{"id":"W4396695858","doi":"10.1002/hbm.26692","title":"<scp>SAN</scp> : Mitigating spatial covariance heterogeneity in cortical thickness data collected from multiple scanners or sites","year":2024,"lang":"en","type":"article","venue":"Human Brain Mapping","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Addiction and Mental Health; University of Toronto","funders":"National Institute of Mental Health; Canadian Institutes of Health Research; Data Science Institute, Columbia University; Connaught Fund; Canada Foundation for Innovation; Natural Sciences and Engineering Research Council of Canada; Centre for Addiction and Mental Health Foundation; Brain and Behavior Research Foundation; McLaughlin Centre, University of Toronto","keywords":"Spatial normalization; Covariance; Scanner; Computer science; Spatial analysis; Spurious relationship; Autocorrelation; Normalization (sociology); Covariance matrix; Gaussian; Neuroimaging; Harmonization; Artificial intelligence; Data mining; Pattern recognition (psychology); Statistics; Machine learning; Mathematics; Algorithm; Psychology; Neuroscience","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":[0.007393665,0.002041219,0.001416409,0.002445924,0.0009098666,0.001779562,0.004576418,0.001445237,0.1253931],"category_scores_gemma":[0.04757378,0.0012508,0.001754971,0.00378987,0.001267956,0.002067686,0.004396678,0.001920994,0.03082162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008584366,"about_ca_system_score_gemma":0.002856826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006382954,"about_ca_topic_score_gemma":0.01556249,"domain_scores_codex":[0.9969734,0.0008353256,0.0002021924,0.0004229181,0.001425127,0.0001410769],"domain_scores_gemma":[0.9803141,0.009303874,0.002422966,0.00451666,0.00286765,0.0005746951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002862339,0.00004876691,0.002437049,0.00116471,0.0003391269,0.0006246797,0.0001828676,0.007512119,0.006849128,0.01047224,0.8638946,0.1061885],"study_design_scores_gemma":[0.0009822069,0.0002577961,0.0210387,0.0006131874,0.0003345965,0.003554085,0.0001066639,0.2672397,0.04855166,0.1368941,0.519931,0.0004962879],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007569149,0.0008390094,0.7185568,0.005548987,0.001938787,0.0008016985,0.09463535,0.1564624,0.01364787],"genre_scores_gemma":[0.07845356,0.001271071,0.7092416,0.002729417,0.001495576,0.003516732,0.09529111,0.09186623,0.01613468],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1253931,"threshold_uncertainty_score":0.4194818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1388933931067203,"score_gpt":0.3235693627848741,"score_spread":0.1846759696781538,"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."}}