{"id":"W3199152014","doi":"10.1016/j.cpet.2021.06.001","title":"Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging","year":2021,"lang":"en","type":"review","venue":"PET Clinics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Simon Fraser University","keywords":"Segmentation; Artificial intelligence; Convolutional neural network; Workflow; Medical imaging; Computer science; Deep learning; Image segmentation; Pattern recognition (psychology); Machine learning; Medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001705452,0.0004538289,0.002420967,0.0002916003,0.00006900043,0.00009462171,0.0002619261,0.0001832249,0.0005358894],"category_scores_gemma":[0.002825095,0.0003732852,0.0006425488,0.0005721286,0.0001917542,0.00005675778,0.0001307049,0.002224276,0.0001244928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004606553,"about_ca_system_score_gemma":0.001340432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005805853,"about_ca_topic_score_gemma":0.000008760831,"domain_scores_codex":[0.9959293,0.0005130853,0.001758082,0.0008134107,0.0005077537,0.0004783784],"domain_scores_gemma":[0.9972779,0.001401708,0.0005389656,0.0004432002,0.0001108939,0.0002273056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001797088,0.0003325818,0.0001243159,0.003772441,0.0000571471,0.003672841,0.00005072101,0.00006326428,3.943104e-7,0.0005090659,0.0003859683,0.9910133],"study_design_scores_gemma":[0.000589265,0.0002295322,0.00002776475,0.01812723,0.001331527,0.0008856954,0.000225923,0.02309807,0.000002505521,0.0009973098,0.953861,0.0006241784],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001870881,0.9773055,0.01616694,0.002953857,0.001875903,0.0009132341,0.00002495313,0.0001187789,0.0004537954],"genre_scores_gemma":[0.0003697891,0.9690311,0.02659553,0.001553159,0.000980546,0.00009203994,0.001198375,0.00008144876,0.00009802179],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9903891,"threshold_uncertainty_score":0.9998719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1305360380263752,"score_gpt":0.456635040400157,"score_spread":0.3260990023737818,"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."}}