{"id":"W3033672396","doi":"10.18383/j.tom.2020.00004","title":"Multisite Technical and Clinical Performance Evaluation of Quantitative Imaging Biomarkers from 3D FDG PET Segmentations of Head and Neck Cancer Images","year":2020,"lang":"en","type":"article","venue":"Tomography","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; Holden Comprehensive Cancer Center, University of Iowa; National Institutes of Health","keywords":"Segmentation; Robustness (evolution); Positron emission tomography; Artificial intelligence; Computer science; Medicine; Medical physics; Pattern recognition (psychology); Radiology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02585733,0.0006538265,0.0006647327,0.002598344,0.0004089062,0.001691323,0.0007051334,0.001005584,0.0006723723],"category_scores_gemma":[0.0713074,0.0003936505,0.0006873999,0.001576967,0.001056039,0.000927994,0.001281411,0.0004186729,0.000388298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000805474,"about_ca_system_score_gemma":0.0005460895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002857413,"about_ca_topic_score_gemma":0.002356343,"domain_scores_codex":[0.9901599,0.005300072,0.001044026,0.001726859,0.00150075,0.0002683844],"domain_scores_gemma":[0.9409257,0.0396227,0.005839515,0.006412778,0.006562086,0.0006371471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004921375,0.000417079,0.6351365,0.0004426088,0.00176921,0.0002309076,0.001110642,0.133961,0.03904447,0.0008181593,0.001230762,0.1809172],"study_design_scores_gemma":[0.000126431,0.001471504,0.5348481,0.00004364478,0.0004091321,0.0006280064,0.0004039114,0.4177748,0.0417925,0.001185625,0.001165246,0.0001511858],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.948193,0.0004828034,0.04897181,0.0000964737,0.00002376401,0.0001397638,0.0007113758,0.0004626809,0.000918344],"genre_scores_gemma":[0.987735,0.00004472799,0.01116411,0.00001633013,0.00001332118,0.0000552573,0.0007967846,0.00005023371,0.0001242985],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02585733,"threshold_uncertainty_score":0.1367483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0361437175790271,"score_gpt":0.394729771033585,"score_spread":0.3585860534545579,"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."}}