Abstract

Osteoarthritis (OA) is a prevalent degenerative joint disease,particularly affecting the knees. Early and accurate detection of OA and its severity, often graded using the Kellgren-Lawrence (KL) scale, is crucial for timely intervention and management. This study explores the application of deep learning techniques to automatically detect OA and assign KL grades from knee X-ray images. We propose a novel deep learning architecture that effectively extracts relevant features from X-ray images and classifies them into different KL grades. Our model demonstrates promising results in terms of accuracy and sensitivity, potentially aiding radiologists in making faster and more accurate diagnoses.

Instructions:

The dataset, compressed in the .7z format, contains three main folders:

discarded: This folder holds discarded X-ray images that were not suitable for further analysis.
KLGrade: This folder houses X-ray images of knees with osteoarthritis. Each image is categorized into one of five KL Grades (0-4) based on expert assessments. The images have undergone pre-processing, including Region of Interest (ROI) extraction.
withoutKLGrade: This folder contains X-ray images from various body joints. The images are classified into two categories: "normal" and "patient." These images have not been subjected to any pre-processing techniques like ROI extraction or segmentation.

Pre-processing Scripts: To gain insights into the image pre-processing techniques applied to the "KLGrade" and "withoutKLGrade" datasets, refer to the attached sample scripts. These scripts can be executed within MATLAB's Image Batch Processor to automate the process.

Note: To access the dataset, you'll need to decompress the .7z file using a tool like 7-Zip.

Datasets

Standard Dataset

Osteoarthritis

Abstract

Dataset Files

QUESTIONS?