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.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Click here for more information on becoming a member.
