A Study on Detection of COVID-19 in Lung CT Images Using Transfer Learning With Resnet Pre-Trained Model
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2021, Vol 9, Issue 2
Abstract
COVID-19 has impacted the lives of each and every person in the world. Diagnosis of COVID-19 using imaging systems can be integrated with the standard Reverse Transcription Polymerase Chain Reaction (RT-PCR) test to perform the diagnosis more accurately. In this paper, transfer learning based method using a pre-trained deep neural network model viz., ResNet is proposed to classify COVID-19 computed tomography (CT) lung images. The pre-trained model is fine-tuned in order to make it learn the features specific to COVID-19 CT lung images. The proposed method is compared with the methods available in the literature. The results show that the proposed method is comparable to the existing methods.
Authors and Affiliations
Rajeswari R
Keywords
Related Articles
- EP ID EP747535
- DOI 10.21276/ijircst.2021.9.2.5
- Views 58
- Downloads 0
Image Enhancement Using MamdaniFuzzy Inference System
—Image enhancement means to improve the quality of the images for better human perception. The impulsive noise can be reduced and also by using different image enhancement techniques edges of the images can be sharpened....
Determining Long-Term Stability in Environmental Science
A person's or a community's related emissions is an indication of the number of energy needed to produce their commodities. However, data shows that it only lasts for a short period of time. There has been much criticism...
Experimental Study on Light Weight Concrete by Partial Replacement of Cement by Flyash, Coarse Aggregate Pumice Stone and Thermocol Beads
In today’s world when focus is on reducing self-weight of concrete, light weight concrete has come with the high number of applications to reduce self-weight of concrete. In this study an attempt has been made to compare...
An Experimental Study on Performance of Bacteria in Concrete
Concrete is the most commonly used building material, the cracks in concrete create problem. Cracks in concrete occur due to various mechanisms such as - shrinkage, freeze-thaw reactions and mechanical compressive and te...
Combinations, Contradictions, And Cross Fertilization in Actor-Network Theory and Assemblage Thinking
This paper shows that assembling thought as well as actor-network theory (ANT) have such a great deal in common than the debate suggests. It proposes three cross-fertilizations depending on intersections as well as disju...