{"id":"W4317933255","doi":"10.3390/app13031516","title":"Detection of Periapical Lesions on Panoramic Radiographs Using Deep Learning","year":2023,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Artificial intelligence; Convolutional neural network; Classifier (UML); Radiography; Computer science; Detector; Pattern recognition (psychology); Dentistry; Medicine; Radiology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003861709,0.00009605168,0.0001319231,0.000546415,0.0005667871,0.00008029708,0.0002152236,0.00003905295,0.00003721963],"category_scores_gemma":[0.00002920534,0.0000863805,0.0001094199,0.002603213,0.0004380712,0.0001170485,0.0000482576,0.0001550851,0.0001006023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001407739,"about_ca_system_score_gemma":0.0000127458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004147114,"about_ca_topic_score_gemma":0.00001440241,"domain_scores_codex":[0.9988422,0.00004140503,0.0001815524,0.0002915529,0.0003776238,0.0002656842],"domain_scores_gemma":[0.9996138,0.0001215684,0.00008739313,0.0001120672,0.00001430147,0.00005088226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003036203,0.00004882703,0.03885674,0.00001991677,0.00002354051,0.000015031,0.0004806826,0.006735514,0.9069905,0.003496578,0.00002727461,0.04327507],"study_design_scores_gemma":[0.001060391,0.0003969322,0.6350958,0.0001191735,0.00009747835,0.0001167676,0.01612397,0.1175038,0.2231756,0.004539011,0.0009968018,0.0007742109],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938689,0.00005928296,0.001430143,0.000008603795,0.0003974304,0.00008961643,0.000001359622,0.0001428442,0.004001853],"genre_scores_gemma":[0.9995462,0.00001748796,0.0003188573,0.00002294181,0.00004437811,0.000006459266,0.000002048367,0.000008378574,0.00003330604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6838149,"threshold_uncertainty_score":0.4359325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02956446719293342,"score_gpt":0.2926277044529598,"score_spread":0.2630632372600264,"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."}}