configs/metadata.json

{
    "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20240725.json",
    "version": "0.6.2",
    "changelog": {
        "0.6.2": "enhance metadata with improved descriptions and task specification",
        "0.6.1": "update to huggingface hosting and fix missing dependencies",
        "0.6.0": "use monai 1.4 and update large files",
        "0.5.9": "update to use monai 1.3.1",
        "0.5.8": "add load_pretrain flag for infer",
        "0.5.7": "add checkpoint loader for infer",
        "0.5.6": "update to use monai 1.3.0",
        "0.5.5": "update AddChanneld with EnsureChannelFirstd and set image_only to False",
        "0.5.4": "fix the wrong GPU index issue of multi-node",
        "0.5.3": "remove error dollar symbol in readme",
        "0.5.2": "remove the CheckpointLoader from the train.json",
        "0.5.1": "add RAM warning",
        "0.5.0": "update TensorRT descriptions",
        "0.4.9": "update the model weights",
        "0.4.8": "update the TensorRT part in the README file",
        "0.4.7": "fix mgpu finalize issue",
        "0.4.6": "enable deterministic training",
        "0.4.5": "add the command of executing inference with TensorRT models",
        "0.4.4": "adapt to BundleWorkflow interface",
        "0.4.3": "update this bundle to support TensorRT convert",
        "0.4.2": "support monai 1.2 new FlexibleUNet",
        "0.4.1": "add name tag",
        "0.4.0": "add support for multi-GPU training and evaluation",
        "0.3.2": "restructure readme to match updated template",
        "0.3.1": "add figures of workflow and metrics, add invert transform",
        "0.3.0": "update dataset processing",
        "0.2.1": "update to use monai 1.0.1",
        "0.2.0": "update license files",
        "0.1.0": "complete the first version 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": {
        "nibabel": "5.2.1",
        "pytorch-ignite": "0.4.11",
        "pillow": "10.4.0",
        "tensorboard": "2.17.0"
    },
    "supported_apps": {},
    "name": "Endoscopic Tool Segmentation",
    "task": "Binary Segmentation of Surgical Tools in Endoscopic Images",
    "description": "A 2D segmentation model that identifies and delineates surgical instruments in endoscopic video frames. The model processes 736x480 pixel RGB images and provides binary segmentation masks. Based on an EfficientNet-UNet architecture, the model supports real-time analysis of surgical procedures.",
    "authors": "MONAI team",
    "copyright": "Copyright (c) MONAI Consortium",
    "data_source": "private dataset",
    "data_type": "RGB",
    "image_classes": "three channel data, intensity [0-255]",
    "label_classes": "single channel data, 1/255 is tool, 0 is background",
    "pred_classes": "2 channels OneHot data, channel 1 is tool, channel 0 is background",
    "eval_metrics": {
        "mean_iou": 0.86
    },
    "references": [
        "Tan, M. and Le, Q. V. Efficientnet: Rethinking model scaling for convolutional neural networks. ICML, 2019a. https://arxiv.org/pdf/1905.11946.pdf",
        "O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234\u2013241. Springer, 2015. https://arxiv.org/pdf/1505.04597.pdf"
    ],
    "network_data_format": {
        "inputs": {
            "image": {
                "type": "magnitude",
                "format": "RGB",
                "modality": "regular",
                "num_channels": 3,
                "spatial_shape": [
                    736,
                    480
                ],
                "dtype": "float32",
                "value_range": [
                    0,
                    1
                ],
                "is_patch_data": false,
                "channel_def": {
                    "0": "R",
                    "1": "G",
                    "2": "B"
                }
            }
        },
        "outputs": {
            "pred": {
                "type": "image",
                "format": "segmentation",
                "num_channels": 2,
                "spatial_shape": [
                    736,
                    480
                ],
                "dtype": "float32",
                "value_range": [
                    0,
                    1
                ],
                "is_patch_data": false,
                "channel_def": {
                    "0": "background",
                    "1": "tools"
                }
            }
        }
    }
}