{"id":"W2024476192","doi":"10.1109/titb.2011.2157829","title":"Automatic Skin Lesion Segmentation via Iterative Stochastic Region Merging","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Information Technology in Biomedicine","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":136,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Sichuan University of Science and Engineering","keywords":"Segmentation; Artificial intelligence; Computer science; Skin lesion; Pattern recognition (psychology); Image segmentation; Pixel; Computer vision; Iterative method; Convergence (economics); Image (mathematics); Market segmentation; Algorithm; Medicine; Pathology","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":[0.0001500625,0.0001943263,0.0002662617,0.00299186,0.0001302895,0.000009698444,0.00008629455,0.0002117188,0.0002803162],"category_scores_gemma":[0.00001478198,0.0001731953,0.00005642757,0.001254192,0.0001550062,0.000373628,0.000002474746,0.000339089,0.0001899726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003262512,"about_ca_system_score_gemma":0.00003283027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000486328,"about_ca_topic_score_gemma":0.00001437331,"domain_scores_codex":[0.9986941,0.00002517604,0.0006210001,0.0001754116,0.0002556422,0.0002286842],"domain_scores_gemma":[0.9993279,0.00003027507,0.0001931158,0.0002813299,0.00009488044,0.00007250202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004634748,0.000467594,0.00004833251,0.0002020538,0.0001250063,0.00007304514,0.005787077,0.000417334,0.005977246,0.0003166235,0.0002724734,0.9858497],"study_design_scores_gemma":[0.03036998,0.01391748,0.005541065,0.00348355,0.001105788,0.008247217,0.03880649,0.3621176,0.5258155,0.005136288,0.003474528,0.001984507],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1072717,0.00001164105,0.8883199,0.001479079,0.0005721068,0.0009098777,0.000003033809,0.0004883069,0.0009443169],"genre_scores_gemma":[0.9960133,0.00004133528,0.003009394,0.0005308347,0.00001792119,0.0001886213,0.00001987057,0.00001299298,0.000165776],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9838653,"threshold_uncertainty_score":0.70627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01742219007937022,"score_gpt":0.2550228283851951,"score_spread":0.2376006383058249,"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."}}