{"id":"W3015481932","doi":"10.1016/j.ejmp.2020.03.018","title":"Bridging the gap between micro- and macro-scales in medical imaging with textural analysis – A biological basis for CT radiomics classifiers?","year":2020,"lang":"en","type":"article","venue":"Physica Medica","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network; Hospital for Sick Children; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Radiomics; Digital pathology; Attenuation; Artificial intelligence; Pattern recognition (psychology); Pixel; Feature (linguistics); Computer science; Nuclear medicine; Medicine; Physics; Optics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00216903,0.0006694717,0.0009285308,0.001693239,0.0004118053,0.003514879,0.001125092,0.001761305,0.003461298],"category_scores_gemma":[0.01192031,0.0004467152,0.0003719038,0.00109395,0.003054443,0.008162789,0.00163872,0.001827122,0.001575472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003715156,"about_ca_system_score_gemma":0.0003733124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004547319,"about_ca_topic_score_gemma":0.0004815884,"domain_scores_codex":[0.9994185,0.000159828,0.00005081749,0.0001456782,0.0001781734,0.00004701804],"domain_scores_gemma":[0.9952741,0.002558193,0.0007063161,0.0006565175,0.0005755451,0.0002293587],"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":[0.0006493742,0.0002132932,0.01298542,0.001741673,0.0003260096,0.0005989859,0.001443282,0.02106091,0.1301031,0.1426652,0.008205333,0.6800074],"study_design_scores_gemma":[0.0000698989,0.0005175492,0.04193605,0.0009250422,0.0002407646,0.001877781,0.0019024,0.3055699,0.03434419,0.5789223,0.03344016,0.0002539882],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.118037,0.02670989,0.8203163,0.01591779,0.001001628,0.0001132178,0.0004811051,0.0007281828,0.01669488],"genre_scores_gemma":[0.8148159,0.01113446,0.165181,0.00198647,0.002450649,0.0001164646,0.0002775171,0.0003396165,0.003697867],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003514879,"threshold_uncertainty_score":0.01157922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02375644555252346,"score_gpt":0.2993892027485168,"score_spread":0.2756327571959933,"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."}}