{"id":"W989272091","doi":"10.1016/j.neuroimage.2015.07.076","title":"An Optimized PatchMatch for multi-scale and multi-feature label fusion","year":2015,"lang":"en","type":"article","venue":"NeuroImage","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"National Institute on Aging; Ministerio de Economía y Competitividad; National Institutes of Health; Agence Nationale de la Recherche; Dana Foundation; Foundation for the National Institutes of Health","keywords":"Segmentation; Computer science; Artificial intelligence; Pattern recognition (psychology); Computation; Fusion; Feature (linguistics); Sørensen–Dice coefficient; Scale (ratio); Image segmentation; Cartography; Algorithm; Geography","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":[0.000383524,0.0001522526,0.0001787216,0.00006905851,0.00008829612,0.0002022168,0.0005219299,0.00008326096,0.000005640348],"category_scores_gemma":[0.0001727186,0.0001332898,0.00003113253,0.0001510552,0.00007211781,0.0007524863,0.0002000732,0.0001598373,0.000009862586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001810686,"about_ca_system_score_gemma":0.00004011491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002713591,"about_ca_topic_score_gemma":0.000006652022,"domain_scores_codex":[0.9987113,0.0001245106,0.0001750888,0.000490631,0.0002583694,0.0002400582],"domain_scores_gemma":[0.9988523,0.00006711966,0.00007875119,0.0005050903,0.000159019,0.000337789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001329399,0.001141307,0.0009165031,0.00009256524,0.00001108392,0.00009704378,0.003661109,0.00001631268,0.6113075,0.0001351069,0.03509668,0.3473919],"study_design_scores_gemma":[0.004714129,0.0004699581,0.001339356,0.00001629012,0.000008688289,0.00002223917,0.00006292943,0.9304458,0.06175498,0.0001304832,0.0007937709,0.0002413466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008878136,0.00005641785,0.9889599,0.0007794429,0.0002163594,0.0005429205,0.0000129258,0.0004948322,0.00005906992],"genre_scores_gemma":[0.003493951,0.00002261336,0.9940787,0.001835345,0.00004294799,0.00006323333,0.00001529924,0.00001945073,0.0004284379],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9304295,"threshold_uncertainty_score":0.5435401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07967791245572012,"score_gpt":0.3579120045990388,"score_spread":0.2782340921433186,"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."}}