{"id":"W2771823977","doi":"10.15353/vsnl.v3i1.173","title":"Skin Lesion Segmentation using Deep Hypercolumn Descriptors","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Jaccard index; Segmentation; Artificial intelligence; Skin lesion; Pattern recognition (psychology); Computer science; Lesion; Image segmentation; Index (typography); Medicine; Dermatology; Pathology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0003463651,0.00008834845,0.0002121254,0.0001979477,0.0003346775,0.0002893804,0.00006094503,0.00002271149,0.00001291666],"category_scores_gemma":[0.00005260285,0.00007119267,0.00007207847,0.00003401455,0.00004532929,0.0003106733,0.00003302563,0.00009754192,0.000004180818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009950664,"about_ca_system_score_gemma":0.00004373469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004286488,"about_ca_topic_score_gemma":9.155658e-7,"domain_scores_codex":[0.9990101,0.00004481027,0.0003850163,0.00008803526,0.0003848594,0.00008722182],"domain_scores_gemma":[0.9989788,0.00003398556,0.0005068157,0.0000969559,0.0002761387,0.0001072921],"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":[0.00163579,0.0009024825,0.1225331,0.001220071,0.0007249817,0.00140184,0.003135501,0.07833715,0.1120562,0.001569814,0.01290411,0.663579],"study_design_scores_gemma":[0.004334583,0.0005113048,0.1818235,0.001139135,0.0002420334,0.01437424,0.003186769,0.7815921,0.0003411498,0.0004302531,0.01177542,0.000249451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8950657,0.00044693,0.1016196,0.0006453703,0.001398318,0.0001994897,8.249936e-7,0.00001271102,0.000611067],"genre_scores_gemma":[0.9938918,0.00003474515,0.005454031,0.0001385363,0.000272672,6.399084e-7,0.000002082714,0.00001077923,0.00019473],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.703255,"threshold_uncertainty_score":0.2903153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02835215583172841,"score_gpt":0.322665110409059,"score_spread":0.2943129545773306,"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."}}