COVID-19 Diagnosis System using SimpNet Deep Model

After the outbreak of COVID-19, immediately it converted from epidemic to pandemic. Radiologic images of CT and X-ray have been widely used to detect COVID-19 disease through observing infrahilar opacity in the lungs. Deep learning has gained popularity in diagnosing many health diseases including COVID-19 and its rapid spreading necessitates the adoption of deep learning in identifying COVID-19 cases. In this study, a deep learning model, based on some principles has been proposed for automatic detection of COVID-19 from X-ray images. The SimpNet architecture has been adopted in our study and trained with X-ray images. The model was evaluated on both binary (COVID-19 and No-findings) classification and multi-class (COVID-19, No-findings, and Pneumonia) classification tasks. Our model has achieved an accuracy value of 98.4% for binary and 93.8% for the multi-class classification. The number of parameters of our model is 11 Million parameters which are fewer than some state-of-the-art methods with achieving higher results. © 2022 University of Baghdad. All rights reserved.

ECOVIDNET: Snapshot Ensembling Approach to Detect Coronavirus from Chest X-ray Images

To tackle the global pandemic of COVID-19, scholars are looking for accurate and efficient artificial intelligence approaches to screen the chest situation of the X-Ray images of the COVID-Affected people. Developing an accurate deep model is a goal which can be achieved through an ensemble of multiple deep models. Utilizing multiple networks boosts the performance and surpasses utilizing a single model classifier. However, it suffers from a high computational cost of training. To avoid this, we propose a novel deep network model namely ECOVIDNet. The proposed model is based on merging multiple model snapshots for final prediction at the cost of a single training run. The proposed scheme adopts EfficientNet through the transfer learning process with freezing all trainable layers and adding two fully connected layers at the end of the model. The model is trained on an X-ray image dataset with achieving an accuracy of 99.2%, 96.8% for binary (Normal vs COVID-19), and ternary (Normal vs COVID-19 vs Pneumonia) classifications. The model is evaluated with 5-fold cross-validation and obtained precision, sensitivity, and F1-score of 99.5%, 99.5, and 99.4%, respectively. Also, the proposed model yields 96.62% of precision, 96.5% of sensitivity, and 96.48% of F1-score in ternary classification. © 2022 IEEE.