{"success":true,"data":{"author":"Phillips et al.; curated by SPORA","bucketAccessType":"public","bucketName":"csmp-hub/phillips-ctcl","bucketPrefix":"","category":"Health & Biomedical","cloudProvider":"huggingface","createdAt":"2026-11-17T19:29:33.071Z","description":"H&E images of skin biopsies from patients with cutaneous T-cell lymphoma (CTCL) in the study of Phillips et al. (Nature Communications 2021), which used CODEX multiplexed imaging to show that immune cell spatial arrangement predicts response to PD-1 blockade with pembrolizumab. The dataset has 69 paired tissue regions from 14 patients. Each 1,440x1,920-pixel core is tiled into 108 overlapping 512x512 RGB crops at 0.377 micrometers per pixel (128-pixel stride), with instance masks that keep the original cell-region IDs and cell-type masks for 23 types from the source table: T cell subsets, B cells, plasma cells, macrophages, dendritic cells, Langerhans cells, mast cells, neutrophils, stromal cells, epithelium and tumor cells (here malignant T cells, not epithelial tumor). Files include crop Parquet tables, cell-annotations.parquet, crop-quality.parquet, a reviewed training index, classes.json and reference.bib; about 3.5 GB (measured 2026-11-17). Images and masks are stored as PNG or TIFF bytes inside Parquet; read them with polars or pandas plus Pillow, or with Hugging Face datasets. Curated and packaged on Hugging Face by the SPORA project (csmp-hub), which keeps the original license and citation files. The original Mendeley Data release (3gmvy3bcmk) is CC BY 4.0; cite Phillips et al., Nature Communications 2021, doi 10.1038/s41467-021-26974-6.","displayTitle":"Phillips CTCL: cutaneous T-cell lymphoma skin biopsy H&E with CODEX cell regions and 23 cell types","doi":"10.17632/3gmvy3bcmk.1","huggingFaceUrl":"https://huggingface.co/datasets/csmp-hub/phillips-ctcl","id":"096021ca-18e4-5cf3-a879-2cb2bad7eeaf","license":"CC-BY-4.0","licenseEvidenceUrl":"https://data.mendeley.com/datasets/3gmvy3bcmk/1","objectCountEstimate":17,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1038/s41467-021-26974-6","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"csmp-hub/phillips-ctcl\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"csmp-hub/phillips-ctcl\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=csmp-hub, license:cc-by-4.0, size_categories:1K<n<10K, downloads=164"],"format":"mixed","generatedAt":"2026-11-17T19:40:15.458Z","layout":{"example":"cell-annotations.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"cell-annotations.parquet","truncatedAt":512}],"sampleObjects":["cell-annotations.parquet","class-distribution.png","class-support.json","classes.json","crop-instances.parquet"],"sidecars":[{"bytes":"Attribution 4.0 International\n\n=======================================================================\n\nCreative Commons Corporation (\"Creative Commons\") is not a law firm and\ndoes not provide legal services or legal advice. Distribution of\nCreative Commons public licenses does not create a lawyer-client or\nother relationship. Creative Commons makes its licenses and related\ninformation available on an \"as-is\" basis. Creative Commons gives no\nwarranties regarding its licenses, any material licensed under their\nterms and conditions, or any related information. Creative Commons\ndisclaims all liability for damages resulting from their use to the\nfullest extent possible.\n\nUsing Creative Commons Public Licenses\n\nCreative Commons public licenses provide a standard set of terms and\nconditions that creators and other rights holders may use to share\noriginal works of authorship and other material subject to copyright\nand certain other rights specified in the public license below. The\nfollowing considerations are for informational purposes only, are not\nexhaustive, and do not form part of our licenses.