Paper Title
A Novel Framework for COVID – 19 Diagnosis Combining U – Net and CNN Architectures

Abstract
The COVID-19 pandemic has posed a significant challenge to the world's wisdom and technologies. Communities around the world are searching for a real-time system for accurate treatment and cure of COVID-19 infected cases. Currently, the worldwide method for detecting COVID-19 is through Reverse Transcription Polymerase Chain Reaction (RT-PCR), which is expensive and time-consuming. Deep active learning can play a vital role in the diagnosis of COVID-19 and checking the spread of this disease [1]. Computer-assisted analysis with deep learning approaches can enable automatic detection [2] of COVID-19 using CT scans. A novel framework is proposed that uses CT scans and patient-level labels to diagnose COVID-19. This framework consists of two key components: a 2D U-Net for lung region segmentation and CNN for classification. The experimental results demonstrate the efficacy of our system. Keyword - COVID 19, U – Net, CT Scans, Convolutional Neural Network, Lung Segmentation.