An Improved Brain MRI Classification Methodology Based on Statistical Features and Machine Learning Algorithms.

In this paper, we have proposed a novel methodology based on statistical features and different machine learning algorithms. The proposed model can be divided into three main stages, namely, preprocessing, feature extraction, and classification. In the preprocessing stage, the median filter has been used in order to remove salt-and-pepper noise because MRI images are normally affected by this type of noise, the grayscale images are also converted to RGB images in this stage. In the preprocessing stage, the histogram equalization has also been used to enhance the quality of each RGB channel. In the feature extraction stage, the three channels, namely, red, green, and blue, are extracted from the RGB images and statistical measures, namely, mean, variance, skewness, kurtosis, entropy, energy, contrast, homogeneity, and correlation, are calculated for each channel; hence, a total of 27 features, 9 for each channel, are extracted from an RGB image. After the feature extraction stage, different machine learning algorithms, such as artificial neural network, k-nearest neighbors' algorithm, decision tree, and Naïve Bayes classifiers, have been applied in the classification stage on the features extracted in the feature extraction stage. We recorded the results with all these algorithms and found that the decision tree results are better as compared to the other classification algorithms which are applied on these features. Hence, we have considered decision tree for further processing. We have also compared the results of the proposed method with some well-known algorithms in terms of simplicity and accuracy; it was noted that the proposed method outshines the existing methods.

Developing the ATX(N) classification for use across the Alzheimer disease continuum.

Breakthroughs in the development of highly accurate fluid and neuroimaging biomarkers have catalysed the conceptual transformation of Alzheimer disease (AD) from the traditional clinical symptom-based definition to a clinical-biological construct along a temporal continuum. The AT(N) system is a symptom-agnostic classification scheme that categorizes individuals using biomarkers that chart core AD pathophysiological features, namely the amyloid-ß (Aß) pathway (A), tau-mediated pathophysiology (T) and neurodegeneration (N). This biomarker matrix is now expanding towards an ATX(N) system, where X represents novel candidate biomarkers for additional pathophysiological mechanisms such as neuroimmune dysregulation, synaptic dysfunction and blood-brain barrier alterations. In this Perspective, we describe the conceptual framework and clinical importance of the existing AT(N) system and the evolving ATX(N) system. We provide a state-of-the-art summary of the potential contexts of use of these systems in AD clinical trials and future clinical practice. We also discuss current challenges related to the validation, standardization and qualification process and provide an outlook on the real-world application of the AT(N) system.

Definitions and classification of malformations of cortical development: practical guidelines.

Malformations of cortical development are a group of rare disorders commonly manifesting with developmental delay, cerebral palsy or seizures. The neurological outcome is extremely variable depending on the type, extent and severity of the malformation and the involved genetic pathways of brain development. Neuroimaging plays an essential role in the diagnosis of these malformations, but several issues regarding malformations of cortical development definitions and classification remain unclear. The purpose of this consensus statement is to provide standardized malformations of cortical development terminology and classification for neuroradiological pattern interpretation. A committee of international experts in paediatric neuroradiology prepared systematic literature reviews and formulated neuroimaging recommendations in collaboration with geneticists, paediatric neurologists and pathologists during consensus meetings in the context of the European Network Neuro-MIG initiative on Brain Malformations (https://www.neuro-mig.org/). Malformations of cortical development neuroimaging features and practical recommendations are provided to aid both expert and non-expert radiologists and neurologists who may encounter patients with malformations of cortical development in their practice, with the aim of improving malformations of cortical development diagnosis and imaging interpretation worldwide.

Accuracy of MRI Classification Algorithms in a Tertiary Memory Center Clinical Routine Cohort.

