Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Feature learning to automatically assess radiographic knee osteoarthritis severity

Antony, Joseph orcid logoORCID: 0000-0001-6493-7829, McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477, Moran, Kieran orcid logoORCID: 0000-0003-2015-8967 and O'Connor, Noel E. orcid logoORCID: 0000-0002-4033-9135 (2020) Feature learning to automatically assess radiographic knee osteoarthritis severity. In: Nanni, Loris, Brahnam, Sheryl, Brattin, Rick, Ghidoni, Stefano and Jain, Lakhmi, (eds.) Deep Learners and Deep Learner Descriptors for Medical Applications. Intelligent Systems Reference Library (ISRL), 186 . Springer, 9 -93. ISBN 978-3-030-42750-4

Abstract
Feature learning refers to techniques that learn to transform raw data input into an effective representation for further higher-level processing in many computer vision tasks. This chapter presents the investigations and the results of feature learning using convolutional neural networks to automatically assess knee osteoarthritis (OA) severity and the associated clinical and diagnostic features of knee OA from radiographs (X-ray images). Also, this chapter demonstrates that feature learning in a supervised manner is more effective than using conventional handcrafted features for automatic detection of knee joints and fine-grained knee OA image classification. In the general machine learning approach to automatically assess knee OA severity, the first step is to localize the region of interest that is to detect and extract the knee joint regions from the radiographs, and the next step is to classify the localized knee joints based on a radiographic classification scheme such as Kellgren and Lawrence grades. First, the existing approaches for detecting (or localizing) the knee joint regions based on handcrafted features are reviewed and outlined in this chapter. Next, three new approaches are introduced: 1) to automatically detect the knee joint region using a fully convolutional network, 2) to automatically assess the radiographic knee OA using CNNs trained from scratch for classification and regression of knee joint images to predict KL grades in ordinal and continuous scales, and 3) to quantify the knee OA severity optimizing a weighted ratio of two loss functions: categorical cross entropy and mean-squared error using multi-objective convolutional learning. The results from these methods show progressive improvement in the overall quantification of the knee OA severity. Two public datasets: the OAI and the MOST are used to evaluate the approaches with promising results that outperform existing approaches. In summary, this work primarily contributes to the field of automated methods for localization (automatic detection) and quantification (image classification) of radiographic knee OA.
Metadata
Item Type:Book Section
Refereed:Yes
Uncontrolled Keywords:Feature learning; Handcrafted features; Convolutional neural networks; Kellgren and Lawrence grades; Automatic detection; Classifcation; Regression; Multi-objective convolutional learning
Subjects:Computer Science > Algorithms
Computer Science > Artificial intelligence
Computer Science > Image processing
Computer Science > Machine learning
Engineering > Signal processing
Engineering > Electronic engineering
Physical Sciences > Radiography, medical
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
DCU Faculties and Schools > Faculty of Science and Health > School of Health and Human Performance
Research Institutes and Centres > INSIGHT Centre for Data Analytics
Publisher:Springer
Official URL:http://dx.doi.org/10.1007/978-3-030-42750-4_2
Copyright Information:© 2020 Springer
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland (SFI) under grant numbers SFI/12/RC/2289 and 15/SIRG/3283., OAI is a public-private partnership comprised of five contracts (N01-AR-2-2258; N01-AR-2-2259; N01-AR-2-2260; N01-AR-2-2261; N01-AR-2-2262) funded by the National Institutes of Health, a branch of the Department of Health and Human Services, Private funding partners include Merck Research Laboratories; Novartis Pharmaceuticals Corporation, GlaxoSmithKline; and Pfizer, Inc., Foundation for the National Institutes of Health
ID Code:24468
Deposited On:20 May 2020 10:23 by Joseph Antony . Last Modified 01 Feb 2023 22:09
Documents

Full text available as:

[thumbnail of Book_Chapter___Feature_Learning_to_Assess_Knee_OA_Severity.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
11MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record