{"success":true,"data":{"author":"Yuanfeng Ji et al., AMOS 2022 challenge (redistributed by Yongcheng Yao)","bucketAccessType":"public","bucketName":"YongchengYAO/AMOS22-Lite","bucketPrefix":"","category":"Health & Biomedical","cloudProvider":"huggingface","createdAt":"2026-11-14T14:15:11.776Z","description":"AMOS (A large-scale abdominal multi-organ benchmark for versatile medical image segmentation) is the MICCAI 2022 challenge dataset of abdominal CT and MRI collected across multiple centres, vendors and disease cohorts, annotated voxel-wise for 15 organs: spleen, both kidneys, gallbladder, esophagus, liver, stomach, aorta, inferior vena cava, pancreas, both adrenal glands, duodenum, bladder and prostate/uterus. This repository, prepared by Yongcheng Yao for the MedVision benchmark, contains every labelled case of the public train and validation splits, 300 CT and 60 MRI volumes with masks, in AMOS22-CT and AMOS22-MRI folders; the unlabelled test images are left out. Image voxel data are unmodified apart from reorientation to RAS+. As measured 2026-11-14 the data ship as three zip parts totalling about 22.7 GB; unzip and read the NIfTI (.nii.gz) files with nibabel, SimpleITK or MONAI. Used for training and benchmarking CT and MRI organ segmentation, cross-modality generalisation and medical foundation models. The AMOS organisers release the data on Zenodo under CC BY 4.0; cite Ji et al., NeurIPS 2022 Datasets and Benchmarks.","displayTitle":"AMOS 2022: abdominal multi-organ segmentation benchmark (300 CT + 60 MRI)","doi":"10.5281/zenodo.7262581","id":"26c6b2aa-4d5f-55bb-a3ef-e1fd89958ee8","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/records/7262581","objectCountEstimate":5,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2206.08023","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"YongchengYAO/AMOS22-Lite\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"YongchengYAO/AMOS22-Lite\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=YongchengYAO, license:cc-by-4.0, size_categories:n<1K, downloads=445"],"format":"mixed","generatedAt":"2026-11-14T14:15:14.660Z","layout":{"example":"data-part001.zip","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"504b030414000000000030055b5bc663d8a72ac29c042ac29c0421000000414d4f5332322d43542f496d616765732f616d6f735f303030312e6e69692e677a1f8b08000000000004ffecdb2f8c24f9f625f65a2f2919b58c06060cc99295bb5a4b492ca76592c0a08041cb326862a90dbc6a190d6cd8c82e583061c2644e19a5b42460008380050b264ce8997ee7b3fabde34dcdefcd54aff7cd8bb77fcedefb3df7dc736f44667f2b7f6fffe77ff1f0cff8cffffef02f1f7ef9dffff27f7af817f95f7f5db47bd87d4f7cfd6f1f1efe8bfc9fc35f527f453cfdf70f0fbf72beffe73fffaba37f12fc8fffebfff6bffc37ffeadffc9b7ffdafffebff6ab3d9fc9393f7fe7ffe677f2df86fff877ff7f07ffddfffeee1e1fff9effe32478e7fcd7fffcfafb3fdf29fef9cefffaf5ffeaf5fe7fc95ffd7fff9b7ffe5bffa2789e7cb5f8215d73dfcba81f53d58df83ff04de832fffc7e5fb737809be053ffc9f7fc9ff14bc253f17be269e82978a1f4a67484c5fbdbed7d4ab7b0c5f9dbc7a793cf56288ef1ceaebfc53fa7d0c6e83faf2bb944ff59bf077417948c73e219feae1101de7facfe96f0e288f07f5f13c215ff4f1e8d90f5db139e8e0e3c1a9de874bc5fce13b3f176f49cc9fe7f229fb39047feff7eaed4efd5bf273f5d1ef73f2f6681e73f73ce682c7cc05f1d59bdbf3b177e710cf1eafd155c79ffc5bcef9a58b","encoding":"hex","key":"data-part001.zip","truncatedAt":512}],"sampleObjects":["data-part001.zip","data-part002.zip","data-part003.zip"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\ntask_categories:\n- image-segmentation\nlanguage:\n- en\ntags:\n- medical\n- image\n- ct\n- mri\n- abdomen\n- segmentation\n- detection\npretty_name: 'amos22-lite'\nsize_categories:\n- n<1K\n---\n\n\n## About\nThis is a preprocessed redistribution of [AMOS22](https://amos22.grand-challenge.org) ([Zenodo](https://zenodo.org/records/7262581)), which is released under the `CC BY 4.0` license.\n\n**Dataset summary:** 360 abdominal scans (300 CT + 60 MRI) with 15-class multi-organ segmentation masks.\n\n**Contents of this repository:**\n\n- `AMOS22-CT/Images/` — 300 files\n- `AMOS22-CT/Masks/` — 300 files\n- `AMOS22-MRI/Images/` — 60 files\n- `AMOS22-MRI/Masks/` — 60 files\n\n📝 Landmark annotations, visualization figures and the benchmark plan files live in 🔥[MedVision](https://huggingface.co/datasets/YongchengYAO/MedVision)🔥, where you can load the complete images and annotations from dataset configs.