ISIC Archive
Sign In
Collections (56)
Reset sort
Name
ISIC-DICM-17K
ISIC-DICM-17K (ISIC Dermoscopic Images and Clinical Metadata 17K) is a curated and balanced dataset derived from the International Skin Imaging Collaboration (ISIC) Archive Gallery. It comprises 17,060 dermoscopic images and clinical metadata (8,530 melanoma and 8,530 non-melanoma classes). For more details, please follow the project’s GitHub repository: [https://github.com/mmu-dermatology-research/isic-dicm-17k](https://github.com/mmu-dermatology-research/isic-dicm-17k) This dataset was used in this study and benchmark to explore the effectiveness of multimodal learning for skin lesion classification: S. Ahammed, X. Cui, W. Lu and M. H. Yap, "Skin Lesion Classification using Dermoscopic Images and Clinical Metadata: Insights from Multimodal Models," 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Nashville, TN, USA, 2025, pp. 222-230, DOI: 10.1109/CVPRW67362.2025.00027
2025-10-03 17,060 images
ISIC Balanced
These are the images used in the paper: Analysis of the ISIC image datasets: Usage, benchmarks and recommendations Paper Link: https://www.sciencedirect.com/science/article/pii/S1361841521003509 They have also been used by newer versions such as: Skin Lesion Classification Using Dermoscopic Images and Clinical Metadata: Insights from Multimodal Models Paper Link: https://openaccess.thecvf.com/content/CVPR2025W/MULA2025/papers/Ahammed_Skin_Lesion_Classification_Using_Dermoscopic_Images_and_Clinical_Metadata_Insights_CVPRW_2025_paper.pdf https://api.isic-archive.com/collections/469/
2025-11-06 9,810 images
15 Exemplar Infundibulocystic Basal Cell Carcinomas
This collection contains the 15 images uploaded for "Dermoscopic Features of Infundibulocystic Basal Cell Carcinoma (IBCC): An Observational Study."
2025-11-07 15 images
IMA++
This collection contains all the images associated with the [IMA++ dataset](https://doi.org/10.5281/zenodo.14201692). The **IMA++ dataset** is the largest publicly available multi-annotator skin lesion segmentation (SLS) dataset, collected from the ISIC Archive to facilitate skin lesion image segmentation research. It contains **17,684 segmentation masks** spanning **14,967 dermoscopic images**, where **2,394 dermoscopic images have 2-5 segmentations per image** from the ISIC Archive, annotated by **16 distinct annotators**, with at least one annotation per image. The dataset captures a wide range of segmentation styles influenced by annotator expertise, tools used, and manual review processes, making it a valuable resource for developing and evaluating SLS models.
2026-03-05 14,967 images
MEL-SELF - Dermoscopic
Dermoscopic lesion images (close-up views of benign and malignant lesions) from the MEL-SELF trial (the Melanoma Self Surveillance trial).
2026-03-30 3,008 images
BCC with histopathologic subtype
2026-04-21 126 images