MONAI/breast_density_classification

1{2    "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20240725.json",3    "version": "0.1.8",4    "changelog": {5        "0.1.8": "enhance metadata with improved descriptions and task specification",6        "0.1.7": "update to huggingface hosting",7        "0.1.6": "Remove meta dict usage",8        "0.1.5": "Fixed duplication of input output format section",9        "0.1.4": "Changed Readme",10        "0.1.3": "Change input_dim from 229 to 299",11        "0.1.2": "black autofix format and add name tag",12        "0.1.1": "update license files",13        "0.1.0": "complete the model package"14    },15    "monai_version": "1.3.0",16    "pytorch_version": "1.13.1",17    "numpy_version": "1.22.2",18    "required_packages_version": {19        "torchvision": "0.14.1"20    },21    "supported_apps": {},22    "name": "Breast density classification",23    "task": "Mammographic Breast Density Classification (BI-RADS)",24    "description": "A deep learning model for automated classification of breast tissue density in mammograms according to the BI-RADS density categories (A through D). The model processes 299x299 pixel images and classifies breast tissue into four categories: fatty, scattered fibroglandular, heterogeneously dense, and extremely dense.",25    "authors": "Center for Augmented Intelligence in Imaging, Mayo Clinic Florida",26    "copyright": "Copyright (c) Mayo Clinic",27    "data_source": "Mayo Clinic",28    "data_type": "jpeg",29    "image_classes": "three channel data, intensity scaled to [0, 1]. A single grayscale is copied to 3 channels",30    "label_classes": "four classes marked as [1, 0, 0, 0], [0, 1, 0, 0], [0, 0, 1, 0] and [0, 0, 0, 1] for the classes A, B, C and D respectively.",31    "pred_classes": "One hot data",32    "eval_metrics": {33        "accuracy": 0.9634    },35    "intended_use": "This is an example, not to be used for diagnostic purposes",36    "references": [37        "Gupta, Vikash, et al. A multi-reconstruction study of breast density estimation using Deep Learning. arXiv preprint arXiv:2202.08238 (2022)."38    ],39    "network_data_format": {40        "inputs": {41            "image": {42                "type": "image",43                "format": "magnitude",44                "modality": "Mammogram",45                "num_channels": 3,46                "spatial_shape": [47                    299,48                    29949                ],50                "dtype": "float32",51                "value_range": [52                    0,53                    154                ],55                "is_patch_data": false,56                "channel_def": {57                    "0": "image"58                }59            }60        },61        "outputs": {62            "pred": {63                "type": "image",64                "format": "labels",65                "dtype": "float32",66                "value_range": [67                    0,68                    169                ],70                "num_channels": 4,71                "spatial_shape": [72                    1,73                    474                ],75                "is_patch_data": false,76                "channel_def": {77                    "0": "A",78                    "1": "B",79                    "2": "C",80                    "3": "D"81                }82            }83        }84    }85}86