{"id":"W4400066081","doi":"10.14245/ns.2448060.030","title":"The Quantitative Evaluation of Automatic Segmentation in Lumbar Magnetic Resonance Images","year":2024,"lang":"en","type":"article","venue":"Neurospine","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Food and Drug Administration","keywords":"Segmentation; Magnetic resonance imaging; Computer science; Lumbar; Artificial intelligence; Spinal stenosis; Lumbar spinal stenosis; Neurogenic claudication; Residual; Radiology; Medicine; Computer vision; Algorithm","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":[0.0004021356,0.0000493833,0.00006940999,0.00005545092,0.00001661949,0.00002633413,0.00005177764,0.00001120245,0.00004471058],"category_scores_gemma":[0.0001850324,0.00003656658,0.00002294781,0.0003147407,0.00003455993,0.00005710707,0.000005973048,0.00007752054,0.00001614835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002207029,"about_ca_system_score_gemma":0.00001251882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009075196,"about_ca_topic_score_gemma":0.000006647362,"domain_scores_codex":[0.9993582,0.00006117058,0.0001677749,0.00007998558,0.0002552052,0.00007762701],"domain_scores_gemma":[0.9997883,0.0000708505,0.00001050864,0.00008672864,0.0000293884,0.00001422986],"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":[5.991013e-7,0.00001398879,0.0004522693,0.000203808,0.00001075405,0.000007616769,0.0004486182,0.01013064,0.07572011,0.0002329706,0.001637785,0.9111409],"study_design_scores_gemma":[0.0001125354,0.0000190627,0.03621964,0.0001017055,0.00003289213,7.32531e-7,0.0000415361,0.9600798,0.002806486,0.0002451845,0.0003055233,0.0000348543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9601386,0.03633714,0.001522392,0.0005604302,0.0003554629,0.00016537,0.000004911249,0.0001377845,0.0007779624],"genre_scores_gemma":[0.9986503,0.0007238638,0.0004478039,0.0000156091,0.00001499293,0.0000253874,0.000002876639,0.000009817803,0.0001093655],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9499492,"threshold_uncertainty_score":0.1491142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01788857608803217,"score_gpt":0.3015342366710155,"score_spread":0.2836456605829833,"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."}}