{"id":"W4402910326","doi":"10.1016/j.ijrobp.2024.07.2250","title":"Automated Segmentation of Pancreatic Tumor Microvasculature in High-Resolution Optical Coherence Tomography (OCT) Using Pre-Trained Large-Scale Supervised Networks for Early Evaluation of Radiation Therapy Response","year":2024,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Optical coherence tomography; Segmentation; Artificial intelligence; Coherence (philosophical gambling strategy); Scale (ratio); Computer science; Medical physics; Radiology; Medicine; Physics","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":[0.002101643,0.0002275969,0.0004704136,0.0005400722,0.00004477677,0.00004198763,0.0003153791,0.0002899896,0.00002320683],"category_scores_gemma":[0.0002004892,0.0002260927,0.0002933783,0.0008376641,0.0001437163,0.0004599277,0.00001944433,0.0003475354,0.000001101379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006207768,"about_ca_system_score_gemma":0.0003576366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002466049,"about_ca_topic_score_gemma":0.000009452733,"domain_scores_codex":[0.9974802,0.0004477892,0.001123849,0.0002499615,0.0004340531,0.0002641175],"domain_scores_gemma":[0.9974216,0.0008859834,0.0004939959,0.0001719557,0.0009520467,0.00007437028],"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":[0.001732515,0.0005591125,0.04916625,0.00008484229,0.001134494,0.000003291055,0.001853732,0.5921903,0.2673562,0.003084107,0.0001082125,0.08272698],"study_design_scores_gemma":[0.004064833,0.0005117407,0.1263789,0.0001437051,0.0002251219,0.00001212188,0.00007647638,0.8500962,0.01531978,0.002940284,0.00005584169,0.0001749699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8363489,0.001608089,0.1601087,0.0001022614,0.0007455774,0.0008334042,0.0001343842,0.0001046521,0.00001404122],"genre_scores_gemma":[0.9842635,0.0002215788,0.0148025,0.00002802594,0.0003371839,0.0001111211,0.0001967406,0.00003826168,0.000001061029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2579059,"threshold_uncertainty_score":0.9219794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01796936334904673,"score_gpt":0.3186847496366089,"score_spread":0.3007153862875622,"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."}}