datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
skin_cancer
The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions
Original Paper and Dataset here
Kaggle dataset here
Introduction to datasets
Training of neural networks for automated diagnosis of pigmented skin lesions is hampered by the small size and lack of diversity of available dataset of dermatoscopic images. We tackle this problem by releasing the HAM10000 ("Human Against Machine with 10000 training images") dataset.… See the full description on the dataset page: https://huggingface.co/datasets/marmal88/skin_cancer.Single-cell_Microscopy_Images_for_Cancer_ClassificationThis datatset is a mirror to the dataset "Single-cell Microscopy Images for Cancer Classification" DOI: "xxxxxxx" in Mendeley Data, we will maintain both to upload new dataset in time and keep these two versions the same.
This is a dataset for single cell fluorescence microscopy images. The dataset includes cancer cells and normal cells. The images contain three channels: red (actin filament), green (vimentin filament), and blue (nucleus). We have 591 normal cells and 542 cancer cells. More… See the full description on the dataset page: https://huggingface.co/datasets/Jiabang/Single-cell_Microscopy_Images_for_Cancer_Classification.skin_cancer
The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions
Original Paper and Dataset here
Kaggle dataset here
Introduction to datasets
Training of neural networks for automated diagnosis of pigmented skin lesions is hampered by the small size and lack of diversity of available dataset of dermatoscopic images. We tackle this problem by releasing the HAM10000 ("Human Against Machine with 10000 training images") dataset.… See the full description on the dataset page: https://huggingface.co/datasets/vnny2/skin_cancer.skin_cancer
The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions
Original Paper and Dataset here
Kaggle dataset here
Introduction to datasets
Training of neural networks for automated diagnosis of pigmented skin lesions is hampered by the small size and lack of diversity of available dataset of dermatoscopic images. We tackle this problem by releasing the HAM10000 ("Human Against Machine with 10000 training images") dataset.… See the full description on the dataset page: https://huggingface.co/datasets/safal-singh/skin_cancer.breast_cancer_xrayAfrica-skin-cancer-images-EHR
Africanized Skin Cancer Multimodal Dataset
Dataset Description
This dataset extends the HAM10000 dermatoscopic image collection with:
Provisional skin-tone annotations (Fitzpatrick scale estimates)
Synthetic African-focused Electronic Health Records (EHR)
Multimodal patient demographics, comorbidities, medications, and lab values
Created by: kossiso RoyceDate: October 2025Version: 1.0
Objective
Create a more representative dataset for training and… See the full description on the dataset page: https://huggingface.co/datasets/Sakhawat077/Africa-skin-cancer-images-EHR.breast_cancer_practice