{"id":"W4411897422","doi":"10.1186/s12880-025-01774-2","title":"Enhancing radiomics robustness using bayesian penalized likelihood PET reconstruction: application to Phantom and non-small cell lung cancer patient studies","year":2025,"lang":"en","type":"article","venue":"BMC Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"University of Tabriz; Tehran University of Medical Sciences and Health Services; Tabriz University of Medical Sciences","keywords":"Radiomics; Imaging phantom; Robustness (evolution); Bayesian probability; Lung cancer; Computer science; Artificial intelligence; Medical physics; Radiology; Medicine; Oncology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009000715,0.0003075193,0.0006742419,0.0003481678,0.0003078284,0.00007516325,0.0001708544,0.00007836034,0.00006121064],"category_scores_gemma":[0.001022672,0.000275862,0.0001046669,0.0005090362,0.0002189155,0.000117405,0.0002266759,0.0005867669,0.000001714673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003480843,"about_ca_system_score_gemma":0.0008938881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002889743,"about_ca_topic_score_gemma":0.00009699574,"domain_scores_codex":[0.9974372,0.0001219887,0.0007067695,0.0006824189,0.0005078971,0.000543711],"domain_scores_gemma":[0.9982926,0.0003746029,0.0001885537,0.0003224183,0.0002276202,0.000594211],"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":[0.0003511267,0.0002953029,0.4085946,0.005884032,0.0004727933,0.0002681212,0.003096286,0.002743055,0.04719693,0.0001064497,0.002075827,0.5289154],"study_design_scores_gemma":[0.003085911,0.00002764541,0.00214892,0.004407212,0.0005068254,0.0005642944,0.002434375,0.9816036,0.004252998,0.00007179467,0.0005349204,0.0003614863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5025811,0.003988229,0.4894338,0.00247773,0.0006729045,0.000523712,0.000001567332,0.0000702903,0.0002506639],"genre_scores_gemma":[0.8804603,0.001200667,0.1136637,0.0036912,0.0006234319,0.0001688338,0.00001194731,0.00005936007,0.0001205358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9788606,"threshold_uncertainty_score":0.9999694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008800969502012123,"score_gpt":0.3139603146497805,"score_spread":0.3051593451477683,"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."}}