{"id":"W4399793492","doi":"10.1101/2024.06.17.24308662","title":"Automated Dentate Nucleus Segmentation from QSM Images Using Deep Learning","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Dentate nucleus; Artificial intelligence; Segmentation; Nucleus; Computer vision; Computer science; Deep learning; Pattern recognition (psychology); Neuroscience; Psychology","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":[0.001446695,0.0005837301,0.0004289023,0.002395393,0.0002015988,0.0008191336,0.0005475283,0.0005110002,0.001444682],"category_scores_gemma":[0.002815735,0.0003192642,0.0003795672,0.0005896004,0.0003274688,0.00052625,0.0006362934,0.0003145096,0.0006289288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000626785,"about_ca_system_score_gemma":0.0007154642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002739426,"about_ca_topic_score_gemma":0.005842489,"domain_scores_codex":[0.9996638,0.00008964038,0.00002977972,0.0001073657,0.0000838992,0.0000255031],"domain_scores_gemma":[0.9993694,0.0001932576,0.0001363503,0.0001156795,0.0001591966,0.00002606163],"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":[0.0008109608,0.0001470741,0.0764785,0.0007961332,0.000324065,0.0008610876,0.0004406238,0.0658711,0.2068723,0.002165552,0.004595994,0.6406367],"study_design_scores_gemma":[0.00007911418,0.0003274671,0.09013058,0.0002074695,0.0001361745,0.002398844,0.0003044201,0.7546891,0.1374521,0.006631769,0.007549852,0.00009312039],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.360503,0.001216736,0.6300927,0.0002577565,0.00003576954,0.0002998571,0.001711439,0.004082698,0.001800023],"genre_scores_gemma":[0.6698603,0.000441158,0.3263174,0.0001146307,0.00002472104,0.0001844882,0.001511115,0.0002765273,0.001269654],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002739426,"threshold_uncertainty_score":0.007650912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01884102670906887,"score_gpt":0.3027975689129055,"score_spread":0.2839565422038367,"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."}}