{"id":"W4380997279","doi":"10.3389/fncir.2023.952921","title":"mEMbrain: an interactive deep learning MATLAB tool for connectomic segmentation on commodity desktops","year":2023,"lang":"en","type":"article","venue":"Frontiers in Neural Circuits","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Connectomics; Computer science; Segmentation; Artificial intelligence; Deep learning; Annotation; Leverage (statistics); Preprocessor; Graphical user interface; Software; Ground truth; Visualization; Machine learning; Pattern recognition (psychology); Connectome; Neuroscience; Operating system","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001186323,0.000121754,0.0001220486,0.00007206674,0.0001181426,0.0000228461,0.0001413047,0.00008373072,0.00000313189],"category_scores_gemma":[0.00005767487,0.0001331737,0.00004812056,0.0001420531,0.00003277192,0.00001385799,0.00002884501,0.0001440648,0.000002935268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005924322,"about_ca_system_score_gemma":0.00001411625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002867417,"about_ca_topic_score_gemma":0.00001115991,"domain_scores_codex":[0.9991604,0.00005713674,0.0001502161,0.0003311348,0.00005465364,0.0002464723],"domain_scores_gemma":[0.999657,0.0000246612,0.00007283506,0.0001747126,0.00003613402,0.00003462722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001174627,0.00005057829,0.002710083,0.0000177677,0.00001609519,0.000001269368,0.0001259997,0.002983982,0.922704,0.0001273618,0.003825894,0.06731948],"study_design_scores_gemma":[0.001212287,0.0009802761,0.004712617,0.00001897906,0.00001396147,0.000006255688,0.0005159917,0.02322284,0.9557521,0.00194732,0.01120375,0.0004136539],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8597422,0.00006029176,0.1392019,0.00009091699,0.0001486978,0.0005619543,0.0000314019,0.00008123868,0.00008138402],"genre_scores_gemma":[0.9956743,0.00006966324,0.002478834,0.0002792703,0.0000744417,0.0003212441,0.000909162,0.00002761429,0.0001654623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1367231,"threshold_uncertainty_score":0.5430666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01393093942109519,"score_gpt":0.3226495656570101,"score_spread":0.308718626235915,"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."}}