Implementation of Image Quality Improvement Methods and Lung Segmentation on Chest X-Ray Images Using U-Net Architectural Modifications

Rudiansyah Rudiansyah; Lucky Indra Kesuma; Muhammad Ikhsan Anggara

doi:10.18495/comengapp.v12i2.426

[1]P. Gibson, L. Qin, and S. Puah, “COVID-19 ARDS: Clinical Features and Differences to ‘Usual’ Ore-COVID ARDS,” Med J Aust, vol. 213, pp. 54–56, 2020.
[2]Y. G. Kim et al., “Deep Learning-Based Four-Region Lung Segmentation in Chest Radiography for COVID-19 Diagnosis,” Diagnostics, vol. 12, no. 101, pp. 1–11, 2022, doi: 10.3390/diagnostics12010101.

Abstract viewed - 404 times
PDF downloaded - 259 times

Affiliations

Rudiansyah Rudiansyah
Universitas Sjakhyakirti

Lucky Indra Kesuma
Affiliation not stated

Muhammad Ikhsan Anggara
Affiliation not stated

Content Top

Implementation of Image Quality Improvement Methods and Lung Segmentation on Chest X-Ray Images Using U-Net Architectural Modifications

Rudiansyah Rudiansyah ,
Lucky Indra Kesuma ,
Muhammad Ikhsan Anggara

Vol 12 No 2 (2023)

DOI 10.18495/comengapp.v12i2.426

Submitted: Sep 24, 2022

Published: Jun 1, 2023

Abstract

COVID-19 is an infectious disease that causes acute respiratory distress syndrome due to the SARS-CoV-2 virus. Rapid and accurate screening and early diagnosis of patients play an essential role in controlling outbreaks and reducing the spread of this disease. This disease can be diagnosed by manually reading CXR images, but it is time-consuming and prone to errors. For this reason, this research proposes an automatic medical image segmentation system using a combination of U-Net architecture with Batch Normalization to obtain more accurate and fast results. The method used in this study consists of pre-processing using the CLAHE method and morphology opening, CXR image segmentation using a combination of U-Net-4 Convolution Block architecture with Batch Normalization, then evaluated using performance measures such as accuracy, sensitivity, specificity, F1-score, and IoU. The results showed that the U-Net architecture modified with Batch Normalization had successfully segmented CXR images, as seen from all performance measurement values above 94%.