{"id":"W4402616223","doi":"10.1117/1.jbo.30.s1.s13706","title":"Deep learning–enabled fluorescence imaging for surgical guidance: in silico training for oral cancer depth quantification","year":2024,"lang":"en","type":"article","venue":"Journal of Biomedical Optics","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network; Princess Margaret Cancer Centre","funders":"Princess Margaret Cancer Foundation; Terry Fox Research Institute; University of Toronto; Rensselaer Polytechnic Institute","keywords":"Cancer; Cancer detection; Optical imaging; Fluorescence; Fluorescence-lifetime imaging microscopy; Medical imaging; Cancer surgery; In silico; Medical physics; Computer science; Biomedical engineering; Medicine; Artificial intelligence; Optics; Chemistry","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":[0.001431927,0.0001566325,0.0003605499,0.0004597809,0.00009924734,0.0002170574,0.000267312,0.0001010416,0.00004065341],"category_scores_gemma":[0.0005351917,0.0001323803,0.0003421663,0.0005716881,0.0001829589,0.0003699206,0.00002522536,0.0004863821,0.000004210475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001287952,"about_ca_system_score_gemma":0.0001676189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001037831,"about_ca_topic_score_gemma":0.0000116195,"domain_scores_codex":[0.997959,0.00006266285,0.0008560029,0.0002421426,0.0004649309,0.0004153218],"domain_scores_gemma":[0.9987367,0.0005507865,0.0002413547,0.00009341851,0.0001812024,0.000196532],"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":[0.0009849337,0.0004312001,0.02508317,0.001075067,0.0003208617,0.001818717,0.001826064,0.0007395878,0.0382807,0.003385067,0.005778949,0.9202757],"study_design_scores_gemma":[0.004953507,0.0003569179,0.01339605,0.001685642,0.000250754,0.001475851,0.001784295,0.8865402,0.00242917,0.001853056,0.08483545,0.0004391671],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5449377,0.02369833,0.4166081,0.003971901,0.009501792,0.0007939851,0.00006537472,0.0001351852,0.0002876127],"genre_scores_gemma":[0.9821399,0.0003153669,0.01638465,0.0000538929,0.0008475384,0.00002860763,0.00002027341,0.00003611734,0.0001736821],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9198365,"threshold_uncertainty_score":0.539831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03311389475455889,"score_gpt":0.3492201724011866,"score_spread":0.3161062776466277,"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."}}