Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 38 Subclasses

Abdurrahim Yilmaz, Sirin Pekcan Yasar, Gulsum Gencoglan, Burak Temelkuran

TL;DR

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, providing a strong and reliable basis for future research.

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 38 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 photos 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 5 super classes, 15 main classes, 38 subclasses and its 12,345 high-resolution dermatoscopic images.

DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 38 Subclasses

TL;DR

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, providing a strong and reliable basis for future research.

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 38 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 photos 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 5 super classes, 15 main classes, 38 subclasses and its 12,345 high-resolution dermatoscopic images.
Paper Structure (11 sections, 2 figures, 1 table)

This paper contains 11 sections, 2 figures, 1 table.

Table of Contents

  1. Background & Summary
  2. Methods
  3. Data Records
  4. Technical Validation
  5. Usage Notes
  6. Acknowledgements
  7. Author contributions statement
  8. Competing interests

Figures (2)

  • Figure 1: Shows an overview of the data collection procedure.
  • Figure 2: Shows an overview of the taxonomy tree. The first level includes the melanocytic and nonmelanocytic. The second level comprises malignant and benign groups of the first level. The third level is banal, dysplastic and lentigo for melanocytic benign, melanoma for melanocytic malignant, keratinocytic, skin appendages, vascular for nonmelanocytic benign, keratinocytic for nonmelanocytic-indeterminate, and keratinocytic, skin appendages, and vascular for nonmelanocytic malignant. The forth level is the subclasses of related to their main and super classes. Our taxonomy tree contains 5 super classes, 15 main classes, and 38 subclasses.