In this chapter, a machine learning-based knee
Osteoarthritis (OA) detection system from magnetic resonance (MR) images is
proposed. This system is capable of detecting the presence of OA considering
two classification categories: ‘non-OA’ and ‘OA’. OA is one of the most
prevalent condition resulting to disability particularly in elderly population.
OA is the most common articular disease of the developed world and a leading
cause of chronic disability, mainly as a consequence of the knee OA and/or hip
OA. Nowadays, medical images such as MR images are widely used for the OA
diagnosis. For this, a medical specialist analyzes medical images by measuring
the changes and in particular for knee OA, the changes in the compartment of
the tibio-femoral cartilage. The proposed method consists mainly of both a data
processing module and binary classification module, which process the 3-D data
from MR images. In this study, we present a novel knee OA diagnostic approach
that can identify the condition using magnetic resonance MR images using the
Support Vector Machine (SVM) algorithm. Our suggested method is predicated on
using 3-D data from MR scans of an actual cohort and the Independent Component
Analysis (ICA) technique. The experimental results showed that our ICA-SVM
machine learning model achieved 86% of testing accuracy with both 72% of
specificity and 100% of sensitivity, once trained with a small MR image
dataset. Furthermore, a benchmark evaluation was performed. The results suggest
that using a larger and more diverse dataset could ensure the robustness of the
proposed method. In future works, we will study the complementary use of ICA
components from MR images and a convolutional neural network (CNN) to try to
achieve better predictive rates in supervised learning using a larger dataset.
Author(s) Details:
Marco Oyarzo Huichaqueo,
School of Engineering, Rovira i Virgili University, 43007,
Tarragona, Spain.
Please see the link here: https://stm.bookpi.org/TAER-V2/article/view/13114
No comments:
Post a Comment