly widespread. A number of works explore the possibilities of computational techniques and algorithms in what is called computed aided diagnosis. Our work presents an automatic parametrization of the brain structure by means of a path generation algorithm based on hidden Markov models (HMMs). The path is traced using information of intensity and spatial orientation in each node, adapting to the structure of the brain. Each path is itself a useful way to characterize the distribution of the tissue inside the magnetic resonance imaging (MRI) image by, for example, extracting the intensity levels at each node or generating statistical information of the tissue distribution. Additionally, a further processing consisting of a modification of the grey level co-occurrence matrix (GLCM) can be used to characterize the textural changes that occur throughout the path, yielding more meaningful values that could be associated to Alzheimers disease (AD), as well as providing a significant feature reduction. This methodology achieves moderate performance, up to 80.3% of accuracy using a single path in differential diagnosis involving Alzheimer-affected subjects versus controls belonging to the Alzheimers disease neuroimaging initiative (ADNI).

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.

A Spherical Brain Mapping of MR Images for the Detection of Alzheimer's Disease

Magnetic Resonance Imaging (MRI) is of fundamental importance in neuroscience, providing good contrast and resolution, as well as not being considered invasive. Despite the development of newer techniques involving radiopharmaceuticals, it is still a recommended tool in Alzheimers Disease (AD) neurological practice to assess neurodegeneration, and recent research suggests that it could reveal changes in the brain even before the symptomatology appears. In this paper we propose a method that performs a Spherical Brain Mapping, using different measures to project the three-dimensional MR brain images onto two-dimensional maps revealing statistical characteristics of the tissue. The resulting maps could be assessed visually, but also perform a significant feature reduction that will allow further supervised or unsupervised processing, reducing the computational load while maintaining a large amount of the original information. We have tested our methodology against a MRI database comprising 180 AD affected patients and 180 normal controls, where some of the mappings have revealed as an optimum strategy for the automatic processing and characterization of AD patterns, achieving up to a 90.9% of accuracy, as well as significantly reducing the computational load. Additionally, our maps allow the visual analysis and interpretation of the images, which can be of great help in the diagnosis of this and other types of dementia.

On the brain structure heterogeneity of autism: Parsing out acquisition site effects with significance-weighted principal component analysis.

Neuroimaging studies have reported structural and physiological differences that could help understand the causes and development of Autism Spectrum Disorder (ASD). Many of them rely on multisite designs, with the recruitment of larger samples increasing statistical power. However, recent large‐scale studies have put some findings into question, considering the results to be strongly dependent on the database used, and demonstrating the substantial heterogeneity within this clinically defined category. One major source of variance may be the acquisition of the data in multiple centres. In this work we analysed the differences found in the multisite, multi‐modal neuroimaging database from the UK Medical Research Council Autism Imaging Multicentre Study (MRC AIMS) in terms of both diagnosis and acquisition sites. Since the dissimilarities between sites were higher than between diagnostic groups, we developed a technique called Significance Weighted Principal Component Analysis (SWPCA) to reduce the undesired intensity variance due to acquisition site and to increase the statistical power in detecting group differences. After eliminating site‐related variance, statistically significant group differences were found, including Brocas area and the temporo‐parietal junction. However, discriminative power was not sufficient to classify diagnostic groups, yielding accuracies results close to random. Our work supports recent claims that ASD is a highly heterogeneous condition that is difficult to globally characterize by neuroimaging, and therefore different (and more homogenous) subgroups should be defined to obtain a deeper understanding of ASD. Hum Brain Mapp 38:1208–1223, 2017.

Case-Based Statistical Learning: A Non-Parametric Implementation With a Conditional-Error Rate SVM

Machine learning has been successfully applied to many areas of science and engineering. Some examples include time series prediction, optical character recognition, signal and image classification in biomedical applications for diagnosis and prognosis and so on. In the theory of semi-supervised learning, we have a training set and an unlabeled data, that are employed to fit a prediction model or learner, with the help of an iterative algorithm, such as the expectation-maximization algorithm. In this paper, a novel non-parametric approach of the so-called case-based statistical learning is proposed in a low-dimensional classification problem. This supervised feature selection scheme analyzes the discrete set of outcomes in the classification problem by hypothesis-testing and makes assumptions on these outcome values to obtain the most likely prediction model at the training stage. A novel prediction model is described in terms of the output scores of a confidence-based support vector machine classifier under class-hypothesis testing. To have a more accurate prediction by considering the unlabeled points, the distribution of unlabeled examples must be relevant for the classification problem. The estimation of the error rates from a well-trained support vector machines allows us to propose a non-parametric approach avoiding the use of Gaussian density function-based models in the likelihood ratio test.

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 D2/3 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.

Automated Diagnosis of Parkinsonian Syndromes by Deep Sparse Filtering-Based Features

Parkinsonian Syndrome (PS) or Parkinsonism is the second most common neurodegenerative disorder in the elderly. Currently there is no cure for PS, and it has important socio-economic implications due to the fact that PS progressively disables people in their ordinary daily tasks. However, precise and early diagnosis can definitely help to start the treatment in the early stages of the disease, improving the patient’s quality of life. The study of neurodegenerative diseases has been usually addressed by visual inspection and semi-quantitative analysis of medical imaging, which results in subjective outcomes. However, recent advances in statistical signal processing and machine learning techniques provide a new way to explore medical images yielding to an objective analysis, dealing with the Computer Aided Diagnosis (CAD) paradigm. In this work, we propose a method that selects the most discriminative regions on 123I-FP-CIT SPECT (DaTSCAN) images and learns features using deep-learning techniques. The proposed system has been tested using images from the Parkinson Progression Markers Initiative (PPMI), obtaining accuracy values up to 95 %, showing its robustness for PS pattern detection and outperforming the baseline Voxels-as-Features (VAF) approach, used as an approximation of the visual analysis.