{"id":"W4387218716","doi":"10.1007/978-3-031-37007-6_10","title":"Deep Learning-Based Pixel-Level Colonoscopy Analysis","year":2023,"lang":"en","type":"book-chapter","venue":"Conference proceedings of the Society for Experimental Mechanics","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"Research Manitoba","keywords":"Overfitting; Artificial intelligence; Segmentation; Computer science; Intersection (aeronautics); Convolutional neural network; Deep learning; Pixel; Pattern recognition (psychology); Image segmentation; Colonoscopy; Artificial neural network; Machine learning; Colorectal cancer; Cancer; Medicine; Cartography; Geography; Internal 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003365659,0.0006112608,0.0005309709,0.0007882204,0.0001809594,0.0008451874,0.0008711519,0.0006827758,0.005449269],"category_scores_gemma":[0.0007637914,0.0003742993,0.0007018466,0.0005749144,0.0002205561,0.0005925343,0.0007706291,0.0008218689,0.001988371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004311851,"about_ca_system_score_gemma":0.0006294367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003969856,"about_ca_topic_score_gemma":0.008712529,"domain_scores_codex":[0.9998533,0.0000163816,0.000006750814,0.00003518904,0.00005780671,0.00003059566],"domain_scores_gemma":[0.9997348,0.00008787929,0.00001874366,0.00003747189,0.0001007151,0.0000204385],"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":[0.000216977,0.000147959,0.001513641,0.0001095991,0.00009938311,0.00009437082,0.00003071548,0.1220717,0.04043661,0.003967378,0.01294256,0.8183692],"study_design_scores_gemma":[0.00000341552,0.00002175739,0.0008292827,0.00001180376,0.00001305797,0.0000528227,0.000006133237,0.9883151,0.006839632,0.001916599,0.001982588,0.000007722955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02749634,0.001356693,0.9620265,0.0005088882,0.0001663447,0.00005125183,0.0007254813,0.002716473,0.004951998],"genre_scores_gemma":[0.426152,0.002224079,0.5376576,0.0004871617,0.0002427953,0.0001104898,0.003033784,0.0005545268,0.02953752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005449269,"threshold_uncertainty_score":0.0182296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05008782829672082,"score_gpt":0.2905304434876258,"score_spread":0.240442615190905,"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."}}