Diagnosing COVID-19 of Lung CT Scan by Using Convolution Neural Network

EasyChair Preprint 6112, version 1

Abstract

The rapid spread and deaths caused by COVID-19 prompted us to find a way to diagnose it in a shorter period of time and with better accuracy. One of the ways to diagnose COVID-19 is through CT images because the disease has an effect on the patient's lungs. The proposed method is to classify the disease by parallel models after performing a preprocessing that involves resize and augmenting CT images using conventional data augmentation techniques and exposing the lungs as regions of interest. The three models (MuNet, NASNet, and MobileNetV2) were selected for the proposed model after comparing them with more than one model and obtaining the best accuracy. where the model got accuracy(0.97), Precision(0.94), Recall(0.99),(0.97) and F1 Score respectively using dataset 1 for covid. As for dataset 2 The proposed model obtained (0.9661 ) inaccuracy, (0.95 ) in Precision, (0.95) in Recall, and (0.95) in F1 Score for covid.

Keyphrases: CNN, CT scan, Diagnosing COVID-19

@booklet{EasyChair:6112,
  author    = {Mustafa Khalaf Hashem and Ahmed Slim Abbas},
  title     = {Diagnosing COVID-19 of Lung CT Scan by Using Convolution Neural Network},
  howpublished = {EasyChair Preprint 6112},
  year      = {EasyChair, 2021}}