{"id":"W2089201234","doi":"10.1118/1.2712043","title":"Iterative threshold segmentation for PET target volume delineation","year":2007,"lang":"en","type":"article","venue":"Medical Physics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Segmentation; Iterative method; Pixel; Partial volume; Imaging phantom; Image resolution; Image segmentation; Contrast (vision); Artificial intelligence; Computer science; Iterative reconstruction; Resolution (logic); Algorithm; Computer vision; Mathematics; Pattern recognition (psychology); Optics; Physics","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":[0.0005103281,0.0001011156,0.0001700375,0.0000277744,0.00008155432,0.00001162001,0.00007760557,0.00006244564,0.0002474143],"category_scores_gemma":[0.0002154746,0.00008341882,0.00007704576,0.0001576499,0.0001016249,0.00006485958,0.00002203937,0.000201478,0.00002922893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005560531,"about_ca_system_score_gemma":0.00008717341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006980498,"about_ca_topic_score_gemma":0.00000172213,"domain_scores_codex":[0.9988056,0.000006797199,0.0002789804,0.0001980715,0.0004969275,0.0002136435],"domain_scores_gemma":[0.9992245,0.00009368594,0.00006431797,0.0001706805,0.0001727898,0.0002740015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004004293,0.00216474,0.022679,0.0005791131,0.0001729679,0.0001031127,0.0009732051,0.00001252579,0.03089124,0.03455398,0.5585034,0.3489663],"study_design_scores_gemma":[0.007143744,0.001175661,0.004376773,0.0007028077,0.0003713969,0.0001440354,0.0002636922,0.2892201,0.2971654,0.04763733,0.3509733,0.0008257224],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01722837,0.00003092371,0.9712164,0.009643528,0.00008457419,0.0006252992,0.00001310864,0.0001482129,0.001009516],"genre_scores_gemma":[0.8544389,0.00003489226,0.1355393,0.005758341,0.001665697,0.0001955277,0.0007754109,0.00003170036,0.00156021],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8372105,"threshold_uncertainty_score":0.3401721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02750679594687929,"score_gpt":0.3582276149140071,"score_spread":0.3307208189671278,"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."}}