Segmentation methods for MRI human spine images using thresholding approaches

Computer-Aided Diagnosis (CAD) in MRI image processing can assist experts in detecting abnormality in human spine image efficiently. The manual process of detecting abnormality is tedious, hence the use of CAD in this field is helpful to increase the diagnosis efficiency. The segmentation method...

Full description

Bibliographic Details
Main Authors: Nor Aqlina Abdul Halim, Aqilah Baseri Huddin
Format: Article
Language:English
Published: Penerbit Universiti Kebangsaan Malaysia 2022
Online Access:http://journalarticle.ukm.my/20327/
http://journalarticle.ukm.my/20327/1/07.pdf
_version_ 1848815074627551232
author Nor Aqlina Abdul Halim,
Aqilah Baseri Huddin,
author_facet Nor Aqlina Abdul Halim,
Aqilah Baseri Huddin,
author_sort Nor Aqlina Abdul Halim,
building UKM Institutional Repository
collection Online Access
description Computer-Aided Diagnosis (CAD) in MRI image processing can assist experts in detecting abnormality in human spine image efficiently. The manual process of detecting abnormality is tedious, hence the use of CAD in this field is helpful to increase the diagnosis efficiency. The segmentation method is an important and critical process in CAD that could affect the accuracy of the MRI spine image’s overall diagnosis. There are various segmentation methods commonly used in CAD. One of the methods is segmentation using thresholding. Thresholding approaches divide the area of interest by identifying the threshold values that can separate the image into desired grayscale levels based on its pixel’s intensity. This study focuses on investigating the optimal approach in segmenting lumbar vertebrae on the MRI images. The steps involved in this study include pre-processing (normalization), segmentation using local and global thresholding, neural network classification, and performance measurement. 20 images are used to evaluate and compare the segmentation methods. The effectiveness of the segmentation method is measured based on the performance measurement technique. This preliminary study shows that local thresholding outperforms the global thresholding approach with an accuracy of 91.4% and 87.7%.
first_indexed 2025-11-15T00:44:12Z
format Article
id oai:generic.eprints.org:20327
institution Universiti Kebangasaan Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T00:44:12Z
publishDate 2022
publisher Penerbit Universiti Kebangsaan Malaysia
recordtype eprints
repository_type Digital Repository
spelling oai:generic.eprints.org:203272022-11-02T01:16:38Z http://journalarticle.ukm.my/20327/ Segmentation methods for MRI human spine images using thresholding approaches Nor Aqlina Abdul Halim, Aqilah Baseri Huddin, Computer-Aided Diagnosis (CAD) in MRI image processing can assist experts in detecting abnormality in human spine image efficiently. The manual process of detecting abnormality is tedious, hence the use of CAD in this field is helpful to increase the diagnosis efficiency. The segmentation method is an important and critical process in CAD that could affect the accuracy of the MRI spine image’s overall diagnosis. There are various segmentation methods commonly used in CAD. One of the methods is segmentation using thresholding. Thresholding approaches divide the area of interest by identifying the threshold values that can separate the image into desired grayscale levels based on its pixel’s intensity. This study focuses on investigating the optimal approach in segmenting lumbar vertebrae on the MRI images. The steps involved in this study include pre-processing (normalization), segmentation using local and global thresholding, neural network classification, and performance measurement. 20 images are used to evaluate and compare the segmentation methods. The effectiveness of the segmentation method is measured based on the performance measurement technique. This preliminary study shows that local thresholding outperforms the global thresholding approach with an accuracy of 91.4% and 87.7%. Penerbit Universiti Kebangsaan Malaysia 2022 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/20327/1/07.pdf Nor Aqlina Abdul Halim, and Aqilah Baseri Huddin, (2022) Segmentation methods for MRI human spine images using thresholding approaches. Jurnal Kejuruteraan, 34 (4). pp. 591-597. ISSN 0128-0198 https://www.ukm.my/jkukm/volume-3404-2022/
spellingShingle Nor Aqlina Abdul Halim,
Aqilah Baseri Huddin,
Segmentation methods for MRI human spine images using thresholding approaches
title Segmentation methods for MRI human spine images using thresholding approaches
title_full Segmentation methods for MRI human spine images using thresholding approaches
title_fullStr Segmentation methods for MRI human spine images using thresholding approaches
title_full_unstemmed Segmentation methods for MRI human spine images using thresholding approaches
title_short Segmentation methods for MRI human spine images using thresholding approaches
title_sort segmentation methods for mri human spine images using thresholding approaches
url http://journalarticle.ukm.my/20327/
http://journalarticle.ukm.my/20327/
http://journalarticle.ukm.my/20327/1/07.pdf