{"id":"W2913282347","doi":"10.1109/bibm.2018.8621552","title":"Optimizing U-Net to Segment Left Ventricle from Magnetic Resonance Imaging","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Segmentation; Dice; Computer science; Convolutional neural network; Convolution (computer science); Artificial intelligence; Net (polyhedron); Volume (thermodynamics); Task (project management); Image segmentation; Pattern recognition (psychology); Medical imaging; Artificial neural network; Mathematics; Engineering; Statistics; Physics; Geometry","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":[0.00006123002,0.0001074192,0.00008912998,0.00004709443,0.0001662779,0.0001026073,0.0007657404,0.00001460915,0.0001544895],"category_scores_gemma":[0.00001222254,0.0001047527,0.00002420147,0.0003881801,0.00003770214,0.0002819852,0.0004562233,0.00006245414,0.0007007733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005063098,"about_ca_system_score_gemma":0.00001525617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003734179,"about_ca_topic_score_gemma":0.00002159226,"domain_scores_codex":[0.9988392,0.00001989461,0.0001653851,0.0004788751,0.0001781771,0.0003184625],"domain_scores_gemma":[0.9990042,0.00007456355,0.00003355078,0.0006951079,0.00005941102,0.0001331453],"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":[0.00001129237,0.00007762168,0.002516618,0.000001581385,0.000003006266,0.00001903309,0.001405706,0.001866676,0.01447866,0.01808963,0.02457388,0.9369563],"study_design_scores_gemma":[0.0005390035,0.0001689436,0.02037649,0.0000434078,0.000006720702,0.00001894864,0.00004906239,0.5724452,0.04065624,0.01267917,0.352412,0.0006047366],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008142622,0.0008098586,0.9837731,0.003197381,0.0001906553,0.0002232581,0.000002588223,0.0002891659,0.003371446],"genre_scores_gemma":[0.2944425,0.0000129614,0.7013742,0.003170049,0.0002039527,0.00002249591,0.000001331967,0.00001062609,0.000761833],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9363515,"threshold_uncertainty_score":0.9007257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01257524577494571,"score_gpt":0.2547224344551139,"score_spread":0.2421471886801682,"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."}}