{"id":"W2523796823","doi":"10.3233/978-1-61499-678-1-712","title":"Expectation-Driven Text Extraction from Medical Ultrasound Images","year":2016,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Grayscale; Consistency (knowledge bases); Table (database); Artificial intelligence; Java; Process (computing); Pixel; Information extraction; Medical imaging; Computer vision; Data mining","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":[0.001349283,0.0009102551,0.001070918,0.001846744,0.0002500029,0.0009967074,0.001048622,0.0008646536,0.002868787],"category_scores_gemma":[0.005750712,0.0002925592,0.0009716974,0.001184421,0.0003472048,0.001382857,0.0007108299,0.0004943407,0.002994969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003539813,"about_ca_system_score_gemma":0.0008038434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000719785,"about_ca_topic_score_gemma":0.0009534918,"domain_scores_codex":[0.9984102,0.0003580835,0.0002007054,0.0003635933,0.0005685322,0.00009882699],"domain_scores_gemma":[0.9967418,0.001855561,0.0002929271,0.0002201755,0.0008174968,0.00007202652],"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":[0.001377181,0.0003195584,0.002707845,0.001109302,0.0001622007,0.0007144416,0.000271563,0.01274215,0.1295274,0.002185668,0.005132048,0.8437507],"study_design_scores_gemma":[0.0001583556,0.001483844,0.01838179,0.0001790315,0.0003793844,0.003922695,0.0005296588,0.6321749,0.3122889,0.01246566,0.01784026,0.0001954954],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02954899,0.0006120882,0.9640771,0.0002170878,0.0000588257,0.0002371861,0.0008780728,0.003492098,0.0008786651],"genre_scores_gemma":[0.352803,0.0007572228,0.6362991,0.0003997751,0.0001746539,0.0005287391,0.005156087,0.0003451823,0.003536244],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002868787,"threshold_uncertainty_score":0.009597123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03215123172729588,"score_gpt":0.3616509547411882,"score_spread":0.3294997230138923,"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."}}