{"id":"W2043731110","doi":"10.1016/j.acra.2014.04.005","title":"Differentiation of Lipoma From Liposarcoma on MRI Using Texture and Shape Analysis","year":2014,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Liposarcoma; Lipoma; Medicine; Kappa; Radiology; Magnetic resonance imaging; Confidence interval; Linear discriminant analysis; Nuclear medicine; Pathology; Sarcoma; Artificial intelligence; Mathematics; Computer science; Internal medicine; Geometry","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":[0.0003075288,0.0001311793,0.0005503568,0.0005219312,0.00004635406,0.000003902108,0.0001018267,0.0003012284,0.00008527419],"category_scores_gemma":[0.000461029,0.0001038849,0.00009658925,0.0003997112,0.0001547095,0.00002993241,0.00003626757,0.0007483662,0.000002964513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002225816,"about_ca_system_score_gemma":0.00001522565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001541393,"about_ca_topic_score_gemma":0.000001856876,"domain_scores_codex":[0.9988766,0.00016796,0.0003212153,0.0003022228,0.0001414774,0.0001904859],"domain_scores_gemma":[0.9990575,0.0004096175,0.0001822585,0.0002035847,0.0000262414,0.0001208006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001637618,0.00004580171,0.8097206,0.00004053748,0.001007968,0.000009629783,0.0005170953,0.0006384615,0.1224326,0.001868715,0.00086452,0.06269025],"study_design_scores_gemma":[0.0008375717,0.0001659777,0.4651892,0.00006601296,0.000936569,0.00005898553,0.00001943038,0.5297326,0.000578334,0.0008126659,0.001505341,0.00009720046],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9849356,0.0008538977,0.01116503,0.002539486,0.0001270564,0.00008806207,0.00000463135,0.00002675167,0.0002595256],"genre_scores_gemma":[0.9953642,0.0006702251,0.002052893,0.001356914,0.0004297991,0.000001917072,0.0000709024,0.0000146018,0.00003848143],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5290942,"threshold_uncertainty_score":0.4236301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01246941990581395,"score_gpt":0.2952536576779136,"score_spread":0.2827842377720996,"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."}}