{"id":"W4214916274","doi":"10.3390/info13030124","title":"An Attentive Multi-Modal CNN for Brain Tumor Radiogenomic Classification","year":2022,"lang":"en","type":"article","venue":"Information","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Brain tumor; Modal; Feature (linguistics); Modality (human–computer interaction); Pattern recognition (psychology); Feature extraction; Process (computing); Magnetic resonance imaging; Embedding; Deep learning; Medical imaging; Image (mathematics); Modalities; 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":[],"consensus_categories":[],"category_scores_codex":[0.000563684,0.00007393692,0.0001162403,0.0001478019,0.0002564091,0.00003657504,0.00009169684,0.00002024535,0.0000713753],"category_scores_gemma":[0.0001953105,0.00007326707,0.00005921842,0.0001027399,0.00002864436,0.0004328393,0.00002139586,0.0002057304,0.00002695821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001875506,"about_ca_system_score_gemma":0.00008311695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001999691,"about_ca_topic_score_gemma":4.015995e-7,"domain_scores_codex":[0.9992555,0.00004082046,0.0002664522,0.00009609908,0.0001932864,0.0001478567],"domain_scores_gemma":[0.9994957,0.00004715024,0.000149722,0.0001565346,0.0000647397,0.0000861607],"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":[0.002010141,0.001060078,0.04328867,0.000655399,0.0002882678,0.00002026066,0.02823725,0.02447012,0.1390316,0.01499122,0.06043489,0.6855121],"study_design_scores_gemma":[0.002224553,0.0002605664,0.03633165,0.000007859878,0.00002763198,0.00006627765,0.001308109,0.8580095,0.0001687428,0.00005981997,0.1014381,0.00009719352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8343444,0.00002236959,0.1565258,0.006577274,0.0004259879,0.0009444902,0.00004327539,0.0001264537,0.0009898756],"genre_scores_gemma":[0.9877663,0.000001596807,0.006423051,0.004377319,0.0001141961,0.0001108914,0.00103287,0.0000117695,0.0001620246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8335394,"threshold_uncertainty_score":0.2987745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01990724538427908,"score_gpt":0.3133428723991584,"score_spread":0.2934356270148793,"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."}}