Dr. Norman Scheel

Photo of Dr. Norman  Scheel

Research Associate
Michigan State University
Radiology Human Medicine Faculty
Lansing, MI





Classification of neurodegenerative brain states based on multivariate fMRI data


In medicine, biomarkers associated with a specific disease are often used as diagnostic tools. In particular, the intrinsic functional organization of the human brain, assessed by resting-state fMRI, has gained increasing attention. Given the myriad of parameters of spatio-temporal fMRI-data, one major challenge in this research is to find those features that are most predictive for a given disease.


We use machine learning approaches on resting-state fMRI data to unravel differences in brain connectivity in different subject groups. Especiallly comparing the predictive value of fine-scale and global connectomes leads the way to standardized methods for the identification of resting-state biomarkers.




  • Scheel, N., Esswanger, A., Münte, T. F., Heldmann, M., Krämer, U. M., and Mamlouk, A. M.: Selection of Seeds for Resting-State fMRI-Based Prediction of Individual Brain Maturity: Bildverarbeitung für die Medizin, Informatik aktuell, pp. 371-376, 2015


  • Scheel, N., Chang, C., and Mamlouk, A. M.: The importance of physiological noise regression in high temporal resolution fMRI: Artificial Neural Networks - ICANN 2014, Springer, pp. 540-547, 2014