{"id":"W4281631055","doi":"10.1016/j.mlwa.2022.100347","title":"A semi-supervised learning approach for bladder cancer grading","year":2022,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sinai Health System; Toronto General Hospital; Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Regularization (linguistics); Labeled data; Machine learning; Pattern recognition (psychology); Consistency (knowledge bases); Semi-supervised learning; Deep learning; Data mining","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003889621,0.0001805731,0.0001717044,0.0001640981,0.001955096,0.0001261076,0.0007166838,0.0000346406,0.00006316131],"category_scores_gemma":[0.00001892753,0.0001796543,0.00006846526,0.001057809,0.00003644683,0.0001960617,0.0002836072,0.000770094,0.000005399615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002432473,"about_ca_system_score_gemma":0.0001101658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002016602,"about_ca_topic_score_gemma":0.00001568356,"domain_scores_codex":[0.9983354,0.0001347445,0.0001957628,0.0006457341,0.000339985,0.0003483473],"domain_scores_gemma":[0.9991048,0.0001304414,0.0001836391,0.0004117044,0.0000836613,0.00008574226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004031408,0.00008529466,0.01253225,0.00003747516,0.00007152711,7.839278e-7,0.00125482,0.9018883,0.0009956042,0.006046104,0.0002885298,0.07675898],"study_design_scores_gemma":[0.0004558225,0.0001708891,0.0002988953,0.000003441433,0.0000231749,0.00003170539,0.0001439752,0.7966265,0.00008680281,0.0002286434,0.2017069,0.0002232295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002266797,0.0004070115,0.9931449,0.001050031,0.00005894761,0.0009564494,0.000008021451,0.0006590609,0.001448765],"genre_scores_gemma":[0.8482366,0.00002928467,0.1314771,0.0002887178,0.0001747723,0.01704268,0.00009018672,0.00006222203,0.002598492],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8616679,"threshold_uncertainty_score":0.9993442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0148553393335113,"score_gpt":0.25355052705762,"score_spread":0.2386951877241087,"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."}}