Differential diagnosis of neurodegenerative diseases using structural MRI data

NeuroImage Clinical

J. Koikkalainen, H. Rhodius-Meester, A. Tolonen, F. Barkhof, B. Tijms, AW. Lemstra, T. Tong, R. Guerrero, A. Schuh, C. Ledig, D. Rueckert, H. Soininen, AM. Remes, G. Waldemar, S. Hasselbalch, P. Mecocci, W. van der Flier, J. Lötjönen

To support differential diagnosis for dementias, features in structural MRI scans were analyzed in this study. An extensive set of features was extracted to quantify volumetric and morphometric characteristics from T1 images and vascular characteristics from FLAIR images. The Disease State Index methodology was used to perform the classification of Alzheimer’s disease, frontotemporal dementia, vascular dementia, dementia with Lewy bodies, and healthy controls. Based on the results, the team determined that automated quantification methods and computerized decision support methods are feasible for clinical practice and might help with diagnosis.