{"id":"W2140996450","doi":"10.1109/titb.2006.884364","title":"A Framework for Medical Image Retrieval Using Machine Learning and Statistical Similarity Matching Techniques With Relevance Feedback","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Information Technology in Biomedicine","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":210,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Relevance feedback; Similarity (geometry); Relevance (law); Computer science; Matching (statistics); Image retrieval; Artificial intelligence; Pattern recognition (psychology); Information retrieval; Image (mathematics); Similarity learning; Machine learning; Data mining; Mathematics; Statistics","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":[0.002568718,0.001235593,0.001999621,0.004006402,0.0005863475,0.001444966,0.00296128,0.001834504,0.001784765],"category_scores_gemma":[0.003168758,0.0005713938,0.00213469,0.003161603,0.0008779981,0.001744297,0.001633608,0.001282288,0.001621105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001208482,"about_ca_system_score_gemma":0.001483695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004301242,"about_ca_topic_score_gemma":0.003358938,"domain_scores_codex":[0.997523,0.0006915453,0.0001804001,0.0004182262,0.001061768,0.000124974],"domain_scores_gemma":[0.9992072,0.000224228,0.0000995097,0.0001332115,0.0002961058,0.00003984887],"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":[0.0001550597,0.00030595,0.0006964396,0.0009102284,0.0002534552,0.0004563341,0.000266822,0.1258323,0.03893084,0.07636058,0.01250025,0.7433317],"study_design_scores_gemma":[0.00004817632,0.000401648,0.0007247392,0.00006316577,0.00009588509,0.001018125,0.0000636249,0.9201601,0.01062361,0.04605659,0.02064737,0.00009693472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004340843,0.0004836798,0.9981908,0.00007853156,0.00002406959,0.00009095314,0.00003493865,0.000411608,0.0002513108],"genre_scores_gemma":[0.03409613,0.0008539681,0.9628708,0.0001514288,0.0001741262,0.0004521025,0.0002780769,0.00005819601,0.001065177],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004301242,"threshold_uncertainty_score":0.01358485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01130334271881323,"score_gpt":0.3019587482381651,"score_spread":0.2906554055193519,"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."}}