Skin Cancer: HAM10000
Description
The logic to split the image dataset, containing the name "paper", was extracted from: Shetty, B., Fernandes, R., Rodrigues, A.P. et al. Skin lesion classification of dermoscopic images using machine learning and convolutional neural network. Sci Rep 12, 18134 (2022). https://doi.org/10.1038/s41598-022-22644-9.
The logic to split the image dataset, containing the name "full," means that all possible images were used to create the splits.
Image source for the skin lesion: 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).
Files
HAM10000_full_leak.csv
Files
(2.8 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:d931250f516a23ba842ec393cc27e489
|
410.6 kB | Preview Download |
|
md5:420833bcd2addb047aed5ee97106ea42
|
410.6 kB | Preview Download |
|
md5:a7c8e7e52fe943c459f599f0063645dc
|
2.8 GB | Preview Download |
|
md5:234749eb2d6850a4ebbf81bbf47986fc
|
28.7 kB | Preview Download |
|
md5:9ad87c8ee3c204153d9cff59c6eb68d6
|
28.7 kB | Preview Download |
Additional details
Additional titles
- Alternative title
- Skin Cancer MNIST: HAM10000
Software
- Repository URL
- https://github.com/ptschandl/HAM10000_dataset