{"success":true,"data":{"author":"Mengye Lyu et al.","bucketAccessType":"public","bucketName":"mylyu/M4Raw_brain","bucketPrefix":"","category":"Neuroscience","cloudProvider":"huggingface","createdAt":"2026-11-17T19:29:32.804Z","description":"M4Raw is a raw k-space dataset for low-field MRI reconstruction research, acquired on a 0.3 T whole-body MRI system with a four-channel head coil from healthy volunteers. Each examination provides T1-weighted, T2-weighted and FLAIR acquisitions with repeated averages (three repetitions for T1w and T2w, two for FLAIR; six and four in the expanded test cohort), plus GRE acquisitions for the original 183-participant cohort, and dedicated inter-scan and intra-scan motion subsets. Version 1.6 holds 2,230 HDF5 files from 208 unique participants: 1,024 training, 240 validation, 400 test, 200 motion and 366 GRE files, in multicoil_train/, multicoil_val/, multicoil_test/, multicoil_motion/ and multicoil_gre/, with manifests in metadata/ and portable readers in code/. The H5 payloads are byte-identical to the authors' Zenodo record 8056074 and store multicoil k-space with root-sum-of-squares (RSS) image slices; read them with h5py. Uses: denoising and super-resolution of low-SNR low-field images, accelerated reconstruction, multi-repetition self-supervised training and motion artifact studies. About 28 GB (measured 2026-11-17). Released by the original authors under CC BY 4.0; cite Lyu et al., Scientific Data 10, 264 (2023).","displayTitle":"M4Raw: multi-contrast, multi-repetition four-channel k-space of brain MRI on a 0.3 T low-field scanner","doi":"10.5281/zenodo.8056074","huggingFaceUrl":"https://huggingface.co/datasets/mylyu/M4Raw_brain","id":"722c55ed-5f5e-5d19-9e94-5219b4e4b893","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/records/8056074","objectCountEstimate":2265,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1038/s41597-023-02181-4","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"mylyu/M4Raw_brain\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"mylyu/M4Raw_brain\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=mylyu, license:cc-by-4.0, size_categories:1K<n<10K, format:csv, downloads=21653"],"format":"mixed","generatedAt":"2026-11-17T19:40:03.489Z","layout":{"example":"metadata/FLAIR_manifest.tsv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"scan_id\tparticipant_cohort\tparticipant_split\tmotion_type\tavailable_repetitions\tgre_available\th5_rep01\th5_rep02\th5_rep03\th5_rep04\th5_rep05\th5_rep06\n2022061001\toriginal\ttrain\tnone\t2\ttrue\tmulticoil_train/2022061001_FLAIR01.h5\tmulticoil_train/2022061001_FLAIR02.h5\t\t\t\t\n2022061002\toriginal\ttrain\tnone\t2\ttrue\tmulticoil_train/2022061002_FLAIR01.h5\tmulticoil_train/2022061002_FLAIR02.h5\t\t\t\t\n2022061003\toriginal\ttrain\tnone\t2\ttrue\tmulticoil_train/2022061003_FLAIR01.h5\tmulticoil_train/2022061003_FLAIR02.h5\t\t\t\t\n2022061004\t","encoding":"utf8","key":"metadata/FLAIR_manifest.tsv","truncatedAt":512}],"sampleObjects":["DATA_CARD.md","H5_FORMAT.md","SHA256SUMS","assets/representative_images.png","code/download_case.py"],"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,","encoding":"utf8","key":"LICENSE","name":"LICENSE","size":18658,"truncated":true},{"bytes":"---\npretty_name: M4Raw Brain\nlicense: cc-by-4.0\ntask_categories:\n- image-to-image\ntags:\n- medical-imaging\n- mri\n- low-field-mri\n- k-space\n- image-reconstruction\n- denoising\n- multicoil\n- hdf5\n- fastmri\nsize_categories:\n- n<1K\nconfigs:\n- config_name: t1_examinations\n  default: true\n  data_files: metadata/T1_manifest.tsv\n  sep: \"\\t\"\n- config_name: t2_examinations\n  data_files: metadata/T2_manifest.tsv\n  sep: \"\\t\"\n- config_name: flair_examinations\n  data_files: metadata/FLAIR_manifest.tsv\n  sep: \"\\t\"\n- config_name: gre_examinations\n  data_files: metadata/GRE_manifest.tsv\n  sep: \"\\t\"\n- config_name: acquisitions\n  data_files: metadata/acquisitions.tsv\n  sep: \"\\t\"\n- config_name: subjects\n  data_files: metadata/subjects.tsv\n  sep: \"\\t\"\n- config_name: file_inventory\n  data_files: metadata/file_inventory.tsv\n  sep: \"\\t\"\n---\n\n# M4Raw Brain v1.6\n\nM4Raw Brain is a multi-contrast, multi-repetition, four-channel k-space\ndataset acquired on a 0.3-T whole-body MRI system. The release contains T1w,\nT2w, FLAIR, and GRE brain acquisitions from healthy volunteers, including\nexplicit motion subsets and an expanded repeated-acquisition test cohort.\n\n> **Companion dataset:** [M4Raw-Abdomen](https://huggingface.co/datasets/mylyu/M4Raw_abdomen)\n> is a separate low-field abdominal MRI k-space and segmentation dataset and\n> will be made public soon. Until then, the linked private repository is\n> accessible only to authorized users.\n\nThis Hugging Face distribution exposes the scientific H5 files from\n[Zenodo record 8056074](https://doi.org/10.5281/zenodo.8056074) individually,\nso one acquisition or examination can be accessed without downloading a\nmulti-gigabyte ZIP archive. All 2,230 scientific H5 payloads are byte-identical\nto the corresponding files extracted from the Zenodo archives: they have not\nbeen recompressed, rewritten, or numerically changed. The Hub repository as a\nwhole is not a byte-identical copy of the original distribution because ZIP\ncontainers were removed, paths were reorganized, and Hub-specific\ndocumentation and metadata were added.