BACKGROUND: Automated volumetry software (AVS) has recently become widely available to neuroradiologists. MRI volumetry with AVS may support the diagnosis of dementias by identifying regional atrophy. Moreover, automatic classifiers using machine learning techniques have recently emerged as promising approaches to assist diagnosis. However, the performance of both AVS and automatic classifiers have been evaluated mostly in the artificial setting of research datasets. OBJECTIVE: Our aim was to evaluate the performance of two AVS and an automatic classifier in the clinical routine condition of a memory clinic. METHODS: We studied 239 patients with cognitive troubles from a single memory center cohort. Using clinical routine T1-weighted MRI, we evaluated the classification performance of: 1) univariate volumetry using two AVS (volBrain and Neuroreader™); 2) Support Vector Machine (SVM) automatic classifier, using either the AVS volumes (SVM-AVS), or whole gray matter (SVM-WGM); 3) reading by two neuroradiologists. The performance measure was the balanced diagnostic accuracy. The reference standard was consensus diagnosis by three neurologists using clinical, biological (cerebrospinal fluid) and imaging data and following international criteria. RESULTS: Univariate AVS volumetry provided only moderate accuracies (46% to 71% with hippocampal volume). The accuracy improved when using SVM-AVS classifier (52% to 85%), becoming close to that of SVM-WGM (52 to 90%). Visual classification by neuroradiologists ranged between SVM-AVS and SVM-WGM. CONCLUSION: In the routine practice of a memory clinic, the use of volumetric measures provided by AVS yields only moderate accuracy. Automatic classifiers can improve accuracy and could be a useful tool to assist diagnosis.

Neuroimagen en fibromialgia / Neuroimaging in fibromialgia

Introducción. La mayoría de las investigaciones actuales sugiere que la fibromialgia es una enfermedad producida por una alteración en el procesamiento de la señal dolorosa en el sistema nervioso central. En los últimos años, gracias al avance de las técnicas de imagen cerebral no invasivas o mínimamente invasivas, se ha podido averiguar cómo participan las diferentes áreas del sistema nervioso en la etiopatogenia de enfermedades consideradas hasta ahora como de perfil funcional. Objetivo. Describir los cambios objetivados, tanto funcionales como estructurales, que ocurren en el cerebro de pacientes con fibromialgia a través de las técnicas de neuroimagen disponibles en la actualidad. Desarrollo. Se revisan los estudios clínicos, tanto anatómicos como moleculares, que se han realizado hasta ahora, con las diferentes técnicas de imagen cerebral, en el campo de la fibromialgia. Conclusiones. Se han descrito diferentes áreas del sistema nervioso central, relacionadas entre sí, que se alteran no sólo de forma funcional, sino también estructural, en los pacientes con fibromialgia. Estas áreas involucradas se extienden más allá de los circuitos de dolor, lo que explicaría la variada sintomatología de los pacientes y el dolor característico referido por ellos

Introduction. Most current research suggests that fibromyalgia is a disease produced by an alteration in the processing of pain signals in the central nervous system. In recent years, advances in non- or minimally-invasive brain imaging techniques have made it possible to discover how different areas of the nervous system are involved in the aetiopathogenesis of diseases that up until now have been considered as having a functional profile. Aim. To describe the objectified functional and the structural changes that take place in the brains of patients with fibromyalgia by means of the currently available neuroimaging techniques. Development. This work reviews the clinical studies, both anatomical and molecular, that have been conducted to date in the field of fibromyalgia using different brain imaging techniques. Conclusions. Different, but related, areas of the central nervous system have been described as altering not only the functional but also the structural form, in patients with fibromyalgia. These involved areas extend beyond the pain circuits, which would explain the variety of symptoms in patients, in addition to the characteristic pain reported by them

Classification of multi-site MR images in the presence of heterogeneity using multi-task learning.

With the advent of Big Data Imaging Analytics applied to neuroimaging, datasets from multiple sites need to be pooled into larger samples. However, heterogeneity across different scanners, protocols and populations, renders the task of finding underlying disease signatures challenging. The current work investigates the value of multi-task learning in finding disease signatures that generalize across studies and populations. Herein, we present a multi-task learning type of formulation, in which different tasks are from different studies and populations being pooled together. We test this approach in an MRI study of the neuroanatomy of schizophrenia (SCZ) by pooling data from 3 different sites and populations: Philadelphia, Sao Paulo and Tianjin (50 controls and 50 patients from each site), which posed integration challenges due to variability in disease chronicity, treatment exposure, and data collection. Some existing methods are also tested for comparison purposes. Experiments show that classification accuracy of multi-site data outperformed that of single-site data and pooled data using multi-task feature learning, and also outperformed other comparison methods. Several anatomical regions were identified to be common discriminant features across sites. These included prefrontal, superior temporal, insular, anterior cingulate cortex, temporo-limbic and striatal regions consistently implicated in the pathophysiology of schizophrenia, as well as the cerebellum, precuneus, and fusiform, middle temporal, inferior parietal, postcentral, angular, lingual and middle occipital gyri. These results indicate that the proposed multi-task learning method is robust in finding consistent and reliable structural brain abnormalities associated with SCZ across different sites, in the presence of multiple sources of heterogeneity.

