{"id":"W4317659928","doi":"10.1038/s41598-023-28530-2","title":"Dual encoder–decoder-based deep polyp segmentation network for colonoscopy images","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Research Manitoba","keywords":"Computer science; Encoder; Colonoscopy; Artificial intelligence; Segmentation; Dual (grammatical number); Computer vision; Pattern recognition (psychology); Medicine; Colorectal cancer; Internal medicine; Cancer","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001172525,0.0001167269,0.0001870045,0.0001983608,0.0004344255,0.0001381221,0.00003270868,0.00006873644,0.00006955493],"category_scores_gemma":[0.0002126185,0.0001102203,0.0001236544,0.0009233576,0.0001052755,0.00009352079,0.00002221207,0.00008077983,0.00003023556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001033841,"about_ca_system_score_gemma":0.0002458738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004903281,"about_ca_topic_score_gemma":0.0001143487,"domain_scores_codex":[0.9983087,0.00002572933,0.0003463219,0.0005672452,0.0003984318,0.0003536022],"domain_scores_gemma":[0.9990271,0.00009214706,0.0001875998,0.0003767982,0.0001904243,0.0001259188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.007716989,0.0002353829,0.03641596,0.0004025508,0.0001457078,0.0010696,0.0008753422,0.02341992,0.1584172,0.00002445832,0.7276836,0.04359324],"study_design_scores_gemma":[0.003584204,0.007113033,0.02807501,0.0003612752,0.0004329818,0.0007900402,0.0007803004,0.1300663,0.6954909,0.007803965,0.124635,0.0008670178],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9400402,0.0002567263,0.04022857,0.0009383808,0.01519151,0.001439163,0.00001001785,0.0007057497,0.00118972],"genre_scores_gemma":[0.9824552,0.000002886134,0.009546107,0.000135903,0.0004910037,0.0002773788,0.0005431474,0.00002724871,0.006521108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6030486,"threshold_uncertainty_score":0.4494654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02430938281852186,"score_gpt":0.3100535682974117,"score_spread":0.2857441854788899,"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."}}