{"id":"W2963691855","doi":"10.1109/ijcnn.2016.7727562","title":"Generating binary tags for fast medical image retrieval based on convolutional nets and Radon Transform","year":2016,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Image retrieval; Convolutional neural network; Artificial intelligence; Feature extraction; Content-based image retrieval; Pattern recognition (psychology); Feature (linguistics); Radon transform; Contextual image classification; Image (mathematics); Automatic image annotation; Invariant (physics); Computer vision; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005212186,0.000118286,0.0001197579,0.00007577497,0.0001518605,0.00007155238,0.0003142861,0.00009758282,0.0001180583],"category_scores_gemma":[0.0001552245,0.00007305217,0.00005908226,0.0001435933,0.0001271542,0.0003318577,0.0000383685,0.00006959615,0.0000106232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004536286,"about_ca_system_score_gemma":0.0001604814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002743109,"about_ca_topic_score_gemma":7.581315e-7,"domain_scores_codex":[0.9987553,0.00003756699,0.0002229522,0.0003407139,0.0004268666,0.0002166337],"domain_scores_gemma":[0.9991934,0.0002914841,0.00004786851,0.0002094138,0.0001175889,0.0001402297],"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":[0.0002023464,0.0002033689,0.00008576762,0.00005043988,0.00001418744,0.00001391814,0.0000718454,9.176859e-7,0.3975162,0.1032823,0.006687354,0.4918713],"study_design_scores_gemma":[0.001547054,0.0005743405,0.0005166557,0.00007727095,0.000004654372,0.00001774556,0.000007439502,0.6185248,0.3668687,0.002275699,0.009318293,0.0002673541],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00134835,0.00002840626,0.9717215,0.02531109,0.00008801245,0.0002473429,0.00001207308,0.0002483539,0.0009949121],"genre_scores_gemma":[0.674602,0.00006673166,0.3185287,0.004234676,0.0002160929,0.00005872996,0.00001513298,0.00002157638,0.002256443],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6732536,"threshold_uncertainty_score":0.2978981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01423198065697123,"score_gpt":0.2610367330790539,"score_spread":0.2468047524220827,"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."}}