configs/metadata.json

{
    "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
    "version": "0.3.7",
    "changelog": {
        "0.3.7": "re-train model with updated dints implementation",
        "0.3.6": "black autofix format and add name tag",
        "0.3.5": "restructure readme to match updated template",
        "0.3.4": "correct typos",
        "0.3.3": "update learning rate and readme",
        "0.3.2": "update to use monai 1.0.1",
        "0.3.1": "fix license Copyright error",
        "0.3.0": "update license files",
        "0.2.0": "unify naming",
        "0.1.1": "fix data type issue in searching/training configurations",
        "0.1.0": "complete the model package",
        "0.0.1": "initialize the model package structure"
    },
    "monai_version": "1.2.0rc4",
    "pytorch_version": "1.13.1",
    "numpy_version": "1.22.2",
    "optional_packages_version": {
        "fire": "0.4.0",
        "nibabel": "4.0.1",
        "pytorch-ignite": "0.4.9"
    },
    "name": "Pancreas CT DiNTS segmentation",
    "task": "Neural architecture search on pancreas CT segmentation",
    "description": "Searched architectures for volumetric (3D) segmentation of the pancreas from CT image",
    "authors": "MONAI team",
    "copyright": "Copyright (c) MONAI Consortium",
    "data_source": "Task07_Pancreas.tar from http://medicaldecathlon.com/",
    "data_type": "nibabel",
    "image_classes": "single channel data, intensity scaled to [0, 1]",
    "label_classes": "single channel data, 1 is pancreas, 2 is pancreatic tumor, 0 is everything else",
    "pred_classes": "3 channels OneHot data, channel 1 is pancreas, channel 2 is pancreatic tumor, channel 0 is background",
    "eval_metrics": {
        "mean_dice": 0.62
    },
    "intended_use": "This is an example, not to be used for diagnostic purposes",
    "references": [
        "He, Y., Yang, D., Roth, H., Zhao, C. and Xu, D., 2021. Dints: Differentiable neural network topology search for 3d medical image segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 5841-5850)."
    ],
    "network_data_format": {
        "inputs": {
            "image": {
                "type": "image",
                "format": "hounsfield",
                "modality": "CT",
                "num_channels": 1,
                "spatial_shape": [
                    96,
                    96,
                    96
                ],
                "dtype": "float32",
                "value_range": [
                    0,
                    1
                ],
                "is_patch_data": true,
                "channel_def": {
                    "0": "image"
                }
            }
        },
        "outputs": {
            "pred": {
                "type": "image",
                "format": "segmentation",
                "num_channels": 3,
                "spatial_shape": [
                    96,
                    96,
                    96
                ],
                "dtype": "float32",
                "value_range": [
                    0,
                    1,
                    2
                ],
                "is_patch_data": true,
                "channel_def": {
                    "0": "background",
                    "1": "pancreas",
                    "2": "pancreatic tumor"
                }
            }
        }
    }
}