{"id":"W3178812510","doi":"10.1109/icicsp55539.2022.10050624","title":"Transclaw U-Net: Claw U-Net With Transformers for Medical Image Segmentation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Claw; Net (polyhedron); Image segmentation; Artificial intelligence; Computer science; Segmentation; Computer vision; Mathematics; Engineering; Geometry","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003147293,0.0003584235,0.0003456279,0.0001054586,0.000304689,0.0001361095,0.001526694,0.0001933595,0.0006568813],"category_scores_gemma":[0.000007847741,0.0003110883,0.0001844445,0.0003811115,0.0001440897,0.0003754506,0.0002746938,0.000756518,0.00001049759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001494116,"about_ca_system_score_gemma":0.0003401714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000310102,"about_ca_topic_score_gemma":0.0001529552,"domain_scores_codex":[0.997071,0.00007048985,0.00047367,0.001055028,0.0008735846,0.0004562768],"domain_scores_gemma":[0.9986116,0.0002544595,0.0001644665,0.0006338607,0.00008433639,0.0002512675],"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":[0.0004262876,0.0008592926,0.00006880618,0.0009409086,0.0005301292,0.00007731813,0.003109099,0.03273582,0.003712029,0.4436713,0.03406515,0.4798039],"study_design_scores_gemma":[0.004868128,0.001200547,0.0001886595,0.0001785589,0.0002380255,0.0001347574,0.0004312054,0.6480642,0.01311823,0.0900581,0.2385857,0.002933915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004611719,0.00006790432,0.9793614,0.009983559,0.0002944041,0.002247397,0.00007530029,0.000472702,0.007036176],"genre_scores_gemma":[0.05886443,0.0003484371,0.927507,0.003611268,0.0002617914,0.006600691,0.0008190379,0.0001041836,0.001883159],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6153284,"threshold_uncertainty_score":0.9999341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01672159803478539,"score_gpt":0.2993248054391024,"score_spread":0.282603207404317,"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."}}