{"id":"W4226034463","doi":"10.1007/s11548-022-02597-0","title":"Can uncertainty estimation predict segmentation performance in ultrasound bone imaging?","year":2022,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Orthopaedic Trauma Association","keywords":"Segmentation; Computer science; Ground truth; Artificial intelligence; Calibration; Artificial neural network; Image segmentation; Pattern recognition (psychology); Machine learning; Computer vision; Statistics; 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":[0.005578055,0.0008344543,0.0009770436,0.002027282,0.0003462328,0.002165125,0.0008835912,0.003142325,0.001193224],"category_scores_gemma":[0.05034536,0.000746973,0.0008773658,0.000869541,0.0008743031,0.002988904,0.0007070696,0.0007900959,0.0008594937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004462898,"about_ca_system_score_gemma":0.0005538664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003879284,"about_ca_topic_score_gemma":0.003092985,"domain_scores_codex":[0.9982509,0.000603274,0.0002072236,0.0003399763,0.0004259782,0.000172663],"domain_scores_gemma":[0.9694212,0.02376621,0.002644841,0.001230529,0.002539871,0.0003974516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002797361,0.0002634337,0.371793,0.0004403971,0.00100092,0.0004570243,0.0002780647,0.3319238,0.03017168,0.002428774,0.002750781,0.2556947],"study_design_scores_gemma":[0.00002854867,0.0002981398,0.0849258,0.0001029592,0.0002003623,0.0006769733,0.0001271035,0.8848799,0.02015193,0.007572535,0.0009220935,0.000113756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6912458,0.01169365,0.290778,0.001782437,0.0002232281,0.00005355651,0.0008769474,0.001256215,0.002090055],"genre_scores_gemma":[0.9855795,0.0007655665,0.0126687,0.0001100744,0.00007996526,0.000008168897,0.0004098556,0.0001296579,0.0002485447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005578055,"threshold_uncertainty_score":0.02949995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006741805957928946,"score_gpt":0.2218219572577179,"score_spread":0.215080151299789,"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."}}