\n\n     Considerations for licensors: Our public licenses are\n     intended for use by those authorized to give the public\n     permission to use material in ways otherwise restricted by\n     copyright and certain other rights. Our licenses are\n     irrevocable. Licensors should read and understand the terms\n     and conditions of the license they choose before applying it.\n     Licensors should also secure all rights necessary before\n     applying our licenses so that the public can reuse the\n     material as expected. Licensors should clearly mark any\n     material not subject to the license. This includes other CC-\n     licensed material, or material used under an exception or\n     limitation to copyright. More considerations for licensors:\n    wiki.creativecommons.org/Considerations_for_licensors\n\n     Considerations for the public: By using one of our public\n     licenses, a licensor grants the public permission to use the\n     licensed material under specified terms and conditions. If\n     the licensor's permission is not necessary for any reason--for\n     example, because of any applicable exception or limitation to\n     copyright--then that use is not regulated by the license. Our\n     licenses grant only permissions under copyright and certain\n     other rights that a licensor has authority to grant. Use of\n     the licensed material may still be restricted for other\n     reasons, including because others have copyright or other\n     rights in the material. A licensor may make special requests,\n     such as asking that all changes be marked or described.\n     Although not required by our licenses, you are encouraged to\n     respect those requests where reasonable. More considerations\n     for the public:\n    wiki.creativecommons.org/Considerations_for_licensees\n\n=======================================================================\n\nCreative Commons Attribution 4.0 International Public License\n\nBy exercising the Licensed Rights (defined below), You accept and agree\nto be bound by the terms and conditions of this Creative Commons\nAttribution 4.0 International Public License (\"Public License\"). To the\nextent this Public License may be interpreted as a contract, You are\ngranted the Licensed Rights in consideration of Your acceptance of\nthese terms and conditions, and the Licensor grants You such rights in\nconsideration of benefits the Licensor receives from making the\nLicensed Material available under these terms and conditions.\n\n\nSection 1 -- Definitions.\n\n  a. Adapted Material means material subject to Copyright and Similar\n     Rights that is derived from or based upon the Licensed Material\n     and in which the Licensed Material is translated, altered,\n     arranged, transformed, or otherwise modified in a manner requiring\n     permission under the Copyright and Similar Rights held by the\n     Licensor. For purposes of this Public License, where the Licensed\n     Material is a musical work, performance, or sound recording,\n ","encoding":"utf8","key":"LICENSE","name":"LICENSE","size":18656,"truncated":true},{"bytes":"---\nlicense: cc-by-4.0\ntask_categories:\n  - image-segmentation\nconfigs:\n  - config_name: default\n    data_files:\n      - split: train\n        path: train.parquet\n      - split: test\n        path: test.parquet\n---\n\n# Phillips CTCL\n\nH&E images of skin biopsies from people with cutaneous T-cell lymphoma, with\ncell-region instance masks and cell types from paired CODEX imaging. The source\nstudy examined how the arrangement of immune and tumour cells relates to\nresponse to pembrolizumab. This dataset contains 69 paired tissue regions from\n14 patients.