Title: Enhancing multiclass classification of knee osteoarthritis severity grades using oneDNN

Authors: Akshay Bhuvaneswari Ramakrishnan; Shriram K. Vasudevan; T.S. Murugesh; Sini Raj Pulari

Addresses: Department of Computer Science and Engineering, SASTRA Deemed to be University, SASTRA University Thanjavur Campus, Thanjavur, Tamil Nadu, India ' Intel India Pvt. Ltd., SRR Elite, RMZ Ecoworld Rd, Sector 3, Bellandur, Bengaluru, Karnataka 560103, India ' Department of Electronics and Communication Engineering, Government College of Engineering Srirangam, Sethurappatti, Tiruchirappalli, 620 012, Tamil Nadu State, India ' Department of Bachelor of ICT, EDICT, Bahrain Polytechnic (Bahrain Technical College), Isa Town, The Kingdom of Bahrain

Abstract: Osteoarthritis of the knee (OA) is a degenerative joint condition affecting around 23% of adult patients in the USA and globally. To diagnose OA early and assess severity grades, knee images were classified into five severity categories using the Knee Osteoarthritis Dataset with Severity Grading dataset from Kaggle. The highest severity grade was grade 4. Pre-processing processes, including data reduction and augmentation, were required to correct the uneven distribution of class information. As the dataset had an uneven distribution of class information, pre-processing processes including data reduction and augmentation were required to correct the problem In addition, the classification process was carried out with the assistance of three widely used convolutional neural network models. We proposed a new architecture and have used three of the following models for classification EfficientNetB5, DenseNet201, and Inception V3. Additionally, all these models are optimised with oneDNN library using oneAPI.

Keywords: osteoarthritis; convolutional neural network; CNN; oneDNN; oneAPI; medical AI.

DOI: 10.1504/IJBRA.2023.133704

International Journal of Bioinformatics Research and Applications, 2023 Vol.19 No.3, pp.200 - 212

Received: 07 Jul 2023
Accepted: 01 Aug 2023
Published online: 29 Sep 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article