{"id":"W4399389101","doi":"10.3390/diagnostics14111204","title":"Enhancing Medical Image Retrieval with UMLS-Integrated CNN-Based Text Indexing","year":2024,"lang":"en","type":"article","venue":"Diagnostics","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Al Jouf University","keywords":"Computer science; Information retrieval; Unified Medical Language System; Image retrieval; Convolutional neural network; Search engine indexing; Metadata; Artificial intelligence; Ranking (information retrieval); Task (project management); Thesaurus; Semantics (computer science); Matching (statistics); Semantic gap; Natural language processing; Image (mathematics); World Wide Web","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":[0.0005694163,0.0001991796,0.0001858502,0.00018181,0.0001169652,0.0005108288,0.0007083851,0.0001521986,0.0001337239],"category_scores_gemma":[0.001712898,0.0001485179,0.00006437689,0.001236778,0.000143292,0.0003498341,0.0001057365,0.0004726646,0.0001965139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000105105,"about_ca_system_score_gemma":0.0007629929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001932995,"about_ca_topic_score_gemma":0.000007646585,"domain_scores_codex":[0.9980321,0.00007293357,0.0003072291,0.0004631298,0.000792483,0.0003321046],"domain_scores_gemma":[0.9978553,0.001205918,0.00005834521,0.0004468655,0.0002415598,0.0001920337],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002148329,0.001214825,0.003109017,0.001430254,0.0003226584,0.009522554,0.002903088,0.00002590423,0.09230401,0.3155073,0.02929931,0.5441462],"study_design_scores_gemma":[0.0003061928,0.0002856274,0.0006418747,0.001151443,0.00002912159,0.00005719622,0.00005550236,0.1508343,0.8194278,0.001417631,0.02530807,0.000485233],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002025195,0.0005442959,0.9914006,0.003092937,0.0003114697,0.0001709082,0.000007710561,0.001247518,0.001199362],"genre_scores_gemma":[0.8695763,0.0003097974,0.127641,0.001517633,0.0002628777,0.00003282055,0.00003785197,0.00005475381,0.0005669429],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8675511,"threshold_uncertainty_score":0.6056383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008790057986984018,"score_gpt":0.2589000978953596,"score_spread":0.2501100399083755,"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."}}