A novel method for automatic localization of joint area on knee plain radiographs

TL;DR

This paper introduces a fast, computationally efficient method for automatically localizing knee joint areas in radiographs, improving objectivity in osteoarthritis diagnosis.

Contribution

The study presents a novel two-part pipeline combining anatomically-based proposals with machine learning for accurate knee joint localization.

Findings

Mean intersection over union scores of 0.84, 0.79, and 0.78 on three datasets.

Automatic annotation within 14-16ms for standard images.

Suitable for large-scale knee radiograph analysis.

Abstract

Osteoarthritis (OA) is a common musculoskeletal condition typically diagnosed from radiographic assessment after clinical examination. However, a visual evaluation made by a practitioner suffers from subjectivity and is highly dependent on the experience. Computer-aided diagnostics (CAD) could improve the objectivity of knee radiographic examination. The first essential step of knee OA CAD is to automatically localize the joint area. However, according to the literature this task itself remains challenging. The aim of this study was to develop novel and computationally efficient method to tackle the issue. Here, three different datasets of knee radiographs were used (n = 473/93/77) to validate the overall performance of the method. Our pipeline consists of two parts: anatomically-based joint area proposal and their evaluation using Histogram of Oriented Gradients and the pre-trained Support Vector Machine classifier scores. The obtained results for the used datasets show the mean intersection over the union equal to: 0.84, 0.79 and 0.78. Using a high-end computer, the method allows to automatically annotate conventional knee radiographs within 14-16ms and high resolution ones within 170ms. Our results demonstrate that the developed method is suitable for large-scale analyses.