{"id":"W4408742026","doi":"10.1101/2025.03.18.25324199","title":"Image-based Mandibular and Maxillary Parcellation and Annotation using Computer Tomography (IMPACT): A Deep Learning-based Clinical Tool for Orodental Dose Estimation and Osteoradionecrosis Assessment","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre","funders":"ZonMw","keywords":"Osteoradionecrosis; Annotation; Computed tomography; Artificial intelligence; Dentistry; Medicine; Estimation; Orthodontics; Computer science; Radiation therapy; Radiology; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007817973,0.0007584029,0.000366571,0.001635714,0.0001975147,0.0007409585,0.0007954672,0.0009522026,0.002636795],"category_scores_gemma":[0.001937174,0.0003650803,0.0005113803,0.0007418324,0.0003925225,0.0004370677,0.0009944855,0.000650922,0.0007103335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008259117,"about_ca_system_score_gemma":0.0007733952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005267204,"about_ca_topic_score_gemma":0.009283924,"domain_scores_codex":[0.9996982,0.00004250949,0.00001942275,0.00008059479,0.0001271612,0.00003214844],"domain_scores_gemma":[0.9995109,0.000171842,0.00009652481,0.00005781966,0.0001287284,0.00003420416],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000635282,0.0001649991,0.01637595,0.0003230883,0.0001402763,0.0004504371,0.0002147194,0.110839,0.06407064,0.001672113,0.007840853,0.7972727],"study_design_scores_gemma":[0.00003215871,0.0001493677,0.01374554,0.0000597818,0.00007961041,0.0009628366,0.00005149308,0.9434698,0.034523,0.002083715,0.004793365,0.00004933055],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1766854,0.001867465,0.8066078,0.0005849553,0.00006330333,0.000332962,0.001465736,0.008451133,0.003941222],"genre_scores_gemma":[0.6376512,0.000955057,0.3538318,0.0003165255,0.00006399789,0.0002893023,0.002073804,0.0005637218,0.00425466],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005267204,"threshold_uncertainty_score":0.01047307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0210248340518761,"score_gpt":0.3503424288929432,"score_spread":0.3293175948410671,"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."}}