{"id":"W2785474956","doi":"10.1007/978-3-319-75238-9_34","title":"Brain Tumor Segmentation Using a 3D FCN with Multi-scale Loss","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Segmentation; Dice; Context (archaeology); Artificial intelligence; Pattern recognition (psychology); Image segmentation; Scale (ratio); Sample (material); Function (biology); High resolution; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004080133,0.0003733192,0.0002774228,0.0004864895,0.0003888154,0.0003001526,0.0007066113,0.0001389699,0.0001101921],"category_scores_gemma":[0.0001463548,0.0003189516,0.00005767211,0.0005659797,0.001492473,0.0003672348,0.0001803374,0.0004785197,0.00007967495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003596081,"about_ca_system_score_gemma":0.000300279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001627268,"about_ca_topic_score_gemma":0.0001637264,"domain_scores_codex":[0.9970712,0.00006282907,0.0003429374,0.001333109,0.0007628103,0.0004271189],"domain_scores_gemma":[0.9985005,0.000292647,0.000342534,0.0006025134,0.0001360797,0.0001257211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001846456,0.0002181408,0.000406053,0.0001565569,0.00001214257,0.000322668,0.005328722,0.02286264,0.6445513,0.0007453813,0.00007672015,0.325135],"study_design_scores_gemma":[0.0008810695,0.0003786549,0.0003142986,0.000421638,0.00001644669,0.0007235256,0.000002531252,0.738628,0.2529246,0.003766349,0.001069587,0.0008732417],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01291265,0.00001467218,0.9844971,0.0003804352,0.0008679737,0.0004939825,0.000009935229,0.0001296093,0.0006936993],"genre_scores_gemma":[0.5757605,0.000008439096,0.4106421,0.0103618,0.000925193,0.00002782875,0.000007328761,0.0001260956,0.002140677],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7157654,"threshold_uncertainty_score":0.9999263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04181104077477439,"score_gpt":0.2826430277317923,"score_spread":0.2408319869570179,"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."}}