{"id":"W3005161615","doi":"10.1371/journal.pone.0228132","title":"Multiclass classification of autofluorescence images of oral cavity lesions based on quantitative analysis","year":2020,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Oral Health Pathology and Treatment","field":"Dentistry","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"BC Cancer Agency; Chang Gung Memorial Hospital, Linkou; Chang Gung University; Chang Gung Memorial Hospital","keywords":"Autofluorescence; Linear discriminant analysis; Artificial intelligence; Tongue; Medicine; Quadratic classifier; Pattern recognition (psychology); Mathematics; Pathology; Computer science; Classifier (UML); Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001233687,0.00008576466,0.0003436421,0.00009133733,0.00005242394,0.000003029191,0.00009167593,0.00007140189,0.00009497366],"category_scores_gemma":[0.0003048716,0.00007677328,0.00009174862,0.0004716711,0.0001174604,0.00004726145,0.00001729873,0.0001141572,0.00008477601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003041929,"about_ca_system_score_gemma":0.00004626622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000126016,"about_ca_topic_score_gemma":0.00007549741,"domain_scores_codex":[0.998933,0.0002073813,0.0002850009,0.0002173383,0.0002443254,0.0001129951],"domain_scores_gemma":[0.9990684,0.0002382371,0.0002206316,0.0002299786,0.0001680949,0.00007459604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005823638,0.006297744,0.8117703,0.0004313599,0.000841594,0.00004554158,0.0004638337,0.0003113123,0.176674,0.001855423,0.00007481097,0.0006517324],"study_design_scores_gemma":[0.0004989397,0.000425847,0.8222979,0.00004777035,0.0008925938,7.377768e-8,0.00008445865,0.0641477,0.1115254,0.00002147019,0.00000122223,0.00005659103],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968643,0.00004058502,0.001256414,0.001108766,0.0000142135,0.0002055308,0.000287891,0.00003119318,0.0001910901],"genre_scores_gemma":[0.9843912,0.000006865731,0.01539002,0.00008740584,0.0000052211,0.00001563501,0.00005549879,0.000006155134,0.00004204612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06514858,"threshold_uncertainty_score":0.3130723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2320265535409856,"score_gpt":0.3679686050895952,"score_spread":0.1359420515486096,"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."}}