Biomedical image segmentation with modified U-Net

Basit Öğe Kaydı
dc.authorid0000-0003-4717-8693en_US
dc.authorid0000-0002-8470-4579en_US
dc.contributor.authorTatlı, Umut
dc.contributor.authorBudak, Cafer
dc.date.accessioned2023-09-01T13:18:04Z
dc.date.available2023-09-01T13:18:04Z
dc.date.issued2023en_US
dc.departmentDicle Üniversitesi, Mühendislik Fakültesi, Biyomedikal Mühendisliği Bölümüen_US
dc.description.abstractImage segmentation is an important field in image processing and computer vision, particularly in the development of methods to assist experts in the biomedical and medical fields. It plays a vital role in saving time and costs. One of the mostsuccessful and significant methods in image segmentation using deep learning is the U-Net model. In this paper, we propose U-Net11, a novel variant of U-Net that uses 11 convolutional layers and introduces some modifications to improve the segmentation performance. The classical U-Net model was developed and tested on three different datasets, outperforming the traditional U-Net approach. The U-Net11 model was evaluated for breast cancer segmentation, lung segmentation from CT images, and the nuclei segmentation dataset from the Data Science Bowl 2018 competition. These datasets are valuable due to their varying image quantities and the varying difficulty levels in segmentation tasks. The modified U-Net model has achieved Dice Similarity Coefficient scores of 69.09% on the breast cancer dataset, 95.02% on the lung segmentation dataset and 81.10% on the nuclei segmentation dataset, exceeding the performance of the classical U-Net model by 5%, 2% and 4% respectively. This difference in success rates is particularly significant for critical segmentation datasets.en_US
dc.identifier.citationTatlı, U. ve Budak, C. (2023). Biomedical image segmentation with modified U-Net. Traitement du Signal, 40(2), 523-531.en_US
dc.identifier.doi10.18280/ts.400211
dc.identifier.endpage531en_US
dc.identifier.issn0765-0019
dc.identifier.issue2en_US
dc.identifier.scopus2-s2.0-85162154250
dc.identifier.scopusqualityQ3
dc.identifier.startpage523en_US
dc.identifier.urihttps://www.scopus.com/record/display.uri?eid=2-s2.0-85162154250
dc.identifier.urihttps://hdl.handle.net/11468/12536
dc.identifier.volume40en_US
dc.identifier.wosWOS:000996210200011
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorTatlı, Umut
dc.institutionauthorBudak, Cafer
dc.language.isoenen_US
dc.publisherInternational Information and Engineering Technology Associationen_US
dc.relation.ispartofTraitement du Signal
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectBiomedical imageen_US
dc.subjectDeep learningen_US
dc.subjectImage segmentationen_US
dc.subjectU-Neten_US
dc.titleBiomedical image segmentation with modified U-Neten_US
dc.titleBiomedical image segmentation with modified U-Net
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
Ä°sim:
Biomedical Image Segmentation with Modified U-Net.pdf
Boyut:
1.61 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Makale Dosyası
Ä°ndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
Ä°sim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
Ä°ndir

Koleksiyon

Biyomedikal Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu