Aristeidis Sotiras, PhD
Assistant Professor of Radiology
School of Medicine
Aristeidis Sotiras, PhD, is focused on developing and applying machine learning and image analysis techniques to extract and integrate relevant information from images and other clinical data toward improving patient-specific diagnosis and prognosis.
Aristeidis Sotiras, PhD, is an Assistant Professor at the Institute for Informatics and the Department of Radiology at Washington University School of Medicine in St. Louis. His research interests are at the intersection of medical image analysis, machine learning, and computational neuroscience. Dr. Sotiras focuses on developing novel computational tools to extract quantitative information from imaging data and delineate patterns in large heterogeneous data sets with the goal of improving patient-specific diagnosis and advancing our understanding of brain structure and function in health and disease.
Dr. Sotiras received his PhD, with the highest distinction and the committee compliments, in applied mathematics from Ecole Centrale Paris, where his research focused on developing novel algorithms for deformable image alignment. Dr. Sotiras also received his graduate degree in applied mathematics from Ecole Polytechnique, and his undergraduate degree in electrical and computer engineering from the National Technical University of Athens.
- Biomedical image processing and analysis
- Machine learning
- Deep learning
- Computer vision
- Imaging biomarkers of neurodegenerative and neuropsychiatric disorders
- White Matter Lesions: Spatial Heterogeneity, Links to Risk Factors, Cognition, Genetics, and Atrophy. Neurology
- Patterns of Coordinated Cortical Remodeling During Adolescence and their Associations with Functional Specialization and Evolutionary expansion. Proceedings of the National Academy of Sciences
- HYDRA: Revealing Heterogeneity of Imaging and Genetic Patterns Through a Multiple Max-margin Discriminative Analysis Framework. Neuroimage
- A Discrete MRF Framework for Integrated Multi-Atlas Registration and Segmentation. International Journal of Computer Vision
- Finding Imaging Patterns of Structural Covariance via Non-Negative Matrix Factorization. Neuroimage
- Deformable Medical Image Registration: A Survey. IEEE Transactions on Medical Imaging
- Deformable Medical Image Registration: Setting the State of the Art with Discrete Methods. Annual Review of Biomedical Engineering