{"id":"W4402168020","doi":"10.2196/57335","title":"The Application of Mask Region-Based Convolutional Neural Networks in the Detection of Nasal Septal Deviation Using Cone Beam Computed Tomography Images: Proof-of-Concept Study","year":2024,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Nasal Surgery and Airway Studies","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cone beam computed tomography; Artificial intelligence; Convolutional neural network; Preprocessor; Coronal plane; Computer science; Nasal septum; Pattern recognition (psychology); Computer vision; Nuclear medicine; Computed tomography; Medicine; Radiology; Nose; Anatomy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.001647839,0.00009474719,0.0002244151,0.0003051905,0.0002085089,0.00001795984,0.0001126186,0.0000506676,0.000001414228],"category_scores_gemma":[0.00007166088,0.00005614709,0.0001315783,0.001669494,0.0005400304,0.0001415145,0.00004689386,0.0004106557,2.850585e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007114511,"about_ca_system_score_gemma":0.00009438266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008471988,"about_ca_topic_score_gemma":0.0000244252,"domain_scores_codex":[0.998098,0.000449305,0.0004570021,0.0001423504,0.0006409668,0.0002123595],"domain_scores_gemma":[0.9977661,0.001380465,0.0001451141,0.0001657984,0.0005180388,0.00002446643],"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":[0.009419073,0.009262208,0.2507403,0.004608387,0.002520312,0.00005468712,0.08436753,0.06040362,0.0324209,0.002822529,0.001638158,0.5417423],"study_design_scores_gemma":[0.001383938,0.002072921,0.1629926,0.0004015924,0.00005305071,0.0000103123,0.0131838,0.7957921,0.02368317,0.0001880656,0.0001270851,0.0001113226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9386918,0.00183801,0.05685211,0.0002815633,0.00009636101,0.00216523,0.00001204753,0.00001777618,0.00004508324],"genre_scores_gemma":[0.9996772,0.000006775345,0.00001646866,0.000008848379,0.00006546173,0.000193073,0.00002060581,0.000007433962,0.000004157875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7353885,"threshold_uncertainty_score":0.2289612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05097184549276106,"score_gpt":0.3730837637663778,"score_spread":0.3221119182736167,"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."}}