\n\nThe data is licensed under **CC BY 4.0**. Credit Phillips and colleagues and\nSPORA, link the license and describe any changes. The original license and\ncitation are included as `LICENSE` and `reference.bib`.\n\n## Images and annotations\n\nImages keep their original RGB values at 0.37744 micrometres per pixel.\nEach crop is 512 × 512 pixels. Crops start 128 pixels apart, with the final\nrow and column placed against the core edge. Each 1,440 × 1,920-pixel core\ncontributes 108 overlapping crops.\n\nThe instance masks keep the original cell-region IDs. Use `core_id` and the\ninstance ID together to identify a cell across crops.\n\nThe 23 cell types retain the source table's `new_cluster` names. They include\nT-cell groups, B cells, plasma cells, macrophages, dendritic cells, Langerhans\ncells, mast cells, neutrophils, stromal cells, epithelium and tumour cells.\nHere, tumour cells are malignant T cells; they should not be treated as\nepithelial tumour cells. `classes.json` maps the names to mask codes.\nBackground is zero; 255 is reserved for unknown labels.\n\nThere are 107,331 distinct cells in the masks.\nThe source cell table contains 9,839\nadditional cell records without an object in the exported masks. These records\nare retained with `present_in_mask=false` in `cell-annotations.parquet`.\n\n![H&E, cell-region boundaries, instance masks and cell-type masks](examples.png)\n\nInstance colours distinguish cell regions. Cell-type colours follow the legend. Black is background.\n\n## Cell-type instance counts\n\nThese counts include only cells present in the crop masks. Each source cell is\ncounted once using its slide and original instance ID, even when crops overlap.\nPartial cells at crop edges are included. Counts include all quality flags;\nUnknown and source quality labels remain separate from biological classes.\n\n![Unique source instances per cell type](class-distribution.png)\n\n| Original class | Train | Test | Unique total | Crop appearances |\n| --- | ---: | ---: | ---: | ---: |\n| B cells | 1,755 | 284 | 2,039 | 26,219 |\n| CD4+ T cells | 848 | 278 | 1,126 | 14,800 |\n| CD8+ T cells | 3,742 | 947 | 4,689 | 60,536 |\n| CLA+ leukocytes | 117 | 54 | 171 | 2,242 |\n| DCs, CD11c+ | 30 | 144 | 174 | 2,117 |\n| IDO+ stromal cells | 173 | 15 | 188 | 2,500 |\n| Langerhans cells | 1,337 | 231 | 1,568 | 19,223 |\n| PD1+CD4+ T cells | 271 | 115 | 386 | 4,788 |\n| PD1+CD8+ T cells | 148 | 178 | 326 | 3,831 |\n| Tregs | 6,863 | 579 | 7,442 | 91,763 |\n| epithelium | 9,779 | 5,483 | 15,262 | 189,546 |\n| lymphatics | 479 | 197 | 676 | 8,430 |\n| macrophages (M1=M2) | 3,266 | 672 | 3,938 | 49,044 |\n| macrophages (M1>M2) | 10,432 | 2,137 | 12,569 | 157,305 |\n| macrophages (M2>M1) | 843 | 815 | 1,658 | 20,523 |\n| mast cells | 479 | 98 | 577 | 7,567 |\n| nerves | 418 | 86 | 504 | 5,883 |\n| neutrophils | 321 | 74 | 395 | 5,442 |\n| plasma cells | 563 | 120 | 683 | 8,670 |\n| stroma | 7,344 | 2,510 | 9,854 | 123,904 |\n| tumor cells | 25,686 | 11,042 | 36,728 | 465,815 |\n| tumor cells, intraepithelial | 652 | 632 | 1,284 | 16,832 |\n| vasculature | 4,046 | 1,048 | 5,094 | 66,267 |\n| Unknown | 0 | 0 | 0 | 0 |\n| **Total** | **79,592** | **27,739** | **107,331** | **1,353,247** |\n\n[instance-counts.csv](instance-counts.csv) has one row per crop in `train.parquet`\nor `test.parquet`. Match `id` to the crop row; `source_file` names its Parquet file.