{"id":"W2552476930","doi":"10.1109/ijcnn.2016.7727810","title":"Automated Growcut for segmentation of endoscopic images","year":2016,"lang":"en","type":"article","venue":"","topic":"Gastrointestinal Bleeding Diagnosis and Treatment","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Image segmentation; Cluster analysis; Ground truth; Scale-space segmentation; Pattern recognition (psychology); Computer vision; Segmentation-based object categorization; Fuzzy logic; Automation; Capsule endoscopy; Medicine","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":[0.001225238,0.001145543,0.0007013502,0.002781992,0.0008368663,0.001578985,0.001395059,0.001712022,0.002615476],"category_scores_gemma":[0.003753882,0.0006880271,0.001009403,0.001634222,0.0007371384,0.001354255,0.001266201,0.001076051,0.001195665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006645214,"about_ca_system_score_gemma":0.001631811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004124754,"about_ca_topic_score_gemma":0.007172904,"domain_scores_codex":[0.9986477,0.0002196343,0.00009468738,0.0003060215,0.0006297893,0.0001021744],"domain_scores_gemma":[0.9982114,0.0006475034,0.0001894731,0.0002822142,0.0006120117,0.00005743363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003280599,0.00007866769,0.002134944,0.0004311565,0.0001213802,0.0006135309,0.0004683106,0.0367388,0.1703217,0.009357485,0.007998967,0.7714069],"study_design_scores_gemma":[0.00003241475,0.0001572806,0.004457472,0.00008026913,0.0000505376,0.001564061,0.0001922147,0.7967715,0.1644877,0.009540171,0.02257135,0.00009508317],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01600706,0.0002801692,0.9792004,0.00008492312,0.00002893401,0.0001420858,0.0001788008,0.00283155,0.001246042],"genre_scores_gemma":[0.07133976,0.0002357821,0.9253232,0.00008826951,0.00002703584,0.000154021,0.0008578467,0.0007073103,0.001266821],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004124754,"threshold_uncertainty_score":0.008749664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0216482968842329,"score_gpt":0.3105865098345794,"score_spread":0.2889382129503465,"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."}}