{"id":"W3160038630","doi":"10.1016/j.compbiomed.2021.104449","title":"Hybrid dilation and attention residual U-Net for medical image segmentation","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Natural Science Foundation of Jiangxi Province; National Natural Science Foundation of China","keywords":"Dilation (metric space); Artificial intelligence; Residual; Segmentation; Computer science; Image segmentation; Computer vision; Pattern recognition (psychology); Algorithm; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002359868,0.00006742025,0.0001252907,0.00005426967,0.00007596658,0.000008255552,0.00009995584,0.00004730176,0.000003332601],"category_scores_gemma":[0.00008903948,0.00005800766,0.000008190425,0.0001063722,0.0001602072,0.0001089934,0.0001104059,0.00007783634,5.382036e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001259139,"about_ca_system_score_gemma":0.00001882929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002440206,"about_ca_topic_score_gemma":0.00000738545,"domain_scores_codex":[0.9992805,0.00006163665,0.0001798674,0.0002978595,0.00006090626,0.0001192769],"domain_scores_gemma":[0.9993675,0.0003581306,0.00005024148,0.0001220738,0.00004098013,0.00006106428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004110819,0.00007440666,0.01195408,0.00007011967,0.00002630408,0.00004668078,0.0004726011,0.00003094338,0.03183257,0.2441722,0.006445742,0.7048333],"study_design_scores_gemma":[0.008849883,0.0008915332,0.1716979,0.0004062283,0.00004116441,0.0007431153,0.0001331745,0.3752834,0.004989837,0.4265136,0.009898739,0.0005513928],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08340444,0.0005813277,0.9025748,0.01292869,0.0002799072,0.0001558826,0.000001616727,0.00003033867,0.00004297005],"genre_scores_gemma":[0.6629655,0.001273301,0.3316411,0.003230031,0.0004881295,0.00007354057,0.0002742673,0.000007622615,0.00004657254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7042819,"threshold_uncertainty_score":0.2365484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01674399251295705,"score_gpt":0.3360908776720004,"score_spread":0.3193468851590434,"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."}}