\n\n\n## Relation to the source dataset\n\n| | |\n| --- | --- |\n| In the source | the AMOS 2022 release - abdominal CT and MRI across train/val/test; expert masks are public for the train+val split only (300 CT + 60 MRI) |\n| Excluded here | the unlabelled test images (`imagesTs`), which ship no public masks |\n| **In this repo** | **300 `AMOS22-CT/Images` + 300 `AMOS22-CT/Masks` + 60 `AMOS22-MRI/Images` + 60 `AMOS22-MRI/Masks`** |\n\n**Every labelled case is included - 300 CT and 60 MRI.** No format conversion was required: the source already ships `nii.gz`, and the image voxel data is carried over unmodified. What is derived here is the RAS+ reorientation and the modality-split layout that replaces the source's `imagesTr`/`imagesVa` + `labelsTr`/`labelsVa` folders.\n\nCT and MRI are shipped as **separate** folder pairs because MedVision treats them as two tasks, and because the source encodes the modality only in the case number (`amos_0001`-`amos_0506` are CT, `amos_0507`+ are MRI) - a fact that is easy to lose once the files are pooled.\n\n**Why `-Lite`?** The suffix marks this as a *derived* redistribution rather than a copy of the source. These are **preprocessed** volumes — every case has been format-converted where needed, geometry-normalised and reoriented to RAS+ — and for some sources cases or modalities are excluded as well (see the table above). Use it to reproduce MedVision, not as a substitute for the original release. See [Preprocessing](#preprocessing) below for exactly what was changed.\n\n\n## Preprocessing\n\n- Built from the single official archive `amos22.zip` (`https://zenodo.org/records/7155725/files/amos22.zip`).\n\n- `imagesTr` + `imagesVa` and `labelsTr` + `labelsVa` are pooled and then split by case number into `AMOS22-CT/` (`amos_0001`-`amos_0506`) and `AMOS22-MRI/` (`amos_0507`+). Filenames keep the source stem, so a case ID is identical across `Images/` and `Masks/`.\n\n- No format conversion and no resampling - the source is already `nii.gz`, and the 15-label mask encoding is the source's. Only the orientation is standardized to RAS+.\n\n\n## Segmentation Labels\n\n```python\nlabels_map = {\n    \"1\": \"spleen\",\n    \"2\": \"right kidney\",\n    \"3\": \"left kidney\",\n    \"4\": \"gall bladder\",\n    \"5\": \"esophagus\",\n    \"6\": \"liver\",\n    \"7\": \"stomach\",\n    \"8\": \"aorta\",\n    \"9\": \"postcava\",\n    \"10\": \"pancreas\",\n    \"11\": \"right adrenal gland\",\n    \"12\": \"left adrenal gland\",\n    \"13\": \"duodenum\",\n    \"14\": \"bladder\",\n    \"15\": \"prostate/uterus\"\n}\n```\n\n\n## News\n- [2 Aug, 2026] Initial release. This dataset is integrated into 🔥[MedVision](https://huggingface.co/datasets/YongchengYAO/MedVision)🔥, where you can use these config names to load data in python:\n\n  - `AMOS22_BoxSize_Task01_Axial_Test`\n  - `AMOS22_BoxSize_Task01_Axial_Train`\n  - `AMOS22_BoxSize_Task01_Coronal_Test`\n  - `AMOS22_BoxSize_Task01_Coronal_Train`\n  - `AMOS22_BoxSize_Task01_Sagittal_Test`\n  - `AMOS22_BoxSize_Task01_Sagittal_Train`\n  - `AMOS22_BoxSize_Task02_Axial_Test`\n  - `AMOS22_BoxSize_Task02_Axial_Train`\n  - `AMOS22_BoxSize_Task02_Coronal_Test`\n  - `AMOS22_BoxSize_Task02_Coronal_Train`\n  - `AMOS22_BoxSize_Task02_Sagittal_Test`\n  - `AMOS22_BoxSize_","encoding":"utf8","key":"README.md","name":"README.md","size":5342,"truncated":true}],"sourceObjectKey":"data-part001.zip","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"YongchengYAO/AMOS22-Lite\", filename=\"data-part001.zip\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"data-part001.zip","totalObjects":5},"summary":"AMOS (A large-scale abdominal multi-organ benchmark for versatile medical image segmentation) is the MICCAI 2022 challenge dataset of abdominal CT and MRI collected across…","title":"AMOS 2022: abdominal multi-organ segmentation benchmark (300 CT + 60 MRI)","updatedAt":"2026-11-14T17:50:42.310Z","visibility":"public","websiteUrl":"https://amos22.grand-challenge.org"}}