| { |
| "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json", |
| "version": "0.2.7", |
| "changelog": { |
| "0.2.7": "enhance metadata with improved descriptions", |
| "0.2.6": "update to huggingface hosting", |
| "0.2.5": "update large files", |
| "0.2.4": "fix black 24.1 format error", |
| "0.2.3": "update AddChanneld with EnsureChannelFirstd and remove meta_dict", |
| "0.2.2": "add name tag", |
| "0.2.1": "fix license Copyright error", |
| "0.2.0": "update license files", |
| "0.1.3": "Add training pipeline for fine-tuning models, support MONAI Label active learning", |
| "0.1.2": "fixed the dimension in convolution according to MONAI 1.0 update", |
| "0.1.1": "fixed the model state dict name", |
| "0.1.0": "complete the model package" |
| }, |
| "monai_version": "1.4.0", |
| "pytorch_version": "2.4.0", |
| "numpy_version": "1.24.4", |
| "optional_packages_version": { |
| "nibabel": "5.2.1", |
| "pytorch-ignite": "0.4.11", |
| "einops": "0.7.0", |
| "fire": "0.6.0", |
| "timm": "0.6.7", |
| "torchvision": "0.19.0", |
| "tensorboard": "2.17.0" |
| }, |
| "name": "Renal Structures UNEST Segmentation", |
| "task": "Kidney Structure Segmentation in CT Images", |
| "description": "A transformer-based 3D segmentation model that delineates kidney cortex, medulla, and pelvicalyceal system in CT images. The model processes 96x96x96 pixel patches and provides segmentation masks for detailed morphological analysis.", |
| "authors": "Vanderbilt University + MONAI team", |
| "copyright": "Copyright (c) MONAI Consortium", |
| "data_source": "RawData.zip", |
| "data_type": "nibabel", |
| "image_classes": "single channel data, intensity scaled to [0, 1]", |
| "label_classes": "1: Kideny Cortex, 2:Medulla, 3:Pelvicalyceal system", |
| "pred_classes": "1: Kideny Cortex, 2:Medulla, 3:Pelvicalyceal system", |
| "eval_metrics": { |
| "mean_dice": 0.85 |
| }, |
| "intended_use": "This is an example, not to be used for diagnostic purposes", |
| "references": [ |
| "Tang, Yucheng, et al. 'Self-supervised pre-training of swin transformers for 3d medical image analysis. arXiv preprint arXiv:2111.14791 (2021). https://arxiv.org/abs/2111.14791." |
| ], |
| "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": 4, |
| "spatial_shape": [ |
| 96, |
| 96, |
| 96 |
| ], |
| "dtype": "float32", |
| "value_range": [ |
| 0, |
| 1 |
| ], |
| "is_patch_data": true, |
| "channel_def": { |
| "0": "background", |
| "1": "kidney cortex", |
| "2": "medulla", |
| "3": "pelvicalyceal system" |
| } |
| } |
| } |
| } |
| } |
|
|
