{"id":"W3141482012","doi":"10.1109/jbhi.2021.3070235","title":"Quantifying Axial Spine Images Using Object-Specific Bi-Path Network","year":2021,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"China Scholarship Council; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Feature extraction; Pattern recognition (psychology); Deep learning; Feature (linguistics); Upsampling; Computer vision; Pooling; Regularization (linguistics); Image (mathematics)","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":[0.001117648,0.0001372062,0.0004908682,0.00015515,0.0001457267,0.00007783544,0.000104616,0.00008622863,0.00004853381],"category_scores_gemma":[0.00006126628,0.0001054699,0.0001041413,0.0004369596,0.0001071892,0.0002018254,0.00002467059,0.0005088875,0.000004495224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006687704,"about_ca_system_score_gemma":0.0002182866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005693579,"about_ca_topic_score_gemma":0.000001093665,"domain_scores_codex":[0.9976604,0.00003422939,0.001366841,0.00005260109,0.0004962477,0.0003896951],"domain_scores_gemma":[0.9988497,0.00005993667,0.0003069888,0.0001008881,0.000113933,0.0005685601],"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":[0.00002324988,0.0002975463,0.00526211,0.006938262,0.0007735483,0.0006459019,0.005832188,0.01864137,0.004346465,0.0003058353,0.2105609,0.7463726],"study_design_scores_gemma":[0.002309048,0.0002366588,0.002805677,0.003124647,0.0001443679,0.002260278,0.001534393,0.813885,0.0006997536,0.0003218764,0.1721172,0.0005610944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2727466,0.01926505,0.7002488,0.00332536,0.003971299,0.00008017309,0.00001453698,0.00008641573,0.0002617411],"genre_scores_gemma":[0.6944033,0.04609399,0.2495391,0.00268792,0.007142346,0.000001249632,0.00002762589,0.00005760521,0.0000468683],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7952437,"threshold_uncertainty_score":0.4300939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05875825279558856,"score_gpt":0.3209500425994432,"score_spread":0.2621917898038547,"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."}}