{"id":"W3084344043","doi":"10.1007/s10853-020-05148-7","title":"Automated segmentation of computed tomography images of fiber-reinforced composites by deep learning","year":2020,"lang":"en","type":"article","venue":"Journal of Materials Science","topic":"Rock Mechanics and Modeling","field":"Engineering","cited_by":113,"is_retracted":false,"has_abstract":false,"ca_institutions":"Object Research Systems (Canada); Polytechnique Montréal","funders":"","keywords":"Materials science; Segmentation; Composite material; Solid mechanics; Fiber; Composite number; Ultimate tensile strength; Ceramic matrix composite; Artificial neural network; Image segmentation; Artificial intelligence; Matrix (chemical analysis); Ceramic; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003030384,0.0007596441,0.0004851928,0.001617521,0.0002977557,0.0008811702,0.0006043956,0.0009104051,0.001055276],"category_scores_gemma":[0.0007352956,0.0004453986,0.0006340493,0.0007876299,0.0003986132,0.000514199,0.0004743991,0.0006396208,0.0004889087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006397016,"about_ca_system_score_gemma":0.00144598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006008643,"about_ca_topic_score_gemma":0.01161628,"domain_scores_codex":[0.9998179,0.00002286126,0.000009009848,0.00004331848,0.00005831062,0.00004856828],"domain_scores_gemma":[0.9996402,0.0001059643,0.00007998386,0.00005728959,0.00009342503,0.00002307332],"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":[0.0007057737,0.0003399432,0.005608746,0.0003214604,0.0001298842,0.0004393558,0.0002363767,0.2680878,0.3251447,0.004544007,0.005581439,0.3888605],"study_design_scores_gemma":[0.000007942966,0.0000255998,0.002154374,0.00001390074,0.00001564954,0.0001074495,0.00003147142,0.9548343,0.04032834,0.001433687,0.001033277,0.00001405021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2895232,0.0007323253,0.7019461,0.0003163733,0.00006043557,0.0001249934,0.0007103948,0.003892113,0.002694054],"genre_scores_gemma":[0.6942654,0.0004591621,0.3006442,0.0001159149,0.00003488741,0.00007880278,0.001251496,0.0004015328,0.002748665],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006008643,"threshold_uncertainty_score":0.01194733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008236152925216218,"score_gpt":0.2227421555183947,"score_spread":0.2145060025931785,"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."}}