{"id":"W3141431470","doi":"10.3390/jimaging7040067","title":"Skin Lesion Segmentation Using Deep Learning with Auxiliary Task","year":2021,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Segmentation; Jaccard index; Task (project management); Feature (linguistics); Pattern recognition (psychology); Multi-task learning; Deep learning; Artificial neural network; Focus (optics); Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004275609,0.00108939,0.0008363992,0.0007809337,0.0002574805,0.0006147525,0.00126085,0.0009884401,0.001651745],"category_scores_gemma":[0.0007827705,0.0003463537,0.0007980798,0.0005354027,0.0002785813,0.0009596705,0.0007903734,0.0008981649,0.0007799813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005348088,"about_ca_system_score_gemma":0.0007123805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003531101,"about_ca_topic_score_gemma":0.005220646,"domain_scores_codex":[0.9997136,0.00003388936,0.00001576794,0.0001060015,0.00007801815,0.00005269295],"domain_scores_gemma":[0.9996812,0.00005861462,0.00004596321,0.00006838108,0.0001073604,0.00003836504],"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":[0.0004243785,0.000407133,0.004269224,0.0002304163,0.0001910238,0.0003523976,0.00007837316,0.1806705,0.0623995,0.002247946,0.01148424,0.7372448],"study_design_scores_gemma":[0.00001110371,0.00007852572,0.000943645,0.000009442269,0.00003219399,0.0001249361,0.00001030836,0.9849738,0.01113063,0.001543729,0.001130555,0.00001106597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.10549,0.001287796,0.8820712,0.0004066295,0.0001831866,0.0001798212,0.0004887744,0.006484265,0.003408443],"genre_scores_gemma":[0.7813469,0.0006338724,0.2061416,0.0006824044,0.0001573515,0.0001563444,0.002487648,0.0002772379,0.008116623],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003531101,"threshold_uncertainty_score":0.00702107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01284715312604302,"score_gpt":0.2750425382792611,"score_spread":0.2621953851532181,"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."}}