{"id":"W4284991579","doi":"10.1016/j.neuroimage.2022.119425","title":"eICAB: A novel deep learning pipeline for Circle of Willis multiclass segmentation and analysis","year":2022,"lang":"en","type":"article","venue":"NeuroImage","topic":"Cerebrovascular and Carotid Artery Diseases","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; Université de Sherbrooke","funders":"National Center for Advancing Translational Sciences; National Institute of Biomedical Imaging and Bioengineering; National Institute on Aging; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; University of Southern California","keywords":"Convolutional neural network; Artificial intelligence; Segmentation; Computer science; Test set; Pattern recognition (psychology); Dice; Data set; Deep learning; Artificial neural network; Pipeline (software); F1 score; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001496447,0.00163331,0.0008734425,0.002002737,0.0006489933,0.001126785,0.002018214,0.001436703,0.003850097],"category_scores_gemma":[0.001852417,0.0007078251,0.001049197,0.001012643,0.0003916408,0.0009608896,0.001467289,0.001693474,0.002297599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001322163,"about_ca_system_score_gemma":0.001954069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01824564,"about_ca_topic_score_gemma":0.02235776,"domain_scores_codex":[0.9995301,0.00006740968,0.00002440555,0.0001617725,0.0001218243,0.00009456187],"domain_scores_gemma":[0.9994673,0.0001272967,0.00005939054,0.00007993884,0.0002139548,0.00005217031],"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":[0.0005391791,0.000308322,0.005068929,0.0001760045,0.0003984369,0.0002051271,0.0001231922,0.0821969,0.02978494,0.002619277,0.03327405,0.8453057],"study_design_scores_gemma":[0.00002287642,0.00005540496,0.001465453,0.00001989047,0.00003051261,0.00008360795,0.00001205032,0.9841049,0.008414898,0.001842562,0.003927198,0.0000206101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03223434,0.001159799,0.9444435,0.0003834437,0.0001323777,0.0002393582,0.001480473,0.01815161,0.001775177],"genre_scores_gemma":[0.2450444,0.0007533915,0.7354625,0.0006870071,0.00009289937,0.0006354583,0.007288571,0.001025026,0.009010778],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01824564,"threshold_uncertainty_score":0.03627884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01274046756040845,"score_gpt":0.2623799851690057,"score_spread":0.2496395176085972,"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."}}