Inter And Intra Subject Variability In Brain Imaging And Decoding

Brain imaging brings together the technology, methodology, research questions and approaches of a wide range of scientific fields including physics, statistics, computer science, neuroscience, biology, and engineering. Thus, methodological and technological advances that enable us to obtain measurements, examine relationships across observations, and link these data to neuroscientific hypotheses happen in a highly interdisciplinary environment. The dynamic field of machine learning with its modern approach to data mining provides many relevant approaches for neuroscience and enables the exploration of open questions. This state-of-the-art survey offers a collection of papers from the Workshop on Machine Learning and Interpretation in Neuroimaging, MLINI 2011, held at the 25th Annual Conference on Neural Information Processing, NIPS 2011, in the Sierra Nevada, Spain, in December 2011. Additionally, invited speakers agreed to contribute reviews on various aspects of the field, adding breadth and perspective to the volume. The 32 revised papers were carefully selected from 48 submissions. At the interface between machine learning and neuroimaging the papers aim at shedding some light on the state of the art in this interdisciplinary field. They are organized in topical sections on coding and decoding, neuroscience, dynamcis, connectivity, and probabilistic models and machine learning.

This book offers a unique guide to the entire chain of biomedical imaging, explaining how image formation is done, and how the most appropriate algorithms are used to address demands and diagnoses. It is an exceptional tool for radiologists, research scientists, senior undergraduate and graduate students in health sciences and engineering, and university professors.

This book constitutes the refereed proceedings of the Third International Workshop on Machine Learning in Medical Imaging, MLMI 2012, held in conjunction with MICCAI 2012, in Nice, France, in October 2012. The 33 revised full papers presented were carefully reviewed and selected from 67 submissions. The main aim of this workshop is to help advance the scientific research within the broad field of machine learning in medical imaging. It focuses on major trends and challenges in this area, and it presents work aimed to identify new cutting-edge techniques and their use in medical imaging.

This book presents recent advances in pattern analysis of the human connectome. The human connectome, measured by magnetic resonance imaging at the macroscale, provides a comprehensive description of how brain regions are connected. Based on machine learning methods, multiviarate pattern analysis can directly decode psychological or cognitive states from brain connectivity patterns. Although there are a number of works with chapters on conventional human connectome encoding (brain-mapping), there are few resources on human connectome decoding (brain-reading). Focusing mainly on advances made over the past decade in the field of manifold learning, sparse coding, multi-task learning, and deep learning of the human connectome and applications, this book helps students and researchers gain an overall picture of pattern analysis of the human connectome. It also offers valuable insights for clinicians involved in the clinical diagnosis and treatment evaluation of neuropsychiatric disorders.

The field of neuroimaging has reached a watershed and critiques and emerging trends are raising foundational issues of methodology, measurement, and theory. Here, scholars reexamine these issues and explore controversies that have arisen in cognitive science, cognitive neuroscience, computer science, and signal processing.

The cognitive psychology of perception and decision-making is at a cross-road. Most studies still employ categorical designs, a priori classified stimuli and perform statistical evaluations across subjects. However, a shift has been observed in recent years towards parametric designs in which the information content of stimuli is systematically manipulated to study the single-trial dynamics of behaviour (reaction times, eye movements) and brain activity (EEG, MEG, fMRI). By using the information contained in the variance of individual trials, the single-trial approach goes beyond the activity of the average brain: it reveals the specificity of information processing in individual subjects, across tasks and stimulus space, revealing both inter-individual commonalties and differences. This Research Topic provides theoretical and empirical support for the study of single-trial data. Topics of particular interest include: 1. description of the richness of information in single-trials and how it can be successfully extracted; 2. statistical issues related to measures of central tendency, control for multiple comparisons, multivariate approaches, hierarchical modelling and characterization of individual differences; 3. how manipulation of the stimulus space can allow for a direct mapping of stimulus properties onto brain activity to infer dynamics of information processing and information content of brain states; 4. how results from different brain imaging techniques can be integrated at the single-trial level.