Detection-Accuracy Enhancement of COVID-19 from Multi-Class Lung Diseases by Instrumenting CLAHE Integrated Deep Learning Technique

ABSTRACT

In this article we have investigated a detection-accuracy enhancement technique of COVID-19 from multi-class lung diseases by instrumenting the CLAHE integrated deep learning technique. The image population is distributed upon disjoint sets of the patients suffering from diseases like (a) Viral-Pneumonia, (b) Lung Opacity, (c) COVID-19 and (d) Normal persons. We have used the CLAHE algorithm to pre-process those images and incorporated the ConvNet algorithm with the help of the transfer learning strategy to perform the analysis. The study reveals that the processing of the X-ray images by CLAHE technique followed by ConvNet algorithm can enhance the performance of the above mentioned four exclusive classes of lung images. Keeping the X-ray image processing using the CLAHE technique intact, we have further explored the diagnosis methods by using several CNN models such as, InceptionResNetV2, InceptionV3 and DenseNet121. In our study, out of 2400 chest X-ray images we have used 80% for the training and 20% for the validation purpose. The comparative study of the performance matrices explicitly shows the enhancement in multi-class detection accuracy. The study also shows that the CLAHE integrated DenseNet121 model provides the best performance exhibiting a maximum accuracy of 98.33% for detecting COVID-19 from multiple diseases. Also we have compared the performance of the present technique with the earlier reported approaches. © 2022 IEEE.