{"id":"W2982389559","doi":"10.1101/824706","title":"Harmonization of diffusion MRI datasets with adaptive dictionary learning","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Engineering and Physical Sciences Research Council; Wolfson Foundation; Cardiff University; Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust","keywords":"Scanner; Pooling; Computer science; Artificial intelligence; Pattern recognition (psychology); Harmonization; Matching (statistics); Image registration; Diffusion MRI; Population; Data mining; Computer vision; Magnetic resonance imaging; Statistics; Mathematics; Image (mathematics); Radiology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00336197,0.0006847493,0.0009673117,0.001238961,0.0003292208,0.0008783751,0.001028246,0.0007463813,0.001031587],"category_scores_gemma":[0.007674349,0.0003156032,0.0008927814,0.001164284,0.0006631059,0.0009015876,0.001674498,0.0009066499,0.0004844714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003396651,"about_ca_system_score_gemma":0.0007340683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00179537,"about_ca_topic_score_gemma":0.001579085,"domain_scores_codex":[0.9984708,0.0006691194,0.0001240568,0.0003865687,0.0002506495,0.00009871167],"domain_scores_gemma":[0.9971323,0.001098052,0.0002831423,0.0008914233,0.0005221505,0.0000728542],"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":[0.001112674,0.000461102,0.005285091,0.0003082284,0.0005273423,0.0002110603,0.0003100352,0.3900293,0.04765939,0.006838856,0.006293826,0.540963],"study_design_scores_gemma":[0.00005994965,0.0002012182,0.002210688,0.00001493031,0.00004766434,0.0001185454,0.0000627835,0.972361,0.01818143,0.004564719,0.002147711,0.00002939546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1005595,0.0002481,0.8964822,0.000187521,0.00007717405,0.0001811595,0.0003185229,0.001246761,0.0006991007],"genre_scores_gemma":[0.5058752,0.0001853131,0.4893385,0.000160465,0.00006700907,0.0003071728,0.002196972,0.0003128024,0.001556607],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00336197,"threshold_uncertainty_score":0.01778001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02812963206835971,"score_gpt":0.2673777411158056,"score_spread":0.2392481090474459,"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."}}