Within the PrevOP research network "Preventing the progression of primary Osteoarthritis by high impact long-term Physical exercise regimen – key mechanisms, efficacy, and long-term results." the aim of sub-project 4 is to assess and to quantitatively analyze morphological and structural changes related to osteoarthritis (OA) with respect to different levels of exercise.
In arthritic knees typical OA-related findings are the degeneration of cartilage, menisci and ligaments. Furthermore, in the majority of cases of severe OA, bone marrow lesions and subarticular cysts occur. It is assumed that these structures can be quantitatively assessed with medical imaging techniques, in particular MRI.
In this project using experts' rating and machine learning techniques, OA-related quantitative image features will be identified for every relevant structure. Combining all image features might lead to a novel image-based OA-score. This OA-score could be used to support the hypothesis that exercise slows down the progression of OA.

Fig 1: Features of osteoarthritis: Cartialge defects, meniscal tears, bone marrow lesions and subarticular cysts.

Osteoarthritis Initiative (OAI) database

In the OAI database MR image data and radiographs are publicly available for almost 5.000 patients. In addition to basic scoring data (i.e. WOMAC and Kellgren-Lawrence score) several image assessment studies have been carried out:

  • Whole-Organ Magnetic Resonance Imaging Score (WORMS) and Boston Leeds Osteoarthritis Knee Score (BLOKS) scoring results have been published in Mai 2011 for 115 patients
  • MRI Osteoarthritis Knee Score (MOAKS) reading results have been published in April 2015 for 600 patients

Extracting and learning OA-related image features with OAI data

Image features will be extracted for each OA-related structure (cartilage, meniscus, ligaments, bone marrow lesions and subarticular cysts). Employing methods of machine learning and using the data of the WORMS, BLOKS and MOAKS image assessment studies, the correlation between these image features and the experts' reading will be investigated.

Prospective PrevOP study

The prospective PrevOP study started in February 2016 at the Charité. For two years, approximately 240 patients will perform regular exercise under psychological supervision.

After suitable image features that correlate with OA-severity and -progression have been identified with data from the OAI database, it will be evaluated for data of the PrevOP study, if regular exercise slows down the rate of OA progression.

Automatic knee segmentation and image feature extraction

To generate specific regions of interest for the considered anatomical structures in the MRI data, the knee bones (femur and tibia), the femoral and tibial cartilage, and the menisci are automatically segmented using statistical shape models. The correlation of image features extracted in these regions and the experts' reading (WORMS, BLOKS, MOAKS) will be evaluated.