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.
Not Available help_outline
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.
Not Available help_outline

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] Marc Combalia, Noel C. F. Codella, Veronica Rotemberg, Brian Helba, Veronica Vilaplana, Ofer Reiter, Allan C. Halpern, Susana Puig, Josep Malvehy: "BCN20000: Dermoscopic Lesions in the Wild", 2019; arXiv:1908.02288.

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.

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