Please use this identifier to cite or link to this item: http://oaps.umac.mo/handle/10692.1/248
Title: Automatic Covid-19 Chest CT Image Classification
Authors: QI, YUAN YUAN(齊圓圓)
Department: Department of Computer and Information Science
Faculty: Faculty of Science and Technology
Issue Date: 2021
Citation: OAPS_2021_FST_DB727055_Qi YuanYuan_Automatic Covid-19 Chest CT Image Classification
Abstract: Background and Purpose: Covid-19 as a world problem has caused devastation in our lives from health issues to the economy, where many people try every day to overcome this hardness, like developing vaccines and recovering the economy. Our project wants to make contributions to this problem by building a high-performance Covid-19 chest CT image classifier. Clinical studies have shown that most Covid-19 patients suffer from lung infection and that chest CT is known to be an effective imaging technique for lung related disease diagnosis. Deep learning, one of the most successful AI techniques, is an effective means to assist radiologists to analyse the vast amount of chest CT images, which can be critical for efficient and reliable Covid-19 screening. We developed in this project a robust, fast, and reliable classifier for chest CT image diagnosis to distinguish Covid-19 images from common pneumonia and healthy chest CT scans. The experimental results achieved an accuracy of 91.25% for slice level and 92.88% for patient level. Material and Method: We use the chest CT images dataset containing 416 Covid-19 patients, 412 common pneumonia patients, and 270 healthy patients, train through the neural network, extract and combine meaningful features to build the automatic Covid-19 chest CT image classifier, which can determine the physical condition of the patients. Besides, we are going to build the user interface for users to get the diagnostic result of the chest CT image. Results: Our experimental results show that our model can reliably detect 86.67% common pneumonia patients, 94.59% Covid-19 patients, and 97.37% healthy patients. We have set a website based on html, css, php, which can visualize our project and provide a tool for the user to diagnose online.
Course: Bachelor of Science in Computer Science
Instructor: Prof. Yibo Bob ZHANG
Programme: Bachelor of Science in Computer Science
URI: http://oaps.umac.mo/handle/10692.1/248
Appears in Collections:FST OAPS 2021

Files in This Item:
File Description SizeFormat 
OAPS_2021_FST_DB727055_Qi YuanYuan_Automatic Covid-19 Chest CT Image Classification.pdf22.06 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.