{"id":"W2790858115","doi":"10.1016/j.eswa.2018.01.056","title":"A sequential search-space shrinking using CNN transfer learning and a Radon projection pool for medical image retrieval","year":2018,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Convolutional neural network; Image retrieval; Projection (relational algebra); Transfer of learning; Pattern recognition (psychology); Closing (real estate); Semantic gap; Similarity (geometry); Radon transform; Artificial intelligence; Image (mathematics); Linear search; Algorithm","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":[0.0006571758,0.0001571165,0.0001844449,0.0001392389,0.0006444652,0.0003121926,0.0003285427,0.000124809,0.000008060823],"category_scores_gemma":[0.00003963134,0.0001301024,0.00004298012,0.0005757186,0.0002254592,0.0003965445,0.00006606023,0.0001828074,0.000007703546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001020405,"about_ca_system_score_gemma":0.0002299299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001443539,"about_ca_topic_score_gemma":0.000003887903,"domain_scores_codex":[0.998311,0.0001133619,0.0002826619,0.0005180615,0.0004858167,0.0002890936],"domain_scores_gemma":[0.9990044,0.00008671551,0.00007078862,0.0003078156,0.000382845,0.0001474808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002649205,0.0002330842,0.0001734321,0.00036211,0.0001176561,0.000006861376,0.007780677,0.000007934886,0.8240262,0.1263021,0.0002566063,0.04046844],"study_design_scores_gemma":[0.001278149,0.0006408037,0.00004370775,0.0003277784,0.00002879534,0.0004416765,0.001064812,0.5711976,0.3335373,0.000265515,0.09056134,0.0006124443],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002539908,0.0002714272,0.9939482,0.000763496,0.00007185269,0.001673603,0.000002567413,0.0004370879,0.0002918183],"genre_scores_gemma":[0.890744,0.00006665638,0.106979,0.00006595606,0.0007462453,0.0009281288,0.00001100428,0.00003829982,0.000420736],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8882041,"threshold_uncertainty_score":0.5305423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02723945521666757,"score_gpt":0.3211081028218519,"score_spread":0.2938686476051844,"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."}}