{"id":"W3198845577","doi":"10.1016/j.compbiomed.2021.104805","title":"Accurate lateralization and classification of MRI-negative 18F-FDG-PET-positive temporal lobe epilepsy using double inversion recovery and machine-learning","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Epilepsy research and treatment","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"Japan Society for the Promotion of Science; Japan Epilepsy Research Foundation","keywords":"Epilepsy; Temporal lobe; Laterality; Lateralization of brain function; Nuclear medicine; Artificial intelligence; Magnetic resonance imaging; Computer science; Medicine; Psychology; Radiology; Neuroscience; Audiology","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":[0.001020007,0.0006332081,0.0005500957,0.001372042,0.0002377035,0.001012318,0.0004904624,0.0008047731,0.0008427508],"category_scores_gemma":[0.002645231,0.0002328126,0.0003823345,0.0003253496,0.0002928508,0.0006873463,0.0005770882,0.0004260927,0.0007339295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001704016,"about_ca_system_score_gemma":0.0005978702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00149674,"about_ca_topic_score_gemma":0.003201739,"domain_scores_codex":[0.9997793,0.0000533961,0.00002448373,0.00004648278,0.00005442588,0.00004189329],"domain_scores_gemma":[0.9992377,0.0003067132,0.0001097783,0.00008246891,0.000217816,0.00004545856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001791242,0.0001862562,0.07360783,0.0002970938,0.0001306367,0.001147491,0.0002256817,0.01545387,0.2339717,0.001822869,0.00441174,0.6669535],"study_design_scores_gemma":[0.00010514,0.000265098,0.06117304,0.0000761362,0.0002353317,0.004367126,0.0004180223,0.805714,0.1162914,0.005493836,0.005759388,0.0001015175],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6541724,0.001993758,0.3375438,0.0007965141,0.000148598,0.0001467719,0.0007606231,0.001525947,0.002911661],"genre_scores_gemma":[0.9144436,0.0005966931,0.08165003,0.0001274385,0.0000777447,0.0000466311,0.001001588,0.0001722957,0.001884056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00149674,"threshold_uncertainty_score":0.00539434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05101432968884976,"score_gpt":0.3469298808867614,"score_spread":0.2959155511979116,"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."}}