{
    "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220729.json",
    "version": "0.4.3",
    "changelog": {
        "0.4.3": "README.md fix",
        "0.4.2": "add name tag",
        "0.4.1": "modify dataset key name",
        "0.4.0": "update license files",
        "0.3.0": "Update to scripts",
        "0.2.0": "Unify naming",
        "0.1.0": "Initial version"
    },
    "monai_version": "1.0.1",
    "pytorch_version": "1.13.0",
    "numpy_version": "1.21.2",
    "optional_packages_version": {},
    "name": "Valve landmarks regression",
    "task": "Given long axis MR images of the heart, identify valve insertion points through the full cardiac cycle",
    "description": "This network is used to find where valves attach to heart to help construct 3D FEM models for computation. The output is an array of 10 2D coordinates.",
    "authors": "Eric Kerfoot",
    "copyright": "Copyright (c) Eric Kerfoot",
    "references": [
        "Kerfoot, E, King, CE, Ismail, T, Nordsletten, D & Miller, R 2021, Estimation of Cardiac Valve Annuli Motion with Deep Learning. https://doi.org/10.1007/978-3-030-68107-4_15"
    ],
    "intended_use": "This is suitable for research purposes only",
    "image_classes": "Single channel data, intensity scaled to [0, 1]",
    "data_source": "Non-public dataset comprised of hand-annotated full cycle long axis MR images",
    "coordinate_values": {
        "0": 10,
        "1": 15,
        "2": 20,
        "3": 25,
        "4": 30,
        "5": 35,
        "6": 100,
        "7": 150,
        "8": 200,
        "9": 250
    },
    "coordinate_meanings": {
        "0": "mitral anterior 2CH",
        "1": "mitral posterior 2CH",
        "2": "mitral septal 3CH",
        "3": "mitral free wall 3CH",
        "4": "mitral septal 4CH",
        "5": "mitral free wall 4CH",
        "6": "aortic septal",
        "7": "aortic free wall",
        "8": "tricuspid septal",
        "9": "tricuspid free wall"
    },
    "network_data_format": {
        "inputs": {
            "image": {
                "type": "image",
                "format": "magnitude",
                "modality": "MR",
                "num_channels": 1,
                "spatial_shape": [
                    256,
                    256
                ],
                "dtype": "float32",
                "value_range": [],
                "is_patch_data": false,
                "channel_def": {
                    "0": "image"
                }
            }
        },
        "outputs": {
            "pred": {
                "type": "tuples",
                "format": "points",
                "num_channels": 2,
                "spatial_shape": [
                    2,
                    10
                ],
                "dtype": "float32",
                "value_range": [],
                "is_patch_data": false,
                "channel_def": {
                    "0": "Y Dimension",
                    "1": "X Dimension"
                }
            }
        }
    }
}