COVID-19 Diagnosis Using VGG-16 with CT Scans

Abstract

Artificial intelligence techniques known as deep learning are a collection of approaches that use interconnected networks to capture higher levels of abstraction in scene data. Analysis of vast amounts of data helps it learn abstraction. Imaging techniques such as x-ray, ultrasound, CT, MRI, and fluoroscopy are used in the medical field of radiology to diagnose and treat disease. Computer performance and networking advancements have made it possible for this field to benefit from the use of deep neural networks. When it comes to lung disease, the most common problem is that the symptoms aren't obvious to patients until they've progressed significantly. To prevent the spread of this disease, it is necessary to educate the public about its symptoms. Artificial intelligence approaches known as “deep learning” use a network of interconnected nodes to extract higher levels of abstraction from raw data such as images and video. Analysis of vast amounts of data helps it learn abstraction. Imaging techniques such as x-ray, ultrasound, CT, MRI, and fluoroscopy are used in the medical field of radiology to diagnose and treat disease. Due to advances in computer performance and networking, deep neural networks are now possible in this field. More than 1.3 million people have been infected by COVID-19 (coronavirus disease 2019) and more than 106,000 people have died. One of the biggest obstacles to containing the spread of this disease is the lack of effective and affordable medical diagnostics. There is a growing interest in developing deep learning methods for detecting COVID-19 from CT scans. These efforts, however, are difficult to replicate and adapt because the CT data used in their investigations is not publicly available.” A large number of CT scans are required for many projects to train appropriate diagnosis models, which are difficult to obtain.

Ähnliche Arbeiten