{
    "architecture_plans": {
        "arch_class_name": "ResEncL",
        "arch_kwargs": null,
        "arch_kwargs_requiring_import": null
    },
    "pretrain_plan": {
        "dataset_name": "Dataset900_MultiTalent_ResEnc",
        "plans_name": "nnUNetResEncUNetLPlansIso1x1x1_bs12",
        "original_median_spacing_after_transp": [
            1.3700000047683716,
            1.25,
            1.25
        ],
        "image_reader_writer": "SimpleITKIOWithReorient",
        "transpose_forward": [
            0,
            1,
            2
        ],
        "transpose_backward": [
            0,
            1,
            2
        ],
        "configurations": {
            "3d_fullres": {
                "data_identifier": "nnUNetResEncUNetLPlansIso1x1x1_3d_fullres",
                "preprocessor_name": "DefaultPreprocessor",
                "normalization_schemes": [
                    "ZScoreNormalization"
                ],
                "use_mask_for_norm": [
                    true
                ],
                "resampling_fn_data": "resample_data_or_seg_to_shape",
                "resampling_fn_data_kwargs": {
                    "force_separate_z": null,
                    "is_seg": false,
                    "order": 3,
                    "order_z": 0
                },
                "resampling_fn_mask": "resample_data_or_seg_to_shape",
                "resampling_fn_mask_kwargs": {
                    "force_separate_z": null,
                    "is_seg": true,
                    "order": 1,
                    "order_z": 0
                },
                "spacing": [
                    1.0,
                    1.0,
                    1.0
                ],
                "patch_size": [
                    192,
                    192,
                    192
                ]
            }
        },
        "experiment_planner_used": "nnUNetPlannerResEncLIso1x1x1_znorm"
    },
    "pretrain_num_input_channels": 1,
    "recommended_downstream_patchsize": [
        192,
        192,
        192
    ],
    "key_to_encoder": "encoder.stages",
    "key_to_stem": "encoder.stem.351_0",
    "keys_to_in_proj": [
        "encoder.stem.351_0.convs.0.conv",
        "encoder.stem.351_0.convs.0.all_modules.0"
    ],
    "key_to_lpe": null,
    "note": "MultiTalent multi-stem checkpoint: stem 351_0 (CT) was selected of several per-dataset/modality stems (see training_log for the full dataset->stem mapping). Other stems are still present in network_weights under encoder.stem.<id> but unused by this plan.",
    "citations": [
        {
            "type": "Pre-Trained Weights",
            "name": "The Missing Piece",
            "apa_citations": [
                "Eckstein, K., Ulrich, C., Baumgartner, M., Kächele, J., Bounias, D., Wald, T., ... & Maier-Hein, K. H. (2025). The missing piece: A case for pre-training in 3D medical object detection. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2025 (Lecture Notes in Computer Science, Vol. 15963, pp. 615–626). Springer. https://doi.org/10.1007/978-3-032-04965-0_58"
            ]
        },
        {
            "type": "Architecture",
            "name": "ResEncL",
            "apa_citations": [
                "Isensee, F., Wald, T., Ulrich, C., Baumgartner, M., Roy, S., Maier-Hein, K., & Jaeger, P. F. (2024). nnU-Net revisited: A call for rigorous validation in 3D medical image segmentation. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2024 (Lecture Notes in Computer Science, pp. 488–498). Springer. https://doi.org/10.1007/978-3-031-72114-4_47",
                "Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nature Methods, 18(2), 203–211. https://doi.org/10.1038/s41592-020-01008-z"
            ]
        },
        {
            "type": "Pretraining Method",
            "name": "MultiTalent",
            "apa_citations": [
                "Ulrich, C., Isensee, F., Wald, T., Zenk, M., Baumgartner, M., & Maier-Hein, K. H. (2023). MultiTalent: A multi-dataset approach to medical image segmentation. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2023 (Lecture Notes in Computer Science, Vol. 14222, pp. 648–658). Springer. https://doi.org/10.1007/978-3-031-43898-1_62"
            ]
        }
    ],
    "trainer_name": "MultiTalent_trainer_multistems_4000ep"
}