Semantic Lung Segmentation from Chest X-ray Images Using Seg-Net Deep CNN Model

Implementing an accurate image segmentation to extract the lung shape from X-ray images is a vital step in designing a CAD system that diagnoses various types of chest diseases. Lung segmentation is a complex process due to the blurred regions that separate the lung area and the rest of the image. T...

Full description

Saved in:
Bibliographic Details
Main Authors: Dathar Abas Hasan, Umed Hayder Jader
Format: Article
Language:English
Published: Erbil Polytechnic University 2023-10-01
Series:Polytechnic Journal
Subjects:
Online Access:https://polytechnic-journal.epu.edu.iq/home/vol13/iss2/1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849403148797476864
author Dathar Abas Hasan
Umed Hayder Jader
author_facet Dathar Abas Hasan
Umed Hayder Jader
author_sort Dathar Abas Hasan
collection DOAJ
description Implementing an accurate image segmentation to extract the lung shape from X-ray images is a vital step in designing a CAD system that diagnoses various types of chest diseases. Lung segmentation is a complex process due to the blurred regions that separate the lung area and the rest of the image. The conventional image segmentation techniques do not meet the ambitions to achieve precise lung segmentation. In this paper, we utilized the Seg-Net semantic segmentation model as a practical approach to distinguish the lung region pixels in X-ray images. The model involves an encoder network that extracts the data from the input images, and a corresponding decoder network that maps the low-resolution encoder feature maps to full input-resolution feature maps for pixel-wise classification. The model is trained and tested using 539 X-ray images from Shenzhen's publicly available dataset. The robust performance of the Seg-Net model is investigated in terms of global accuracy, dice coefficient, and intersection over union. The model achieved global accuracy (97.71%), dice coefficient (96.95%), and Jaccard index (94.08%). The experimental results indicate that the Seg-Net model is an effective tool for performing complicated segmentation tasks and extracting regions of interest such as lung area, eye vessels, lesions, and tumors from medical images.
format Article
id doaj-art-93c93b562b7946f89adec69dda49e6d2
institution Kabale University
issn 2707-7799
language English
publishDate 2023-10-01
publisher Erbil Polytechnic University
record_format Article
series Polytechnic Journal
spelling doaj-art-93c93b562b7946f89adec69dda49e6d22025-08-20T03:37:20ZengErbil Polytechnic UniversityPolytechnic Journal2707-77992023-10-0113217https://doi.org/10.59341/2707-7799.1712Semantic Lung Segmentation from Chest X-ray Images Using Seg-Net Deep CNN ModelDathar Abas Hasan0Umed Hayder Jader1Duhok Polytechnic University, College of Health and Medical Technology, Shekhan, Duhok, IraqErbil Polytechnic University, Soran Technical College, IT Department, Erbil, IraqImplementing an accurate image segmentation to extract the lung shape from X-ray images is a vital step in designing a CAD system that diagnoses various types of chest diseases. Lung segmentation is a complex process due to the blurred regions that separate the lung area and the rest of the image. The conventional image segmentation techniques do not meet the ambitions to achieve precise lung segmentation. In this paper, we utilized the Seg-Net semantic segmentation model as a practical approach to distinguish the lung region pixels in X-ray images. The model involves an encoder network that extracts the data from the input images, and a corresponding decoder network that maps the low-resolution encoder feature maps to full input-resolution feature maps for pixel-wise classification. The model is trained and tested using 539 X-ray images from Shenzhen's publicly available dataset. The robust performance of the Seg-Net model is investigated in terms of global accuracy, dice coefficient, and intersection over union. The model achieved global accuracy (97.71%), dice coefficient (96.95%), and Jaccard index (94.08%). The experimental results indicate that the Seg-Net model is an effective tool for performing complicated segmentation tasks and extracting regions of interest such as lung area, eye vessels, lesions, and tumors from medical images.https://polytechnic-journal.epu.edu.iq/home/vol13/iss2/1semantic segmentation, cnn, seg-net, chest x-ray, deep learning
spellingShingle Dathar Abas Hasan
Umed Hayder Jader
Semantic Lung Segmentation from Chest X-ray Images Using Seg-Net Deep CNN Model
Polytechnic Journal
semantic segmentation, cnn, seg-net, chest x-ray, deep learning
title Semantic Lung Segmentation from Chest X-ray Images Using Seg-Net Deep CNN Model
title_full Semantic Lung Segmentation from Chest X-ray Images Using Seg-Net Deep CNN Model
title_fullStr Semantic Lung Segmentation from Chest X-ray Images Using Seg-Net Deep CNN Model
title_full_unstemmed Semantic Lung Segmentation from Chest X-ray Images Using Seg-Net Deep CNN Model
title_short Semantic Lung Segmentation from Chest X-ray Images Using Seg-Net Deep CNN Model
title_sort semantic lung segmentation from chest x ray images using seg net deep cnn model
topic semantic segmentation, cnn, seg-net, chest x-ray, deep learning
url https://polytechnic-journal.epu.edu.iq/home/vol13/iss2/1
work_keys_str_mv AT datharabashasan semanticlungsegmentationfromchestxrayimagesusingsegnetdeepcnnmodel
AT umedhayderjader semanticlungsegmentationfromchestxrayimagesusingsegnetdeepcnnmodel