KalbeDigitalLab/PathologyNucleiClassification

1{2    "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",3    "version": "0.0.5",4    "changelog": {5        "0.0.5": "add name tag",6        "0.0.4": "Fix evaluation",7        "0.0.3": "Update to use MONAI 1.1.0",8        "0.0.2": "Update The Torch Vision Transform",9        "0.0.1": "initialize the model package structure"10    },11    "monai_version": "1.1.0",12    "pytorch_version": "1.13.0",13    "numpy_version": "1.21.2",14    "optional_packages_version": {15        "nibabel": "4.0.1",16        "pytorch-ignite": "0.4.9"17    },18    "name": "Pathology nuclei classification",19    "task": "Pathology Nuclei classification",20    "description": "A pre-trained model for Nuclei Classification within Haematoxylin & Eosin stained histology images",21    "authors": "MONAI team",22    "copyright": "Copyright (c) MONAI Consortium",23    "data_source": "consep_dataset.zip from https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet",24    "data_type": "png",25    "image_classes": "RGB channel data, intensity scaled to [0, 1]",26    "label_classes": "single channel data",27    "pred_classes": "4 channels OneHot data, channel 0 is Other, channel 1 is Inflammatory, channel 2 is Epithelial, channel 3 is Spindle-Shaped",28    "eval_metrics": {29        "f1_score": 0.8530    },31    "intended_use": "This is an example, not to be used for diagnostic purposes",32    "references": [33        "S. Graham, Q. D. Vu, S. E. A. Raza, A. Azam, Y-W. Tsang, J. T. Kwak and N. Rajpoot. \"HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images.\" Medical Image Analysis, Sept. 2019. https://doi.org/10.1016/j.media.2019.101563"34    ],35    "network_data_format": {36        "inputs": {37            "image": {38                "type": "magnitude",39                "format": "RGB",40                "modality": "regular",41                "num_channels": 4,42                "spatial_shape": [43                    128,44                    12845                ],46                "dtype": "float32",47                "value_range": [48                    0,49                    150                ],51                "is_patch_data": false,52                "channel_def": {53                    "0": "R",54                    "1": "G",55                    "2": "B",56                    "3": "Mask"57                }58            }59        },60        "outputs": {61            "pred": {62                "type": "probabilities",63                "format": "classes",64                "num_channels": 4,65                "spatial_shape": [66                    1,67                    468                ],69                "dtype": "float32",70                "value_range": [71                    0,72                    1,73                    2,74                    375                ],76                "is_patch_data": false,77                "channel_def": {78                    "0": "Other",79                    "1": "Inflammatory",80                    "2": "Epithelial",81                    "3": "Spindle-Shaped"82                }83            }84        }85    }86}87