ISIC Challenge Datasets

Task Training Data Training Ground Truth Test Data Test Ground Truth License
1 Download (602MB)
900 dermoscopic lesion images in JPEG format, with EXIF data stripped. 		Download (6MB)
900 binary mask images in PNG format. 		Download (232MB)
379 images of the exact same format as the Training Data. 		Download (2MB)
CC-0
2 Download (671MB)
807 lesion images in JPEG format and 807 corresponding superpixel masks in PNG format, with EXIF data stripped. 		Download (5MB)
807 dermoscopic feature files in JSON format. 		Download (257MB)
335 lesion images and 335 corresponding superpixel masks of the exact same formats as the Training Data. 		Download (2MB)
2B Download (565MB)
807 lesion images in JPEG format, with EXIF data stripped. 		Download (5MB)
1614 binary mask images in PNG format. 		Download (216MB)
335 lesion images of the exact same formats as the Training Data. 		Download (2MB)
3 Download (602MB)
900 dermoscopic lesion images in JPEG format. 		Download (19KB)
900 entries of gold standard malignant status. 		Download (232MB)
379 images of the exact same format as the Training Data. 		Download (7KB)
3B Download (608MB)
900 dermoscopic lesion images in JPEG format and 900 associated segmentation binary masks in PNG format. 		Download (19KB)
900 entries of gold standard malignant status. 		Download (234MB)
379 images and 379 associated segmentation masks, of the exact same format as the Training Data. 		Download (7KB)

Citing 2016 datasets:

Gutman, David; Codella, Noel C. F.; Celebi, Emre; Helba, Brian; Marchetti, Michael; Mishra, Nabin; Halpern, Allan. "Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)". eprint arXiv:1605.01397. 2016.
Task Training Data Training Ground Truth Validation Data Validation Ground Truth Test Data Test Ground Truth License
1 Download (5.8GB)
2000 lesion images in JPEG format and 2000 corresponding superpixel masks in PNG format, with EXIF data stripped. 		Download (9MB)
2000 binary mask images in PNG format. 		Download (878MB) Download (559KB) Download (5.4GB) Download (18MB) CC-0
2 Download (710KB)
2000 dermoscopic feature files in JSON format. 		Download (51KB) Download (210KB)
3 Download (43KB)
2000 entries of gold standard lesion diagnoses. 		Download (3KB) Download (13KB)

Citing 2017 datasets:

Codella N, Gutman D, Celebi ME, Helba B, Marchetti MA, Dusza S, Kalloo A, Liopyris K, Mishra N, Kittler H, Halpern A. "Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)". arXiv: 1710.05006 [cs.CV]
Task Training Data Training Ground Truth Validation Data Validation Ground Truth Test Data Test Ground Truth License
1 Download (10.4GB)
2594 images and 12970 corresponding ground truth response masks (5 for each image). 		Download (26MB)
Download (228MB) Download (742KB) Download (2.2GB)
1000 images. 		Download (9MB) CC-0
2 Download (33MB)
Download (1MB) Download (11MB)
3

Download (2.6GB)
10015 images and 1 ground truth response CSV file (containing 1 header row and 10015 corresponding response rows).

Download (481KB)
10015 entries grouping each lesion by image and diagnosis confirm type. A further explanation on this supplemental data can be found here.

Download (36KB) Download (51MB) Download (7KB) Download (401MB)
1512 images. 		Download (11KB) CC-BY-NC

Citing 2018 datasets:

To comply with the attribution requirements of the CC-BY-NC license , the aggregate "ISIC 2018: Training" data must be cited as:

HAM10000 Dataset: (c) by ViDIR Group, Department of Dermatology, Medical University of Vienna; https://doi.org/10.1038/sdata.2018.161

MSK Dataset: (c) Anonymous; https://arxiv.org/abs/1710.05006; https://arxiv.org/abs/1902.03368

When referencing this dataset in your own manuscripts and publications, please use the following full citations:

[1] Noel Codella, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Marchetti, Harald Kittler, Allan Halpern: "Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)", 2018; https://arxiv.org/abs/1902.03368

[2] Tschandl, P., Rosendahl, C. & Kittler, H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5, 180161 doi:10.1038/sdata.2018.161 (2018).

