{"id":"W4310964503","doi":"10.3791/64435","title":"Deep Learning-Based Segmentation of Cryo-Electron Tomograms","year":2022,"lang":"en","type":"article","venue":"Journal of Visualized Experiments","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Object Research Systems (Canada)","funders":"Pennsylvania State University; University of Pennsylvania; Penn State College of Medicine; Pennsylvania Department of Health","keywords":"Segmentation; Artificial intelligence; Computer science; Convolutional neural network; Preprocessor; Context (archaeology); Deep learning; Cryo-electron tomography; Tomography; Electron tomography; Pattern recognition (psychology); Tracing; Computer vision; Image segmentation; Electron microscope; Optics; Physics; Geology","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":[],"consensus_categories":[],"category_scores_codex":[0.0001644369,0.00008893205,0.0001422683,0.00006463149,0.0001123345,0.000007157634,0.0001611373,0.00003353915,0.00007972863],"category_scores_gemma":[0.00001254565,0.00009056627,0.0001130932,0.0001166014,0.00002809912,0.000004786402,0.00004846049,0.0001372159,3.730436e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005943904,"about_ca_system_score_gemma":0.00006017671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003508077,"about_ca_topic_score_gemma":3.52698e-7,"domain_scores_codex":[0.9991362,0.0000883187,0.0003227427,0.0001134574,0.000197167,0.000142125],"domain_scores_gemma":[0.9992972,0.000006241932,0.0004555275,0.0001082083,0.0000911724,0.00004164833],"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":[0.0002965594,0.0002577302,0.000278824,0.000004078732,0.00003485846,8.264836e-7,0.00006284265,0.002543738,0.9950841,0.00003548646,0.0003215318,0.001079434],"study_design_scores_gemma":[0.0009157824,0.002008661,0.00003645668,0.000004280656,0.00001254688,0.00001472568,0.0001697517,0.0001944001,0.9719664,0.00004836041,0.02454624,0.0000824334],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.806819,0.001843188,0.1910031,0.00003550374,0.00005355871,0.00016885,0.000002868813,0.000008710212,0.00006520465],"genre_scores_gemma":[0.9878923,0.0001131432,0.01157781,0.0001203823,0.00004419258,0.00004691656,0.0000581149,0.00001916254,0.000127972],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1810733,"threshold_uncertainty_score":0.3693185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0107611482860993,"score_gpt":0.4312685831314168,"score_spread":0.4205074348453175,"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."}}