{"id":"W4312791247","doi":"10.1109/sibgrapi55357.2022.9991752","title":"Segmenting White Matter Hyperintensity in Alzheimer’s Disease using U-Net CNNs","year":2022,"lang":"en","type":"article","venue":"","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"Canada Foundation for Innovation; Health Research","keywords":"Hyperintensity; Fluid-attenuated inversion recovery; White matter; Segmentation; Magnetic resonance imaging; Neuroimaging; Dementia; Psychology; Neuroscience; Artificial intelligence; Medicine; Pathology; Computer science; Disease; Radiology","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":[0.001127241,0.001518986,0.0006938454,0.001150844,0.0003490662,0.0007799987,0.001119044,0.001208867,0.001284325],"category_scores_gemma":[0.001562866,0.0004757944,0.001063315,0.0006912371,0.0004342321,0.0008336322,0.0007092036,0.0006627833,0.0006156384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001249008,"about_ca_system_score_gemma":0.0007827425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02450885,"about_ca_topic_score_gemma":0.02539785,"domain_scores_codex":[0.9997663,0.00003233981,0.00001454956,0.00008904782,0.00002894077,0.00006883681],"domain_scores_gemma":[0.9996667,0.0001304908,0.0000452851,0.00004194262,0.00008731861,0.00002823189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001420859,0.0003869031,0.01734269,0.0002167985,0.0005327432,0.0004958499,0.0001730325,0.6121786,0.0212502,0.001276417,0.006038436,0.3386875],"study_design_scores_gemma":[0.000009855904,0.00009433499,0.002497815,0.00001835231,0.00004012649,0.00006101625,0.0000235534,0.9925305,0.00374639,0.0006139139,0.0003552358,0.000008910786],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8301447,0.003422536,0.1549017,0.0005164378,0.0002775063,0.0001843962,0.001366685,0.004698241,0.004487734],"genre_scores_gemma":[0.9542866,0.0004768116,0.03988281,0.0002216372,0.00004251717,0.00007387951,0.002031102,0.00009638811,0.002888245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02450885,"threshold_uncertainty_score":0.04873234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04509829774235706,"score_gpt":0.3234812301095098,"score_spread":0.2783829323671527,"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."}}