{"id":"W3163728664","doi":"10.48550/arxiv.2105.03847","title":"Automatic segmentation of vertebral features on ultrasound spine images using Stacked Hourglass Network","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Coronal plane; Segmentation; Artificial intelligence; Gold standard (test); Radiography; Ultrasound; Hourglass; Computer science; Deformity; Nuclear medicine; Computer vision; Medicine; Anatomy; Radiology; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004033981,0.000973477,0.0005256968,0.001142239,0.0003640005,0.0005764752,0.0007009268,0.0008028058,0.002027048],"category_scores_gemma":[0.0009502604,0.0003638553,0.0005586913,0.0005548444,0.0003798623,0.0005625166,0.0005094427,0.0003585189,0.0006352506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007381053,"about_ca_system_score_gemma":0.0006236646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01770434,"about_ca_topic_score_gemma":0.01735875,"domain_scores_codex":[0.9997715,0.0000256995,0.00001054254,0.00009585648,0.00004395214,0.00005246019],"domain_scores_gemma":[0.9997457,0.00007219669,0.00005117803,0.00003006003,0.00007996423,0.00002096736],"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":[0.0006622942,0.0001886838,0.01409064,0.000100362,0.0002303011,0.0004057667,0.0001695953,0.2602743,0.05222246,0.0006782041,0.004136506,0.6668407],"study_design_scores_gemma":[0.000008649821,0.0000668018,0.004781523,0.00001036182,0.00003583566,0.00005681357,0.00003565297,0.9856223,0.008322079,0.000502032,0.0005475507,0.00001035516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4698124,0.001097009,0.5186371,0.0002997697,0.0001616563,0.0001963774,0.000809762,0.005591649,0.003394341],"genre_scores_gemma":[0.8867224,0.0003334524,0.1065944,0.0001153363,0.00005640986,0.0001146325,0.00122021,0.00009978494,0.004743307],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01770434,"threshold_uncertainty_score":0.03520256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03371312097139956,"score_gpt":0.1931671909402396,"score_spread":0.15945406996884,"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."}}