{"id":"W2781725568","doi":"10.31237/osf.io/8y6s7","title":"Voxel-Wise Image Analysis for White Matter Hyperintensity Segmentation","year":2018,"lang":"en","type":"preprint","venue":"","topic":"RNA regulation and disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Segmentation; Interpretability; Artificial intelligence; Computer science; Voxel; Pattern recognition (psychology); Hyperintensity; Image segmentation; Overfitting; Fluid-attenuated inversion recovery; Logistic regression; Pixel; Scale-space segmentation; Computer vision; Machine learning; Magnetic resonance imaging; Medicine; Artificial neural network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004129316,0.00123405,0.001000197,0.00255611,0.0007948004,0.002423647,0.001621151,0.001491895,0.003477829],"category_scores_gemma":[0.01697561,0.0005692803,0.001637253,0.002284627,0.0008704943,0.001222257,0.001607409,0.001782697,0.002920646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007566296,"about_ca_system_score_gemma":0.001655401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002785448,"about_ca_topic_score_gemma":0.003150289,"domain_scores_codex":[0.9983395,0.0005481,0.0001240093,0.0004291063,0.0004355397,0.0001236288],"domain_scores_gemma":[0.9964283,0.00136989,0.000431043,0.0007396613,0.0009288489,0.0001022001],"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":[0.0005817001,0.0002263049,0.009916223,0.0006624128,0.0006393151,0.0003316884,0.0005083617,0.1787179,0.07314435,0.02138951,0.02069694,0.6931853],"study_design_scores_gemma":[0.0000240802,0.0001303562,0.005643302,0.00006930281,0.00007717194,0.0004800395,0.0001218867,0.9193618,0.04329924,0.01970252,0.01103133,0.00005902978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0199769,0.0005302266,0.9708334,0.0002620083,0.00008590096,0.0001536958,0.0007966752,0.006173004,0.001188257],"genre_scores_gemma":[0.1660216,0.0004997858,0.825307,0.0001208857,0.00008660927,0.0003306687,0.003712075,0.002494954,0.001426475],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004129316,"threshold_uncertainty_score":0.02183819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01259970866892447,"score_gpt":0.276588086501675,"score_spread":0.2639883778327506,"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."}}