{"id":"W4387521217","doi":"10.1016/j.media.2023.102985","title":"SurgT challenge: Benchmark of soft-tissue trackers for robotic surgery","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Benchmark (surveying); BitTorrent tracker; Segmentation; Ground truth; Benchmarking; Bounding overwatch; Computer vision; Metric (unit); Machine learning; Eye tracking","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":[0.007045038,0.001755184,0.00138236,0.001693692,0.0007508562,0.002426974,0.002787669,0.003397093,0.008886718],"category_scores_gemma":[0.01753642,0.0005249828,0.001335017,0.001138837,0.0008581656,0.00181116,0.003758767,0.001807016,0.008934514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007858921,"about_ca_system_score_gemma":0.00243397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00420541,"about_ca_topic_score_gemma":0.004596963,"domain_scores_codex":[0.994534,0.001550612,0.000257957,0.001024428,0.002288084,0.0003448697],"domain_scores_gemma":[0.9927421,0.00245941,0.0003301515,0.001145149,0.002277808,0.00104544],"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":[0.00437344,0.002124088,0.01173897,0.002851714,0.0008961447,0.0006258505,0.0004144541,0.1415255,0.02823755,0.006681501,0.2483375,0.5521933],"study_design_scores_gemma":[0.001164796,0.004719954,0.02458406,0.000428563,0.0002788466,0.002452162,0.0005338062,0.7757223,0.02913038,0.01057947,0.1501731,0.0002324861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.296218,0.01528931,0.4849844,0.009303262,0.008540561,0.002567485,0.04195439,0.07188046,0.06926207],"genre_scores_gemma":[0.5706248,0.003086238,0.28135,0.001939386,0.001000145,0.0008677342,0.1052918,0.006611637,0.02922812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008886718,"threshold_uncertainty_score":0.03725821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04643213624207263,"score_gpt":0.3571337986646587,"score_spread":0.310701662422586,"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."}}