TY - GEN
T1 - Osteoarthritis Diagnosis
T2 - 10th International Conference on Robot Intelligence Technology and Applications, RiTA 2022
AU - Salman, Abdulaziz Abdo Saif
AU - Almanifi, Omair Rashed Abdulwareth
AU - Abdullah, Muhammad Amirul
AU - Mohd Razman, Mohd Azraai
AU - Ahmad, Ahmad Fakhri
AU - Liu, Chenguang
AU - Yap, Eng Hwa
AU - P. P. Abdul Majeed, Anwar
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - Osteoarthritis (OA) is a condition that causes the protective cartilage between two bones in joints to wear away. Consequently, more often than not, patients with OA experience joint discomfort, stiffness and limited flexibility, amongst other symptoms. It is worth noting that the conventional approach in diagnosing OA is rather labour-intensive and susceptible to misdiagnosis. Nevertheless, with the advancement of computer vision, automatic OA diagnostics is no longer a far cry. In this extended work, different feature-based transfer learning (TL) models, namely Resnet50, VGG16, and VGG19 are used to extract features from the X-ray images prior being fed into a Random Forest (RF) model to classify the different degrees of OA. It was demonstrated through the present study that the VGG16+RF pipeline yielded a better average in the validation and testing classification accuracy against the other evaluated pipelines, suggesting the efficacy of VGG16 as a feature extractor for OA based images.
AB - Osteoarthritis (OA) is a condition that causes the protective cartilage between two bones in joints to wear away. Consequently, more often than not, patients with OA experience joint discomfort, stiffness and limited flexibility, amongst other symptoms. It is worth noting that the conventional approach in diagnosing OA is rather labour-intensive and susceptible to misdiagnosis. Nevertheless, with the advancement of computer vision, automatic OA diagnostics is no longer a far cry. In this extended work, different feature-based transfer learning (TL) models, namely Resnet50, VGG16, and VGG19 are used to extract features from the X-ray images prior being fed into a Random Forest (RF) model to classify the different degrees of OA. It was demonstrated through the present study that the VGG16+RF pipeline yielded a better average in the validation and testing classification accuracy against the other evaluated pipelines, suggesting the efficacy of VGG16 as a feature extractor for OA based images.
KW - CNN
KW - Ensemble
KW - Feature extraction
KW - Osteoarthritis
KW - Random forest
UR - http://www.scopus.com/inward/record.url?scp=85151063614&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-26889-2_41
DO - 10.1007/978-3-031-26889-2_41
M3 - Conference Proceeding
AN - SCOPUS:85151063614
SN - 9783031268885
T3 - Lecture Notes in Networks and Systems
SP - 451
EP - 455
BT - Robot Intelligence Technology and Applications 7 - Results from the 10th International Conference on Robot Intelligence Technology and Applications
A2 - Jo, Jun
A2 - Choi, Han-Lim
A2 - Helbig, Marde
A2 - Oh, Hyondong
A2 - Hwangbo, Jemin
A2 - Lee, Chang-Hun
A2 - Stantic, Bela
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 7 December 2022 through 9 December 2022
ER -