{"id":"W1693743017","doi":"10.1120/jacmp.v8i2.2367","title":"Comparison of three image segmentation techniques for target volume delineation in positron emission tomography","year":2007,"lang":"en","type":"article","venue":"Journal of Applied Clinical Medical Physics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Cancer Foundation; Institute of Cancer Research; BC Cancer Agency","funders":"","keywords":"Positron emission tomography; Sobel operator; Thresholding; Segmentation; Imaging phantom; Computer science; Artificial intelligence; Image segmentation; Tomography; Nuclear medicine; Computer vision; Image processing; Edge detection; Physics; Image (mathematics); Medicine; Optics","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":[0.003455,0.0001426751,0.0007614621,0.0001376423,0.00003537618,0.000007263798,0.0002077127,0.000278586,0.00003766238],"category_scores_gemma":[0.0007270785,0.0001113171,0.000307795,0.0003595498,0.0002555114,0.00007430364,0.00003989826,0.0008077462,0.000001209868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005868946,"about_ca_system_score_gemma":0.0001778501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005068619,"about_ca_topic_score_gemma":0.000001591696,"domain_scores_codex":[0.9964784,0.00002758638,0.002204725,0.0001930578,0.0008701175,0.0002261453],"domain_scores_gemma":[0.9973915,0.0006551098,0.0009508417,0.0002008038,0.0004042183,0.0003974899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002783702,0.005747631,0.1347219,0.0004005766,0.0001391587,0.00001638559,0.0001755414,0.000005047861,0.1078408,0.00284975,0.02168435,0.7236351],"study_design_scores_gemma":[0.01087043,0.005631826,0.05387103,0.002218041,0.0007531053,0.00004018119,0.000441014,0.03745192,0.7972251,0.07630874,0.01457829,0.0006103782],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1666533,0.00004211689,0.8299503,0.002186566,0.00008525265,0.0006403044,0.000003894403,0.00003594869,0.0004022813],"genre_scores_gemma":[0.6803285,0.00004634633,0.318331,0.0005035009,0.0007162648,0.0000180493,0.0000329796,0.00001734067,0.000005963754],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7230248,"threshold_uncertainty_score":0.453938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05088020849272552,"score_gpt":0.4519482689171648,"score_spread":0.4010680604244393,"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."}}