TY - GEN
T1 - The Diagnostics of Osteoarthritis
T2 - 9th International Conference on Robot Intelligence Technology and Applications, RiTA 2021
AU - Salman, Abdulaziz Abdo Saif
AU - Razman, Mohd Azraai Mohd
AU - Khairuddin, Ismail Mohd
AU - Abdullah, Muhammad Amirul
AU - Majeed, Anwar P.P.Abdul
N1 - Funding Information:
Acknowledgement. The authors would like to thank Universiti Malaysia Pahang for funding the study via RDU190360.
Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - Osteoarthritis (OA) is an illness that causes the wear of the protective cartilage between two bones in joints. Patients with OA disease suffer from pain in joints, stiffness, loss of flexibility, amongst others. Conventional means of identifying OA is considered laborious and prone to mistakes. Owing to the advancement of computer vision and computational models, automatic diagnostics is possible. Therefore, this paper proposes the use of transfer learning models for the classification of the different classes of OA. The pre-trained Convolutional Neural Network models used are VGG16, VGG19 and Resnet50, with their fully connected layers, are heuristically fine-tuned. It was demonstrated from this preliminary study that the fine-tuned VGG16 model could classify the classes fairly well in comparison to those that have been reported in the literature.
AB - Osteoarthritis (OA) is an illness that causes the wear of the protective cartilage between two bones in joints. Patients with OA disease suffer from pain in joints, stiffness, loss of flexibility, amongst others. Conventional means of identifying OA is considered laborious and prone to mistakes. Owing to the advancement of computer vision and computational models, automatic diagnostics is possible. Therefore, this paper proposes the use of transfer learning models for the classification of the different classes of OA. The pre-trained Convolutional Neural Network models used are VGG16, VGG19 and Resnet50, with their fully connected layers, are heuristically fine-tuned. It was demonstrated from this preliminary study that the fine-tuned VGG16 model could classify the classes fairly well in comparison to those that have been reported in the literature.
KW - CNN
KW - Fine-tuning
KW - Osteoarthritis
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85128446243&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-97672-9_41
DO - 10.1007/978-3-030-97672-9_41
M3 - Conference Proceeding
AN - SCOPUS:85128446243
SN - 9783030976712
T3 - Lecture Notes in Networks and Systems
SP - 455
EP - 461
BT - Robot Intelligence Technology and Applications 6 - Results from the 9th International Conference on Robot Intelligence Technology and Applications
A2 - Kim, Jinwhan
A2 - Englot, Brendan
A2 - Park, Hae-Won
A2 - Choi, Han-Lim
A2 - Myung, Hyun
A2 - Kim, Junmo
A2 - Kim, Jong-Hwan
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 16 December 2021 through 17 December 2021
ER -