sudo-rajarshi / Covid-Detection-from-CXR-Scans-using-Deep-Multi-layered-CNN

Covid Detection from CXR Scans using Deep Multi-layered CNN

Covid-Detection-from-CXR-Scans-using-Deep-Multi-layered-CNN

This is a multiclass classification of different disease related to Chest X-Ray like-

1. Severe Acute Respiratiory Syndrome Corona Virus 2 (SARS-CoV-2) or COVID-19
2. Pneumonia
3. Normal Condition.

Using advanced image processing and deep learning algorithms the results of the classification are-

1. Training Accuracy = 99.5 (±0.001) %

2. Validation Accuracy = 97.6 (±0.011)%

3. Test Accuracy = 99.1%

4. Sensitivity = 98.8 %

5. Specificity = 99.4%

Read the paper at https://ieeexplore.ieee.org/document/9332210

Run in your machine:

• git clone https://github.com/sudo-rajarshi/Covid-Detection-from-CXR-Scans-using-Deep-Multi-layered-CNN.git
• cd Covid-Detection-from-CXR-Scans-using-Deep-Multi-layered-CNN
• pip3 install -r requirements.txt
• Open jupyter notebook and enjoy!