{"id":"W4396696718","doi":"10.20944/preprints202405.0358.v1","title":"3-Dimension Epithelial Segmentation in Optical Coherence Tomography of the Oral Cavity Using Deep Learning","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vancouver General Hospital; University of British Columbia; Simon Fraser University","funders":"","keywords":"Optical coherence tomography; Segmentation; Dimension (graph theory); Oral cavity; Artificial intelligence; Optics; Computer science; Physics; Medicine; Mathematics; Dentistry; Combinatorics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005547943,0.0003525279,0.000410867,0.0002957872,0.00007226677,0.00003133701,0.0005550836,0.000371163,0.0001339316],"category_scores_gemma":[0.00009820082,0.0003249396,0.0002940664,0.0008832373,0.0002270791,0.00007194802,0.001358003,0.002016409,0.000104634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001886954,"about_ca_system_score_gemma":0.00006985245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002559752,"about_ca_topic_score_gemma":0.00008689942,"domain_scores_codex":[0.9977829,0.0001518559,0.0006532575,0.0006375713,0.0004131805,0.0003612489],"domain_scores_gemma":[0.9987427,0.0001132579,0.0001325049,0.000810978,0.0001039746,0.00009656102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00001750963,0.00009687633,0.352418,0.0005702171,0.0001180206,0.000004693976,0.0009117763,0.3774912,0.2652133,0.000703051,0.000001500114,0.002453787],"study_design_scores_gemma":[0.000334383,0.00002069498,0.5443698,0.0009023573,0.0002484211,0.00000735632,0.0002548066,0.1777026,0.2657113,0.009731941,0.00003961377,0.0006766974],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947737,0.0001913175,0.001318538,0.00004518962,0.0005199158,0.0009602889,0.00002176295,0.000288238,0.001880993],"genre_scores_gemma":[0.9966858,0.00003576714,0.002941579,0.000007354307,0.00004673083,0.0001930002,0.00001505865,0.00005701249,0.00001770508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1997886,"threshold_uncertainty_score":0.9999202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06218652363859321,"score_gpt":0.3216342971440073,"score_spread":0.259447773505414,"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."}}