{"id":"W2589644515","doi":"10.1016/j.media.2017.11.005","title":"Learning normalized inputs for iterative estimation in medical image segmentation","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":229,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Pipeline (software); Segmentation; Convolutional neural network; Artificial intelligence; Benchmark (surveying); Deep learning; Residual; Image segmentation; Pattern recognition (psychology); Computer vision; Algorithm","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001615724,0.0002260321,0.0006245942,0.0004940872,0.000295987,0.0002938892,0.0004772674,0.0001970773,0.002311855],"category_scores_gemma":[0.006033029,0.0002008405,0.0003308536,0.0005573875,0.0002503605,0.0006131686,0.00007988804,0.0005318856,0.00006422897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000854138,"about_ca_system_score_gemma":0.00006053718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00017869,"about_ca_topic_score_gemma":0.0001935958,"domain_scores_codex":[0.9973022,0.0001330942,0.0006428875,0.0003477915,0.001166388,0.0004076904],"domain_scores_gemma":[0.9986051,0.0003040189,0.0001460732,0.0003747853,0.0001200135,0.0004499815],"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":[0.00008047334,0.0005998332,0.0773045,0.0008994309,0.007785271,0.001427946,0.005730023,0.0317929,0.01404973,0.000128184,0.008825431,0.8513763],"study_design_scores_gemma":[0.001176851,0.00001669173,0.002810479,0.00009100547,0.0006621415,0.000003293077,0.00009647256,0.9925235,0.00199444,0.00009220414,0.0003161137,0.0002168405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09953765,0.00007797196,0.8950861,0.003205884,0.0001173933,0.0001444503,0.000008789583,0.0001766932,0.001645078],"genre_scores_gemma":[0.9811086,0.0001766675,0.01735086,0.0003516992,0.0001653086,0.0001047801,0.0003814539,0.00003206052,0.0003285824],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9607306,"threshold_uncertainty_score":0.9986002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00796106501721744,"score_gpt":0.3132501830028003,"score_spread":0.3052891179855828,"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."}}