{"id":"W2782425054","doi":"10.1007/s00330-017-5214-0","title":"Spectral multi-energy CT texture analysis with machine learning for tissue classification: an investigation using classification of benign parotid tumours as a testing paradigm","year":2018,"lang":"en","type":"article","venue":"European Radiology","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":80,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre; Royal Victoria Hospital; McGill University; Jewish General Hospital","funders":"","keywords":"Texture (cosmology); Computer science; Artificial intelligence; Energy (signal processing); Pattern recognition (psychology); Linear discriminant analysis; Medicine; Radiology; Nuclear medicine; Image (mathematics); Statistics; Mathematics","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":[0.0003161828,0.0002181973,0.0003121788,0.0002405221,0.0002030125,0.00002570165,0.0001861312,0.00003791359,0.00001314309],"category_scores_gemma":[0.0001077311,0.0002090721,0.0000505712,0.0006556956,0.000225387,0.0002293436,0.000013345,0.0001996322,0.000005489318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006519233,"about_ca_system_score_gemma":0.00002747702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000431441,"about_ca_topic_score_gemma":0.00007363036,"domain_scores_codex":[0.998593,0.0002837665,0.0003694008,0.000368327,0.0000875925,0.0002979076],"domain_scores_gemma":[0.9991625,0.0001120859,0.0002284866,0.0002884548,0.0001043546,0.0001041096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006932924,0.00004482082,0.1459855,0.00005076155,0.0003108475,0.0000208871,0.001269797,0.5653003,0.2760274,0.003561027,0.00001731775,0.007342007],"study_design_scores_gemma":[0.0004255815,0.000326191,0.1372265,0.00002584964,0.0002335206,0.0001250937,0.0002015977,0.8548494,0.005802542,0.0001582859,0.0003669613,0.0002585204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5433377,0.0001339481,0.4555929,0.00003703094,0.00006086102,0.0001207596,0.000005933549,0.0001842582,0.0005266524],"genre_scores_gemma":[0.9515861,0.000008990567,0.04772858,0.00003555119,0.0003198695,0.00001052469,0.0001917434,0.0000679841,0.00005069555],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4082484,"threshold_uncertainty_score":0.8525714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04298193117570142,"score_gpt":0.27244855928804,"score_spread":0.2294666281123385,"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."}}