Overview of neuroradiology.

Neuroradiology with computed tomography (CT) and magnetic resonance imaging (MRI) is essential for the initial evaluation of patients with a clinical suspicion of brain and spine disorders. Morphologic imaging is required to obtain a probable diagnosis to support the treatment decisions in pre- and perinatal disorders, vascular diseases, traumatic injuries, metabolic disorders, epilepsy, infection/inflammation, neurodegenerative disorders, degenerative spinal disease, and tumors of the central nervous system. Different postprocessing tools are increasingly used for three-dimensional visualization and quantification of lesions. Additional information is provided by angiographic methods and physiologic CT and MRI techniques, such as diffusion MRI, perfusion CT/MRI, MR spectroscopy, functional MRI, tractography, and nuclear medicine imaging methods. Positron emission tomography (PET) is now integrated with CT (PET/CT), and PET/MR scanners have recently also been introduced. These hybrid techniques facilitate the co-registration of lesions with different modalities, and give new possibilites for functional imaging. Repeated imaging is increasingly performed for treatment monitoring. The improved imaging techniques together with the neuropathologic diagnosis after biopsy or surgery allow more personalized treatment of the patient. Neuroradiology also includes endovascular treatment of aneurysms and arteriovenous malformations as well as thrombectomy in acute stroke. This catheter-based treatment has replaced invasive neurosurgery in many cases.

Sudden neurologic deficit.

Clinicians treating sudden neurologic deficit are being faced with an increasing number of available imaging modalities. In this chapter we discuss a general approach to acute neuroimaging and weigh the considerations that determine which modality or modalities should be utilized.

Movement disorders.

Movement disorders can be hypokinetic (e.g., parkinsonism), hyperkinetic, or dystonic in nature and commonly arise from altered function in nuclei of the basal ganglia or their connections. As obvious structural changes are often limited, standard imaging plays less of a role than in other neurologic disorders. However, structural imaging is indicated where clinical presentation is atypical, particularly if the disorder is abrupt in onset or remains strictly unilateral. More recent advances in magnetic resonance imaging (MRI) may allow for differentiation between Parkinson's disease and atypical forms of parkinsonism. Functional imaging can assess regional cerebral blood flow (functional MRI (fMRI), positron emission tomography (PET), or single-photon emission computed tomography (SPECT)), cerebral glucose metabolism (PET), neurochemical and neuroreceptor status (PET and SPECT), and pathologic processes such as inflammation or abnormal protein deposition (PET) (Table 49.1). Cerebral blood flow can be assessed at rest, during the performance of motor or cognitive tasks, or in response to a variety of stimuli. In appropriate situations, the correct imaging modality and/or combination of modalities can be used to detect early disease or even preclinical disease, and to monitor disease progression and the effects of disease-modifying interventions. Various approaches are reviewed here.

Rethinking cognition and behavior in the new classification for childhood epilepsy: Examples from frontal lobe and temporal lobe epilepsies.

The new approach to classification of the epilepsies emphasizes the role of dysfunction in networks in defining types of epilepsies. This paper reviews the structural and neuropsychological deficits in two types of childhood epilepsy: frontal lobe and temporal lobe epilepsy. The evidence for and against a pattern of specificity of deficits in executive function and memory associated with these two types of epilepsies is presented. The evidence varies with the methodologies used in the studies, but direct comparison of the two types of epilepsies does not suggest a clear-cut mapping of function onto structure. These findings are discussed in light of the concept of network dysfunction. The evidence supports the conceptualization of epilepsy as a network disease. Implications for future work in the neuropsychology of pediatric epilepsy are suggested. This article is part of a Special Issue entitled "The new approach to classification: Rethinking cognition and behavior in epilepsy".

