{"success":true,"data":{"author":"Andre G. C. Pacheco, Renato A. Krohling et al. (UFES); repackaged by Chehab Lab","bucketAccessType":"public","bucketName":"chehablab/PAD-UFES-20","bucketPrefix":"","category":"Health & Biomedical","cloudProvider":"huggingface","createdAt":"2026-11-21T22:16:41.541Z","description":"PAD-UFES-20 is a skin cancer dataset of clinical photographs taken with smartphones by the Dermatological and Surgical Assistance Program (PAD) of the Federal University of Espirito Santo (UFES), Brazil, rather than with a dermatoscope. It has 2,298 images of 1,641 lesions from 1,373 patients across six diagnoses: actinic keratosis (ACK), basal cell carcinoma (BCC), melanoma (MEL), nevus (NEV), squamous cell carcinoma (SCC) and seborrheic keratosis (SEK). PAD is a nonprofit program that treats skin lesions, mainly for low-income patients. Each image comes with the patient and lesion fields of the original metadata.csv, such as age, lesion location, Fitzpatrick skin type, lesion diameters and whether the diagnosis was biopsy-proven. The repackaging keeps the original PNGs unchanged and adds an integer label; split by patient_id to avoid leakage. Eight Parquet files under data/, about 3.6 GB (measured 2026-11-21); read with Hugging Face datasets. Use for multimodal skin lesion classification combining images and patient data. Original data on Mendeley Data (DOI 10.17632/zr7vgbcyr2.1), released under CC BY 4.0. Cite Pacheco et al., Data in Brief 32:106221 (2020).","displayTitle":"PAD-UFES-20: smartphone photographs of 1,641 skin lesions from 1,373 patients with clinical metadata (UFES, Brazil)","doi":"10.17632/zr7vgbcyr2.1","huggingFaceUrl":"https://huggingface.co/datasets/chehablab/PAD-UFES-20","id":"5182db11-ae25-5942-9a53-a439c23a1e44","license":"CC-BY-4.0","licenseEvidenceUrl":"https://data.mendeley.com/public-api/datasets/zr7vgbcyr2?version=1","objectCountEstimate":10,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1016/j.dib.2020.106221","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"chehablab/PAD-UFES-20\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"chehablab/PAD-UFES-20\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=chehablab, license:cc-by-4.0, size_categories:1K<n<10K, format:parquet, downloads=128"],"format":"mixed","generatedAt":"2026-11-21T22:32:05.889Z","layout":{"example":"data/train-00000-of-00008.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"data/train-00000-of-00008.parquet","truncatedAt":512}],"sampleObjects":["data/train-00000-of-00008.parquet","data/train-00001-of-00008.parquet","data/train-00002-of-00008.parquet","data/train-00003-of-00008.parquet","data/train-00004-of-00008.parquet"],"sidecars":[{"bytes":"---\ndataset_info:\n  features:\n  - name: image_id\n    dtype: string\n  - name: image\n    dtype: image\n  - name: patient_id\n    dtype: string\n  - name: lesion_id\n    dtype: string\n  - name: diagnostic\n    dtype: string\n  - name: label\n    dtype: int32\n  - name: smoke\n    dtype: string\n  - name: drink\n    dtype: string\n  - name: background_father\n    dtype: string\n  - name: background_mother\n    dtype: string\n  - name: age\n    dtype: string\n  - name: pesticide\n    dtype: string\n  - name: gender\n    dtype: string\n  - name: skin_cancer_history\n    dtype: string\n  - name: cancer_history\n    dtype: string\n  - name: has_piped_water\n    dtype: string\n  - name: has_sewage_system\n    dtype: string\n  - name: fitspatrick\n    dtype: string\n  - name: region\n    dtype: string\n  - name: diameter_1\n    dtype: string\n  - name: diameter_2\n    dtype: string\n  - name: itch\n    dtype: string\n  - name: grew\n    dtype: string\n  - name: hurt\n    dtype: string\n  - name: changed\n    dtype: string\n  - name: bleed\n    dtype: string\n  - name: elevation\n    dtype: string\n  - name: biopsed\n    dtype: string\n  splits:\n  - name: train\n    num_bytes: 3934962362\n    num_examples: 2298\n  download_size: 3607027267\n  dataset_size: 3934962362\nconfigs:\n- config_name: default\n  data_files:\n  - split: train\n    path: data/train-*\nlicense: cc-by-4.0\ntask_categories:\n- image-classification\nlanguage:\n- en\ntags:\n- dermatology\n- skin-lesions\n- skin-cancer\n- smartphone\n- clinical-images\n- medical\n- classification\npretty_name: PAD-UFES-20\nsize_categories:\n- 1K<n<10K\n---\n\n# PAD-UFES-20 — Skin Lesion Images and Patient Data Collected from Smartphones\n\n> [!NOTE]\n> This dataset card was generated with the help of generative AI and checked against the original sources. If you find an error or anything unclear, please open a discussion in the [Community tab](https://huggingface.co/datasets/chehablab/PAD-UFES-20/discussions) of this repository.\n\nThis dataset is derived from PAD-UFES-20 (Pacheco et al., 2020), a skin lesion dataset originally hosted on Mendeley Data. It was collected by the Dermatological and Surgical Assistance Program (Programa de Assistência Dermatológica e Cirúrgica, PAD) at the Federal University of Espírito Santo (UFES), Brazil, a nonprofit program that provides free skin lesion treatment, mainly to low-income patients.\nEach sample is a clinical photograph taken with a smartphone, together with patient and lesion metadata. We kept the original PNG images unchanged and added the metadata from the original `metadata.csv` and an integer label.\nThe dataset is designed for skin lesion classification, with or without clinical metadata.\n\n\n## 📦 Dataset Structure\n\nThe dataset has a single `train` split, with each row corresponding to a single skin lesion image:\n\n| Field | Description |\n|---|---|\n| `image_id` | Original image filename without extension |\n| `image` | RGB clinical photograph of the lesion (variable size, PNG) |\n| `patient_id` | Patient identifier from the original metadata |\n| `lesion_id` | Lesion identifier from the original metadata |\n| `diagnostic` | Diagnosis: `ACK`, `BCC`, `MEL`, `NEV`, `SCC` or `SEK` |\n| `label` | Integer diagnosis: `0`–`5` (see Feature Descriptions) |\n| other columns | All remaining columns of the original `metadata.csv` (e.g., age, lesion location, Fitzpatrick skin type, lesion diameters, whether the diagnosis was biopsy-proven), stored as strings, `\"\"` when missing |\n\nIn total, the dataset contains 2,298 images of 1,641 lesions from 1,373 patients.\n\n\n## ⚙️ Preprocessing\n\n- `metadata.csv` and `imgs_part_1.zip`, `imgs_part_2.zip`, `imgs_part_3.zip` were downloaded from Mendeley Data (`zr7vgbcyr2`, version 1)\n- Images were kept as the original PNG files (no re-encoding, resizing, cropping or color normalization)\n- Each image was matched to its row in `metadata.csv` by filename\n- `label` is the index of `diagnostic` in the list `ACK, BCC, MEL, NEV, SCC, SEK`\n- All metadata columns and all images were preserved\n\n\n## 🚀 Usage\n\n```python\nfrom datasets import load_dataset\nimport matplotlib.pyplot as plt\nfrom sklearn.m","encoding":"utf8","key":"README.md","name":"README.md","size":10339,"truncated":true}],"sourceObjectKey":"data/train-00000-of-00008.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"chehablab/PAD-UFES-20\")\nprint(ds)","starterSamplePath":"data/train-00000-of-00008.parquet","totalObjects":10},"summary":"PAD-UFES-20 is a skin cancer dataset of clinical photographs taken with smartphones by the Dermatological and Surgical Assistance Program (PAD) of the Federal University of…","title":"PAD-UFES-20: smartphone photographs of 1,641 skin lesions from 1,373 patients with clinical metadata (UFES, Brazil)","updatedAt":"2026-11-22T01:03:29.779Z","visibility":"public","websiteUrl":"https://data.mendeley.com/datasets/zr7vgbcyr2/1"}}