{"id":"W4385496529","doi":"10.1016/j.patrec.2023.07.014","title":"Segmenting white matter hyperintensities in brain magnetic resonance images using convolution neural networks","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Foothills Medical Centre; University of Alberta; University of Calgary","funders":"","keywords":"Fluid-attenuated inversion recovery; Hyperintensity; Segmentation; Convolutional neural network; Artificial intelligence; Magnetic resonance imaging; Pattern recognition (psychology); Generalizability theory; White matter; Computer science; Psychology; Medicine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004746298,0.0005993299,0.0004246287,0.001445404,0.0002730836,0.0008504729,0.0003542207,0.0005582604,0.0008798581],"category_scores_gemma":[0.00104465,0.0002567079,0.0005814487,0.0008997773,0.0002830364,0.0005113062,0.0004209597,0.0004924118,0.0003743869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003495917,"about_ca_system_score_gemma":0.0005934301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006725941,"about_ca_topic_score_gemma":0.008674363,"domain_scores_codex":[0.9998814,0.0000133553,0.0000103566,0.00003300864,0.00002659606,0.00003530263],"domain_scores_gemma":[0.9997075,0.0001198977,0.00004957705,0.00002739227,0.00007073123,0.00002481903],"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":[0.0008089764,0.0002341587,0.01284941,0.0001837684,0.0001862654,0.0005636315,0.0001520594,0.05562386,0.1635995,0.002492886,0.003029517,0.760276],"study_design_scores_gemma":[0.00001320259,0.00009365016,0.01675738,0.00002339232,0.00008777698,0.0003792296,0.00007989913,0.9216934,0.05555531,0.003756588,0.001536044,0.00002406686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4466047,0.001352505,0.5475725,0.0003950191,0.0001043831,0.0001064635,0.000486012,0.001492965,0.001885424],"genre_scores_gemma":[0.8412532,0.0007335758,0.1535599,0.00008792736,0.00007849353,0.00004915219,0.0007732043,0.000125735,0.003338838],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006725941,"threshold_uncertainty_score":0.01337355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.047294712120708,"score_gpt":0.2513466540722519,"score_spread":0.2040519419515439,"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."}}