{"id":"W2113221073","doi":"10.1080/21681163.2013.864958","title":"3D segmentation of the tongue in MRI: a minimally interactive model-based approach","year":2014,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization","topic":"Cleft Lip and Palate Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Ground truth; Artificial intelligence; Computer vision; Tongue; Matching (statistics); Boundary (topology); Image registration; Image segmentation; Magnetic resonance imaging; Pattern recognition (psychology); Image (mathematics); Medicine; Radiology; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009129098,0.001046697,0.001287888,0.001828211,0.0006467165,0.002217849,0.002129306,0.002501888,0.002169852],"category_scores_gemma":[0.002024335,0.001532963,0.002259776,0.0009218807,0.000885585,0.0008841707,0.003128774,0.001129562,0.001333226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000696928,"about_ca_system_score_gemma":0.001200692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00309116,"about_ca_topic_score_gemma":0.005553165,"domain_scores_codex":[0.9990854,0.0002347173,0.00005406721,0.0001505402,0.0004182358,0.00005692442],"domain_scores_gemma":[0.9994035,0.0002900174,0.00006292052,0.000137143,0.00006993667,0.00003652506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002930515,0.0001765059,0.001624292,0.0005418259,0.0002613494,0.0006675484,0.001064963,0.4190328,0.2129579,0.006162984,0.002914271,0.3543025],"study_design_scores_gemma":[0.00001461563,0.00008529942,0.0006803534,0.00003403977,0.00004159343,0.000686915,0.00008688513,0.9758816,0.01432766,0.0046351,0.00347672,0.00004921737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007701473,0.0001654799,0.9902332,0.00009165095,0.000009832595,0.00006665771,0.00005228841,0.001122692,0.0005566492],"genre_scores_gemma":[0.1258753,0.0004657736,0.870788,0.0001342669,0.00003168801,0.000217418,0.0003254236,0.0007098733,0.001452275],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00309116,"threshold_uncertainty_score":0.007258892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01229471134366077,"score_gpt":0.338344408319031,"score_spread":0.3260496969753702,"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."}}