{"id":"W2887311618","doi":"10.1007/s11548-018-1840-5","title":"Using the variogram for vector outlier screening: application to feature-based image registration","year":2018,"lang":"en","type":"review","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"National Institute of Biomedical Imaging and Bioengineering; International Research Center for Neurointelligence, University of Tokyo; National Institutes of Health; University of Tokyo","keywords":"Outlier; Variogram; Computer science; Matching (statistics); Point set registration; Image registration; Anomaly detection; Artificial intelligence; Feature vector; Feature (linguistics); Euclidean vector; Pattern recognition (psychology); Displacement (psychology); Data mining; Image (mathematics); Mathematics; Point (geometry); Statistics; Machine learning; Kriging","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002292018,0.001064016,0.002212051,0.005017209,0.0002881951,0.00252177,0.00142505,0.00133605,0.001863656],"category_scores_gemma":[0.005182665,0.0005091585,0.001332971,0.006600206,0.001308305,0.001460985,0.0009952646,0.001512627,0.001144812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004672612,"about_ca_system_score_gemma":0.001252898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002405506,"about_ca_topic_score_gemma":0.00228107,"domain_scores_codex":[0.99872,0.000270037,0.0001377641,0.000257524,0.0005615443,0.00005305598],"domain_scores_gemma":[0.997304,0.001520306,0.0003137523,0.0001605041,0.0006539222,0.0000476278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001165985,0.00006304028,0.002713349,0.003448176,0.0003094603,0.0001958807,0.00007594196,0.003073497,0.00708585,0.003562801,0.003348061,0.9760074],"study_design_scores_gemma":[0.0002422713,0.002003166,0.06236807,0.005990863,0.00405129,0.02716334,0.001038747,0.2406409,0.1638943,0.04611607,0.4451807,0.001310271],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01225996,0.6042455,0.3755055,0.001075508,0.000667373,0.0001829799,0.0004097567,0.001565923,0.004087467],"genre_scores_gemma":[0.1293954,0.5805365,0.2833708,0.0006545011,0.00100315,0.0002147601,0.0007586089,0.0005021751,0.003564028],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.005017209,"threshold_uncertainty_score":0.0121215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08154513706720924,"score_gpt":0.3883939012649314,"score_spread":0.3068487641977222,"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."}}