{"id":"W2618758840","doi":"10.1186/s12938-017-0350-y","title":"Evaluation of an automated thresholding algorithm for the quantification of paraspinal muscle composition from MRI images","year":2017,"lang":"en","type":"article","venue":"BioMedical Engineering OnLine","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Thresholding; Segmentation; Artificial intelligence; Computer science; Preprocessor; Sciatica; Magnetic resonance imaging; Image segmentation; Lumbar; Pattern recognition (psychology); Medicine; Radiology; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003556041,0.0006036095,0.0007203419,0.001272561,0.0003921435,0.001078864,0.001108426,0.001042822,0.0009217576],"category_scores_gemma":[0.009610523,0.0003049067,0.0004462433,0.0007347608,0.0003540097,0.0007972164,0.0005314537,0.0004619785,0.0004607365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005268433,"about_ca_system_score_gemma":0.0008343001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001242889,"about_ca_topic_score_gemma":0.001523751,"domain_scores_codex":[0.9978036,0.0005689438,0.0001869594,0.0004093985,0.0009433001,0.00008781901],"domain_scores_gemma":[0.9934958,0.002308971,0.0006259714,0.0003654289,0.003095422,0.0001084314],"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":[0.001352589,0.0004496064,0.02125813,0.0005046744,0.0002725308,0.0002282407,0.0003970412,0.03137066,0.2580149,0.001071875,0.001504607,0.6835751],"study_design_scores_gemma":[0.0001530991,0.001743958,0.04901506,0.00009788365,0.0003175536,0.001352254,0.000190265,0.8066801,0.134978,0.00100439,0.004327657,0.000139714],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2787918,0.000740477,0.7171617,0.0001001445,0.0001183902,0.0005232443,0.0001218091,0.001279427,0.00116307],"genre_scores_gemma":[0.2898115,0.0002468702,0.7084408,0.00005106806,0.00003497376,0.0004175905,0.0002099485,0.000164892,0.0006224217],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003556041,"threshold_uncertainty_score":0.0188064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03812257313066786,"score_gpt":0.3422743954869144,"score_spread":0.3041518223562465,"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."}}