{"id":"W4391693732","doi":"10.1016/j.ndteint.2024.103067","title":"Novel thresholding method and convolutional neural network for fiber volume content determination from 3D μCT images","year":2024,"lang":"en","type":"article","venue":"NDT & E International","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Covestro; Deutsche Forschungsgemeinschaft; Fraunhofer-Institut für Sichere Informationstechnologie","keywords":"Scalable Vector Graphics; Convolutional neural network; Volume (thermodynamics); Thresholding; Fiber; Artificial intelligence; Content (measure theory); Computer science; Algorithm; Computer graphics (images); Mathematics; Physics; Materials science; World Wide Web; Mathematical analysis; Composite material; Thermodynamics","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":[0.00024617,0.0001099263,0.0001436369,0.00006485668,0.00006694718,0.0000880335,0.00009373123,0.00006658027,0.0006276572],"category_scores_gemma":[0.0001391726,0.00009641235,0.00008333303,0.00006106531,0.00007168599,0.0001289639,0.0000577189,0.0001719972,0.00001592057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008068638,"about_ca_system_score_gemma":0.00004329174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009088831,"about_ca_topic_score_gemma":0.000002354975,"domain_scores_codex":[0.9990422,0.000009812939,0.0002440809,0.0002996882,0.0002545872,0.0001496846],"domain_scores_gemma":[0.9993048,0.0002821868,0.00004812791,0.000103345,0.0001739758,0.00008752471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002499934,0.0003152224,0.009821029,0.0001708966,0.0005749979,0.00004327415,0.0002069475,0.0002464425,0.1213373,0.03269016,0.3825583,0.4517855],"study_design_scores_gemma":[0.0006233004,0.00005026104,0.01346179,0.0002313151,0.0001197336,0.0001147403,0.000008064288,0.7318228,0.001036212,0.003307147,0.2491027,0.0001219473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02489307,0.0005751865,0.9457865,0.02608079,0.0006298569,0.0004960818,0.000469465,0.0002228522,0.0008462202],"genre_scores_gemma":[0.2258025,0.00003249268,0.7639469,0.001566728,0.001678692,0.0002734864,0.00077655,0.00002784798,0.00589479],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7315764,"threshold_uncertainty_score":0.6872406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06623074849489424,"score_gpt":0.3784860563258785,"score_spread":0.3122553078309842,"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."}}