Task Training Data Training Ground Truth Test Data Test Ground Truth License
1 Download (9.1GB)
25,331 JPEG images of skin lesions. 		Download (1MB)
25,331 entries of gold standard lesion diagnoses. 		Download (3.6GB)
8,238 JPEG images of skin lesions. 		Download (454KB)
8,238 entries of gold standard lesion diagnoses. Includes the scoring and validation weights. 		CC-BY-NC
2 Download (1MB)
25,331 metadata entries of age, sex, general anatomic site, and common lesion identifier. 		Download (287KB)
8,238 metadata entries of age, sex, and general anatomic site.

Citing 2019 datasets:

To comply with the attribution requirements of the CC-BY-NC license , the aggregate "ISIC 2019: Training" data must be cited as:

BCN_20000 Dataset: (c) Department of Dermatology, Hospital Clínic de Barcelona

HAM10000 Dataset: (c) by ViDIR Group, Department of Dermatology, Medical University of Vienna; https://doi.org/10.1038/sdata.2018.161

MSK Dataset: (c) Anonymous; https://arxiv.org/abs/1710.05006; https://arxiv.org/abs/1902.03368

When referencing this dataset in your own manuscripts and publications, please use the following full citations:

[1] Tschandl P., Rosendahl C. & Kittler H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5, 180161 doi.10.1038/sdata.2018.161 (2018)

[2] Noel C. F. Codella, David Gutman, M. Emre Celebi, Brian Helba, Michael A. Marchetti, Stephen W. Dusza, Aadi Kalloo, Konstantinos Liopyris, Nabin Mishra, Harald Kittler, Allan Halpern: "Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)", 2017; arXiv:1710.05006.

[3] Hernández-Pérez C, Combalia M, Podlipnik S, Codella NC, Rotemberg V, Halpern AC, Reiter O, Carrera C, Barreiro A, Helba B, Puig S, Vilaplana V, Malvehy J. BCN20000: Dermoscopic lesions in the wild. Scientific Data. 2024 Jun 17;11(1):641.

Training Data Training Ground Truth Test Data Test Ground Truth License

Download DICOM (48.9GB)
33,126 DICOM images with embedded metadata.

Download DICOM Corrected* (23.0GB)
33,126 DICOM images with embedded metadata.

Download JPEG (23GB)
33,126 JPEG images.

Download metadata (2MB)
33,126 metadata entries of patient ID, sex, age, and general anatomic site.

Download metadata v2 (2MB)
33,126 metadata entries of patient ID, lesion ID, sex, age, and general anatomic site.

Download duplicate image list (2MB)
List of 425 duplicate images.

Download (2MB)
33,126 entries of gold standard lesion diagnoses.

Download DICOM (15.3GB)
10,982 DICOM images with embedded metadata.

Download DICOM Corrected* (6.7GB)
10,982 DICOM images with embedded metadata.

Download JPEG (6.7GB)
10,982 JPEG images.

Download metadata (458KB)
10,982 metadata entries of patient ID, sex, age, and general anatomic site.

Not Available help_outline
CC-BY-NC

*The newer version of the DICOM files are provided to avoid potential errors stemming from readers implementing a strict DICOM verification, as implemented in http://dclunie.com/dicom3tools/dciodvfy.html.

Datasets were curated by the International Skin Imaging Collaboration (ISIC) from images contributed by the following:

  • Memorial Sloan Kettering Cancer Center (USA)
  • Hospital Clínic de Barcelona (Spain)
  • Medical University of Vienna (Austria)
  • Melanoma Institute Australia (Australia)
  • The University of Queensland (Australia)
  • University of Athens (Greece)

A dataset descriptor published in Scientific Data and is openly available at https://doi.org/10.1038/s41597-021-00815-z.

Citing 2020 datasets:

To comply with the attribution requirements of the CC-BY-NC license , the aggregate "ISIC 2020" data must be cited as:

International Skin Imaging Collaboration. SIIM-ISIC 2020 Challenge Dataset. International Skin Imaging Collaboration https://doi.org/10.34970/2020-ds01 (2020).

Creative Commons Attribution-Non Commercial 4.0 International License.

