{"id":"W2567599812","doi":"10.1016/j.neuroimage.2017.04.039","title":"3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study","year":2017,"lang":"en","type":"review","venue":"NeuroImage","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":429,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Segmentation; Convolutional neural network; Artificial intelligence; Inference; Normalization (sociology); Context (archaeology); Atlas (anatomy); Pattern recognition (psychology); Process (computing); Machine learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00108119,0.0004054847,0.001095479,0.0002773283,0.0002333916,0.0004053809,0.001626394,0.0002105232,0.00004267351],"category_scores_gemma":[0.0002923405,0.0003728025,0.0002844011,0.0002895693,0.000145128,0.0006066729,0.0005129367,0.0005939083,0.00004129265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001502077,"about_ca_system_score_gemma":0.0002917696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007300692,"about_ca_topic_score_gemma":0.00002166695,"domain_scores_codex":[0.9964059,0.0004929048,0.0009660684,0.001019073,0.0005646402,0.0005513901],"domain_scores_gemma":[0.9976173,0.0004622738,0.0005313336,0.001098574,0.0001149663,0.0001755476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006011855,0.0005508171,0.00005358682,0.0009696971,0.00002521126,0.0001185953,0.0001110977,0.000002827291,0.000001914529,0.0001669765,0.003795112,0.9941981],"study_design_scores_gemma":[0.004291436,0.001647886,0.001036224,0.003843654,0.0006065897,0.0001420449,0.0000718924,0.08072897,0.00001548885,0.0003362774,0.9053935,0.001886019],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.000001280584,0.254586,0.7417025,0.00003964017,0.0004730977,0.002887727,0.00003012591,0.0001784263,0.0001012699],"genre_scores_gemma":[0.0000211997,0.8576088,0.1390366,0.000378546,0.0003217404,0.001988753,0.0002006152,0.00006906007,0.0003747489],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9923121,"threshold_uncertainty_score":0.9998724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09490925143572054,"score_gpt":0.411405731701633,"score_spread":0.3164964802659124,"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."}}