{"id":"W2799738340","doi":"10.1016/j.media.2019.02.009","title":"Constrained-CNN losses for weakly supervised segmentation","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Kahnawake Education Center","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Leverage (statistics); Computer science; Segmentation; Iterated function; Mathematical optimization; Differentiable function; Artificial intelligence; Dual (grammatical number); Pixel; Machine learning; Mathematics","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":[0.000242667,0.0001127253,0.0002452605,0.0001536091,0.00008571257,0.00009525158,0.0006477513,0.00005592716,0.0005673956],"category_scores_gemma":[0.0001407747,0.00009848409,0.000203818,0.001425089,0.00008720926,0.0004222263,0.0001055419,0.00009644982,0.0002114994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000253768,"about_ca_system_score_gemma":0.00005594831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009539893,"about_ca_topic_score_gemma":0.000009577391,"domain_scores_codex":[0.9985665,0.00004173299,0.0002776969,0.000422414,0.0004495489,0.0002420844],"domain_scores_gemma":[0.9986756,0.0004115815,0.00008585292,0.0005238134,0.0001273703,0.0001757495],"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":[0.00004624775,0.0007138632,0.01954319,0.0001664109,0.002471037,0.00006733307,0.000680828,0.004452173,0.09364945,0.08169131,0.01148876,0.7850294],"study_design_scores_gemma":[0.0006435411,0.00005836511,0.001445551,0.00001000657,0.0002882908,0.000004990115,0.00005922544,0.9847953,0.005670786,0.002770979,0.004011978,0.0002409382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01911923,0.00004006743,0.9748856,0.004698119,0.00005805049,0.0002958975,0.000007144426,0.0001223386,0.0007735765],"genre_scores_gemma":[0.7087473,0.00005347203,0.2879939,0.002174629,0.0001183982,0.0001461319,0.0001154566,0.00001200701,0.0006386329],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9803432,"threshold_uncertainty_score":0.6212584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0113012703349794,"score_gpt":0.2936607132017627,"score_spread":0.2823594428667833,"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."}}