{"id":"W2952786159","doi":"10.48550/arxiv.1809.10245","title":"Cylindrical Transform: 3D Semantic Segmentation of Kidneys With Limited Annotated Images","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Segmentation; Convolutional neural network; Computer science; Pattern recognition (psychology); Computer vision; Image segmentation; Dependency (UML)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004811192,0.0007502321,0.0005698704,0.001437804,0.0002655309,0.001133965,0.0008376621,0.0008892582,0.001718287],"category_scores_gemma":[0.001737687,0.0005247471,0.0008181199,0.00129028,0.0005880447,0.001495303,0.001108959,0.0007621403,0.0007647502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004402301,"about_ca_system_score_gemma":0.00104485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002794759,"about_ca_topic_score_gemma":0.004303994,"domain_scores_codex":[0.9996376,0.00006404235,0.00002425105,0.000111624,0.0001229949,0.00003946186],"domain_scores_gemma":[0.9995456,0.0001234166,0.0000795337,0.0001245142,0.00009275324,0.00003428092],"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":[0.0008266606,0.0001201273,0.00451333,0.0004842745,0.0001581894,0.0006153285,0.0004745893,0.1267221,0.1667564,0.01841659,0.007211452,0.673701],"study_design_scores_gemma":[0.00003232538,0.0001797783,0.003505419,0.00005217138,0.00007409874,0.001571551,0.0001609318,0.8922243,0.071531,0.01533533,0.01526105,0.00007205598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01888975,0.0003184563,0.9782899,0.0001265057,0.0000307055,0.00004940131,0.0002357693,0.001176289,0.0008832596],"genre_scores_gemma":[0.240027,0.000744185,0.7550005,0.0002123554,0.0001091228,0.0001316742,0.001612296,0.000506031,0.001656791],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002794759,"threshold_uncertainty_score":0.005748212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04291435884004442,"score_gpt":0.2130733856342832,"score_spread":0.1701590267942388,"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."}}