{"id":"W3214565892","doi":"10.18280/ria.350505","title":"SRGAN Assisted Encoder-Decoder Deep Neural Network for Colorectal Polyp Semantic Segmentation","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Segmentation; Encoder; Benchmark (surveying); Colonoscopy; Computer science; Colorectal Polyp; Deep learning; Sørensen–Dice coefficient; Dice; Colorectal cancer; Artificial neural network; Pattern recognition (psychology); Image segmentation; Radiology; Medicine; Cancer; Internal medicine; Mathematics; Cartography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003211743,0.0007285082,0.0005073217,0.0003517258,0.0001644612,0.0003685481,0.0007719888,0.0007796079,0.001340056],"category_scores_gemma":[0.0008326823,0.0002732713,0.000516871,0.000245231,0.0003408215,0.0005438741,0.0005230894,0.001105806,0.0004336187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006386681,"about_ca_system_score_gemma":0.0006002311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007360848,"about_ca_topic_score_gemma":0.0101743,"domain_scores_codex":[0.9998298,0.00003605065,0.000007968049,0.00005162421,0.00004413982,0.00003047343],"domain_scores_gemma":[0.9997949,0.00009279045,0.00002095264,0.00002651811,0.00005132851,0.00001346219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003521779,0.0001020023,0.001627442,0.0001285824,0.0001154743,0.0003381578,0.00006531613,0.745033,0.01964955,0.004024832,0.005426252,0.2231372],"study_design_scores_gemma":[0.000004979835,0.00003173236,0.0001643616,0.000005575875,0.000009798012,0.00005118128,0.000003183534,0.9959455,0.002448539,0.0009014584,0.0004290906,0.000004658032],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1244729,0.003161371,0.8585795,0.0009914702,0.0002226681,0.0001096084,0.0007857617,0.00433445,0.007342361],"genre_scores_gemma":[0.8400683,0.000967049,0.1460264,0.0005682286,0.00007812081,0.00009493934,0.00148505,0.0001663446,0.01054557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007360848,"threshold_uncertainty_score":0.01463598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04396579066490906,"score_gpt":0.3057317565073456,"score_spread":0.2617659658424365,"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."}}