{"id":"W2394987826","doi":"10.1016/j.procs.2015.08.226","title":"Automatic Detection of Polyp Using Hessian Filter and HOG Features","year":2015,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Japan Society for the Promotion of Science","keywords":"Computer science; Artificial intelligence; Hessian matrix; AdaBoost; Computer vision; Feature (linguistics); Endoscope; Pattern recognition (psychology); Filter (signal processing); Support vector machine; Random forest; Mathematics","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":[0.0004624783,0.0003655209,0.0004545089,0.00142229,0.0002105255,0.0004206768,0.0003343586,0.0005651149,0.0007710385],"category_scores_gemma":[0.0007797134,0.0002772107,0.0004989409,0.000564739,0.0002106471,0.0005865627,0.0003124052,0.0002327323,0.0003934786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002604041,"about_ca_system_score_gemma":0.0003533901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002921192,"about_ca_topic_score_gemma":0.003602988,"domain_scores_codex":[0.9995816,0.0000593345,0.00001889923,0.00008380402,0.0002039624,0.00005232672],"domain_scores_gemma":[0.9996752,0.00008994505,0.00004313241,0.00002598513,0.0001416008,0.00002418122],"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":[0.0003656947,0.0001597045,0.006454381,0.0001674784,0.00008651045,0.0002210234,0.00006160705,0.009810835,0.3183048,0.0007953115,0.002204215,0.6613684],"study_design_scores_gemma":[0.0000421911,0.0003598944,0.0383594,0.0000308586,0.00008457027,0.001401625,0.00007725241,0.7851411,0.1693994,0.0009511306,0.004053601,0.00009891641],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2256107,0.001005611,0.7678489,0.0001719838,0.0001166327,0.0001133097,0.0002046775,0.002055455,0.002872802],"genre_scores_gemma":[0.6320588,0.0005122315,0.3639475,0.00009367422,0.00005051202,0.00004726295,0.0003469329,0.00008540408,0.002857803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002921192,"threshold_uncertainty_score":0.005808294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0343980325590157,"score_gpt":0.2847317780932471,"score_spread":0.2503337455342314,"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."}}