{"id":"W2951719372","doi":"10.48550/arxiv.1610.00320","title":"Stacked Autoencoders for Medical Image Search","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Image retrieval; Artificial intelligence; Benchmark (surveying); ENCODE; Pattern recognition (psychology); Feature extraction; Content-based image retrieval; Medical imaging; Image (mathematics); Local binary patterns; Computer vision; Information retrieval; Histogram; Geography","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":[0.0007748455,0.000796067,0.0008879246,0.001132764,0.0002376591,0.0007093523,0.0006683455,0.001049599,0.00247234],"category_scores_gemma":[0.002770403,0.0004179529,0.0008254168,0.00106795,0.0003631682,0.0009402668,0.0005750409,0.001036934,0.00130653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005704805,"about_ca_system_score_gemma":0.0006863702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007995876,"about_ca_topic_score_gemma":0.008220063,"domain_scores_codex":[0.9995486,0.00009377288,0.00004132356,0.0001052659,0.0001674831,0.00004349157],"domain_scores_gemma":[0.9992222,0.0003761434,0.00007698551,0.0001112056,0.000192617,0.00002089607],"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":[0.0002034194,0.0001185513,0.001158866,0.0001536477,0.0001829233,0.0001522086,0.00008907267,0.3112134,0.01890553,0.005384935,0.006321388,0.6561161],"study_design_scores_gemma":[0.000005821936,0.00003697951,0.0005671389,0.00001405164,0.00002166258,0.00006529118,0.00001856695,0.9904172,0.003900529,0.003570456,0.001372362,0.000009954124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04607082,0.004256197,0.942661,0.0006318018,0.0001685794,0.00006934384,0.0004548277,0.002647958,0.003039446],"genre_scores_gemma":[0.5706443,0.003429183,0.4130218,0.0004706203,0.0003019822,0.0001571388,0.001929937,0.0002044276,0.009840604],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007995876,"threshold_uncertainty_score":0.01589864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08300237818767757,"score_gpt":0.2355329733591308,"score_spread":0.1525305951714533,"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."}}