The dataset was generated by the International Skin Imaging Collaboration (ISIC) and images are from the following sources: Hospital Clínic de Barcelona, Medical University of Vienna, Memorial Sloan Kettering Cancer Center, Melanoma Institute Australia, The University of Queensland, and the University of Athens Medical School.

You should have received a copy of the license along with this work.

If not, see https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt .

When referencing this dataset in your own manuscripts and publications, please use the following full citation. Please note this is a preprint and has not undergone peer review. It is being prepared for submission and if accepted to a peer reviewed journal the below will be updated accordingly:

[1] Rotemberg, V., Kurtansky, N., Betz-Stablein, B., Caffery, L., Chousakos, E., Codella, N., Combalia, M., Dusza, S., Guitera, P., Gutman, D., Halpern, A., Helba, B., Kittler, H., Kose, K., Langer, S., Lioprys, K., Malvehy, J., Musthaq, S., Nanda, J., Reiter, O., Shih, G., Stratigos, A., Tschandl, P., Weber, J. & Soyer, P. A patient-centric dataset of images and metadata for identifying melanomas using clinical context. Sci Data 8, 34 (2021). https://doi.org/10.1038/s41597-021-00815-z

Organizers

Sponsors:

Chairs of the Committee:

Name Affiliation
H. Peter Soyer, Prof., M.D. The University of Queensland, Dermatology Research Centre, Brisbane, AUS
Allan Halpern, M.D. Memorial Sloan Kettering Cancer Center, New York City, NY, USA
Pascale Guitera, M.D. Melanoma Institute Australia & Sydney Melanoma Diagnostic Center
Noel C. F. Codella, Ph.D.
Marc Combalia, M.S. Fundació Clínic per a la Recerca Biomèdica, Barcelona, Spain
Veronica Rotemberg, M.D., Ph.D. Memorial Sloan Kettering Cancer Center, New York City, NY, USA

Partners:

Name Affiliation
George Shih SIIM
Steve Langer SIIM
Anna Zawacki SIIM
Jochen Weber Memorial Sloan Kettering Cancer Center
Nick Kurtansky Memorial Sloan Kettering Cancer Center
Steve Dusza Memorial Sloan Kettering Cancer Center
Josep Malvehy, M.D. Hospital Clinic de Barcelona
Harald Kittler, Prof., M.D. Medical University of Vienna
Philipp Tschandl Medical University of Vienna
David Gutman Emory University
Brigid Betz-Stablein The University of Queensland
Konstantinos Liopyris, M.D. University of Athens
Alexander Stratigos, M.D. University of Athens
Dataset Training Data Training Ground Truth Test Data Test Ground Truth License
SLICE-3D

Download (1.2GB)
401,059 JPEG images of skin lesion image crops extracted from 3D TBP with metadata entries of age, sex, general anatomic site, common patient identifier, clinical size, and various data fields from the TBP Lesion Visualizer.

Download Supplemental Metadata (40MB)
401,059 metadata entries of attributes which may be useful for training cross-validation.

Download (7MB)
401,059 entries of gold standard lesion malignancy values.
Not Available help_outline
Not Available help_outline
CC-BY-NC
SLICE-3D Permissive

Download (623MB)
217,477 JPEG images of skin lesion image crops extracted from 3D TBP with metadata entries of age, sex, general anatomic site, common patient identifier, clinical size, and various data from the TBP Lesion Visualizer.

Download Supplemental Metadata (21MB)
217,477 metadata entries of attributes which may be useful for training cross-validation.

Download (4MB)
217,477 entries of gold standard lesion malignancy values.
Not Available help_outline
Not Available help_outline
CC-BY

The datasets contain 15mm-by-15mm field-of-view cropped images, centered on distinct lesions, extracted from 3D total body photographs.

Datasets were curated by the International Skin Imaging Collaboration (ISIC) from images contributed by the following:

  • Memorial Sloan Kettering Cancer Center (USA)
  • Hospital Clínic de Barcelona (Spain)
  • The University of Queensland (Australia)
  • Medical University of Vienna (Austria)
  • University of Athens (Greece)
  • Melanoma Institute Australia (Australia)
  • University Hospital of Basel (Switzerland)
  • Alfred Hospital (Australia)
  • FNQH Cairns (Australia)

A dataset descriptor covering the SLICE-3D dataset was published in Scientific Data and is openly available at https://doi.org/10.1038/s41597-024-03743-w.

