Meeting Banner
Abstract #1206

K-means clustering of multi-parametric MRI data for improved classification of articular cartilage degeneration

Victor Casula 1 , Simo Saarakkala 2 , Elli-Noora Salo 2 , Jari Rautiainen 1 , Virpi Tiitu 3 , Olli-Matti Aho 4 , Petri Lehenkari 4 , Jutta Ellermann 5 , Mikko J. Nissi 5 , and Miika T. Nieminen 1

1 Department of Radiology, University of Oulu, Oulu, Oulu, Finland, 2 Department of Diagnostic Radiology, University of Oulu, Oulu, Oulu, Finland, 3 Institute of Biomedicine, Anatomy, University of Eastern Finland, Kuopio, Kuopio, Finland, 4 Department of Anatomy and Cell Biology, University of Oulu, Oulu, Oulu, Finland, 5 Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, Minnesota, United States

In this study k-means clustering algorithm was applied to multiparametric MRI data to classify normal and degenerated articular cartilage. Various MRI parameters were assessed at 9.4 T in intact and degraded human cartilage samples and enzymatically degraded bovine cartilage samples. OARSI grading was used as reference for human cartilage. High sensitivity and specificity were achieved using several combinations of two parameters. The best classification involved rotating-frame techniques. Similar results were obtained with combinations of three parameters with no improvements in terms of specificity and sensitivity.

This abstract and the presentation materials are available to members only; a login is required.

Join Here