The diagnostics of osteoarthritis : A fine-tuned transfer learning approach

No default citation style available for Eprints

	Pdf The Diagnostics of Osteoarthritis_A Fine-Tuned Transfer Learning Approach.pdf Restricted to Repository staff only Download (679kB) | Request a copy
Preview	Pdf The diagnostics of osteoarthritis_A fine-tuned transfer learning approach_ABS.pdf Download (88kB) | Preview

Abstract

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.

Item Type:	Conference or Workshop Item (Lecture)
Additional Information:	Indexed by Scopus
Uncontrolled Keywords:	CNN; Fine-tuning; Osteoarthritis; Transfer learning
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) T Technology > TA Engineering (General). Civil engineering (General) T Technology > TJ Mechanical engineering and machinery T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division:	College of Engineering Faculty of Computing Faculty of Manufacturing and Mechatronic Engineering Technology
Depositing User:	Mr Muhamad Firdaus Janih@Jaini
Date Deposited:	01 Dec 2023 07:42
Last Modified:	01 Dec 2023 07:42
URI:	http://umpir.ump.edu.my/id/eprint/39468
Download Statistic:	View Download Statistics

Actions (login required)

View Item