Performance Analysis of CNN and Quantized CNN Model for Rheumatoid Arthritis Identification Using Thermal Image

Abstract

Rheumatoid Arthritis (RA) is distinguished by antibody-mediated inflammation. The most prevalent indications of RA are inflammatory, swollen ankles, tightness, and severe joint discomfort. Finally, RA affects function, impairment, and morbidity by damaging neighboring connective tissues like ligaments, tendons, and cartilages. A range of techniques, comprising radiography, Computed Tomography (CT), ultrasonic, Magnetic resonance imaging (MRI), and thermal imaging, are used to identify and RA diagnose. Infrared (IR) thermal imaging is a non-invasive, fast, and effective approach for assessing early RA. IR-based examinations are a common imaging modality since it is radiation-free and non-invasive. In this study, the required dataset is collected using the IR thermal camera. The collected dataset consists of normal and arthritis-affected thermal images. The dataset is then prepared to be compatible with the Convolution Neural Network (CNN) of the Deep Learning (DL) model and statistical parameters such as mean, mode, mode, kurtosis, etc. are derived and the correlation between the parameters is drawn using the covariance matrix. The dataset is then visualized using graphical plots to view the distribution of the statistical parameters. The dataset is then pre-processed using the normalization method and then analyzed using the CNN model. To find the efficiency of the DL model performance metrics such as accuracy, precision, loss, F-1 score, recall, etc. are calculated. To reduce the complexity and to reduce the computational time, the dataset is quantized using the optimization method and a comparison between the trained model and the quantized model is drawn.