{"id":"W4399612084","doi":"10.1016/j.engappai.2024.108681","title":"Multi-scale spatial consistency for deep semi-supervised skin lesion segmentation","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Outaouais","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Artificial intelligence; Scale (ratio); Consistency (knowledge bases); Pattern recognition (psychology); Computer vision; Skin lesion; Cartography; Medicine; Pathology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001195685,0.0001068863,0.000140196,0.0001891139,0.00005685819,0.00002770816,0.00006816065,0.00005446428,0.00006087705],"category_scores_gemma":[0.00003409683,0.0001107572,0.0000996359,0.0002779608,0.00003143467,0.00003855063,0.00001941795,0.00008222519,0.00005927851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006298994,"about_ca_system_score_gemma":0.00002833366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004791575,"about_ca_topic_score_gemma":0.0000353489,"domain_scores_codex":[0.9991559,0.000005213254,0.0003471181,0.0002390319,0.0001247245,0.0001280153],"domain_scores_gemma":[0.9995111,0.00008909374,0.00003346872,0.0002105174,0.00009387422,0.00006198397],"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":[0.00004683887,0.0001755547,0.00001059014,0.0005639129,0.00005545599,0.000002655472,0.0004941602,0.009889929,0.3580131,0.00347172,0.00005774977,0.6272184],"study_design_scores_gemma":[0.00004402101,0.00009323436,0.00005497293,0.00007122396,0.0000719089,0.00001606843,0.0003780252,0.7224579,0.2704771,0.0001613025,0.006074538,0.00009974735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009978212,0.0002282505,0.9878804,0.0002200807,0.000237733,0.001131746,0.0000145717,0.0002003668,0.0001086568],"genre_scores_gemma":[0.8993081,0.00005909466,0.09958339,0.00002299433,0.0001705467,0.0005356949,0.00004846574,0.00002592373,0.0002457185],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.88933,"threshold_uncertainty_score":0.4516548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03042508163249349,"score_gpt":0.300635297790566,"score_spread":0.2702102161580725,"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."}}