{"id":"W2808276994","doi":"10.1016/j.jvcir.2018.06.001","title":"Multiple disjoint dictionaries for representation of histopathology images","year":2018,"lang":"en","type":"article","venue":"Journal of Visual Communication and Image Representation","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Pattern recognition (psychology); Artificial intelligence; Histogram; Bag-of-words model; Computer science; Histogram of oriented gradients; Bag-of-words model in computer vision; Support vector machine; Representation (politics); Intersection (aeronautics); Image (mathematics); Image retrieval; Mathematics; Visual Word","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003537312,0.0004425647,0.0007008286,0.001001476,0.0002233642,0.0005918187,0.0008223805,0.0005447093,0.003515176],"category_scores_gemma":[0.001357394,0.0002103471,0.0005201212,0.001321431,0.0003506057,0.0009714988,0.0009874828,0.0008002395,0.001852887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003055641,"about_ca_system_score_gemma":0.0003999568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001495727,"about_ca_topic_score_gemma":0.001981645,"domain_scores_codex":[0.9995508,0.00006811904,0.00004246044,0.0001292052,0.0001524812,0.00005690837],"domain_scores_gemma":[0.9994783,0.000120883,0.00006237812,0.0001767846,0.0001324385,0.00002920454],"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":[0.0004558474,0.0001486008,0.001322569,0.0002853689,0.00008309487,0.0001718542,0.0001151382,0.03532303,0.1066095,0.005865719,0.00735878,0.8422606],"study_design_scores_gemma":[0.00004492009,0.000366877,0.005150873,0.00006160623,0.00009524705,0.0009518516,0.0002182607,0.8902234,0.08026314,0.007536933,0.01503225,0.00005466209],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07955809,0.001922909,0.9121955,0.0002925025,0.0001816198,0.0001310337,0.0008594519,0.001750686,0.003108233],"genre_scores_gemma":[0.5822524,0.001493027,0.4041975,0.0003147176,0.0001737268,0.0002224699,0.003861955,0.0002799866,0.007204195],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003515176,"threshold_uncertainty_score":0.01175946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04057181106023062,"score_gpt":0.3755460995192327,"score_spread":0.3349742884590021,"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."}}