{"id":"W4390604273","doi":"10.1007/s11554-023-01398-1","title":"Deep learning models for bolus segmentation in videofluoroscopic swallow studies","year":2024,"lang":"en","type":"article","venue":"Journal of Real-Time Image Processing","topic":"Dysphagia Assessment and Management","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"North York General Hospital; University of Toronto","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Bolus (digestion); Swallowing; Dysphagia; Deep learning; Segmentation; Medicine; Encoder; Artificial intelligence; Computer science; Nuclear medicine; Radiology; Surgery","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":[0.001865588,0.0001721185,0.0004145504,0.0004062417,0.0003759036,0.0001179578,0.0001405248,0.00007707901,0.00006956152],"category_scores_gemma":[0.000189438,0.0001408027,0.00009679659,0.000302888,0.00003378731,0.001641927,0.00007964666,0.0005397595,0.00002817075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004794292,"about_ca_system_score_gemma":0.0003367555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009178959,"about_ca_topic_score_gemma":0.000007692618,"domain_scores_codex":[0.9979283,0.0001983409,0.0009223532,0.0002073872,0.0003309825,0.0004126049],"domain_scores_gemma":[0.9984756,0.0004375863,0.0005179216,0.00007230014,0.000423054,0.00007349971],"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":[0.0007555821,0.0003743197,0.004811182,0.02661768,0.001124946,0.0004990791,0.06230119,0.01623982,0.1232921,0.0009730405,0.04229352,0.7207175],"study_design_scores_gemma":[0.005445756,0.0007500667,0.001687838,0.01495438,0.0007887541,0.00002345477,0.04456499,0.8965809,0.001496184,0.02497849,0.008039218,0.0006899163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1485558,0.04138077,0.7744117,0.006765352,0.002908934,0.003104963,0.000004567809,0.0004056501,0.02246227],"genre_scores_gemma":[0.6542874,0.01101229,0.3008537,0.0007156939,0.001564306,0.0003978995,0.00002744482,0.0002179976,0.0309233],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8803411,"threshold_uncertainty_score":0.5741768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0582000051062934,"score_gpt":0.4382279911149201,"score_spread":0.3800279860086266,"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."}}