Transfer Learning for COVID-19 Detection in Medical Images

As of late, the COVID infection 2019 (COVID-19) has caused a pandemic sickness in more than 200 nations, therefore impacting billions of people. To control the spread of the coronavirus, it is crucial to detect infected individuals and ensure their complete isolation to prevent further infection. Chest X-rays and CT-scans have been proven to be very promising as signals of the infection can be clearly shown in lung areas. Transfer learning from ImageNet dataset has become the latent trend in medical imaging applications. However, there are major differences between ImageNet and medical imaging datasets. Therefore, the feasibility of transfer learning in medical applications remains questionable. This paper investigates the performance of five fine-tuned pre-trained models for chest X-rays and CT-scans classification in contrast with a deep CNN model built from scratch. DenseNet121, Resnet-50, Inception v2, Resnet101-V2 and VGG16 are selected and initialized with either random or pre-trained weights to classify augmented images into two classes: COVID and non-COVID. The performance evaluation proves the minuscule impact of training transfer learning models for good quality results, as all CNN models contribute almost equally to the classification and achieve considerable results in terms of precision, accuracy, recall and F1 score. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.