{"id":"W4323665786","doi":"10.3389/fnimg.2023.1099301","title":"Optimizing automated white matter hyperintensity segmentation in individuals with stroke","year":2023,"lang":"en","type":"article","venue":"Frontiers in Neuroimaging","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Biomedical Imaging and Bioengineering; National Health and Medical Research Council; National Institute of Neurological Disorders and Stroke; Medical Research Council; National Institutes of Health; University of Melbourne; Canadian Institutes of Health Research; National Imaging Facility","keywords":"Segmentation; Hyperintensity; Stroke (engine); Artificial intelligence; Computer science; Machine learning; Medicine; Magnetic resonance imaging; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001437952,0.0001577843,0.0002570084,0.0006101403,0.00005443471,0.00003167699,0.0001002275,0.00003191388,0.000009125763],"category_scores_gemma":[0.00002049964,0.0001545538,0.00003161314,0.0008903107,0.00006503209,0.0001934998,0.00007248312,0.0003301736,0.00001756202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008798394,"about_ca_system_score_gemma":0.00002403936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001272593,"about_ca_topic_score_gemma":0.00000176384,"domain_scores_codex":[0.9987757,0.00003563603,0.0002534557,0.0004064528,0.0001884486,0.0003402982],"domain_scores_gemma":[0.9995208,0.00002170844,0.0000726361,0.0002924017,0.00003315874,0.00005926464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002433363,0.00003603446,0.9857551,0.00002990118,0.000005405615,0.0001359792,0.0002902644,0.001630816,0.003233762,0.000004193444,0.007974057,0.0008801628],"study_design_scores_gemma":[0.001010102,0.00003588525,0.9260696,0.0001302863,0.00001745988,0.00008135032,0.0004524529,0.06981271,0.001346042,0.00009421544,0.0007845188,0.0001653628],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9600937,0.00003101529,0.03086579,0.005426026,0.00014891,0.000775937,0.00001590624,0.001396356,0.001246337],"genre_scores_gemma":[0.7919673,0.00004529351,0.2060229,0.001409793,0.00001923079,0.0001019159,0.0000495596,0.00005339597,0.0003305532],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1751571,"threshold_uncertainty_score":0.6302519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03168775683516509,"score_gpt":0.3118026041172791,"score_spread":0.280114847282114,"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."}}