{"id":"W2963464382","doi":"10.1007/s11307-019-01411-9","title":"Machine Learning Methods for Optimal Radiomics-Based Differentiation Between Recurrence and Inflammation: Application to Nasopharyngeal Carcinoma Post-therapy PET/CT Images","year":2019,"lang":"en","type":"article","venue":"Molecular Imaging and Biology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":74,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Nasopharyngeal carcinoma; Radiomics; Random forest; Artificial intelligence; Support vector machine; Medicine; Feature selection; Positron emission tomography; Magnetic resonance imaging; Machine learning; Receiver operating characteristic; Pattern recognition (psychology); Nuclear medicine; Radiology; Computer science; Radiation therapy","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":[0.0005554178,0.0001789775,0.0003380633,0.0001749718,0.0001106166,0.00004480865,0.00007521813,0.00002134975,0.0000074073],"category_scores_gemma":[0.0002289554,0.0001554988,0.00006079075,0.00009990106,0.00008350925,0.00004648581,0.00004436949,0.000266587,0.000002227739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002828968,"about_ca_system_score_gemma":0.00003692164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007914806,"about_ca_topic_score_gemma":2.216018e-7,"domain_scores_codex":[0.9988434,0.0001821849,0.0002350209,0.0004356831,0.00006120406,0.0002425227],"domain_scores_gemma":[0.9992797,0.0002141825,0.0001066916,0.0001604177,0.00009644314,0.0001425391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001120006,0.00001180563,0.3046797,0.0000703434,0.00003014476,0.000006978225,0.00004805214,0.00005769958,0.3388917,0.00009387683,0.000008871749,0.3559889],"study_design_scores_gemma":[0.006399404,0.001151584,0.1751446,0.000106951,0.0001849893,0.0004272613,0.00005348366,0.7162393,0.07968716,0.0004071948,0.01964394,0.0005542113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6782906,0.001575691,0.3135991,0.005897827,0.00006202799,0.0005036455,0.000007937992,0.00004066146,0.0000225546],"genre_scores_gemma":[0.9238827,0.00007280387,0.07454468,0.0008395475,0.00009716052,0.00005144736,0.0004644091,0.00002551176,0.00002174722],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7161816,"threshold_uncertainty_score":0.6341059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01102335113908815,"score_gpt":0.3293432638001109,"score_spread":0.3183199126610227,"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."}}