adaptation_plan.json

{
    "architecture_plans": {
        "arch_class_name": "ResEncL",
        "arch_kwargs": null,
        "arch_kwargs_requiring_import": null
    },
    "pretrain_plan": {
        "dataset_name": "Dataset745_OpenNeuro_v2",
        "plans_name": "nnsslPlans",
        "original_median_spacing_after_transp": [
            1,
            1,
            1
        ],
        "image_reader_writer": "SimpleITKIO",
        "transpose_forward": [
            0,
            1,
            2
        ],
        "transpose_backward": [
            0,
            1,
            2
        ],
        "configurations": {
            "onemmiso": {
                "data_identifier": "nnsslPlans_3d_fullres",
                "preprocessor_name": "DefaultPreprocessor",
                "spacing_style": "onemmiso",
                "normalization_schemes": [
                    "ZScoreNormalization"
                ],
                "use_mask_for_norm": [
                    false
                ],
                "resampling_fn_data": "resample_data_or_seg_to_shape",
                "resampling_fn_data_kwargs": {
                    "is_seg": false,
                    "order": 3,
                    "order_z": 0,
                    "force_separate_z": null
                },
                "resampling_fn_mask": "resample_data_or_seg_to_shape",
                "resampling_fn_mask_kwargs": {
                    "is_seg": true,
                    "order": 1,
                    "order_z": 0,
                    "force_separate_z": null
                },
                "spacing": [
                    1,
                    1,
                    1
                ],
                "patch_size": [
                    160,
                    160,
                    160
                ]
            }
        },
        "experiment_planner_used": "FixedResEncUNetPlanner"
    },
    "pretrain_num_input_channels": 1,
    "recommended_downstream_patchsize": [
        160,
        160,
        160
    ],
    "key_to_encoder": "encoder.stages",
    "key_to_stem": "encoder.stem",
    "keys_to_in_proj": [
        "encoder.stem.convs.0.conv",
        "encoder.stem.convs.0.all_modules.0"
    ],
    "key_to_lpe": null,
    "citations": [
        {
            "type": "Architecture",
            "name": "ResEncL",
            "apa_citations": [
                "Isensee, F., Wald, T., Ulrich, C., Baumgartner, M., Roy, S., Maier-Hein, K., & Jaeger, P. F. (2024, October). nnu-net revisited: A call for rigorous validation in 3d medical image segmentation. MICCAI."
            ]
        },
        {
            "type": "Pretraining Method",
            "name": "Volume Fusion",
            "apa_citations": [
                "Wang, G., Wu, J., Luo, X., Liu, X., Li, K., & Zhang, S. (2023). Mis-fm: 3d medical image segmentation using foundation models pretrained on a large-scale unannotated dataset. arXiv preprint arXiv:2306.16925."
            ]
        },
        {
            "type": "Pre-Training Dataset",
            "name": "OpenMind",
            "apa_citations": [
                "Wald, T., Ulrich, C., Suprijadi, J., Ziegler, S., Nohel, M., Peretzke, R., ... & Maier-Hein, K. H. (2024). An OpenMind for 3D medical vision self-supervised learning. arXiv preprint arXiv:2412.17041."
            ]
        },
        {
            "type": "Framework",
            "name": "nnssl",
            "apa_citations": [
                "Wald, T., Ulrich, C., Lukyanenko, S., Goncharov, A., Paderno, A., Maerkisch, L., ... & Maier-Hein, K. (2024). Revisiting MAE pre-training for 3D medical image segmentation. CVPR."
            ]
        }
    ],
    "trainer_name": "VolumeFusionTrainer_BS8_lr_1e3"
}