Using Machine Learning for Neuronal Activity Imaging

Review Article

Abstract

Recent advancements in understanding neuronal activity have been significantly propelled by the incorporation of machine learning methodologies within the realm of neuroimaging. Machine learning techniques have proven instrumental in recognizing intricate patterns within neuroimaging datasets. Neuroimaging itself represents a convergence of various disciplines, including neuroscience, computer science, psychology, and statistics. It employs quantitative approaches to explore the structure and functions of the central nervous system, serving as a non-invasive and objective avenue for scientific inquiry into the healthy human brain. With its capability to investigate both normal and pathological states, neuroimaging plays a pivotal role in clinical practice and research endeavors. Machine learning and deep learning algorithms have been extensively applied to analyze brain images, facilitating the development of diagnostic and classification systems for conditions such as strokes, psychiatric disorders, epilepsy, neurodegenerative diseases, and demyelinating disorders. This review article presents a thorough examination of the current landscape of neuronal activity imaging, emphasizing the advancements facilitated by machine learning techniques, thereby offering insights into the state-of-the-art methodologies and applications in this burgeoning field