{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005561271,0.00009700697,0.0002997067,0.0001152698,0.00004298997,0.000009208698,0.00004574377,0.00002710159,0.00004592013],"category_scores_gemma":[0.0003477231,0.00008468195,0.00007355422,0.0002670896,0.0004477827,0.0000946475,0.00004001302,0.0002037534,4.171089e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009172571,"about_ca_system_score_gemma":0.00003972172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004600218,"about_ca_topic_score_gemma":0.00001389457,"domain_scores_codex":[0.9988606,0.0001019699,0.0003830694,0.000241702,0.0003071331,0.0001055095],"domain_scores_gemma":[0.9992268,0.0002135093,0.000169313,0.0001009495,0.0001557526,0.000133682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001524612,0.00005621262,0.8980957,0.00007358458,0.0001488642,0.000003095724,0.0003306862,0.00001851995,0.01326562,0.000008066498,0.0002070052,0.08764022],"study_design_scores_gemma":[0.002261312,0.0002034465,0.8389128,0.0002532583,0.0004172331,0.000005927875,0.0002096573,0.1569809,0.0006157169,0.00002112022,0.00004753676,0.00007113151],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933508,0.002839677,0.0009833606,0.002230252,0.00005127171,0.0002769788,0.00004474213,0.0000237354,0.0001991877],"genre_scores_gemma":[0.9595224,0.001026288,0.03903659,0.0003216558,0.00003932679,0.00001078511,0.00003025812,0.00001140127,0.000001289043],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1569623,"threshold_uncertainty_score":0.345323,"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."}}