Investigating generalization in automatic COVID-19 detection using deep learning

Abstract

Computer Vision and Deep Learning have been widely used to automatically detect and analyze many diseases in various fields. Some of these include tumor detection, diabetic retinopathy classification, automatic prostate segmentation, nodules classification, etc. In this work, we are investigating the application of computer vision and deep learning techniques in COVID-19 detection from X-ray images. The general purpose was to offer an aided diagnosis system to assist radiologists in COVID-19 detection or to present a preliminary assessment when a radiologist is not immediately available. To address the problem of dependence on training data, and given the nature of the task, we opted for a double evaluation of the developed models. The proposed system appears promising for the diagnosis of COVID19, showing potential results in two different datasets.

Ähnliche Arbeiten