{"id":"W3155650309","doi":"10.2196/14755","title":"Automatically Diagnosing Disk Bulge and Disk Herniation With Lumbar Magnetic Resonance Images by Using Deep Convolutional Neural Networks: Method Development Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China","keywords":"Sagittal plane; Lumbar; Magnetic resonance imaging; Convolutional neural network; Intervertebral disk; Computer science; Lumbar vertebrae; Vertebra; Medicine; Back pain; Radiology; Artificial intelligence; Anatomy; Pathology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004778246,0.0002253444,0.0003572194,0.00005758848,0.0001579717,0.0001345834,0.0001403006,0.000106004,0.0001405456],"category_scores_gemma":[0.0002132209,0.0001832404,0.00003605642,0.0003389766,0.0001294113,0.0002689644,0.00009460803,0.0004015337,0.000005057109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008201517,"about_ca_system_score_gemma":0.00008767533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006566591,"about_ca_topic_score_gemma":0.00001226769,"domain_scores_codex":[0.9977426,0.00009648582,0.0007166099,0.0001515301,0.0009182934,0.0003744957],"domain_scores_gemma":[0.9990381,0.000241065,0.00007841134,0.0001767304,0.00008829631,0.000377418],"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":[0.00001147057,0.0006115434,0.06460112,0.0007957365,0.0003479206,0.0002141265,0.009779369,0.03721103,0.00007779345,0.00004347334,0.002786586,0.8835198],"study_design_scores_gemma":[0.0007154822,0.000034188,0.01435024,0.0001882503,0.00008091031,0.00005574903,0.001256026,0.9823033,0.00002829498,0.00000806302,0.0007391946,0.000240364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5056587,0.002328355,0.4912992,0.0001441225,0.00008476426,0.0002036201,0.000005757688,0.000183233,0.00009226932],"genre_scores_gemma":[0.8955153,0.0002330415,0.10339,0.0004826944,0.0001231517,0.00008496568,0.0000825446,0.00003937802,0.00004884891],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9450922,"threshold_uncertainty_score":0.7472324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006530040880933705,"score_gpt":0.2569827443400721,"score_spread":0.2504527034591383,"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."}}