{"id":"W4411855123","doi":"10.1038/s41598-025-03268-1","title":"CLASEG: advanced multiclassification and segmentation for differential diagnosis of oral lesions using deep learning","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Qatar University; McGill University","keywords":"Segmentation; Differential diagnosis; Artificial intelligence; Computer science; Differential (mechanical device); Deep learning; Medicine; Computational biology; Pathology; Biology; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00103742,0.001350867,0.0008477278,0.001725982,0.0004540588,0.0009482151,0.001662217,0.001886809,0.002422885],"category_scores_gemma":[0.001536895,0.0004602175,0.001307476,0.0008191285,0.0003832035,0.0009655719,0.001351972,0.00131895,0.001235003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001191329,"about_ca_system_score_gemma":0.001773028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01294147,"about_ca_topic_score_gemma":0.02089652,"domain_scores_codex":[0.9995692,0.00006255382,0.00002353176,0.0001519472,0.0001156792,0.00007708808],"domain_scores_gemma":[0.99965,0.0001128564,0.00004067446,0.00005033117,0.0001109009,0.00003518947],"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":[0.0005626653,0.0004146698,0.009412161,0.0003015484,0.0004087242,0.0003501587,0.0001481844,0.1220788,0.03604916,0.00216814,0.01769727,0.8104087],"study_design_scores_gemma":[0.00002596499,0.000147491,0.002199464,0.0000437257,0.00006859934,0.0002102826,0.00003249876,0.9763864,0.014331,0.002628042,0.003899861,0.00002654286],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1809209,0.006483573,0.7825659,0.001304903,0.0003544608,0.0004272548,0.002931451,0.01924014,0.005771428],"genre_scores_gemma":[0.6345556,0.001379057,0.3459861,0.000962086,0.0001451131,0.0003530936,0.006360305,0.0005543124,0.009704366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01294147,"threshold_uncertainty_score":0.02573228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02998114596194854,"score_gpt":0.31579403857094,"score_spread":0.2858128926089915,"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."}}