\n\n![Representative M4Raw Brain T1-weighted, T2-weighted, FLAIR, and GRE images from one participant.](assets/representative_images.png)\n\n*One participant at the same stored central slice. The top row shows\nacquisition 01; the bottom row shows the repeat average (three acquisitions\nfor T1w/T2w and two for FLAIR/GRE). Every stored RSS slice is displayed\ndirectly, following the original M4Raw tutorial, without transpose, rotation,\nor anatomical flip. Each contrast is independently windowed from the 0.5th to\n99.5th nonzero percentiles for display.*\n\n## Release inventory\n\n| Content | Participants | H5 files |\n| --- | ---: | ---: |\n| Training: T1w/T2w/FLAIR | 128 | 1,024 |\n| Validation: T1w/T2w/FLAIR | 30 | 240 |\n| Motion subsets: T1w/T2w/FLAIR | 25 | 200 |\n| Expanded test: T1w/T2w/FLAIR | 25 | 400 |\n| GRE for the original cohort | 183 | 366 |\n| **Total** | **208 unique** | **2,230** |\n\nThe released motion subsets contain 25 participants: eight in the inter-scan\nsubset and 17 in the intra-scan subset, totaling 200 H5 files. One sentence in\nthe paper's subset-partition Methods paragraph reports 26 participants, while\nthe paper's cohort summaries and the released files correspond to 25. For\noperational use, `metadata/subjects.tsv` and the sequence manifests are\nauthoritative.\n\nT1w and T2w contain three repetitions in the training, validation, and\nmotion subsets and six repetitions in the test subset. FLAIR contains two\nand four repetitions, respectively. GRE contains two repetitions for each\nof the 183 original-cohort participants.\n\n## Layout\n\n```text\nmulticoil_train/                    1,024 H5\nmulticoil_val/                        240 H5\nmulticoil_test/                       400 H5\nmulticoil_motion/inter_scan/           64 H5\nmulticoil_motion/intra_scan/          136 H5\nmulticoil_gre/                        366 H5\nmetadata/                         manifests and provenance\ncode/                             portable readers and validator\nassets/                           reproducible homepage montage\n```\n\n","encoding":"utf8","key":"README.md","name":"README.md","size":11135,"truncated":true},{"bytes":"# Metadata tables\n\n- `acquisitions.tsv`: one row per H5, including split, sequence, repetition,\n  shape, source ZIP/member, CRC32, and release path.\n- `T1_manifest.tsv`, `T2_manifest.tsv`, `FLAIR_manifest.tsv`, and\n  `GRE_manifest.tsv`: one row per examination with all repetition paths.\n- `subjects.tsv`: participant-level cohort, split, motion, and sequence\n  availability.\n- `source_archive_members.tsv`: complete frozen ZIP central-directory\n  inventory, including the source documentation entries not mirrored as\n  scientific payload.\n- `source_to_release_map.tsv`: exact source-member to Hub-path mapping.\n- `legacy_header_findings.tsv`: per-file status of the two non-authoritative\n  legacy custom XML extensions and the authoritative replacement source.\n- `source_h5_audit_summary.json`: exhaustive array/XML/RSS audit summary.\n- `zenodo_record_8056074.json`: frozen Zenodo API record.\n- `zenodo_source_manifest.json`: source ZIP sizes and verified MD5 hashes.\n- `provenance.json`: repackaging provenance and version information.\n- `dataset_description.json`: compact machine-readable release contract.\n- `api_contract.json`: common Brain/Abdomen reader signatures and fields.\n- `compatibility_validation.json`: stock fastMRI full-indexing smoke test and\n  callable-signature parity audit against M4Raw-Abdomen.\n- `known_quality_findings.tsv`: motion-scope and legacy-header cautions.\n- `file_inventory.tsv`: SHA-256 and byte size for every staged file.\n- `hf_upload_audit.json`: post-upload remote path/hash audit.\n\n`participant_split` is participant-disjoint across train, validation,\nmotion, and test. GRE inherits its participant's original split but remains\nphysically stored under `multicoil_gre`.\n\n`motion_type` records participant-level subset assignment. It does not assert\nthat every individual acquisition from that participant contains visible\nmotion.\n\nThe released motion subsets contain 25 participants (eight inter-scan and 17\nintra-scan). One Methods sentence in the paper reports 26; the released files,\n`subjects.tsv`, and sequence manifests are authoritative. The nominal stored\nmatrix is `256 x 256`, while `acquisitions.tsv` records the actual PE support:\n195 lines for T1w/T2w, 198 for FLAIR, and 256 for GRE.\n","encoding":"utf8","key":"metadata/README.md","name":"README.md","size":2240,"truncated":false}],"sourceObjectKey":"metadata/FLAIR_manifest.tsv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/mylyu/M4Raw_brain/metadata/FLAIR_manifest.tsv\", sep='\\t')\ndf.head()","starterSamplePath":"assets/representative_images.png","totalObjects":2265},"summary":"M4Raw is a raw k-space dataset for low-field MRI reconstruction research, acquired on a 0.3 T whole-body MRI system with a four-channel head coil from healthy volunteers.","title":"M4Raw: multi-contrast, multi-repetition four-channel k-space of brain MRI on a 0.3 T low-field scanner","updatedAt":"2026-11-17T23:15:42.039Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/mylyu/M4Raw_brain"}}