{"id":"W2768896610","doi":"10.1016/j.asoc.2017.11.024","title":"Parallel deep solutions for image retrieval from imbalanced medical imaging archives","year":2017,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Semantic gap; Computer science; Deep learning; Convolutional neural network; Artificial intelligence; Image retrieval; Scheme (mathematics); Task (project management); Key (lock); Bridge (graph theory); Feature (linguistics); Similarity (geometry); Semantics (computer science); Machine learning; Pattern recognition (psychology); Information retrieval; Image (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":[0.001177907,0.0011895,0.001511801,0.001787644,0.0006480863,0.001608704,0.001978623,0.00138646,0.005565107],"category_scores_gemma":[0.003011752,0.0005796675,0.001094467,0.002416723,0.0005962609,0.002235038,0.002410646,0.001598886,0.002032984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008078514,"about_ca_system_score_gemma":0.001585048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005853769,"about_ca_topic_score_gemma":0.01261618,"domain_scores_codex":[0.9993082,0.0001141561,0.000055637,0.0001526832,0.0002368921,0.0001323656],"domain_scores_gemma":[0.9988874,0.0003107561,0.0001034775,0.0003289345,0.0003039346,0.00006557006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008133831,0.0004465709,0.001340478,0.000245182,0.0002154996,0.0001583257,0.0001421003,0.1357184,0.02494344,0.005759459,0.01405336,0.8161638],"study_design_scores_gemma":[0.00004099455,0.00007175437,0.0003919489,0.000007551316,0.00004464632,0.00007686566,0.00006016357,0.9837422,0.00550621,0.008480734,0.001566758,0.00001014706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08141078,0.00188595,0.9075973,0.001000455,0.0002654401,0.0001368536,0.0008727344,0.004285485,0.002544992],"genre_scores_gemma":[0.5485941,0.001027737,0.4355682,0.00041138,0.0005067516,0.0002059588,0.00327305,0.0004179467,0.009994827],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005853769,"threshold_uncertainty_score":0.01861715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01950741243215443,"score_gpt":0.2824617520525718,"score_spread":0.2629543396204174,"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."}}