{
    "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20240725.json",
    "version": "1.0.2",
    "changelog": {
        "1.0.2": "enhanced metadata with improved descriptions and task specification",
        "1.0.1": "update to huggingface hosting",
        "1.0.0": "Initial release"
    },
    "monai_version": "1.4.0",
    "pytorch_version": "2.5.1",
    "numpy_version": "1.26.4",
    "required_packages_version": {
        "transformers": "4.46.3",
        "einops": "0.8.1",
        "pillow": "10.4.0"
    },
    "name": "Chest X-ray Latent Diffusion Synthesis",
    "task": "Conditional Synthesis of Chest X-ray Images with Pathology Control",
    "description": "A latent diffusion model that generates 512x512 pixel chest X-ray images from a 64x64x77 dimensional latent space. The model processes text-based condition inputs through a 1024-dimensional context vector, enabling controlled generation of X-rays with specific pathological features.",
    "copyright": "Copyright (c) MONAI Consortium",
    "authors": "Walter Hugo Lopez Pinaya, Mark Graham, Eric Kerfoot, Virginia Fernandez",
    "data_source": "https://physionet.org/content/mimic-cxr-jpg/2.0.0/",
    "data_type": "image",
    "image_classes": "Radiography (X-ray) with 512 x 512 pixels",
    "intended_use": "This is a research tool/prototype and not to be used clinically",
    "network_data_format": {
        "inputs": {
            "latent_representation": {
                "type": "image",
                "format": "magnitude",
                "modality": "CXR",
                "num_channels": 3,
                "spatial_shape": [
                    77,
                    64,
                    64
                ],
                "dtype": "float32",
                "value_range": [],
                "is_patch_data": false
            },
            "timesteps": {
                "format": "magnitude",
                "num_channels": 1,
                "spatial_shape": [
                    1
                ],
                "type": "vector",
                "value_range": [
                    0,
                    1000
                ],
                "dtype": "long"
            },
            "context": {
                "format": "magnitude",
                "num_channels": 1024,
                "spatial_shape": [
                    1
                ],
                "type": "vector",
                "value_range": [],
                "dtype": "float32"
            }
        },
        "outputs": {
            "pred": {
                "type": "image",
                "format": "magnitude",
                "modality": "CXR",
                "num_channels": 1,
                "spatial_shape": [
                    512,
                    512
                ],
                "dtype": "float32",
                "value_range": [
                    0,
                    1
                ],
                "is_patch_data": false,
                "channel_def": {
                    "0": "X-ray"
                }
            }
        }
    }
}