{"id":"W2912468918","doi":"10.1038/s41598-018-37984-8","title":"Combining Multiple Magnetic Resonance Imaging Sequences Provides Independent Reproducible Radiomics Features","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence Nationale de la Recherche; McMaster University","keywords":"Magnetic resonance imaging; Concordance; Concordance correlation coefficient; Reproducibility; Coronal plane; Correlation; Hierarchical clustering; Medicine; Artificial intelligence; Radiology; Radiomics; Nuclear medicine; Computer science; Cluster analysis; Pattern recognition (psychology); Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003123574,0.0002294581,0.0004116768,0.0002819927,0.0003165566,0.0004053896,0.000200117,0.00007088889,0.0001758695],"category_scores_gemma":[0.001677469,0.0001924995,0.0001384952,0.0005269132,0.000404821,0.0002583411,0.0001399595,0.0005842608,0.00005341964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001174618,"about_ca_system_score_gemma":0.0003780586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002006445,"about_ca_topic_score_gemma":0.000008797925,"domain_scores_codex":[0.9962968,0.00006828454,0.0006202747,0.001519122,0.0009450017,0.0005505541],"domain_scores_gemma":[0.9976093,0.00009835968,0.0003100456,0.001529137,0.0001993713,0.0002538266],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005009762,0.0001106203,0.7935911,0.0001434149,0.00001388066,0.00167467,0.0008384609,0.0002233342,0.117427,0.00009610212,0.01403255,0.07179867],"study_design_scores_gemma":[0.003895362,0.0004055413,0.2904603,0.002046002,0.0002194006,0.02126099,0.001522506,0.06078044,0.05160061,0.01076548,0.555624,0.00141936],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9742777,0.008313775,0.00008658408,0.002104308,0.008229127,0.0008476265,0.000001116747,0.0002073301,0.005932397],"genre_scores_gemma":[0.9780367,0.00002888709,0.00439036,0.0003726317,0.0001821835,0.00002237065,0.00004507475,0.00004137231,0.0168804],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5415915,"threshold_uncertainty_score":0.7849902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009597508499225067,"score_gpt":0.2641475245877596,"score_spread":0.2545500160885345,"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."}}