{"id":"W2586839650","doi":"10.1007/s00586-017-4956-3","title":"ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist","year":2017,"lang":"en","type":"article","venue":"European Spine Journal","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":210,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Engineering and Physical Sciences Research Council; Research Councils UK","keywords":"Medicine; Grading (engineering); Magnetic resonance imaging; Radiology; Radiological weapon; Neuroradiology; Lumbar; Discitis; Intervertebral disc; Neurology","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":[0.001014617,0.0001320689,0.0003512159,0.0001446877,0.000151959,0.00006840147,0.0007109513,0.00002439133,0.00003761844],"category_scores_gemma":[0.0002155302,0.00008493188,0.00008249655,0.000159654,0.0005574843,0.0002867942,0.000073986,0.0002963971,7.646187e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003697973,"about_ca_system_score_gemma":0.00001328349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000805996,"about_ca_topic_score_gemma":0.00000502197,"domain_scores_codex":[0.9987588,0.0001158045,0.0005008806,0.0001644894,0.0002757107,0.0001843327],"domain_scores_gemma":[0.9990634,0.000006505919,0.0003499052,0.0004224095,0.00008379152,0.00007402717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00001096791,0.00008444002,0.03304084,0.00007509854,0.00003584376,0.00002579778,0.0006664747,0.006809052,0.9456972,0.00003511449,0.0005373093,0.01298178],"study_design_scores_gemma":[0.0006602627,0.0001956041,0.9338155,0.001180473,0.0000242117,0.0000420583,0.00008439219,0.03160005,0.03221896,0.0000191456,0.00004852956,0.0001107483],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9883025,0.002345916,0.008279656,0.00007794906,0.0001069908,0.00006264649,0.000004557404,0.00002455815,0.0007951942],"genre_scores_gemma":[0.9893082,0.0002466974,0.01023462,0.000008395548,0.0001001648,7.450066e-7,0.000001882023,0.00001383254,0.00008548939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9134783,"threshold_uncertainty_score":0.3463422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01958555070652137,"score_gpt":0.2884183246079902,"score_spread":0.2688327739014689,"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."}}