Carotidinia, a vueltas con una vieja controversia / Carotidynia, back to an old controversial issue

No disponible

Resting functional imaging tools (MRS, SPECT, PET and PCT).

Functional imaging includes imaging techniques that provide information about the metabolic and hemodynamic status of the brain. Most commonly applied functional imaging techniques in patients with traumatic brain injury (TBI) include magnetic resonance spectroscopy (MRS), single photon emission computed tomography (SPECT), positron emission tomography (PET) and perfusion CT (PCT). These imaging modalities are used to determine the extent of injury, to provide information for the prediction of outcome, and to assess evidence of cerebral ischemia. In TBI, secondary brain damage mainly comprises ischemia and is present in more than 80% of fatal cases with traumatic brain injury (Graham et al., 1989; Bouma et al., 1991; Coles et al., 2004). In particular, while SPECT measures cerebral perfusion and MRS determines metabolism, PET is able to assess both perfusion and cerebral metabolism. This chapter will describe the application of these techniques in traumatic brain injury separately for the major groups of severity comprising the mild and moderate to severe group. The application in TBI and potential difficulties of each technique is described. The use of imaging techniques in children will be separately outlined.

Advances in imaging explosive blast mild traumatic brain injury.

In the past, direct physical evidence of mild traumatic brain injury (mTBI) from explosive blast has been difficult to obtain through conventional imaging modalities such as T1- and T2-weighted magnetic resonance imaging (MRI) and computed tomography (CT). Here, we review current progress in detecting evidence of brain injury from explosive blast using advanced imaging, including diffusion tensor imaging (DTI), functional MRI (fMRI), and the metabolic imaging methods such as positron emission tomography (PET) and magnetic resonance spectroscopic imaging (MRSI), where each targets different aspects of the pathology involved in mTBI. DTI provides a highly sensitive measure to detect primary changes in the microstructure of white matter tracts. fMRI enables the measurement of changes in brain activity in response to different stimuli or tasks. Remarkably, all three of these paradigms have found significant success in conventional mTBI where conventional clinical imaging frequently fails to provide definitive differences. Additionally, although used less frequently for conventional mTBI, PET has the potential to characterize a variety of neurotransmitter systems using target agents and will undoubtedly play a larger role, once the basic mechanisms of injury are better understood and techniques to identify the injury are more common. Finally, our MRSI imaging studies, although acquired at much lower spatial resolution, have demonstrated selectivity to different metabolic and physiologic processes, uncovering some of the most profound differences on an individual by individual basis, suggesting the potential for utility in the management of individual patients.

Demencia frontotemporal variante conductual: biomarcadores, una aproximación a la enfermedad / Biomarkers: A new approach to behavioural variant frontotemporal dementia

Introducción: Las degeneraciones lobares frontotemporales (DLFT) son un grupo de patologías moleculares que se definen en función de la proteína acumulada en el sistema nervioso central. La demencia frontotemporal variante conductual (DFT vc) es el síndrome clínico de presentación más frecuente. Los avances realizados en los últimos anos han contribuido a un mayor conocimiento de esta entidad, que puede ser el modo de presentación de diferentes enfermedades neurodegenerativas. Desarrollo: Se revisa la correlación entre clínica, patología y genética de las DLFT, en especial de la DFT vc, así como los principales biomarcadores de la enfermedad. La anatomía patológica de la DFT vc es muy variada, sin mostrar asociación significativa con ningún subtipo histopatológico concreto. Entre los biomarcadores disponibles, destacan la neuroimagen anatómica y funcional, los biomarcadores analíticos y la genética. Se están disenando fármacos dirigidos contra dianas moleculares concretas implicadas en la patogenia de las DLFT. Conclusiones: La DFT vc es una causa frecuente de demencia. De entre todas las variantes clínicas de las DLFT, es en la que resulta más difícil establecer una relación clínico-patológica. El uso de biomarcadores puede ayudar a predecir la anatomía patológica subyacente, lo que junto al desarrollo de fármacos ligando-específicos ofrece nuevas posibilidades terapéuticas

