{"id":"W2160856184","doi":"10.1109/iembs.2009.5332916","title":"Speckle reduction and lesion segmentation of OCT tooth images for early caries detection","year":2009,"lang":"en","type":"article","venue":"","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics; University of Manitoba","funders":"National Institute of Dental and Craniofacial Research; National Institutes of Health; Mitacs","keywords":"Artificial intelligence; Speckle noise; Segmentation; Thresholding; Computer vision; Computer science; Speckle pattern; Pattern recognition (psychology); Optical coherence tomography; Image segmentation; Noise reduction; Kernel (algebra); Mathematics; Medicine; Radiology; Image (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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002942286,0.00005139878,0.0000597105,0.00005767562,0.0000377883,0.00001894981,0.00002091154,0.00003144329,0.000006703608],"category_scores_gemma":[0.000004346016,0.00005086775,0.00002133348,0.0001180359,0.00002447295,0.0001610817,0.000002168156,0.00002887348,0.000001098349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001367954,"about_ca_system_score_gemma":0.000002071428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000020264,"about_ca_topic_score_gemma":0.000005695175,"domain_scores_codex":[0.999703,0.000003472501,0.0001022274,0.0000775746,0.00004703502,0.00006664867],"domain_scores_gemma":[0.9998468,0.00001552983,0.00001557025,0.00006620189,0.00003493618,0.00002102299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001224341,0.00001421424,0.0001239572,0.00002518462,0.000007251463,2.229083e-8,0.0001207536,0.0004207221,0.8480211,0.001544718,0.0001146113,0.1495952],"study_design_scores_gemma":[0.0001726163,0.0001674945,0.03578066,0.000006379539,0.00001968454,0.000001636825,0.0001651786,0.002631205,0.9570119,0.003871477,0.00009141601,0.00008028949],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7942324,0.0000701099,0.2033553,0.00006060787,0.00004317631,0.0003264799,0.000005819011,0.0001496575,0.00175644],"genre_scores_gemma":[0.9859548,0.00004755774,0.013888,0.000002487469,0.00002680412,0.00002733456,0.000003386803,0.000005088194,0.00004457704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1917224,"threshold_uncertainty_score":0.2074327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01289553714876183,"score_gpt":0.2458646009806256,"score_spread":0.2329690638318638,"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."}}