{"id":"W3003783572","doi":"10.1109/jbhi.2020.2970091","title":"CycleGAN With an Improved Loss Function for Cell Detection Using Partly Labeled Images","year":2020,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Artificial intelligence; Object detection; Object (grammar); Annotation; Image (mathematics); Field (mathematics); Labeled data; Pattern recognition (psychology); Function (biology); Deep learning; Computer vision; Data mining; Machine learning; 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":[0.0003616812,0.0001006732,0.0002107454,0.00009631766,0.0001300307,0.000211497,0.0001941865,0.00003547619,5.390872e-7],"category_scores_gemma":[0.00002565819,0.00007130906,0.00004041251,0.0002149876,0.00008004148,0.001844768,0.00002678415,0.0001336953,7.234879e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003088171,"about_ca_system_score_gemma":0.0003222682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000691491,"about_ca_topic_score_gemma":0.000001539487,"domain_scores_codex":[0.9987537,0.00001680796,0.0006465606,0.00007098164,0.0002845968,0.0002273928],"domain_scores_gemma":[0.9984426,0.00003006518,0.0006052322,0.00008561074,0.0001672752,0.0006691801],"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":[0.001606483,0.001368398,0.001144139,0.005218023,0.0002107807,0.00004158065,0.009181778,0.0005422133,0.008936776,0.0002621945,0.003785361,0.9677023],"study_design_scores_gemma":[0.005129157,0.0158847,0.0004629994,0.0002029429,0.00008319013,0.0003229063,0.0009229882,0.9609535,0.008545168,0.0008731252,0.00628904,0.0003302281],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2511499,0.0000876972,0.7461661,0.002179694,0.0002345825,0.0001336262,0.000008339922,0.00002955337,0.00001054332],"genre_scores_gemma":[0.9130996,0.00002768389,0.08301815,0.003543238,0.0002978583,0.000001547243,0.000002410327,0.000007231927,0.000002279007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9673721,"threshold_uncertainty_score":0.2907899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03418622069485453,"score_gpt":0.2877342374770207,"score_spread":0.2535480167821662,"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."}}