Introduction: Lobar frontotemporal degeneration (FTLD) encompasses a group of molecular disease defined by the deposition of an abnormal protein in the central nervous system. Behavioural variant frontotemporal dementia (bvFTD) is the most frequent clinical presentation of FTLD. The past two decades of research have contributed to a better understanding of this entity, which may be the first manifestation in many different neurodegenerative disorders. Development: We reviewed correlations between clinical, pathological, and genetic findings and the main disease biomarkers of FTLD, with particular interest in bvFTD. Anatomical pathology findings in FTLD are heterogeneous and the syndrome is not associated with any one specific histopathological type. Promising available biomarkers include structural and functional neuroimaging techniques and biochemical and genetic biomarkers. Disease-modifying drugs designed for specific molecular targets that are implicated in FTLD pathogenesis are being developed. Conclusions: BvFTD is a frequent cause of dementia. Of all the clinical variants of FTLD, behavioural variant is the one in which establishing a correlation between clinical and pathological signs is the most problematic. A biomarker evaluation may help predict the underlying pathology; this approach, in conjunction with the development of disease-modifying drugs, offers new therapeutic possibilities

Panic and the brainstem: clues from neuroimaging studies.

One of the most influential theories has conceived unexpected panic attack (PA) as a primal defensive reaction to threat within the internal milieu of the body. This theory is based on findings suggesting the involvement of dysfunctional respiratory regulation and/or abnormally sensitive central neural network of carbon dioxide (CO2)/hydrogen ion (H+) chemoreception in PA. Thus, unexpected PA may be related to phylogenetically older brain structures, including the brainstem areas, which process basic functions related to the organism's internal milieu. The brainstem represents a crucial area for homeostatic regulation, including chemoreception and cardio-respiratory control. In addition, the midbrain dorsal periaqueductal gray may be involved in the unconditioned defense reactions to proximal threats, including internal physical stimuli. Our aim was to specifically consider the potential involvement of the brainstem in panic disorder (PD) by a comprehensive review of the available neuroimaging studies. Available data are limited and potentially affected by several limitations. However, preliminary evidence of a role of the brainstem in PD can be found and, secondly, the brainstem serotonergic system seems to be involved in panic modulation with indications of both altered serotonergic receptors and 5-HT transporter bindings. In conclusion, our review suggests that the brainstem may be involved in psychopathology of PD and supports the relevant role of subcortical serotonergic system in panic pathogenesis.

Population-based studies of brain imaging patterns in cerebral palsy.

AIM: The aim of this study was to review the distribution of neuroimaging findings from a contemporary population cohort of individuals with cerebral palsy (CP) and to facilitate standardization of imaging classification. METHOD: Publications from 1995 to 2012 reporting imaging findings in population cohorts were selected through a literature search, and review of the titles, abstracts, and content of studies. Relevant data were extracted, including unpublished data from Victoria, Australia. The proportions for each imaging pattern were tabulated, and heterogeneity was assessed for all individuals with CP, and for subgroups based on gestational age, CP subtype, and Gross Motor Function Classification System level. RESULTS: Studies from three geographic regions met the inclusion criteria for individuals with CP, and two additional studies reported on specific CP subtypes. Brain abnormalities were observed in 86% of scans, but were observed least often in children with ataxia (24-57%). White matter injury was the most common imaging pattern (19-45%), although the proportions showed high heterogeneity. Additional patterns were grey matter injury (21%), focal vascular insults (10%), malformations (11%), and miscellaneous findings (4-22%). INTERPRETATION: This review suggests areas where further dialogue will facilitate progress towards standardization of neuroimaging classification. Standardization will enable future collaborations aimed at exploring the relationships among magnetic resonance imaging patterns, risk factors, and clinical outcomes, and, ultimately, lead to better understanding of causal pathways and opportunities for prevention.

Quantifying the reliability of image replication studies: the image intraclass correlation coefficient (I2C2).

