Deteksi Covid-19 Berbasis Citra Medis Ultrasound Menggunakan Metode Convolutional Neural Network

Robby, Muhammad Fadhlan Min (2021) Deteksi Covid-19 Berbasis Citra Medis Ultrasound Menggunakan Metode Convolutional Neural Network. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 05111740000123-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) | Request a copy

Abstract

Merebaknya Corona Virus Disease 2019 (COVID-19) telah menyebabkan krisis kesehatan global yang berdampak besar pada berbagai aspek kehidupan. Tidak dapat dimungkiri, hal ini memicu berbagai upaya untuk menghentikan penyebaran virus lebih luas.
Oleh karena itu, diagnosis yang akurat dalam mendeteksi COVID-19 diperlukan untuk membantu para dokter dan tenaga medis dalam mengatasi pandemi global ini.
Dalam penelitian ini, disajikan pendeteksi COVID-19 berbasis kecerdasan buatan. Sistem ini memanfaatkan citra medis ultrasound paru–paru sebagai inputan dan model arsitektur VGG-16 sebagai tulang punggung untuk mendapatkan fitur citra dan melatih pengklasifikasi.
Hasil eksperimen pada dataset publik citra medis ultrasound paru–paru menunjukkan cara pendeteksian yang diusulkan memiliki performa yang yang lebih unggul bila dibandingkan model pendeteksi berbasis deep learning lainnya, dengan presisi dan recall melebihi 86%.
======================================================================================================
The outbreak of Coronavirus Disease 2019 (COVID-19)
has created a global health crisis that has had a profound impact
on humanity. Undeniably, this has been triggering dramatic efforts
to slow its spread. Accurate diagnosis of COVID-19, therefore, is
necessary to assist doctors in fighting against this global
pandemic.
In this study, we present an intelligent detection technique
of COVID-19 from medical imaging ultrasound using a VGG-16
deep convolutional neural network (DCNN) model. In particular,
lung ultrasound imaging is used as the input, and the VGG-16
network is employed as the backbone to obtain image features and
train classifiers. Experimental results on a public dataset
demonstrate the promising detection performance of the technique
over the other deep learning models, with precision and recall of
more than 86%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Deteksi Covid-19, VGG16, Citra Medis Ultrasound, CNN, Detection, Medical Imaging Ultrasound
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Muhammad Fadhlan Min Robby
Date Deposited:	04 Aug 2021 20:43
Last Modified:	28 Mar 2022 03:22
URI:	http://repository.its.ac.id/id/eprint/84830

Actions (login required)

View Item