configs/metadata.json

{
    "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
    "version": "0.1.0",
    "changelog": {
        "0.1.0": "complete the model package"
    },
    "monai_version": "1.2.0",
    "pytorch_version": "1.13.1",
    "numpy_version": "1.24.3",
    "optional_packages_version": {
        "nibabel": "5.1.0",
        "pytorch-ignite": "0.4.11",
        "einops": "0.6.1",
        "fire": "0.5.0",
        "torchvision": "0.14.1"
    },
    "name": "Segmentation of renal structures based on contrast computed tomography scans",
    "task": "Renal structures segmentation",
    "description": "A UNET-based model for renal segmentation from contrast enhanced CT image",
    "authors": "Sechenov university",
    "copyright": "Copyright (c) Sechenov university",
    "data_source": "AVUCTK_cases.zip",
    "data_type": "nibabel",
    "image_classes": "three channel data, intensity scaled to [0, 1]",
    "label_classes": "1: artery, 2: vein, 3: ureter, 4: cyst, 5: tumor, 6: parenchyma",
    "pred_classes": "1: artery, 2: vein, 3: ureter, 4: neoplasm, 5: parenchyma",
    "eval_metrics": {
        "mean_dice": 0.79
    },
    "intended_use": "This is  PoC, not to be used for diagnostic purposes",
    "references": [
        "Chernenkiy I. M. et al. Segmentation of renal structures based on contrast computed tomography scans using a convolutional neural network //Sechenov Medical Journal. \u2013 2023. \u2013 \u0422. 14. \u2013 \u2116. 1. \u2013 \u0421. 39-49. URL - https://www.sechenovmedj.com/jour/article/view/899"
    ],
    "network_data_format": {
        "inputs": {
            "image": {
                "type": "image",
                "format": "hounsfield",
                "modality": "CT",
                "num_channels": 3,
                "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": 6,
                "spatial_shape": [
                    96,
                    96,
                    96
                ],
                "dtype": "float32",
                "value_range": [
                    0,
                    1
                ],
                "is_patch_data": true,
                "channel_def": {
                    "0": "background",
                    "1": "artery",
                    "2": "vein",
                    "3": "ureter",
                    "4": "neoplasm",
                    "5": "parenchyma"
                }
            }
        }
    }
}