{"success":true,"data":{"author":"Chu Han, Xipeng Pan et al. (WSSS4LUAD organizers); repackaged by MedOtter","bucketAccessType":"public","bucketName":"MedOtter/WSSS4LUAD-v2","bucketPrefix":"","category":"Health & Biomedical","cloudProvider":"huggingface","createdAt":"2026-11-21T22:16:41.453Z","description":"WSSS4LUAD is the dataset of the Grand Challenge on weakly supervised tissue semantic segmentation for lung adenocarcinoma (LUAD): H&E-stained histopathology patches where training images carry only image-level labels and the model must still produce pixel-level tissue maps. The 10,091 training patches are labeled with which of three tissue classes they contain (tumor epithelial tissue, tumor-associated stroma, normal tissue); 40 validation and 80 test patches have pixel-level masks plus a background mask for unstained areas. Each row has the PNG patch, filename, width and height, the three binary labels (training) or the masks (validation and test). Three Parquet files (train, validation, test), about 1.6 GB (measured 2026-11-21); read with Hugging Face datasets or pandas plus Pillow. Use for weakly supervised semantic segmentation, class activation map methods and tumor microenvironment analysis in digital pathology. The challenge site states the dataset is licensed CC BY 4.0. Cite Han et al., WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma, arXiv:2204.06455 (2022).","displayTitle":"WSSS4LUAD: lung adenocarcinoma H&E patches for weakly supervised tissue segmentation (tumor, stroma, normal)","huggingFaceUrl":"https://huggingface.co/datasets/MedOtter/WSSS4LUAD-v2","id":"a6878e21-5392-5275-8e60-36f105fd1b60","license":"CC-BY-4.0","licenseEvidenceUrl":"https://wsss4luad.grand-challenge.org/License/","objectCountEstimate":6,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2204.06455","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"MedOtter/WSSS4LUAD-v2\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"MedOtter/WSSS4LUAD-v2\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=MedOtter, license:cc-by-4.0, size_categories:10K<n<100K, format:parquet, downloads=261"],"format":"mixed","generatedAt":"2026-11-21T22:32:04.506Z","layout":{"example":"test.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"test.parquet","truncatedAt":512}],"sampleObjects":["test.parquet","train.parquet","validation.parquet"],"sidecars":[{"bytes":"---\ndataset_info:\n  features:\n  - name: image_id\n    dtype: string\n  - name: image\n    dtype: image\n  - name: filename\n    dtype: string\n  - name: width\n    dtype: int32\n  - name: height\n    dtype: int32\n  - name: split\n    dtype: string\n  - name: label_tumor\n    dtype: int8\n  - name: label_stroma\n    dtype: int8\n  - name: label_normal\n    dtype: int8\n  - name: mask\n    dtype: image\n  - name: background_mask\n    dtype: image\n  splits:\n  - name: train\n    num_examples: 10091\n  - name: validation\n    num_examples: 40\n  - name: test\n    num_examples: 80\nlicense: cc-by-4.0\ntask_categories:\n- image-segmentation\ntags:\n- medical\n- pathology\n- lung-cancer\n---\n\n# WSSS4LUAD Dataset\n\nThis is the WSSS4LUAD dataset for weakly-supervised tissue semantic segmentation in lung adenocarcinoma.\n\n## Dataset Description\n\nThe dataset contains histopathology image patches from lung adenocarcinoma tissue samples, designed for weakly-supervised semantic segmentation tasks.\n\n## Dataset Structure\n\n- **Training**: 10,091 patches with image-level labels\n- **Validation**: 40 patches with pixel-level masks\n- **Test**: 80 patches with pixel-level masks\n\n## Classes\n\nThe dataset includes 3 tissue classes:\n1. **Tumor epithelial tissue** (label_tumor)\n2. **Tumor-associated stroma tissue** (label_stroma)\n3. **Normal tissue** (label_normal)\n\n## Features\n\n- `image_id`: Unique identifier for each image\n- `image`: The histopathology image patch (PNG format, embedded)\n- `filename`: Original filename\n- `width`: Image width in pixels\n- `height`: Image height in pixels\n- `split`: Dataset split (train/validation/test)\n- `label_tumor`: Binary label for tumor epithelial tissue (training only)\n- `label_stroma`: Binary label for tumor stroma tissue (training only)\n- `label_normal`: Binary label for normal tissue (training only)\n- `mask`: Pixel-level segmentation mask (validation/test only)\n- `background_mask`: Background region mask (validation/test only)\n\n## Usage\n\n```python\nfrom datasets import load_dataset\n\n# Load the dataset\ndataset = load_dataset(\"USERNAME/WSSS4LUAD\")\n\n# Access different splits\ntrain_data = dataset['train']\nval_data = dataset['validation']\ntest_data = dataset['test']\n\n# Example: Load and display an image\nexample = train_data[0]\nimage = example['image']  # PIL Image\nlabels = {\n    'tumor': example['label_tumor'],\n    'stroma': example['label_stroma'],\n    'normal': example['label_normal']\n}\n```\n\n## Citation\n\nIf you use this dataset, please cite the original WSSS4LUAD paper.\n\n## License\n\nThis dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.\n","encoding":"utf8","key":"README.md","name":"README.md","size":2606,"truncated":false},{"bytes":"{\n  \"dataset_name\": \"WSSS4LUAD\",\n  \"description\": \"Weakly-Supervised Tissue Semantic Segmentation for Lung Adenocarcinoma\",\n  \"num_classes\": 3,\n  \"classes\": [\n    \"tumor_epithelial\",\n    \"tumor_stroma\",\n    \"normal_tissue\"\n  ],\n  \"total_samples\": 10211,\n  \"splits\": {\n    \"train\": {\n      \"num_examples\": 10091,\n      \"file_size_mb\": 1171.9069919586182,\n      \"max_row_group_mb\": 1.5423202514648438,\n      \"num_row_groups\": 1010\n    },\n    \"validation\": {\n      \"num_examples\": 40,\n      \"file_size_mb\": 150.56257247924805,\n      \"max_row_group_mb\": 142.52832126617432,\n      \"num_row_groups\": 4\n    },\n    \"test\": {\n      \"num_examples\": 80,\n      \"file_size_mb\": 234.02422714233398,\n      \"max_row_group_mb\": 156.98893070220947,\n      \"num_row_groups\": 8\n    }\n  },\n  \"image_format\": \"PNG (embedded as bytes)\",\n  \"license\": \"CC BY 4.0\",\n  \"batch_size_used\": 10\n}","encoding":"utf8","key":"dataset_info.json","name":"dataset_info.json","size":864,"truncated":false}],"sourceObjectKey":"test.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"MedOtter/WSSS4LUAD-v2\")\nprint(ds)","starterSamplePath":"test.parquet","totalObjects":6},"summary":"WSSS4LUAD is the dataset of the Grand Challenge on weakly supervised tissue semantic segmentation for lung adenocarcinoma (LUAD): H&E-stained histopathology patches where training…","title":"WSSS4LUAD: lung adenocarcinoma H&E patches for weakly supervised tissue segmentation (tumor, stroma, normal)","updatedAt":"2026-11-22T00:54:25.227Z","visibility":"public","websiteUrl":"https://wsss4luad.grand-challenge.org/"}}