{"id":"W2050560110","doi":"10.1016/j.cviu.2014.03.011","title":"Hybrid structural and texture distinctiveness vector field convolution for region segmentation","year":2014,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Initialization; Optimal distinctiveness theory; Artificial intelligence; Computer science; Pattern recognition (psychology); Convolution (computer science); Computer vision; Segmentation; Texture (cosmology); Convergence (economics); Texture filtering; Feature (linguistics); Image texture; Image segmentation; Image (mathematics); Artificial neural network","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":[0.0002145849,0.0001331864,0.0001456666,0.00009264518,0.0002744524,0.0003602905,0.0001429367,0.00004214993,0.000004195021],"category_scores_gemma":[0.00005548999,0.0001133801,0.00003063528,0.0000706553,0.00008546194,0.0007620379,0.0001444076,0.00008355448,6.055781e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008058271,"about_ca_system_score_gemma":0.00001006302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003846008,"about_ca_topic_score_gemma":6.655674e-7,"domain_scores_codex":[0.999065,0.0000816026,0.0001787807,0.0003647924,0.0001485517,0.0001612114],"domain_scores_gemma":[0.9992718,0.000321134,0.00009586943,0.0001550462,0.0000551128,0.0001011152],"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":[0.00008952941,0.00003007635,0.0003310132,0.0002724823,0.00002597778,0.00001149178,0.0009275087,0.000003798533,0.02222307,0.1088794,0.009482803,0.8577228],"study_design_scores_gemma":[0.001585792,0.0008490235,0.001663778,0.0001717533,0.00001601761,0.00009897851,0.0001148079,0.9187644,0.02413754,0.05195343,0.0003039088,0.0003405654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004473708,0.0000382808,0.9938761,0.0008235654,0.0002888643,0.0003031965,0.000001613738,0.0001514392,0.00004323748],"genre_scores_gemma":[0.7395737,0.00001989328,0.2595838,0.0006772358,0.00009905232,0.000009112601,0.00001215255,0.000007389559,0.00001767132],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9187606,"threshold_uncertainty_score":0.4623508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02420147694611768,"score_gpt":0.2931098703540574,"score_spread":0.2689083934079397,"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."}}