{"id":"W4393281987","doi":"10.1016/j.media.2024.103150","title":"Boundary-aware information maximization for self-supervised medical image segmentation","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Hôpital Notre-Dame","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Artificial intelligence; Computer science; Cluster analysis; Feature learning; Segmentation; Pattern recognition (psychology); Mutual information; Maximization; Image segmentation; Feature (linguistics); 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":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001540458,0.0001765267,0.0002747322,0.0006459683,0.0002496933,0.00121267,0.0006255914,0.0001708935,0.002085577],"category_scores_gemma":[0.0008795523,0.0001559973,0.0002947521,0.002266967,0.0000879977,0.002902487,0.0001358865,0.000270707,0.0003301831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109631,"about_ca_system_score_gemma":0.0004330774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003136688,"about_ca_topic_score_gemma":0.00001930417,"domain_scores_codex":[0.9968301,0.0001544029,0.0006145756,0.0003779234,0.001710456,0.0003125134],"domain_scores_gemma":[0.998608,0.0003104588,0.0001015431,0.0003206912,0.0002773936,0.0003819118],"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":[0.00002296503,0.0001720692,0.0003106772,0.0004062754,0.00143213,0.0001418858,0.007513513,0.0003775737,0.0002919936,0.007077919,0.0169022,0.9653508],"study_design_scores_gemma":[0.000502913,0.00003542749,0.0002720669,0.00003336055,0.000274116,0.00001025564,0.000246565,0.9773006,0.0001216755,0.000400956,0.02062471,0.0001773619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006715715,0.0001073783,0.9890257,0.00798355,0.0003129085,0.0002221481,0.00001025158,0.000621094,0.001045365],"genre_scores_gemma":[0.2175939,0.0004782333,0.7664641,0.01050416,0.0006774491,0.0003464501,0.002890721,0.00005902667,0.0009859116],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.976923,"threshold_uncertainty_score":0.9998242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007274381179233694,"score_gpt":0.2781048143756569,"score_spread":0.2708304331964232,"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."}}