\nIt records `total_instances` and one `class:<original name>` column per class,\nincluding zero counts. It also includes the split, slide, patient, crop position,\nreview status and `skip_training` fl","encoding":"utf8","key":"README.md","name":"README.md","size":9196,"truncated":true},{"bytes":"{\n  \"dataset\": \"Phillips CTCL\",\n  \"license\": \"CC BY 4.0\",\n  \"sources\": {\n    \"SPORA\": \"https://spora.bioimagearchive.org/projects/spora\",\n    \"study\": \"https://doi.org/10.1038/s41467-021-26974-6\",\n    \"original_cell_table\": \"https://doi.org/10.17632/3gmvy3bcmk.1\",\n    \"data_root\": \"https://livingobjects.ebi.ac.uk/bioimaging-01-pub/spora-submissions/phillips2021immune/\"\n  },\n  \"splits\": {\n    \"train\": {\n      \"crops\": 5940,\n      \"patients\": 11\n    },\n    \"test\": {\n      \"crops\": 1512,\n      \"patients\": 3\n    }\n  },\n  \"cores\": 69,\n  \"unique_source_cells_visible_in_masks\": 107331,\n  \"source_cell_records\": 117170,\n  \"source_records_absent_from_masks\": 9839,\n  \"source_mask_ids_without_cell_record\": 0,\n  \"crop_shape_yx\": [\n    512,\n    512\n  ],\n  \"nominal_stride\": 128,\n  \"mpp\": 0.37744,\n  \"instance_mask\": \"Original cell-region IDs, uint16 PNG; background0\",\n  \"type_mask\": \"23 original new_cluster names, codes in classes.json; uint8 PNG; background0,unknown255\",\n  \"quality\": {\n    \"reviewed_usable\": 24,\n    \"unreviewed\": 7428,\n    \"skip_training\": 0,\n    \"selected_training_review_only\": true,\n    \"test_crops_reviewed\": 0\n  },\n  \"changes\": [\n    \"Native overlapping RGB crops with edge anchoring\",\n    \"Original instance IDs retained as lossless uint16 PNG\",\n    \"Source updated cell-type names rasterized by original cell ID\",\n    \"Patient splits retained\",\n    \"Original cell-table records absent from masks retained explicitly; no replacement objects generated\",\n    \"Direct human quality reviews recorded for24 crops; unreviewed areas not implicitly approved\"\n  ],\n  \"sha256\": {\n    \"train.parquet\": \"88f14b6ebfcaf6a4b41e195cebd3f32403594830689c9b824e3c59533de87e09\",\n    \"test.parquet\": \"46f23aa4e5cfc2163ec90430ec2a327389eb7a77b0e2549ae82e04f488422a45\",\n    \"cell-annotations.parquet\": \"c4e1c28e7eeec125dd4d1ff0409398bd1435d8162723fe75ed22b7ab24e055a5\",\n    \"crop-instances.parquet\": \"b93ce8e7a4faf8540410ee1b4774c04403b9f6b3f695a6424a157e23899df905\",\n    \"training-index.parquet\": \"ed109a0baba5f26a2e19080ceacfa49e17cdae00177cc3ef36dd201e8e9d5eea\",\n    \"reviewed-training-index.parquet\": \"06808b30ae2e1dbe8b9c92491649af57b4134ae7a4f6fc900cd9449527a9f6f3\",\n    \"crop-quality.parquet\": \"6c59c79353bf8e31a2cf26006484f48ffa45881d44fabf54696c2649b5884a98\",\n    \"classes.json\": \"295e02af0f28668660f496b796d08677efa56a6c8affc99ff43ee03fddaeea3a\",\n    \"class-support.json\": \"98191dba14d77aab16fd45b0e078b7c259934a6bd36a79668b8ee7aaeda50b6e\",\n    \"LICENSE\": \"9e5f1b3c610b9c2da5c313bf81d577a7d1acec686bdb0384edefa6df0f90cd94\",\n    \"reference.bib\": \"3eb2026ae68a76be7e688686176243bca97537d538c5364766dff85cfd41cf2b\",\n    \"examples.png\": \"e6f94d1677acff6d83beffeb384f8ca272784a94fd22590d53d22ff4e3cb3873\",\n    \"README.md\": \"1d1d6eaaf54883c4e8fb45bc4df68081b6b8c54d49393cd069779576886325e4\",\n    \"class-distribution.png\": \"5d0aeb150eadce7aebb5268e3765c2a507af44843baca45e6fc078f2564ae40f\",\n    \"instance-counts.csv\": \"7c9a74133928d3925acbd57b1d79c46d66234593ec4979f7b658b304adcd7585\"\n  }\n}\n","encoding":"utf8","key":"manifest.json","name":"manifest.json","size":2995,"truncated":false}],"sourceObjectKey":"cell-annotations.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"csmp-hub/phillips-ctcl\")\nprint(ds)","starterSamplePath":"cell-annotations.parquet","totalObjects":17},"summary":"H&E images of skin biopsies from patients with cutaneous T-cell lymphoma (CTCL) in the study of Phillips et al.","title":"Phillips CTCL: cutaneous T-cell lymphoma skin biopsy H&E with CODEX cell regions and 23 cell types","updatedAt":"2026-11-17T23:28:44.677Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/csmp-hub/phillips-ctcl"}}