{"id":"W3089741206","doi":"10.1016/j.media.2021.102191","title":"Realistic image normalization for multi-Domain segmentation","year":2021,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Fonds Québécois de la Recherche sur la Nature et les Technologies; Nvidia","keywords":"Normalization (sociology); Computer science; Artificial intelligence; Segmentation; Dice; Pattern recognition (psychology); Adversarial system; Image segmentation; Spatial normalization; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001389049,0.001016788,0.000978922,0.001047878,0.0006066811,0.002302154,0.001289899,0.002031751,0.006790479],"category_scores_gemma":[0.004859082,0.0009701225,0.001092484,0.001344111,0.0009738587,0.001916888,0.002135928,0.002175202,0.002571941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001039946,"about_ca_system_score_gemma":0.001076075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001893314,"about_ca_topic_score_gemma":0.002712401,"domain_scores_codex":[0.9991539,0.0001970422,0.00004383727,0.0002261221,0.0002987388,0.00008041489],"domain_scores_gemma":[0.9988995,0.0003106576,0.00009819376,0.0004215738,0.0002108912,0.00005915483],"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":[0.0006011817,0.0001737798,0.001081726,0.0006768914,0.0002177333,0.0004494331,0.000244318,0.2473783,0.2266458,0.09831207,0.0135519,0.4106669],"study_design_scores_gemma":[0.00002010695,0.00004696914,0.0007877069,0.00003620201,0.00003912576,0.0006734434,0.00003988581,0.8854795,0.06250774,0.03723151,0.01310613,0.00003181733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004485251,0.0002391917,0.9921756,0.0001907448,0.00006014807,0.00003384878,0.00009477846,0.0008062142,0.001914108],"genre_scores_gemma":[0.1908343,0.0007915871,0.7952266,0.0003531203,0.0001407683,0.0001548449,0.0009264626,0.001793661,0.009778711],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006790479,"threshold_uncertainty_score":0.02271646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02859912760029211,"score_gpt":0.3504421923977118,"score_spread":0.3218430647974198,"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."}}