{"id":"W2338593764","doi":"10.1016/j.compbiomed.2016.04.006","title":"Shape, texture and statistical features for classification of benign and malignant vertebral compression fractures in magnetic resonance images","year":2016,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":77,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Financiadora de Estudos e Projetos; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Magnetic resonance imaging; Texture (cosmology); Compression (physics); Radiology; Artificial intelligence; Computer science; Medicine; Pattern recognition (psychology); Materials science; Image (mathematics); Composite material","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001333103,0.00007542819,0.0002165965,0.00008564421,0.00001509963,0.000001950654,0.00003786531,0.00007670213,0.000009225005],"category_scores_gemma":[0.00009234269,0.00004240642,0.000005832376,0.00004246624,0.0003268757,0.00001864281,0.00001700731,0.00007603313,5.317506e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005026096,"about_ca_system_score_gemma":0.000003041274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001166371,"about_ca_topic_score_gemma":0.000008462494,"domain_scores_codex":[0.99953,0.00003320456,0.0001501553,0.0001502191,0.00003103207,0.0001053822],"domain_scores_gemma":[0.9994639,0.000405389,0.0000178763,0.00005646075,0.00001035626,0.00004601448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003509675,0.00001422487,0.07180434,0.0001345538,0.000008889447,0.000005734616,0.0002259694,0.000003604887,0.04079553,0.002512249,0.004183711,0.8802761],"study_design_scores_gemma":[0.001659316,0.0001464238,0.9418946,0.0006758332,0.00001778645,0.000009977761,0.00004523118,0.04895896,0.0002910636,0.005014497,0.001198961,0.00008738264],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8012276,0.05461315,0.1390423,0.004445204,0.0002614079,0.000227936,0.00004709757,0.00003545159,0.00009983042],"genre_scores_gemma":[0.9950744,0.001796612,0.00293522,0.0001183001,0.00004358804,0.000005449274,0.00001267065,0.00000374091,0.00001002592],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8801887,"threshold_uncertainty_score":0.1729283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009458620043709261,"score_gpt":0.2895267234508843,"score_spread":0.280068103407175,"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."}}