{"success":true,"data":{"author":"Xavier P. Burgos-Artizzu, Elisenda Eixarch, Eduard Gratacos et al.; repackaged by Chehab Lab","bucketAccessType":"public","bucketName":"chehablab/FETAL_PLANES_DB","bucketPrefix":"","category":"Health & Biomedical","cloudProvider":"huggingface","createdAt":"2026-11-21T22:16:41.644Z","description":"FETAL_PLANES_DB is a large set of routine maternal-fetal screening ultrasound images collected at two hospitals by several operators on different ultrasound machines, and labeled by an expert maternal-fetal clinician into the standard planes a sonographer must capture: fetal abdomen, fetal brain, fetal femur, fetal thorax, maternal cervix, and other. Fetal brain images also carry one of the three most common brain sub-plane labels. The repackaging keeps the original images unchanged and adds the original train/test split column, patient number, operator, ultrasound machine, plane and an integer label, so models can be tested across operators and devices. Five Parquet files under data/, about 2.1 GB (measured 2026-11-21); read with Hugging Face datasets. Use for automatic fetal ultrasound plane classification and prenatal screening quality control. Original data on Zenodo (DOI 10.5281/zenodo.3904280), released under CC BY 4.0. Cite Burgos-Artizzu et al., Scientific Reports 10:10200 (2020), doi 10.1038/s41598-020-67076-5.","displayTitle":"FETAL_PLANES_DB: maternal-fetal screening ultrasound images labeled by fetal anatomical plane (Burgos-Artizzu et al., Barcelona)","doi":"10.5281/zenodo.3904280","huggingFaceUrl":"https://huggingface.co/datasets/chehablab/FETAL_PLANES_DB","id":"3dc1c02e-50da-5818-a965-7d8a59ff67f9","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/records/3904280","objectCountEstimate":7,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1038/s41598-020-67076-5","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"chehablab/FETAL_PLANES_DB\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"chehablab/FETAL_PLANES_DB\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=chehablab, license:cc-by-4.0, size_categories:10K<n<100K, format:parquet, downloads=83"],"format":"mixed","generatedAt":"2026-11-21T22:32:07.352Z","layout":{"example":"data/train-00000-of-00005.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"data/train-00000-of-00005.parquet","truncatedAt":512}],"sampleObjects":["data/train-00000-of-00005.parquet","data/train-00001-of-00005.parquet","data/train-00002-of-00005.parquet","data/train-00003-of-00005.parquet","data/train-00004-of-00005.parquet"],"sidecars":[{"bytes":"---\ndataset_info:\n  features:\n  - name: image_id\n    dtype: string\n  - name: split\n    dtype: string\n  - name: image\n    dtype: image\n  - name: patient_id\n    dtype: string\n  - name: plane\n    dtype: string\n  - name: brain_plane\n    dtype: string\n  - name: operator\n    dtype: string\n  - name: us_machine\n    dtype: string\n  - name: label\n    dtype: int32\n  splits:\n  - name: train\n    num_bytes: 2464989256\n    num_examples: 12400\n  download_size: 2087493012\n  dataset_size: 2464989256\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- ultrasound\n- fetal\n- obstetrics\n- prenatal\n- medical\n- classification\npretty_name: FETAL_PLANES_DB\n---\n\n# FETAL_PLANES_DB — Common Maternal-Fetal Ultrasound Images\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/FETAL_PLANES_DB/discussions) of this repository.\n\nThis dataset is derived from FETAL_PLANES_DB (Burgos-Artizzu et al., 2020), a large dataset of routinely acquired maternal-fetal screening ultrasound images, originally hosted on Zenodo. The images were collected at two hospitals by several operators and ultrasound machines, and were manually labelled by an expert maternal-fetal clinician into six classes: four widely used fetal anatomical planes, the maternal cervix, and a general category for other planes. Fetal brain images are further labelled into the three most common brain planes.\nWe kept the original images unchanged and added the original train/test split, the patient, operator and machine metadata, the plane labels and an integer label, all from the original metadata file.\nThe dataset is designed for ultrasound plane classification.\n\n\n## 📦 Dataset Structure\n\nThe dataset has a single `train` split on the Hub; the original train/test split is kept in the `split` column. Each row corresponds to a single ultrasound image:\n\n| Field | Description |\n|---|---|\n| `image_id` | Original image name |\n| `split` | Original split used in the Sci Rep paper: `train` or `test` |\n| `image` | Ultrasound image |\n| `patient_id` | Patient number from the original metadata |\n| `plane` | One of six classes (see Feature Descriptions) |\n| `brain_plane` | Fetal brain sub-plane for brain images; a non-brain value for the other images |\n| `operator` | Operator who acquired the image |\n| `us_machine` | Ultrasound machine used |\n| `label` | Integer class: the index of `plane` in the alphabetically sorted list of planes |\n\n\n## ⚙️ Preprocessing\n\n- `FETAL_PLANES_ZENODO.zip` was downloaded from Zenodo (record `3904280`, version 1.0)\n- Images were kept as the original files (no re-encoding, resizing, cropping or intensity normalization)\n- `split`, `patient_id`, `plane`, `brain_plane`, `operator` and `us_machine` were taken from the original metadata file `FETAL_PLANES_DB_data.csv`\n- `label` is the index of `plane` in the alphabetically sorted list of the six planes\n- All images listed in the metadata file were preserved\n\n\n## 🚀 Usage\n\n```python\nfrom datasets import load_dataset\nimport matplotlib.pyplot as plt\n\nds = load_dataset(\"chehablab/FETAL_PLANES_DB\", split=\"train\")\n\n# One example image per plane\nplanes = ds[\"plane\"]\nclasses = sorted(set(planes))\nfig, axes = plt.subplots(1, len(classes), figsize=(16, 3))\nfor ax, c in zip(axes, classes):\n    sample = ds[planes.index(c)]\n    ax.imshow(sample[\"image\"], cmap=\"gray\")\n    ax.set_title(c, fontsize=9)\n    ax.axis(\"off\")\nplt.tight_layout()\nplt.show()\n\n# Original train/test split\ntrain = ds.filter(lambda x: x[\"split\"] == \"train\")\ntest = ds.filter(lambda x: x[\"split\"] == \"test\")\nprint(f\"Train: {len(train)}, test: {len(test)}\")\n\n# Fine-grained brain planes\nprint(ds.to_pandas().groupby([\"plane\", \"brain_plane\"]).size())\n```\n\n---\n\n## 🏷️ Feature Descriptions\n\n### Planes\nSix classes:\n\n- Fetal abdomen — Fetal anatomical plane\n- Fetal brain — F","encoding":"utf8","key":"README.md","name":"README.md","size":8153,"truncated":true}],"sourceObjectKey":"data/train-00000-of-00005.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"chehablab/FETAL_PLANES_DB\")\nprint(ds)","starterSamplePath":"data/train-00000-of-00005.parquet","totalObjects":7},"summary":"FETAL_PLANES_DB is a large set of routine maternal-fetal screening ultrasound images collected at two hospitals by several operators on different ultrasound machines, and labeled…","title":"FETAL_PLANES_DB: maternal-fetal screening ultrasound images labeled by fetal anatomical plane (Burgos-Artizzu et al., Barcelona)","updatedAt":"2026-11-22T01:06:16.112Z","visibility":"public","websiteUrl":"https://zenodo.org/records/3904280"}}