DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 40 Subclasses

Abstract Skin lesion datasets provide essential information for understanding various skin conditions and developing effective diagnostic tools. They aid the artificial intelligence-based early detection of skin cancer, facilitate treatment planning, and contribute to medical education and research....

Full description

Saved in:
Bibliographic Details
Main Authors: Abdurrahim Yilmaz, Sirin Pekcan Yasar, Gulsum Gencoglan, Burak Temelkuran
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-024-04104-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850056181238726656
author Abdurrahim Yilmaz
Sirin Pekcan Yasar
Gulsum Gencoglan
Burak Temelkuran
author_facet Abdurrahim Yilmaz
Sirin Pekcan Yasar
Gulsum Gencoglan
Burak Temelkuran
author_sort Abdurrahim Yilmaz
collection DOAJ
description Abstract Skin lesion datasets provide essential information for understanding various skin conditions and developing effective diagnostic tools. They aid the artificial intelligence-based early detection of skin cancer, facilitate treatment planning, and contribute to medical education and research. Published large datasets have partially coverage the subclassifications of the skin lesions. This limitation highlights the need for more expansive and varied datasets to reduce false predictions and help improve the failure analysis for skin lesions. This study presents a diverse dataset comprising 12,345 dermatoscopic images with 40 subclasses of skin lesions, collected in Turkiye, which comprises different skin types in the transition zone between Europe and Asia. Each subgroup contains high-resolution images and expert annotations, providing a strong and reliable basis for future research. The detailed analysis of each subgroup provided in this study facilitates targeted research endeavors and enhances the depth of understanding regarding the skin lesions. This dataset distinguishes itself through a diverse structure with its 5 super classes, 15 main classes, 40 subclasses and 12,345 high-resolution dermatoscopic images.
format Article
id doaj-art-5519e1aed03345b6a4023c5e00aecb61
institution DOAJ
issn 2052-4463
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-5519e1aed03345b6a4023c5e00aecb612025-08-20T02:51:46ZengNature PortfolioScientific Data2052-44632024-11-0111111210.1038/s41597-024-04104-3DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 40 SubclassesAbdurrahim Yilmaz0Sirin Pekcan Yasar1Gulsum Gencoglan2Burak Temelkuran3Imperial College London, Division of Systems Medicine, Department of Metabolism, Digestion, and ReproductionThe University of Health Sciences, Haydarpasa Numune Research and Training Hospital, Department of Dermatology and VenereologyIstinye University, Liv Hospital Vadistanbul, Department of Dermatology and VenereologyImperial College London, Division of Systems Medicine, Department of Metabolism, Digestion, and ReproductionAbstract Skin lesion datasets provide essential information for understanding various skin conditions and developing effective diagnostic tools. They aid the artificial intelligence-based early detection of skin cancer, facilitate treatment planning, and contribute to medical education and research. Published large datasets have partially coverage the subclassifications of the skin lesions. This limitation highlights the need for more expansive and varied datasets to reduce false predictions and help improve the failure analysis for skin lesions. This study presents a diverse dataset comprising 12,345 dermatoscopic images with 40 subclasses of skin lesions, collected in Turkiye, which comprises different skin types in the transition zone between Europe and Asia. Each subgroup contains high-resolution images and expert annotations, providing a strong and reliable basis for future research. The detailed analysis of each subgroup provided in this study facilitates targeted research endeavors and enhances the depth of understanding regarding the skin lesions. This dataset distinguishes itself through a diverse structure with its 5 super classes, 15 main classes, 40 subclasses and 12,345 high-resolution dermatoscopic images.https://doi.org/10.1038/s41597-024-04104-3
spellingShingle Abdurrahim Yilmaz
Sirin Pekcan Yasar
Gulsum Gencoglan
Burak Temelkuran
DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 40 Subclasses
Scientific Data
title DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 40 Subclasses
title_full DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 40 Subclasses
title_fullStr DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 40 Subclasses
title_full_unstemmed DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 40 Subclasses
title_short DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 40 Subclasses
title_sort derm12345 a large multisource dermatoscopic skin lesion dataset with 40 subclasses
url https://doi.org/10.1038/s41597-024-04104-3
work_keys_str_mv AT abdurrahimyilmaz derm12345alargemultisourcedermatoscopicskinlesiondatasetwith40subclasses
AT sirinpekcanyasar derm12345alargemultisourcedermatoscopicskinlesiondatasetwith40subclasses
AT gulsumgencoglan derm12345alargemultisourcedermatoscopicskinlesiondatasetwith40subclasses
AT buraktemelkuran derm12345alargemultisourcedermatoscopicskinlesiondatasetwith40subclasses