DescriptionBack to top
Neuroimaging involves generating images of the central nervous system to understand its structure, function, or pharmacology. The field is rapidly evolving, with new techniques emerging for data acquisition and advanced statistical learning methods being developed for data analysis. Recently, there’s been a surge in collecting neuroimaging data across healthcare, research, and clinical trials. Such imaging aids in diagnosing and prognosing brain diseases, like multiple sclerosis, dementia, and schizophrenia. It helps identify issues such as strokes, tumors, and brain swelling. Current applications, like MRI for multiple sclerosis monitoring, still present opportunities for enhanced statistical modeling.
Large biomedical studies gather extensive neuroimaging data, including sMRI, DWI, and fMRI. These studies target the human brain’s connectivity, understanding brain disorders, monitoring neuropsychiatric progression, and diagnosing brain cancer. The influx of data can significantly enhance our comprehension of the brain and help in creating effective treatments for neurological and psychiatric conditions. However, analyzing this data necessitates the progression of statistical learning techniques, encompassing image processing and population-based statistical evaluations. While topics like image enhancement and predictive models are of interest, the growth in statistical analysis lags behind neuroimaging advancements, challenging the application of research in clinical settings.
This workshop aims is to provide a comprehensive discussion of mathematical and statistical challenges in neuroimaging data analysis from neuroimaging techniques to large-scale neuroimaging studies to statistical learning methods. This research topic is important and timely to ensure that researchers are equipped with the tools and methods needed to handle the large and complex datasets and to produce reliable and reproducible research findings.