{"id":"W4414168442","doi":"10.1117/1.jbo.30.s3.s34109","title":"Deep learning-enabled fluorescence imaging for oral cancer margin classification in preclinical models","year":2025,"lang":"en","type":"article","venue":"Journal of Biomedical Optics","topic":"Optical Imaging and Spectroscopy Techniques","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"Princess Margaret Cancer Foundation","keywords":"Margin (machine learning); Cancer; Medical imaging; Optical imaging; Cancer detection; Fluorescence-lifetime imaging microscopy; Cancer imaging; Preclinical imaging","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":[0.001148331,0.0001320865,0.0004967267,0.0003744863,0.00004681229,0.00003931257,0.0001734161,0.0001465544,0.00002217528],"category_scores_gemma":[0.00129147,0.0001021787,0.0001619776,0.0004113061,0.0002466662,0.0001488211,0.00003884624,0.0008212694,9.42401e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000238804,"about_ca_system_score_gemma":0.0003761887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000918401,"about_ca_topic_score_gemma":0.000001743174,"domain_scores_codex":[0.9981874,0.00006595315,0.0008690608,0.0001911298,0.0003727761,0.0003136545],"domain_scores_gemma":[0.9987123,0.0003270267,0.0002315592,0.0001397909,0.0003783262,0.000210999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004930215,0.005536289,0.1349265,0.001699361,0.0006073008,0.0004313703,0.0007362706,0.0009607997,0.1703768,0.02555361,0.01831161,0.6359299],"study_design_scores_gemma":[0.003050936,0.0006135484,0.007827114,0.001191406,0.0002326052,0.00004832912,0.0001701953,0.9701294,0.002214713,0.01014039,0.004238688,0.0001426246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0457994,0.001706382,0.9070858,0.04266252,0.0006803019,0.0005577747,0.000003506325,0.00008779972,0.001416491],"genre_scores_gemma":[0.7968917,0.001419938,0.2002039,0.0007258876,0.0002553815,0.00002423568,0.000007332862,0.00002076239,0.0004508048],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9691687,"threshold_uncertainty_score":0.4166727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04071483152267039,"score_gpt":0.4056191596681433,"score_spread":0.3649043281454729,"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."}}