{"id":"W4389742512","doi":"10.3390/life13122340","title":"The Fusion of Wide Field Optical Coherence Tomography and AI: Advancing Breast Cancer Surgical Margin Visualization","year":2023,"lang":"en","type":"article","venue":"Life","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Texas MD Anderson Cancer Center; Cancer Prevention and Research Institute of Texas","keywords":"Optical coherence tomography; Convolutional neural network; Margin (machine learning); Breast cancer; Artificial intelligence; Surgical margin; Medicine; Visualization; Computer science; Deep learning; Radiology; Medical physics; Machine learning; Cancer; Internal medicine","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":[0.0001386043,0.0000947532,0.0001181617,0.00007655767,0.00009594172,0.00003123772,0.0001135851,0.00006826456,0.00005674039],"category_scores_gemma":[0.00005696817,0.00007505525,0.00004396275,0.0008271406,0.00008777042,0.00008010863,0.00004630523,0.0001246185,0.000008782593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008144122,"about_ca_system_score_gemma":0.00001552559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002863767,"about_ca_topic_score_gemma":0.00004673241,"domain_scores_codex":[0.9992574,0.00001779333,0.0002039028,0.0001343267,0.0001651839,0.0002214253],"domain_scores_gemma":[0.9991084,0.0005323175,0.00002261259,0.0001675791,0.00005406702,0.0001150721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002624016,0.0001801821,0.6371888,0.0008827071,0.0003305994,0.00002567081,0.0008679439,0.02079632,0.02946934,0.1317311,0.03357752,0.1446874],"study_design_scores_gemma":[0.001226824,0.0001821645,0.7301853,0.0004317734,0.0001202604,0.00002483033,0.0006062501,0.2262917,0.01330997,0.004846425,0.02187921,0.0008952993],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9868607,0.0007641718,0.006117069,0.002913199,0.0002048246,0.0003973024,0.00003952215,0.000499453,0.002203779],"genre_scores_gemma":[0.9989112,0.0006592218,0.000170511,0.00007268985,0.00005013414,0.00009262215,0.00000590808,0.0000148085,0.00002289413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2054954,"threshold_uncertainty_score":0.3060664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006966895372505995,"score_gpt":0.2609017524630314,"score_spread":0.2539348570905254,"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."}}