Corona-Nidaan: lightweight deep convolutional neural network for chest X-Ray based COVID-19 infection detection

Abstract

The coronavirus COVID-19 pandemic is today’s major public health crisis, we have faced since the Second World War. The pandemic is spreading around the globe like a wave, and according to the World Health Organization’s recent report, the number of confirmed cases and deaths are rising rapidly. COVID-19 pandemic has created severe social, economic, and political crises, which in turn will leave long-lasting scars. One of the countermeasures against controlling coronavirus outbreak is specific, accurate, reliable, and rapid detection technique to identify infected patients. The availability and affordability of RT-PCR kits remains a major bottleneck in many countries, while handling COVID-19 outbreak effectively. Recent findings indicate that chest radiography anomalies can characterize patients with COVID-19 infection. In this study, Corona-Nidaan, a lightweight deep convolutional neural network (DCNN), is proposed to detect COVID-19, Pneumonia, and Normal cases from chest X-ray image analysis; without any human intervention. We introduce a simple minority class oversampling method for dealing with imbalanced dataset problem. The impact of transfer learning with pre-trained CNNs on chest X-ray based COVID-19 infection detection is also investigated. Experimental analysis shows that Corona-Nidaan model outperforms prior works and other pre-trained CNN based models. The model achieved 95% accuracy for three-class classification with 94% precision and recall for COVID-19 cases. While studying the performance of various pre-trained models, it is also found that VGG19 outperforms other pre-trained CNN models by achieving 93% accuracy with 87% recall and 93% precision for COVID-19 infection detection. The model is evaluated by screening the COVID-19 infected Indian Patient chest X-ray dataset with good accuracy.

Study of Different Deep Learning Methods for Coronavirus (COVID-19) Pandemic: Taxonomy, Survey and Insights

“…Convid-Net achieved an accuracy of 97.99%. The authors of [111] suggested a lightweight deep convolutional neural network for chest X-rays. The proposed architecture was inspired by InceptionV3, InceptionResNetV2, and MobileNetV2.…”

COVID-19 Diagnosis on Chest Radiographs with Enhanced Deep Neural Networks

“…A novel deep neural network known as Corona-Nidaan was proposed in Chakraborty et al (2021) [ 14 ]. The Corona-Nidaan was built of 91 layers with depth-wise separable convolutional layers, batch normalization layers, a global average pooling layer, residual connection as the uniqueness.…”

An evaluation of lightweight deep learning techniques in medical imaging for high precision COVID-19 diagnostics

“…Other approaches that have reported the use and evaluated the performance of deep learning algorithms in the diagnosis of COVID-19 applications with X-ray images include the use of space transformer network (STN) with CNNs by Soni et al. [36] , Alqudah, Qazan and Alqudah [37] , Chakraborty, Dhavale and Ingole [38] , Karakanis and Leontidis [39] , Bekhet et al. [40] ; Huang and Liao [41] developed lightweight CNNs using Chest X-ray images based COVID-19 detection.…”