Automated Detection of Knee Cartilage Region in X-ray Image

The prevalence of a symptomatic knee or osteoarthritis (OA) is approximately 9.6% in men and 18.0% women over 60 years age according to the OARSI 2016 report. Using early on-stage clinical qualitative assessments through means X-ray scans, cartilage health degradation an individual can be monitored shape surface time. In this paper, we implement application transfer learning models such as InceptionV3, Xception DenseNet201 for feature extraction rebalanced 1,000 images taken from Osteoarthritis Initiative (OAI) dataset with 5 classes graded 0–4 Kellgren-Lawrence grading split into 70/15/15 training/validation/testing split. features extracted are subsequently fed machine classifiers, namely support vector (SVM). An average multiclass accuracy 71.33% was achieved hyperparameter fine-tuned DenseNet201-SVM model.