Abstract #0350

Gray Level Co-occurrence Matrix Based 3D Texture Analysis of Knee Articular Cartilage using 3D DESS Images

Ari Väärälä^1,2, Arttu Peuna³, Egor Panfilov^1,2, Victor Casula^1,2, Marianne Haapea^2,4, Eveliina Lammentausta^1,2,4, and Miika T Nieminen^1,2,4

¹Research Unit of Medical Imaging, Physics and Technology, University of Oulu, Oulu, Finland, ²Medical Research Center, University of Oulu and Oulu University Hospital, Oulu, Finland, ³Medical Imaging, Central Finland Health Care District, Jyväskylä, Finland, ⁴Department of Diagnostic Radiology, Oulu University Hospital, Oulu, Finland

In the present study, a gray level co-occurrence matrix-based 3D texture analysis of knee 3D DESS images was used to investigate longitudinal changes in articular cartilage using data from the Osteoarthritis Initiative (baseline, 36-month and 72-month visits). At baseline, all subjects included in the study had Kellgren-Lawrence grade < 2. Three groups were defined, based on time of progression into radiographic osteoarthritis (Kellgren-Lawrence grades ≥ 2): control, slow progressor and fast progressor groups. 3D texture analysis of 3D DESS images was able to distinguish progressors from controls before radiographic signs of osteoarthritis and showed significant longitudinal changes across all groups.

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

Join Here