Citing SLICE-3D dataset:

To comply with the attribution requirements of the CC-BY-NC license, the "SLICE-3D" data must be cited as:

International Skin Imaging Collaboration. SLICE-3D 2024 Challenge Dataset. International Skin Imaging Collaboration https://doi.org/10.34970/2024-slice-3d (2024).

Creative Commons Attribution-Non Commercial 4.0 International License.

The dataset was generated by the International Skin Imaging Collaboration (ISIC) and images are from the following sources: Hospital Clínic de Barcelona, Memorial Sloan Kettering Cancer Center, Hospital of Basel, FNQH Cairns, The University of Queensland, Melanoma Institute Australia, Monash University and Alfred Health, University of Athens Medical School, and Medical University of Vienna.

You should have received a copy of the license along with this work.

If not, see https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt .

Citing SLICE-3D Permissive dataset:

To comply with the attribution requirements of the CC-BY license, the "SLICE-3D Permissive" data must be cited as:

International Skin Imaging Collaboration. SLICE-3D 2024 Permissive Challenge Dataset. International Skin Imaging Collaboration https://doi.org/10.34970/2024-slice-3d-permissive (2024).

Creative Commons Attribution 4.0 International License.

The dataset was generated by the International Skin Imaging Collaboration (ISIC) and images are from the following sources: Memorial Sloan Kettering Cancer Center, FNQH Cairns, The University of Queensland, Melanoma Institute Australia, and University of Athens Medical School.

You should have received a copy of the license along with this work.

If not, see https://creativecommons.org/licenses/by/4.0/legalcode.txt .

Version control:

Any future changes to the ISIC Archive will not affect the versions of the data available at the above links. The metadata on the ISIC Archive proper are subject to change. The training data reflected currently in the ISIC Archive proper are available at https://api.isic-archive.com/collections/390/.

Organizers

Sponsors:

Challenge Co-Chairs:

Name Affiliation
Veronica Rotemberg, M.D., Ph.D. Memorial Sloan Kettering Cancer Center, New York City, NY, USA
Nicholas Kurtansky Memorial Sloan Kettering Cancer Center, New York City, NY, USA

Partners:

Name Affiliation
Jochen Weber Memorial Sloan Kettering Cancer Center
Kivanc Kose, Ph.D. Memorial Sloan Kettering Cancer Center
Allan Halpern, M.D. Memorial Sloan Kettering Cancer Center
Maura Gillis Memorial Sloan Kettering Cancer Center
Josep Malvehy, M.D. Hospital Clinic de Barcelona
H Peter Soyer, Prof., M.D. The University of Queensland
Harald Kittler, Prof., M.D. Medical University of Vienna
Konstantinos Liopyris, M.D. University of Athens
Linda K Martin, M.D. Melanoma Institute Australia
Pascale Guitera, M.D. Melanoma Institute Australia
Alexander A Navarini, Prof., M.D. University Hospital of Basel
Victoria J Mar, M.D. Alfred Hospital
Vin Rajeswaran, M.D. FNQH Cairns
Noel Codella, Ph.D. Microsoft
Training Data Training Ground Truth Test Data Test Ground Truth License

Download (314MB)
10,480 JPEG images, for 5,240 lesions.

Download (2MB)
10,480 metadata entries, for 5,240 lesions.

Download (549KB)
10,480 supplemental metadata entries. 		Download (287KB)
5,240 lesion diagnoses.

Download (30MB)
958 JPEG images, for 479 lesions.

Download (217KB)
958 metadata entries, for 479 lesions.

Not Available help_outline
CC-BY-NC

A dataset descriptor covering the MILK10K dataset was published in The Journal of Investigative Dermatology and is available at https://doi.org/10.1016/j.jid.2025.06.1594.

Citing 2025 datasets:

To comply with the attribution requirements of the CC-BY-NC license , the "ISIC 2025" data must be cited as:
MILK study team. MILK10k. ISIC Archive, 2025, doi:10.34970/648456.