{
    "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20240725.json",
    "version": "0.5.8",
    "changelog": {
        "0.5.8": "enhance metadata with improved descriptions",
        "0.5.7": "update to huggingface hosting",
        "0.5.6": "use monai 1.4 and update large files",
        "0.5.5": "update to use monai 1.3.1",
        "0.5.4": "add load_pretrain flag for infer",
        "0.5.3": "update to use monai 1.3.0",
        "0.5.2": "update the checkpoint loader logic for inference",
        "0.5.1": "add option to validate at training start, and I/O param entries",
        "0.5.0": "enable finetune and early stop",
        "0.4.9": "fix orientation issue on clicks",
        "0.4.8": "Add infer transforms to manage clicks from viewer",
        "0.4.7": "fix the wrong GPU index issue of multi-node",
        "0.4.6": "update to use rc7 which solves dynunet issue",
        "0.4.5": "remove error dollar symbol in readme",
        "0.4.4": "add RAM comsumption with Cachedataset",
        "0.4.3": "update ONNX-TensorRT descriptions",
        "0.4.2": "deterministic retrain benchmark, update fig links",
        "0.4.1": "add the ONNX-TensorRT way of model conversion",
        "0.4.0": "fix mgpu finalize issue",
        "0.3.9": "enable deterministic training",
        "0.3.8": "adapt to BundleWorkflow interface",
        "0.3.7": "add name tag",
        "0.3.6": "restructure readme to match updated template",
        "0.3.5": "update metric in metadata",
        "0.3.4": "add validate.json file and dice score in readme",
        "0.3.3": "update to use monai 1.0.1",
        "0.3.2": "enhance readme on commands example",
        "0.3.1": "fix license Copyright error",
        "0.3.0": "update license files",
        "0.2.0": "unify naming",
        "0.1.0": "complete the model package",
        "0.0.1": "initialize the model package structure"
    },
    "monai_version": "1.4.0",
    "pytorch_version": "2.4.0",
    "numpy_version": "1.24.4",
    "required_packages_version": {
        "itk": "5.4.0",
        "pytorch-ignite": "0.4.11",
        "scikit-image": "0.23.2",
        "einops": "0.7.0",
        "tensorboard": "2.17.0",
        "nibabel": "5.2.1"
    },
    "supported_apps": {},
    "name": "Spleen DeepEdit Interactive Segmentation",
    "task": "Interactive Spleen Segmentation in CT Images with Point-based Guidance",
    "description": "An interactive 3D segmentation model that processes 128x128x128 pixel patches from CT scans to segment the spleen. The model incorporates user-provided point annotations through the DeepEdit framework. It accepts positive and negative click inputs to refine segmentation boundaries in real-time.",
    "authors": "MONAI team",
    "copyright": "Copyright (c) MONAI Consortium",
    "data_source": "Task09_Spleen.tar from http://medicaldecathlon.com/",
    "data_type": "nibabel",
    "image_classes": "Three channel input: channel 0: CT image scaled to [0, 1], channels 1-2: positive and negative click maps",
    "label_classes": "Single channel binary mask: 1: spleen, 0: background",
    "pred_classes": "2 channels OneHot data, channel 1 is spleen, channel 0 is background",
    "eval_metrics": {
        "mean_dice": 0.97
    },
    "intended_use": "This is an example, not to be used for diagnostic purposes",
    "references": [
        "Sakinis, Tomas, et al. 'Interactive segmentation of medical images through fully convolutional neural networks.' arXiv preprint arXiv:1903.08205 (2019)"
    ],
    "network_data_format": {
        "inputs": {
            "image": {
                "type": "image",
                "format": "hounsfield",
                "modality": "CT",
                "num_channels": 3,
                "spatial_shape": [
                    128,
                    128,
                    128
                ],
                "dtype": "float32",
                "value_range": [
                    0,
                    1
                ],
                "is_patch_data": false,
                "channel_def": {
                    "0": "image"
                }
            }
        },
        "outputs": {
            "pred": {
                "type": "image",
                "format": "segmentation",
                "num_channels": 2,
                "spatial_shape": [
                    128,
                    128,
                    128
                ],
                "dtype": "float32",
                "value_range": [
                    0,
                    1
                ],
                "is_patch_data": false,
                "channel_def": {
                    "0": "background",
                    "1": "spleen"
                }
            }
        }
    }
}