{"id":"W4417530586","doi":"10.1016/j.media.2025.103920","title":"GloW-VSNet: A scribble-based weakly supervised framework for global-view vitiligo lesion segmentation","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"melanin and skin pigmentation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Vancouver Coastal Health","funders":"Shenzhen Science and Technology Innovation Program; Natural Sciences and Engineering Research Council of Canada; Shenzhen University; University of British Columbia; National Natural Science Foundation of China","keywords":"Segmentation; Vitiligo; Pattern recognition (psychology); Image segmentation; Cluster analysis; Noise (video); Consistency (knowledge bases); Market segmentation","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":[0.0004110966,0.0001641291,0.000275217,0.00009876303,0.0001193383,0.00005722837,0.0002205583,0.0002486453,0.0004150876],"category_scores_gemma":[0.0005392769,0.0001491614,0.0003372449,0.0007317188,0.00007981784,0.000006667935,0.0000505278,0.00007589938,0.00001146848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004482571,"about_ca_system_score_gemma":0.0001591335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000606441,"about_ca_topic_score_gemma":0.0001382672,"domain_scores_codex":[0.9984978,0.0001289326,0.0003496728,0.0004289947,0.0003586842,0.00023593],"domain_scores_gemma":[0.9992394,0.00006602252,0.00007516798,0.0003356756,0.0001434414,0.0001402401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001253936,0.001335315,0.03449994,0.0009626428,0.005733558,0.00004857283,0.0001325186,0.0004945108,0.6028008,0.004478611,0.05954526,0.2887143],"study_design_scores_gemma":[0.008151804,0.0007911297,0.01709365,0.0005975985,0.007695777,0.000005321521,0.001002022,0.1223997,0.7957126,0.009371957,0.03583524,0.001343184],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07677311,0.0006485045,0.9191976,0.001946056,0.0001465814,0.0002964135,0.00005596589,0.00002241415,0.0009133094],"genre_scores_gemma":[0.9196238,0.000473061,0.06638863,0.00790818,0.0002528175,0.0002214317,0.004563278,0.00001970211,0.0005491189],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.852809,"threshold_uncertainty_score":0.6082625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01237205503245195,"score_gpt":0.3405596409592523,"score_spread":0.3281875859268003,"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."}}