{"id":"W4200122440","doi":"10.1109/embc46164.2021.9629614","title":"Pixel Distribution Learning for Vessel Segmentation under Multiple Scales","year":2021,"lang":"en","type":"article","venue":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Softmax function; Convolutional neural network; Pixel; Segmentation; Pattern recognition (psychology); Benchmark (surveying); Image segmentation; Deep learning; Layer (electronics)","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":[0.0003861752,0.0001633939,0.0003533867,0.00007432428,0.00006337737,0.00001240665,0.0001781392,0.0001252419,0.00008987442],"category_scores_gemma":[0.0009800211,0.0001245829,0.0002293656,0.000343281,0.0001854935,0.00007243981,0.00005417363,0.0003682622,0.00000316703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001082071,"about_ca_system_score_gemma":0.00007983699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009045059,"about_ca_topic_score_gemma":0.00004377156,"domain_scores_codex":[0.9988568,0.00005944834,0.0003935626,0.0002802387,0.000206081,0.0002039025],"domain_scores_gemma":[0.9986522,0.0003037123,0.0001519311,0.0001699854,0.0006675301,0.00005465201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001051791,0.0002014917,0.1026435,0.0002302876,0.0008522437,0.000002307528,0.001616535,0.02181866,0.8573623,0.001410556,0.01145985,0.002297072],"study_design_scores_gemma":[0.01253745,0.0006560994,0.1668365,0.003972741,0.001005689,0.0001775232,0.01451484,0.6347761,0.0673644,0.001607817,0.09536494,0.00118592],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6638925,0.000328118,0.3227553,0.01161971,0.0009657544,0.0001932055,0.00008898917,0.00003586661,0.0001205388],"genre_scores_gemma":[0.9919636,0.0005146237,0.004162883,0.0002171284,0.0003751664,0.00002759308,0.0011627,0.00001445589,0.001561838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7899979,"threshold_uncertainty_score":0.5080343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04046618692580766,"score_gpt":0.3344505071326336,"score_spread":0.293984320206826,"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."}}