{"id":"W4393372396","doi":"10.1109/tmi.2024.3383716","title":"Deep Generative Adversarial Reinforcement Learning for Semi-Supervised Segmentation of Low-Contrast and Small Objects in Medical Images","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Segmentation; Computer science; Reinforcement learning; Artificial intelligence; Dice; Generalization; Contrast (vision); Image segmentation; Generative grammar; Machine learning; Pattern recognition (psychology); Pipeline (software); Computer vision; 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":[0.0003973687,0.0001499747,0.0001881979,0.0001894111,0.0001375706,0.00006194934,0.0002587234,0.00007239144,0.00005327992],"category_scores_gemma":[0.00006420429,0.0001416687,0.00006622951,0.0003948237,0.0001347754,0.000367171,0.000008226428,0.0004407446,0.00000345495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007824632,"about_ca_system_score_gemma":0.0001560398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002102833,"about_ca_topic_score_gemma":0.00005443418,"domain_scores_codex":[0.9983428,0.00008268345,0.0003948808,0.0004163795,0.0004974105,0.0002658786],"domain_scores_gemma":[0.9988274,0.000729398,0.00004855695,0.0001477141,0.00005302987,0.0001939167],"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":[0.00005068499,0.0001108075,0.00002832503,0.0001663863,0.00004722392,0.00005617572,0.002388407,0.197314,0.01317341,0.0008620828,0.00005403045,0.7857485],"study_design_scores_gemma":[0.0009690481,0.00004932959,0.00001833325,0.000253419,0.00001488604,0.00002254289,0.0001658266,0.97002,0.02796435,0.0003487682,0.0000480469,0.000125472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002885937,0.0002282225,0.9932687,0.002560016,0.0004386213,0.0004232414,0.000001888625,0.00012328,0.00007008959],"genre_scores_gemma":[0.9758325,0.0002572849,0.02306624,0.0004699191,0.0001026235,0.0002081858,0.000006490946,0.00001593256,0.00004080601],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9729466,"threshold_uncertainty_score":0.5777081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01138433519432029,"score_gpt":0.2756944898552132,"score_spread":0.2643101546608929,"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."}}