Χρήση συνελικτικών νευρωνικών δικτύων για την ανίχνευση COVID-19 σε ακτινογραφικές θώρακα

Σπύρου, Ευαγγελία - Μαρία

Using convolutional neural networks to detect COVID-19 in chest X-rays

Master Thesis

Author

Σπύρου, Ευαγγελία - Μαρία

Date

2024-02

Abstract

The significant advances in image processing and recognition using deep learning algorithms in recent years, as well as the profound impact of the Covid-19 pandemic, provide the motivation for this thesis. The virus's rapid spread has highlighted the urgent need to equip the healthcare sector with innovative technologies to improve patient care. The growth of research in image processing and recognition has created new opportunities for advanced techniques in medical diagnosis. Image classification is a valuable tool in radiology for identifying abnormalities in X- rays. Our aim is to develop effective models for Covid-19 detection by harnessing the power of deep learning and convolutional neural networks. The objective of this study is to assess the efficacy of deep machine learning methods in analyzing chest X-rays, specifically in identifying the presence or absence of Covid- 19 in patients. This study used a large dataset of chest radiographs collected from patients diagnosed as either positive or negative for Covid-19. Deep learning models were employed to extract meaningful features and inferences from the images and classify them into positive or negative categories. The expected results of this paper are intended to examine how close we can get to the correct diagnosis with the help of artificial intelligence. However, in no way can it bypass a health scientist.

Postgraduate Studies Programme

Πληροφοριακά Συστήματα και Υπηρεσίες

Department

Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών Συστημάτων

Number of pages

Language

Greek

URI

https://dione.lib.unipi.gr/xmlui/handle/unipi/18741

Collections

Τμήμα Ψηφιακών Συστημάτων

Show full item record

Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα