Skin lesion segmentation with semantic SAM: Pros and cons

Basit Öğe Kaydı
dc.authorid0000-0002-7040-7952
dc.authorid0000-0002-1999-2797
dc.authorid0000-0002-5965-0687
dc.authorid0000-0002-0770-599X
dc.authorid0000-0003-1828-5844
dc.contributor.authorGül, Sevda
dc.contributor.authorAydın, Bekir Murat
dc.contributor.authorAkgün, Devrim
dc.contributor.authorKara, Rabia Öztaş
dc.contributor.authorÇetinel, Gökçen
dc.date.accessioned2025-02-13T06:55:07Z
dc.date.available2025-02-13T06:55:07Z
dc.date.issued2024
dc.departmentBaşka Kurum
dc.description.abstractThe Segment Anything Model (SAM), introduced in April 2023, has gained prominence for its ability to generalize across various image segmentation tasks. This study evaluates SAM's performance on skin lesion segmentation using both public (3463 images) and private (773 images) dermoscopy image datasets, the latter collected with ethical approval from *** University Training and Research Hospital. The segmentation performance was assessed using Intersection over Union (IoU) and Dice metrics, achieving Dice scores of 0.6598 (IoU: 0.5865) for the private database and 0.6513 (IoU: 0.5624) for the public database. A post-processing step was applied to refine the segmentation results, enhancing SAM's ability to delineate lesion boundaries. However, while SAM demonstrated strong generalization, its performance on low-contrast and irregularly shaped lesions indicates the need for further adaptation. This paper highlights SAM’s potential in medical image segmentation while outlining its limitations, especially in specialized tasks like skin lesion analysis.
dc.identifier.citationGül, S., Aydın, B. M., Akgün, D., Kara, R. Ö., Çetinel, G. (2024). Skin lesion segmentation with semantic SAM: Pros and cons. Selcuk University Journal of Engineering Sciences, 23 (3), 77-84.
dc.identifier.endpage84
dc.identifier.issn2757-8828
dc.identifier.issue3
dc.identifier.startpage77
dc.identifier.urihttps://hdl.handle.net/20.500.12395/54399
dc.identifier.volume23
dc.language.isoen
dc.publisherSelçuk Üniversitesi
dc.relation.ispartofSelcuk University Journal of Engineering Sciences
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Başka Kurum Yazarı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectSkin Lesion Segmentation
dc.subjectSegment Anything Model
dc.subjectDeep Learning
dc.subjectCilt Lezyonu Segmentasyonu
dc.subjectHer Şeyi Segmentleme Modeli
dc.subjectDerin Öğrenme
dc.titleSkin lesion segmentation with semantic SAM: Pros and cons
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Sevda GÜL, Bekir Murat AYDIN, Devrim AKGÜN, Rabia ÖZTAŞ KARA, Gökçen ÇETİNEL.pdf
Boyut:
517.94 KB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Dergi Yayın Koleksiyonu