{"id":"W2916122096","doi":"10.1016/j.cmpb.2019.02.011","title":"Polymorph segmentation representation for medical image computing","year":2019,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Cancer Care Ontario; Canarie","keywords":"Computer science; Representation (politics); Artificial intelligence; Segmentation; Image segmentation; Computer vision; Image (mathematics); Scale-space segmentation; Pattern recognition (psychology); Computer graphics (images)","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":[],"consensus_categories":[],"category_scores_codex":[0.002361344,0.0001725464,0.0003225309,0.0003845612,0.00006977589,0.00019038,0.0004728517,0.000109899,0.000008413412],"category_scores_gemma":[0.00003615463,0.0001495852,0.00006159507,0.0008981113,0.00008900632,0.0002762777,0.0003872439,0.0001305943,0.000001396907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002207688,"about_ca_system_score_gemma":0.00003721561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003758171,"about_ca_topic_score_gemma":0.000001896045,"domain_scores_codex":[0.9980476,0.0002651091,0.0005124705,0.0005810802,0.0003153906,0.0002783808],"domain_scores_gemma":[0.9987965,0.0004388873,0.0001540265,0.0003558893,0.0001191417,0.0001356189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007032393,0.00007499201,0.005542833,0.0000811618,0.00001294545,0.000004185751,0.0007192394,8.883757e-7,0.0007191148,0.0405335,0.0001486816,0.9521554],"study_design_scores_gemma":[0.001506436,0.0006717204,0.004156174,0.0002126254,0.000005963233,0.00003946696,0.00004435331,0.9764365,0.001639865,0.01166959,0.003388301,0.0002290053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01420399,0.0002630228,0.9826139,0.0009451105,0.0008039549,0.0008876057,6.546375e-7,0.0002380453,0.000043711],"genre_scores_gemma":[0.03520406,0.00007667272,0.9636608,0.0007356326,0.0002143439,0.00003804453,0.00004251051,0.00001298896,0.00001490858],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9764356,"threshold_uncertainty_score":0.6099909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05063992210272202,"score_gpt":0.4334800562401838,"score_spread":0.3828401341374618,"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."}}