Machine learning based texture analysis of patella from X-rays for detecting patellofemoral osteoarthritis

Highlights

• Texture features of patellar region from lateral view radiographs (X-rays) were studied.

• The performances of hand-crafted features, deep convolutional neural network features, and clinical variables were compared.

• We proposed a stacked model where both patellar texture and clinical feature predictions are combined with a second level machine learning model.

• Our results showed that texture features of patellar bone are different between knees with and without PFOA.

• As a result, patellar bone texture features may be used in the future as novel imaging biomarkers in OA diagnostics..

Abstract

Objective

To assess the ability of texture features for detecting radiographic patellofemoral osteoarthritis (PFOA) from knee lateral view radiographs.

Design

We used lateral view knee radiographs from The Multicenter Osteoarthritis Study (MOST) public use datasets (n  = 5507 knees). Patellar region-of-interest (ROI) was automatically detected using landmark detection tool (BoneFinder), and subsequently, these anatomical landmarks were used to extract three different texture ROIs. Hand-crafted features, based on Local Binary Patterns (LBP), were then extracted to describe the patellar texture. First, a machine learning model (Gradient Boosting Machine) was trained to detect radiographic PFOA from the LBP features. Furthermore, we used end-to-end trained deep convolutional neural networks (CNNs) directly on the texture patches for detecting the PFOA. The proposed classification models were eventually compared with more conventional reference models that use clinical assessments and participant characteristics such as age, sex, body mass index (BMI), the total Western Ontario and McMaster Universities Arthritis Index (WOMAC) score, and tibiofemoral Kellgren-Lawrence (KL) grade. Atlas-guided visual assessment of PFOA status by expert readers provided in the MOST public use datasets was used as a classification outcome for the models. Performance of prediction models was assessed using the area under the receiver operating characteristic curve (ROC AUC), the area under the precision-recall (PR) curve -average precision (AP)-, and Brier score in the stratified 5-fold cross validation setting.

Results

Of the 5507 knees, 953 (17.3%) had PFOA. AUC and AP for the strongest reference model including age, sex, BMI, WOMAC score, and tibiofemoral KL grade to predict PFOA were 0.817 and 0.487, respectively. Textural ROI classification using CNN significantly improved the prediction performance (ROC AUC = 0.889, AP = 0.714).

Conclusion

We present the first study that analyses patellar bone texture for diagnosing PFOA. Our results demonstrates the potential of using texture features of patella to predict PFOA.