{"id":"W3097329159","doi":"10.1109/access.2020.3035772","title":"Esophagus Segmentation in Computed Tomography Images Using a U-Net Neural Network With a Semiautomatic Labeling Method","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Esophageal Cancer Research and Treatment","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; Shandong Academy of Medical Sciences; Shandong First Medical University; China Scholarship Council; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Segmentation; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); Image segmentation; Deep learning; Computer vision; Convex hull; Regular polygon; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001472956,0.0001668352,0.0003211628,0.0001222874,0.00006850997,0.0000977056,0.0001316151,0.00003912363,0.00003019374],"category_scores_gemma":[0.00001471237,0.0001295115,0.0000528242,0.00111066,0.0000332268,0.0002688772,0.00004418849,0.0002171263,0.000003340906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009530209,"about_ca_system_score_gemma":0.00009671756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003867045,"about_ca_topic_score_gemma":0.00004509385,"domain_scores_codex":[0.9986457,0.0001268323,0.0002308669,0.0003049387,0.000337972,0.0003536625],"domain_scores_gemma":[0.9993909,0.0001019324,0.00008367086,0.0001398183,0.00006874419,0.0002149153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0013015,0.0002227581,0.8655954,0.0007070601,0.0003685802,0.002477214,0.0009472806,0.11167,0.002124421,0.000007437655,0.0005969698,0.01398145],"study_design_scores_gemma":[0.01190294,0.001799607,0.2286627,0.0008091169,0.0003903341,0.0001878852,0.000177158,0.703401,0.05204867,0.0001995816,0.000004344334,0.00041671],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9498249,0.008821054,0.03863507,0.001103347,0.00009908092,0.001279266,0.00001239661,0.0001725739,0.00005228449],"genre_scores_gemma":[0.941793,0.0000144016,0.05671912,0.001148847,0.0002218769,0.00004965407,0.00002377797,0.0000256845,0.000003639431],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6369327,"threshold_uncertainty_score":0.5281326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05878362097239677,"score_gpt":0.3905326732478157,"score_spread":0.3317490522754189,"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."}}