{"id":"W4233516421","doi":"10.32920/ryerson.14644602.v1","title":"Improved diagnosis and navigation for CT colonography","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Contouring; Artificial intelligence; Segmentation; Computer science; Computer vision; Feature (linguistics); Texture (cosmology); Set (abstract data type); Pattern recognition (psychology); Image (mathematics); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007613842,0.0006085293,0.0004888633,0.001513826,0.0002529409,0.0007259764,0.0005622049,0.001219774,0.004230551],"category_scores_gemma":[0.003487147,0.0003446604,0.0004789474,0.0007798442,0.0006261327,0.001264287,0.0007731911,0.0009028212,0.002015553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004783727,"about_ca_system_score_gemma":0.0006242691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001213081,"about_ca_topic_score_gemma":0.001469504,"domain_scores_codex":[0.9990537,0.0002794574,0.00005139195,0.0001407282,0.0004464749,0.00002819212],"domain_scores_gemma":[0.9991836,0.0003466376,0.00006064157,0.0001182254,0.0002551684,0.00003577829],"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":[0.0003258537,0.00006479938,0.002452373,0.0006324204,0.00004894188,0.0004804302,0.0001440426,0.01291536,0.09107111,0.02683041,0.009848674,0.8551856],"study_design_scores_gemma":[0.0003407365,0.0007613452,0.01206922,0.0005762614,0.0003606346,0.01696759,0.0000973969,0.4042582,0.1069599,0.07270028,0.3846506,0.0002579057],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007586113,0.01204812,0.974067,0.001426241,0.0004541092,0.0000477891,0.00009136977,0.001473578,0.002805612],"genre_scores_gemma":[0.06530792,0.007892055,0.9214947,0.0004828122,0.000924117,0.000080494,0.0003163645,0.0002508183,0.003250724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004230551,"threshold_uncertainty_score":0.01415265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02426622471328224,"score_gpt":0.3143882006970169,"score_spread":0.2901219759837347,"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."}}