{"id":"W2217077692","doi":"10.1371/journal.pone.0145118","title":"Classifiers for Ischemic Stroke Lesion Segmentation: A Comparison Study","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":157,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"","keywords":"Segmentation; Random forest; Fluid-attenuated inversion recovery; Convolutional neural network; Artificial intelligence; Computer science; Pattern recognition (psychology); Context (archaeology); Stroke (engine); Medicine; Magnetic resonance imaging; Machine learning; Radiology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002048346,0.00009039844,0.0001470065,0.00006437404,0.0001248625,0.00005412955,0.0001335881,0.00003718184,0.00002209926],"category_scores_gemma":[0.000423078,0.00008954271,0.00002977566,0.0001658539,0.00003834487,0.0001415995,0.00002223914,0.0001061491,0.0001014339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009284937,"about_ca_system_score_gemma":0.00003875228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003325814,"about_ca_topic_score_gemma":0.000004934007,"domain_scores_codex":[0.9988288,0.00009064474,0.0002090107,0.0003029974,0.0004213297,0.0001472339],"domain_scores_gemma":[0.9993843,0.0001085164,0.0001156682,0.000201921,0.00007977946,0.0001098037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001229194,0.003004178,0.003819681,0.00001545689,0.00001240237,6.417508e-7,0.0009075387,0.000004386426,0.9885592,0.00006137258,0.001914272,0.001577933],"study_design_scores_gemma":[0.001527979,0.0006786649,0.001195581,0.00001396852,0.00004827735,0.00000108513,0.004600974,0.004287073,0.9864941,0.00003269701,0.001005388,0.0001141929],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928907,0.00001034339,0.001675255,0.0007520074,0.0001278666,0.0009648988,0.0000104046,0.0001514096,0.003417123],"genre_scores_gemma":[0.9955557,0.000003160475,0.001171122,0.0001739706,0.00008557448,0.0002480162,0.000004394605,0.00001514682,0.002742943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004282687,"threshold_uncertainty_score":0.3651446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3345058749814552,"score_gpt":0.3450128142396757,"score_spread":0.01050693925822049,"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."}}