A novel method for automatic localization of joint area on knee plain radiographs
This work addresses the problem of subjective and experience-dependent visual evaluation in knee osteoarthritis diagnosis for medical practitioners, offering an incremental improvement in computer-aided diagnostics.
The study tackled the challenge of automatically localizing joint areas on knee radiographs for osteoarthritis diagnosis, achieving mean intersection over union scores of 0.84, 0.79, and 0.78 across three datasets with processing times as low as 14-16ms.
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.