Abstract: A method for detecting symptomatic osteoarthritis in a human patient who is otherwise asymptomatic comprises: taking a plurality of magnetic resonance (MR) image signal features from MR sequences in a joint of the patient; submitting the MR image signal features to a classifier for performing a feature reduction for redundant or unnecessary features; calculating a signal texture index (STI) value from the remaining image features; comparing that STI value against the STI values of one group of individuals suspected of being vulnerable to developing osteoarthritis at the first point in time; and the same group of individuals years later; predicting from that comparison of STI values a likelihood of the patient developing osteoarthritis; and treating the patient accordingly.

Abstract: A method for detecting symptomatic osteoarthritis in a human patient who is otherwise asymptomatic comprises: taking a plurality of magnetic resonance (MR) image signal features from MR sequences in a joint of the patient; submitting the MR image signal features to a classifier for performing a feature reduction for redundant or unnecessary features which are then eliminated; calculating a signal texture index (STI) value from the remaining image features; comparing that STI value against two population databases, one for individuals known to develop osteoarthritis and a second for individuals known not to develop osteoarthritis at a given time point; prognosticating from the STI value, a likelihood of the patient developing osteoarthritis; and treating the patient accordingly.

Abstract: In this work, a Magnetic Resonance Imaging (MRI)-based automatic classifier was designed to predict changes due to osteoarthritis (OA) years prior to their symptomatic presentation and radiographic detection. For each patient, multiple image texture features were measured from the T2 map of the patella cartilage and the lateral and medial compartments of the femoral condyle. A support vector machine (SVM)-based linear discriminant function was trained to predict health status, as well as the affected knee compartment. Feature selection was integrated into the classifier training to drastically reduce the number of image (biomarker) features without sacrificing classification accuracy. It was found that a dominant knee compartment determined the classification decision for most patients. We demonstrate that the signal texture index (STI) predicts disease progression prior to symptoms or radiographic signs of OA.