{"id":"W4391983449","doi":"10.1016/j.neucom.2024.127446","title":"Redundant co-training: Semi-supervised segmentation of medical images using informative redundancy","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Co-training; Computer science; Segmentation; Artificial intelligence; Training (meteorology); Redundancy (engineering); Pattern recognition (psychology); Machine learning; Training set; Image segmentation; Computer vision; Semi-supervised learning; Geography","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":[0.0003846876,0.0001732494,0.0002074331,0.000167621,0.000200253,0.000182521,0.0007811235,0.00006696171,0.00001219712],"category_scores_gemma":[0.00006937041,0.0001685806,0.00008044232,0.0008852203,0.00009920733,0.0007797848,0.0003465186,0.0003480834,0.00001633726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005189582,"about_ca_system_score_gemma":0.0002053438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006825711,"about_ca_topic_score_gemma":3.532032e-7,"domain_scores_codex":[0.9979461,0.0000850084,0.000553617,0.0004094419,0.0006815858,0.0003242248],"domain_scores_gemma":[0.998885,0.0004215341,0.0001651101,0.0003277604,0.0000731197,0.0001274699],"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":[0.000006986007,0.00006444811,0.000147834,0.0003041475,0.00004900106,0.0001048823,0.01265154,0.02373258,0.07969822,0.03539834,0.0007962386,0.8470458],"study_design_scores_gemma":[0.0001775545,0.00004187409,0.0001915491,0.0002708268,0.000007487557,0.000157263,0.0001545805,0.9741801,0.02176382,0.001468986,0.001421338,0.0001645887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09833204,0.0001718062,0.8983334,0.0008981702,0.0003448648,0.0002804333,0.000003761814,0.0004537163,0.001181842],"genre_scores_gemma":[0.8642725,0.00003294104,0.1351139,0.0003222623,0.0001951319,0.00001170911,0.000007304077,0.0000225636,0.00002173627],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9504476,"threshold_uncertainty_score":0.6874516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04970423001009774,"score_gpt":0.3515411510063972,"score_spread":0.3018369209962994,"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."}}