This article proposes the image intraclass correlation (I2C2) coefficient as a global measure of reliability for imaging studies. The I2C2 generalizes the classic intraclass correlation (ICC) coefficient to the case when the data of interest are images, thereby providing a measure that is both intuitive and convenient. Drawing a connection with classical measurement error models for replication experiments, the I2C2 can be computed quickly, even in high-dimensional imaging studies. A nonparametric bootstrap procedure is introduced to quantify the variability of the I2C2 estimator. Furthermore, a Monte Carlo permutation is utilized to test reproducibility versus a zero I2C2, representing complete lack of reproducibility. Methodologies are applied to three replication studies arising from different brain imaging modalities and settings: regional analysis of volumes in normalized space imaging for characterizing brain morphology, seed-voxel brain activation maps based on resting-state functional magnetic resonance imaging (fMRI), and fractional anisotropy in an area surrounding the corpus callosum via diffusion tensor imaging. Notably, resting-state fMRI brain activation maps are found to have low reliability, ranging from .2 to .4. Software and data are available to provide easy access to the proposed methods.

Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration.

Cerebral small vessel disease (SVD) is a common accompaniment of ageing. Features seen on neuroimaging include recent small subcortical infarcts, lacunes, white matter hyperintensities, perivascular spaces, microbleeds, and brain atrophy. SVD can present as a stroke or cognitive decline, or can have few or no symptoms. SVD frequently coexists with neurodegenerative disease, and can exacerbate cognitive deficits, physical disabilities, and other symptoms of neurodegeneration. Terminology and definitions for imaging the features of SVD vary widely, which is also true for protocols for image acquisition and image analysis. This lack of consistency hampers progress in identifying the contribution of SVD to the pathophysiology and clinical features of common neurodegenerative diseases. We are an international working group from the Centres of Excellence in Neurodegeneration. We completed a structured process to develop definitions and imaging standards for markers and consequences of SVD. We aimed to achieve the following: first, to provide a common advisory about terms and definitions for features visible on MRI; second, to suggest minimum standards for image acquisition and analysis; third, to agree on standards for scientific reporting of changes related to SVD on neuroimaging; and fourth, to review emerging imaging methods for detection and quantification of preclinical manifestations of SVD. Our findings and recommendations apply to research studies, and can be used in the clinical setting to standardise image interpretation, acquisition, and reporting. This Position Paper summarises the main outcomes of this international effort to provide the STandards for ReportIng Vascular changes on nEuroimaging (STRIVE).

Dementia and neuroimaging.

Early diagnosis of dementing conditions and an accurate monitoring of their progression are important clinical and research goals, especially given the improving prospects of disease-modifying therapies. Neuroimaging has played and is playing an important role in detecting reversible, treatable causes of dementia, and in characterizing the dementia syndromes by demonstrating structural and functional signatures that can aid in their differentiation. Many new imaging techniques and modalities are also available that allow the assessment of specific aspects of brain structure and function, such as positron emission tomography with new ligands, diffusion tensor magnetic resonance imaging (MRI) and functional MRI. In this review, we report the most recent findings from the papers published in the Journal of Neurology that used conventional and advanced neuroimaging techniques for the study of various dementing conditions.

Predictive classification of individual magnetic resonance imaging scans from children and adolescents.

Neuroimaging techniques are increasingly being explored as potential tools for clinical prediction in psychiatry. There are a wide range of approaches which can be applied to make individual predictions for various aspects of disorders such as diagnostic status, symptom severity scores, identification of patients at risk of developing disorders and estimation of the likelihood of response to treatment. This selective review highlights a popular group of pattern recognition techniques, support vector machines (SVMs) for use with structural magnetic resonance imaging scans. First, however, we outline various practical issues, limitations and techniques which need to be considered before SVM's can be applied. We begin with a discussion on the practicalities of scanning children and adolescent participants and the importance of acquiring high quality images. Scan processing required for inter-subject comparisons is then discussed. We then briefly discuss feature selection and other considerations when applying pattern recognition techniques. Finally, SVMs are described and various studies highlighted to indicate the potential of these techniques for child and adolescent psychiatric research.