Melola Discovery

← Melola Discovery

Open access Journal SINTA 1

Automated DeepLabV3+ based model for left ventricle segmentation on short-axis late gadolinium enhancement-magnetic cardiac resonance imaging images

International Journal of Electrical and Computer Engineering (IJECE) · Vol. 14 No. 3 (2024)

DOI
10.11591/ijece.v14i3.pp3362-3371
ISSN
2722-2578, 2088-8708
Published
2024-06-01
Publisher
Institute of Advanced Engineering and Science
License
creativecommons.org/licenses/by-sa/4.0

Abstract

Accurate segmentation of myocardial scar tissue on late gadolinium enhancement-magnetic cardiac resonance imaging (LGE-CMR) is exceptionally vital for clinical applications, enabling precise diagnosis and effective treatment of various cardiac diseases, such as myocardial infarction and cardiomyopathies. However, the ventricle (LV) variations in the size and shape, artifacts, and image resolution of LGE-CMR has made automatic segmentation of myocardial scar tissue more challenging. While many existing approaches delineate the LV myocardium region using multi-modal segmentation, these models may be computationally complex and suffer from misalignment. Therefore, this study proposed an automatic dual-stage DeepLabV3+ based approach tailored for myocardial scar segmentation on short-axis LGE-MRI exclusively. To segment myocardial scar tissue, the second stage employs the segmented LV chamber from the previous stage. The encoder part of the framework utilizes a MobileNetV2 and ResNet50 backbone for the first and second segmentation, respectively, aiming for optimal resolution of feature maps. Both stages tailor an improved Atrous Spatial Pyramid Pooling module in the DeepLabV3+ model with fine-tuned dilated atrous rates to effectively extract the LV chamber and myocardial scar from the complex LGE-MRI background. Based on the results, the proposed dual-stage network recorded an outstanding segmentation performance, with mean Dice score of 96.02% for LV chamber segmentation and 68.01% for scar tissue extraction.

Collaboration network of the authors

23 authors · 69 co-authorship links · 12 across different organisations

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Universiti Teknologi MARA
  • State University of Malang
  • Universiti Sains Malaysia
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Iza Sazanita IsaUniversiti Teknologi MARA8
Mohd Firdaus AbdullahUniversiti Teknologi MARA4
Noor Fadzilah RazaliUniversiti Teknologi MARA4
Zul Imran AzhariUniversiti Teknologi MARA2
Denis Eka CahyaniState University of Malang2
Siti Juliana Abu BakarUniversiti Teknologi MARA2
Emilia NoorsalUniversiti Teknologi MARA1
Mohd Hanapiah AbdullahUniversiti Teknologi MARA1
Muhammad Fa'iz AlfarisiState University of Malang1
Anis Diyana RosliUniversiti Teknologi MARA1
Muhammad Abbas Abu TalibUniversiti Teknologi MARA1
Adi Izhar Che AniUniversiti Teknologi MARA1
Mohammad Nizam IbrahimUniversiti Teknologi MARA1
Samihah AbdullahUniversiti Teknologi MARA1
Irni Hamiza HamzahUniversiti Teknologi MARA1
Nor Shahanim Mohamad HadisUniversiti Teknologi MARA1
Muhammad Ameerul Syafiqie Abdul SukorUniversiti Teknologi MARA1
Azwati AzminUniversiti Teknologi MARA1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

This record comes from Crossref (what the publisher deposited), because the journal's own OAI-PMH endpoint could not be harvested.

Metadata source: Crossref API (cadangan, berdasarkan ISSN) https://api.crossref.org/journals/2088-8708/works, first harvested 27 Oct 2026, last seen 15 Nov 2026.
Metadata as oai_dc, converted from Crossref
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title>Automated DeepLabV3+ based model for left ventricle segmentation on short-axis late gadolinium enhancement-magnetic cardiac resonance imaging images</dc:title><dc:creator>Awang Damit, Dayang Suhaida</dc:creator><dc:creator>Sulaiman, Siti Noraini</dc:creator><dc:creator>Osman, Muhammad Khusairi</dc:creator><dc:creator>A. Karim, Noor Khairiah</dc:creator><dc:creator>Setumin, Samsul</dc:creator><dc:description>&lt;jats:p&gt;Accurate segmentation of myocardial scar tissue on late gadolinium enhancement-magnetic cardiac resonance imaging (LGE-CMR) is exceptionally vital for clinical applications, enabling precise diagnosis and effective treatment of various cardiac diseases, such as myocardial infarction and cardiomyopathies. However, the ventricle (LV) variations in the size and shape, artifacts, and image resolution of LGE-CMR has made automatic segmentation of myocardial scar tissue more challenging. While many existing approaches delineate the LV myocardium region using multi-modal segmentation, these models may be computationally complex and suffer from misalignment. Therefore, this study proposed an automatic dual-stage DeepLabV3+ based approach tailored for myocardial scar segmentation on short-axis LGE-MRI exclusively. To segment myocardial scar tissue, the second stage employs the segmented LV chamber from the previous stage. The encoder part of the framework utilizes a MobileNetV2 and ResNet50 backbone for the first and second segmentation, respectively, aiming for optimal resolution of feature maps. Both stages tailor an improved Atrous Spatial Pyramid Pooling module in the DeepLabV3+ model with fine-tuned dilated atrous rates to effectively extract the LV chamber and myocardial scar from the complex LGE-MRI background. Based on the results, the proposed dual-stage network recorded an outstanding segmentation performance, with mean Dice score of 96.02% for LV chamber segmentation and 68.01% for scar tissue extraction.&lt;/jats:p&gt;</dc:description><dc:publisher>Institute of Advanced Engineering and Science</dc:publisher><dc:date>2024-06-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/ijece.v14i3.pp3362-3371</dc:identifier><dc:identifier>10.11591/ijece.v14i3.pp3362-3371</dc:identifier><dc:source>International Journal of Electrical and Computer Engineering (IJECE); Vol 14 No 3 (2024); 3362</dc:source><dc:source>2722-2578</dc:source><dc:source>2088-8708</dc:source><dc:relation>https://ijece.iaescore.com/index.php/IJECE/article/viewFile/35258/17441</dc:relation><dc:rights>http://creativecommons.org/licenses/by-sa/4.0</dc:rights></oai_dc:dc>