{"id":"W2059887294","doi":"10.1155/2011/846312","title":"Conditional Random Fields and Supervised Learning in Automated Skin Lesion Diagnosis","year":2011,"lang":"en","type":"article","venue":"International Journal of Biomedical Imaging","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vancouver Coastal Health Research Institute; University of British Columbia; Simon Fraser University; Vancouver Coastal Health","funders":"CIHR Skin Research Training Centre; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canadian Dermatology Foundation","keywords":"CRFS; Conditional random field; Artificial intelligence; Generalization; Computer science; Pixel; Maximum a posteriori estimation; Probabilistic logic; Graph; Pattern recognition (psychology); Machine learning; Cut; A priori and a posteriori; Set (abstract data type); Random walker algorithm; Image (mathematics); Mathematics; Image segmentation; Maximum likelihood; Statistics; Theoretical computer science","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":[0.0003180298,0.00007205609,0.0001658885,0.000467153,0.00002441663,0.00002290791,0.00008418311,0.00003861498,0.0007030586],"category_scores_gemma":[0.0002344431,0.00005949095,0.00006865463,0.00008822899,0.00008233538,0.0001083719,0.00004689824,0.0002486495,0.000007045684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006582147,"about_ca_system_score_gemma":0.00004174526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005299145,"about_ca_topic_score_gemma":0.000003847514,"domain_scores_codex":[0.9989575,0.00004384535,0.0003778971,0.00009453367,0.0004254851,0.0001007263],"domain_scores_gemma":[0.9994748,0.00009739857,0.000124178,0.00003401263,0.0001497253,0.0001198593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003962772,0.001820824,0.3743762,0.0001068602,0.0008182437,0.01716242,0.004111877,0.00005275601,0.01074376,0.0004012117,0.01443784,0.5720053],"study_design_scores_gemma":[0.04509391,0.00145718,0.6942359,0.00212788,0.0003197964,0.0252765,0.003307091,0.1392917,0.009110203,0.002399571,0.07676664,0.0006136963],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9804271,0.0002673962,0.01012364,0.006607967,0.0008921071,0.0001164929,0.000002720185,0.00006658903,0.001495997],"genre_scores_gemma":[0.9978026,0.0002031192,0.0009942667,0.0007032706,0.0001956568,0.000003522505,0.00001116878,0.000006962382,0.00007947589],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5713916,"threshold_uncertainty_score":0.7697999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01866805432196263,"score_gpt":0.2906907681153296,"score_spread":0.272022713793367,"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."}}