{"id":"W2584167071","doi":"10.1007/978-3-319-61188-4_7","title":"Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study","year":2017,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre","funders":"National Center for Research Resources; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute","keywords":"COPD; Pulmonary disease; Subtyping; Radiological weapon; Mesa; Computer science; Artificial intelligence; Texture (cosmology); Homogeneous; Radiology; Pulmonary emphysema; Lung disease; Medicine; Lung; Image (mathematics); Internal medicine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001486353,0.0009295979,0.0008158137,0.001582784,0.0003641684,0.001039912,0.0008081579,0.001276428,0.001331047],"category_scores_gemma":[0.003218874,0.0003392601,0.001517153,0.0005678161,0.0003707414,0.0006607075,0.0007146625,0.0007985256,0.0006924674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000289384,"about_ca_system_score_gemma":0.0004277386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003718241,"about_ca_topic_score_gemma":0.004828443,"domain_scores_codex":[0.9995344,0.0001437587,0.00003121037,0.0001657887,0.00007195394,0.00005291604],"domain_scores_gemma":[0.998244,0.001001048,0.00008917795,0.000324897,0.0002076158,0.0001331866],"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":[0.01032492,0.003865615,0.2083943,0.001429725,0.002776844,0.002580347,0.001092617,0.07226925,0.0692348,0.001345524,0.01860193,0.6080841],"study_design_scores_gemma":[0.0006330801,0.002295681,0.181971,0.0001719772,0.001427637,0.004393441,0.001471464,0.769962,0.02790983,0.002675775,0.006947619,0.0001405548],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9733692,0.001770522,0.02073198,0.0002260267,0.00006495127,0.0001317853,0.002013997,0.0006479109,0.001043596],"genre_scores_gemma":[0.9769353,0.0003678078,0.01733379,0.00006227462,0.00005923083,0.00003770567,0.003886824,0.0001020213,0.00121508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003718241,"threshold_uncertainty_score":0.007860661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0238353943230537,"score_gpt":0.3108089474089106,"score_spread":0.2869735530858569,"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."}}