Automatic Classification of the Severity of Knee Osteoarthritis Using Enhanced Image Sharpening and CNN

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Knee osteoarthritis is a significant cause of physical inactivity and disability. Early detection and treatment of osteoarthritis (OA) degeneration can decrease its course. Physicians’ scores may differ significantly amongst interpreters and are greatly influenced by personal experience based solely on visual assessment. Deep convolutional neural networks (CNN) in conjunction with the Kellgren–Lawrence (KL) grading system are used to assess the severity of OA in the knee. Recent research applied for knee osteoarthritis using machine learning and deep learning results are not encouraging. One of the major reasons for this was that the images taken are not pre-processed in the correct way. Hence, feature extraction using deep learning was not great, thus impacting the overall performance of the model. Image sharpening, a type of image filtering, was required to improve image clarity due to noise in knee X-ray images. The assessment used baseline X-ray images from the Osteoarthritis Initiative (OAI). On enhanced images acquired utilizing the image sharpening process, we achieved a mean accuracy of 91.03%, an improvement of 19.03% over the earlier accuracy of 72% by using the original knee X-ray images for the detection of OA with five gradings. The image sharpening method is used to advance knee joint recognition and knee KL grading.

Related collections

Most cited references 28

Record: found
Abstract: not found
Article: not found

Radiological assessment of osteo-arthrosis.

J H KELLGREN, J. S. Lawrence (1957)

0 comments Cited 1400 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

An Ensemble of Fine-Tuned Convolutional Neural Networks for Medical Image Classification

Jinman Kim, Dagan Feng, Ashnil Kumar … (2017)

The availability of medical imaging data from clinical archives, research literature, and clinical manuals, coupled with recent advances in computer vision offer the opportunity for image-based diagnosis, teaching, and biomedical research. However, the content and semantics of an image can vary depending on its modality and as such the identification of image modality is an important preliminary step. The key challenge for automatically classifying the modality of a medical image is due to the visual characteristics of different modalities: some are visually distinct while others may have only subtle differences. This challenge is compounded by variations in the appearance of images based on the diseases depicted and a lack of sufficient training data for some modalities. In this paper, we introduce a new method for classifying medical images that uses an ensemble of different convolutional neural network (CNN) architectures. CNNs are a state-of-the-art image classification technique that learns the optimal image features for a given classification task. We hypothesise that different CNN architectures learn different levels of semantic image representation and thus an ensemble of CNNs will enable higher quality features to be extracted. Our method develops a new feature extractor by fine-tuning CNNs that have been initialized on a large dataset of natural images. The fine-tuning process leverages the generic image features from natural images that are fundamental for all images and optimizes them for the variety of medical imaging modalities. These features are used to train numerous multiclass classifiers whose posterior probabilities are fused to predict the modalities of unseen images. Our experiments on the ImageCLEF 2016 medical image public dataset (30 modalities; 6776 training images, and 4166 test images) show that our ensemble of fine-tuned CNNs achieves a higher accuracy than established CNNs. Our ensemble also achieves a higher accuracy than methods in the literature evaluated on the same benchmark dataset and is only overtaken by those methods that source additional training data.