{"id":"W3158432719","doi":"10.1111/tra.12789","title":"Deep learning for automatic segmentation of the nuclear envelope in electron microscopy data, trained with volunteer segmentations","year":2021,"lang":"en","type":"article","venue":"Traffic","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Francis Crick Institute; Medical Research Council Canada; Cancer Research UK; Wellcome Trust","keywords":"Envelope (radar); Biology; Segmentation; Electron microscope; Microscopy; Cell biology; Artificial intelligence; Deep learning; Computer vision; Computer science; Optics; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002262216,0.001187364,0.0008572401,0.001000207,0.0006797295,0.000919283,0.001585193,0.00173854,0.001252726],"category_scores_gemma":[0.004419515,0.0006323773,0.0009792644,0.0008817625,0.0009043192,0.001148437,0.001456225,0.00187587,0.001014966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001284657,"about_ca_system_score_gemma":0.001623734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01027379,"about_ca_topic_score_gemma":0.01640992,"domain_scores_codex":[0.9993464,0.0001735314,0.00003010097,0.0002532034,0.0001015543,0.00009523559],"domain_scores_gemma":[0.998639,0.0004837869,0.0001174455,0.0003085426,0.0003677536,0.00008342221],"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":[0.0005303426,0.0003184015,0.005498101,0.0002652199,0.0002248547,0.0002112303,0.000505736,0.5240902,0.02767915,0.006286539,0.01943913,0.414951],"study_design_scores_gemma":[0.000009964405,0.00003042697,0.0003109452,0.000007562431,0.000006116457,0.00001948112,0.00002457475,0.9923549,0.003173175,0.003018924,0.001037276,0.000006595492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1515624,0.0007964124,0.8328612,0.0006427163,0.0001108719,0.000138394,0.001145632,0.01064756,0.002094907],"genre_scores_gemma":[0.5440984,0.0003281574,0.440531,0.0004418422,0.00008054406,0.0002754193,0.00832499,0.0008403296,0.005079284],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01027379,"threshold_uncertainty_score":0.02042794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008632848563828378,"score_gpt":0.3137155355735513,"score_spread":0.3050826870097229,"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."}}