{"id":"W2998158849","doi":"10.1109/access.2019.2961630","title":"Automated Brain Tumor Segmentation Based on Multi-Planar Superpixel Level Features Extracted From 3D MR Images","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Pattern recognition (psychology); Histogram; Computer science; Segmentation; Consistency (knowledge bases); Image segmentation; Pixel; Feature (linguistics); Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001469567,0.0002269632,0.000184358,0.0002012291,0.0001774559,0.000352641,0.000491782,0.00009327245,0.0004734599],"category_scores_gemma":[0.000327575,0.0002101074,0.0000633977,0.0004298633,0.00006196376,0.0006787834,0.00001744369,0.0002649308,0.000550804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009728697,"about_ca_system_score_gemma":0.00006208359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002794017,"about_ca_topic_score_gemma":0.0000657108,"domain_scores_codex":[0.9981071,0.000268335,0.0002713264,0.0006613149,0.0004199723,0.0002720022],"domain_scores_gemma":[0.9986181,0.0005825415,0.0001898925,0.0004544248,0.00005843792,0.00009664527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001129774,0.0001753558,0.001577768,0.00001447606,0.000003850517,0.00001601299,0.00009173902,0.0004689902,0.9891903,0.00001270898,0.006478427,0.001857389],"study_design_scores_gemma":[0.001158106,0.00004890195,0.2142278,0.00002757412,0.000007325084,0.000006101553,0.00004746396,0.08077309,0.703176,0.00001536642,0.0003028797,0.0002094686],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904409,0.000006263394,0.004056884,0.001431668,0.001308215,0.000634398,0.0003529327,0.0009773006,0.0007914128],"genre_scores_gemma":[0.9911656,0.000002214199,0.0007532874,0.006344486,0.00008565188,0.00006031312,0.00008753365,0.00003974499,0.001461146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2860144,"threshold_uncertainty_score":0.8567932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06340299569899394,"score_gpt":0.3302339180242083,"score_spread":0.2668309223252143,"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."}}