{"id":"W4388024378","doi":"10.1016/j.media.2023.103011","title":"Anatomically-aware uncertainty for semi-supervised image segmentation","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec; Compute Canada","keywords":"Segmentation; Artificial intelligence; Computer science; Inference; Pixel; Representation (politics); Scale-space segmentation; Image segmentation; Pattern recognition (psychology); Segmentation-based object categorization; Machine learning","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001507319,0.0002450987,0.0007557395,0.0006824469,0.0001901285,0.00008195839,0.0002658642,0.0001829109,0.002884331],"category_scores_gemma":[0.003058734,0.0001990228,0.0006833204,0.00245316,0.0002755298,0.0001372261,0.0001008135,0.0005024083,0.0001945672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000116539,"about_ca_system_score_gemma":0.0001932916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001756013,"about_ca_topic_score_gemma":0.00002292571,"domain_scores_codex":[0.9969957,0.0001151305,0.000600946,0.0005852581,0.001122855,0.0005800419],"domain_scores_gemma":[0.9979424,0.000500164,0.0001142412,0.0004372144,0.0002703095,0.0007356853],"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":[0.0009319692,0.001230293,0.07069523,0.001683795,0.01383886,0.003254991,0.002153828,0.001507058,0.119757,0.0003179488,0.3167388,0.4678902],"study_design_scores_gemma":[0.002802577,0.00009199893,0.00529277,0.00007015852,0.002671107,0.00001963656,0.0004749204,0.9818188,0.0009778073,0.0002125251,0.005321827,0.0002458532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.441838,0.000111617,0.5093331,0.04559599,0.0002642316,0.0007926063,0.00006959581,0.0007324626,0.001262387],"genre_scores_gemma":[0.9472764,0.0005782082,0.02922467,0.01179091,0.001166611,0.0003139798,0.005562419,0.000143248,0.003943585],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9803118,"threshold_uncertainty_score":0.9980271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01154270319084425,"score_gpt":0.3355492827702796,"score_spread":0.3240065795794353,"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."}}