Covid-19 Detection For CT-scan Images Using Transfer Learning Models

COVID-19 is a respiratory illness caused by virus called SARS-CoV-2 which affected around 455 million people the world. CT-scan medical imaging technique that uses X-rays to create detailed images of body and can be used detect many diseases. Transfer learning models are type machine model trained on large dataset for their already ability extract features from image in other tasks. They then classify new with similar features.This paper presents study different transfer task classifying chest X-ray into three classes: COVID-19, pneumonia, normal. The was implemented using Python Chest Dataset. train-test split 0.2–0.8. parameters test were precision, recall, accuracy, F1 score, Matthew’s correlation score. Other than these, optimizers also compared such as ADAM, SGD rates 0.01, 0.001, 0.0001.The this EfficientNetB0, EfficientNetB7, VGG16, InceptionV3. Out these models, most effective EfficientNetB0 model, achieved an accuracy 98.6%. This provides valuable insights use analysis. results suggest develop accurate efficient secondary option diagnosis images.