{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001411575,0.000135849,0.0008825236,0.0005959976,0.00005804964,0.00001087643,0.00008865447,0.0001507139,0.005342745],"category_scores_gemma":[0.003450937,0.0001102722,0.0007036413,0.002309244,0.0001586331,0.00005981156,0.00002758857,0.0001536802,0.00006532174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001976997,"about_ca_system_score_gemma":0.0001114967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004245398,"about_ca_topic_score_gemma":0.00003073246,"domain_scores_codex":[0.9978959,0.00006992645,0.0005878543,0.0003005178,0.0008051726,0.0003406492],"domain_scores_gemma":[0.9964877,0.002558477,0.0001129632,0.0002579399,0.0001794337,0.0004034447],"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":[0.0006471563,0.00127998,0.09775896,0.001210801,0.01080881,0.001948773,0.001357686,0.003506571,0.0004186833,0.0004606059,0.01775488,0.8628471],"study_design_scores_gemma":[0.007371153,0.0003458294,0.1663949,0.000394457,0.01190233,0.00002049707,0.001599694,0.7644362,0.001220532,0.0007220583,0.04480059,0.0007917244],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7199214,0.001710075,0.2132964,0.04723717,0.0009216307,0.001406377,0.00005639088,0.001021065,0.0144295],"genre_scores_gemma":[0.9977513,0.0001374406,0.0003928264,0.0003106991,0.0001646402,0.00002362073,0.0004315792,0.0000193027,0.0007686223],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8620554,"threshold_uncertainty_score":0.9955665,"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."}}