{"id":"W4415035370","doi":"10.48550/arxiv.2505.16561","title":"Auto-nnU-Net: Towards Automated Medical Image Segmentation","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Bundesministerium für Bildung und Forschung; Volkswagen Foundation; Institute for Catastrophic Loss Reduction; Niedersächsische Ministerium für Wissenschaft und Kultur","keywords":"Segmentation; Hyperparameter; Image segmentation; Heuristic; Scale-space segmentation; Segmentation-based object categorization; Resource (disambiguation)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00309578,0.001995634,0.001506929,0.002438634,0.0008700321,0.002716074,0.003870946,0.003783978,0.006323353],"category_scores_gemma":[0.006528116,0.001515089,0.00162969,0.001840867,0.001359967,0.002093153,0.003330291,0.002694395,0.005046889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002216241,"about_ca_system_score_gemma":0.002271142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007434644,"about_ca_topic_score_gemma":0.01542045,"domain_scores_codex":[0.9986724,0.0003549448,0.00007293896,0.0004532796,0.0003479071,0.00009858218],"domain_scores_gemma":[0.9986211,0.0006157135,0.0001091628,0.0003207819,0.000229247,0.0001039569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003992878,0.0001659841,0.002124951,0.0005338737,0.0002876171,0.0001967,0.0001652539,0.3738664,0.01042704,0.01150298,0.0477353,0.5525947],"study_design_scores_gemma":[0.00001996448,0.00004005487,0.0001924848,0.00003435776,0.00001602383,0.0001197239,0.0000222362,0.9774763,0.005664588,0.01073627,0.005656968,0.0000209385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007780654,0.001068402,0.9508502,0.0006277325,0.000148591,0.0001659595,0.000821777,0.03533034,0.003206244],"genre_scores_gemma":[0.09588279,0.000529954,0.8900307,0.001330759,0.0001622737,0.0003571526,0.002990221,0.003475094,0.005241049],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007434644,"threshold_uncertainty_score":0.02115375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05810395685738217,"score_gpt":0.3364600518440115,"score_spread":0.2783560949866293,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}