Connectomics is the study of whole brain association maps, i.e., the connectome, with a focus on understanding, quantifying, and visualizing brain network organization. Connectomics research is fo interest to the neuroscientific community largely because of its potential to understand human cognition, its variation over development and aging, and its alteration in disease or injury. As such, big data in connectomics are rapidly growing with emerging international research initiatives collecting large, high quality brain images with structural, diffusion and functional imaging modalities. CNI aims to propel research which leverages this increasing wealth of connectomic data. CNI will bring together computational researchers (computer scientists, data scientists, computational neuroscientists) to discuss advancements in connectome construction, analysis, visualization and their use in clinical diagnosis and group comparison studies.
CNI aims to unify computational researchers with neuroscientists and cultivate interactions toward translational applications for the clinic. For the 3rd year, CNI will feature a single-track workshop with keynote speakers, technical paper presentations and poster sessions. In conjunction, CNI will host a Challenge
with collaborators at the Kennedy Krieger Institute in Baltimore, MD, USA.
Topics of interest include but are not limited to:
Accepted papers are published as LNCS proceedings here.
- Machine learning and data driven methods for biomarker discovery
- Geometric deep learning for connectomics
- Connectome construction: Multi-modal and combinatorial fusion
- Connectome modeling
- Evaluation and validation of connectome models
- Longitudinal analyses
- Computer-assisted diagnoses
- High performance computation