{"id":"W4313361291","doi":"10.3390/diagnostics13010123","title":"GAR-Net: Guided Attention Residual Network for Polyp Segmentation from Colonoscopy Video Frames","year":2022,"lang":"en","type":"article","venue":"Diagnostics","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Segmentation; Benchmark (surveying); Computer science; Artificial intelligence; Residual; Net (polyhedron); Feature (linguistics); Pattern recognition (psychology); Intersection (aeronautics); Pixel; Block (permutation group theory); Noise (video); Computer vision; Image (mathematics); Algorithm; Mathematics; Cartography","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":[0.0003959353,0.001390385,0.0007810943,0.001015663,0.0003420603,0.0005296309,0.001778972,0.001130225,0.002280409],"category_scores_gemma":[0.001020475,0.0003968079,0.0007669744,0.0006673078,0.00033337,0.000860334,0.0006602766,0.0008571461,0.0008000058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001237257,"about_ca_system_score_gemma":0.001139365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02432639,"about_ca_topic_score_gemma":0.02921616,"domain_scores_codex":[0.9997931,0.00002194938,0.00001083527,0.000079231,0.00005048246,0.00004431991],"domain_scores_gemma":[0.9998276,0.00004584131,0.00002158068,0.000024635,0.00006112207,0.00001913128],"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":[0.001083273,0.0002216771,0.00265542,0.0002417618,0.0001755388,0.0004471146,0.00009744042,0.29585,0.02665709,0.002037755,0.01741843,0.6531145],"study_design_scores_gemma":[0.00001930894,0.00009138504,0.0004834538,0.00001334591,0.0000340802,0.00008288288,0.00001157586,0.9890028,0.007708328,0.00109125,0.001450828,0.00001066146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1737738,0.005283635,0.7886759,0.0009731312,0.0005009493,0.0004291337,0.002946959,0.01821195,0.009204581],"genre_scores_gemma":[0.7330788,0.001587932,0.2414869,0.0006714914,0.0002039943,0.0002609116,0.007128873,0.0004548654,0.01512625],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02432639,"threshold_uncertainty_score":0.04836959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02433033042198405,"score_gpt":0.3026943590199199,"score_spread":0.2783640285979358,"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."}}