{"id":"W4286487934","doi":"10.1038/s41598-022-16375-0","title":"Minimising multi-centre radiomics variability through image normalisation: a pilot study","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"European Regional Development Fund; Institució Catalana de Recerca i Estudis Avançats; Ministerio de Economía y Competitividad; European Commission; Ministerio de Ciencia e Innovación; British Heart Foundation; Horizon 2020; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Barts Charity; Ministerio de Ciencia, Innovación y Universidades","keywords":"Pattern recognition (psychology); Artificial intelligence; Histogram; Feature (linguistics); Computer science; Matching (statistics); Radiomics; Similarity (geometry); Magnetic resonance imaging; Image (mathematics); Medicine; Radiology; Pathology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005819869,0.0001851954,0.0003540811,0.0001373905,0.00112964,0.0002228892,0.0001637788,0.00002013013,0.000936894],"category_scores_gemma":[0.001314833,0.0001738412,0.0001047689,0.0006804132,0.0002996023,0.0002133316,0.00027822,0.0005842109,0.00001087454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002857157,"about_ca_system_score_gemma":0.0003577025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001762101,"about_ca_topic_score_gemma":0.00000619806,"domain_scores_codex":[0.9964766,0.0003302424,0.0007338068,0.0009967093,0.001055965,0.0004066816],"domain_scores_gemma":[0.99806,0.00009353107,0.0003364682,0.001133133,0.0001745385,0.000202319],"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":[0.0004826284,0.02042946,0.7494764,0.0003060261,0.0003893388,0.01542819,0.033353,0.002269516,0.09261515,0.0002158866,0.07512638,0.009907958],"study_design_scores_gemma":[0.02082074,0.00506397,0.1321185,0.000278915,0.001817917,0.02352471,0.03242338,0.1980892,0.005644252,0.01021938,0.5670426,0.002956336],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9820033,0.00006575814,0.005286703,0.001736767,0.007542419,0.001068057,0.000003544367,0.0001626949,0.002130812],"genre_scores_gemma":[0.9799137,0.000001208889,0.01621891,0.0003113412,0.0001577403,0.00003755148,0.000104697,0.00003201146,0.003222901],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6173579,"threshold_uncertainty_score":0.9999764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03060934115460844,"score_gpt":0.3093892596280017,"score_spread":0.2787799184733933,"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."}}