An intelligent IoMT enabled feature extraction method for early detection of knee arthritis

Abstract

AbstractOsteoarthritis and rheumatoid are most common form of arthritis disorder, affecting millions of people worldwide. This article presents a computer aided detection system (CAD) for early knee osteoarthritis and rheumatoid detection using X‐ray images and machine learning classifiers. This work also proposed a novel feature extractor from X‐ray images of knee to assist in detection and classification, called explainable Renyi entropic segmentation with Internet of Things (IoT) framework. The proposed method later utilizes model agnostic algorithm using post hoc explainability for extracting relevant information from prediction of knee joint segmentation. CAD system is integrated with an IoT framework and can be used remotely to assist medical practitioners in treatments of knee arthritis. The presented results show commendable improvement over different existing feature extractors in combination with different classifiers. The best result of proposed extractor method was obtained when combined with random forest classifier having Euclidean hyperparameter that gave an accuracy of 95.23%, among all the evaluators. The obtained results show the effectiveness of proposed feature extractor model to determine relevant features from knee and describe the suitable knee disorders.