{"id":"W3198829827","doi":"10.1038/s41598-021-96600-4","title":"Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"National Institute of Biomedical Imaging and Bioengineering; Peter MacCallum Foundation; Royal Australian and New Zealand College of Radiologists; Radiological Society of North America","keywords":"Radiomics; Feature (linguistics); Software; Effective diffusion coefficient; Open source software; Open source; Head and neck cancer; Computer science; Diffusion; Head and neck; Stability (learning theory); Cancer; Medicine; Artificial intelligence; Radiology; Machine learning; Surgery; Internal medicine; Physics; Magnetic resonance imaging","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":[0.002005196,0.0001598261,0.0004601357,0.0001488059,0.0001531345,0.0001521985,0.0001176979,0.00008754198,0.0001321081],"category_scores_gemma":[0.00152981,0.0001297822,0.00006818115,0.0006687472,0.0002880706,0.00006068864,0.0002721616,0.0004160643,0.00000100821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001811461,"about_ca_system_score_gemma":0.0005375849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002663042,"about_ca_topic_score_gemma":0.0001004806,"domain_scores_codex":[0.9974853,0.0001229833,0.0005166354,0.0008775377,0.0007082543,0.0002892839],"domain_scores_gemma":[0.9984035,0.00007673667,0.0002524087,0.0007741257,0.0002706779,0.0002225772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002833349,0.001541057,0.8180101,0.0005539596,0.00005235251,0.001470013,0.002245722,0.003471275,0.0820455,0.00003075832,0.01884095,0.07145496],"study_design_scores_gemma":[0.01049635,0.0006245332,0.5096213,0.006931063,0.0003528823,0.002497017,0.001374313,0.1076857,0.09625201,0.001681052,0.2613564,0.001127407],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935555,0.001167801,0.0003563719,0.001939499,0.002074052,0.0005673328,0.000007156258,0.00003126165,0.000301012],"genre_scores_gemma":[0.9961027,0.00006682955,0.00163333,0.0002587874,0.0000421915,0.00002161819,0.0001785851,0.00002384281,0.001672132],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3083888,"threshold_uncertainty_score":0.5292363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02270265121956816,"score_gpt":0.3277586097178452,"score_spread":0.305055958498277,"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."}}