{"id":"W2752568171","doi":"10.1002/jbio.201700072","title":"Pixel classification method in optical coherence tomography for tumor segmentation and its complementary usage with OCT microangiography","year":2017,"lang":"en","type":"article","venue":"Journal of Biophotonics","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Russian Foundation for Basic Research; Radford University","keywords":"Microangiography; Optical coherence tomography; Artificial intelligence; Feature (linguistics); Computer science; Segmentation; Ground truth; Computer vision; Biomedical engineering; Pattern recognition (psychology); Pathology; Medicine; Radiology","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":[0.0004494532,0.0001549731,0.0002501288,0.0003354901,0.0001420491,0.0001283421,0.0002957263,0.000055755,0.000009440814],"category_scores_gemma":[0.00002129232,0.0001361867,0.0001194067,0.000266283,0.00009826766,0.000327862,0.00002222799,0.0002090988,7.8944e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003950482,"about_ca_system_score_gemma":0.00002858817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000684818,"about_ca_topic_score_gemma":0.00003998208,"domain_scores_codex":[0.9989816,0.0000222106,0.0004302217,0.0001608816,0.000186346,0.0002187708],"domain_scores_gemma":[0.9990858,0.0001368751,0.000267387,0.0002339501,0.0001537868,0.0001222434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0004031027,0.000383818,0.05789665,0.0004031126,0.0004553349,0.00002397917,0.0006036868,0.001028083,0.9162614,0.004357622,0.0002488746,0.01793432],"study_design_scores_gemma":[0.007810256,0.001997772,0.6284372,0.0005990398,0.0006489145,0.00034116,0.002020667,0.1481091,0.2016724,0.00396122,0.003163291,0.001239005],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9574183,0.0005775117,0.04053949,0.0002499925,0.00009683288,0.0007299552,0.00006232536,0.00002584422,0.0002997464],"genre_scores_gemma":[0.8193759,0.0001333732,0.1803487,0.00002924347,0.00002360119,0.00006315784,0.000006555239,0.00001774343,0.000001729076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7145891,"threshold_uncertainty_score":0.5553533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02916693606510761,"score_gpt":0.302261737300466,"score_spread":0.2730948012353584,"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."}}