{"id":"W2963465156","doi":"10.1016/j.artmed.2019.101769","title":"Fully-automated deep learning-powered system for DCE-MRI analysis of brain tumors","year":2019,"lang":"en","type":"preprint","venue":"Artificial Intelligence in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Future Earth","funders":"Narodowe Centrum Badań i Rozwoju; Silesian University of Technology","keywords":"Computer science; Segmentation; Magnetic resonance imaging; Artificial intelligence; Grading (engineering); Glioma; Deep learning; Brain tumor; Pattern recognition (psychology); Radiology; Medicine; Pathology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003639132,0.0005885165,0.003032706,0.002275607,0.00008833546,0.00003457824,0.0005917376,0.0005512872,0.0002730511],"category_scores_gemma":[0.006029243,0.0005005953,0.0006076624,0.001934925,0.0005599704,0.00004916077,0.0002622654,0.002020286,0.00003225863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003615033,"about_ca_system_score_gemma":0.0002938614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001539282,"about_ca_topic_score_gemma":0.000156495,"domain_scores_codex":[0.9943762,0.0003304658,0.002516801,0.001118935,0.000942692,0.0007149259],"domain_scores_gemma":[0.9953583,0.001689968,0.001107951,0.0009688945,0.0005543864,0.0003205011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002139617,0.0007922676,0.03967189,0.008988543,0.005411098,0.0004613422,0.01081432,0.7698064,0.01213584,0.008852083,0.001820427,0.1391061],"study_design_scores_gemma":[0.0003800172,0.0006816279,0.00301262,0.003819135,0.00245428,0.00002314746,0.004218635,0.9822164,0.001267086,0.0008455121,0.0006804569,0.000401126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4732184,0.003518422,0.4933113,0.01676233,0.004178811,0.004709762,0.00005826633,0.001068601,0.003174126],"genre_scores_gemma":[0.9940407,0.0002357476,0.003462382,0.0004917281,0.0005523413,0.0001191303,0.0007442434,0.00009520302,0.0002585611],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5208223,"threshold_uncertainty_score":0.9997446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03164588298953321,"score_gpt":0.3635783111487204,"score_spread":0.3319324281591872,"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."}}