{"id":"W4410808471","doi":"10.1371/journal.pcbi.1013115","title":"RETINA: Reconstruction-based pre-trained enhanced TransUNet for electron microscopy segmentation on the CEM500K dataset","year":2025,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sinai Health System; Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; University of Toronto; University Health Network; Canadian Institute for Advanced Research","funders":"Canadian Institutes of Health Research","keywords":"Artificial intelligence; Segmentation; Computer science; Convolutional neural network; Pattern recognition (psychology); Image segmentation; Deep learning; Artificial neural network; Computer vision; Scale-space segmentation; Feature extraction","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":[0.0001657246,0.0001384902,0.0001385786,0.00008020508,0.0001373131,0.000019866,0.000178356,0.0001145394,0.00002582199],"category_scores_gemma":[0.0001173705,0.0001133758,0.00008383342,0.0001199725,0.0001268001,0.000003233075,0.00001843129,0.00007696059,0.000003308279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002877929,"about_ca_system_score_gemma":0.0001184261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006254136,"about_ca_topic_score_gemma":0.000015979,"domain_scores_codex":[0.9990262,0.0001274828,0.0002387022,0.0003813637,0.00005546527,0.0001707781],"domain_scores_gemma":[0.9992979,0.0002276708,0.0001002882,0.0002212733,0.0001336434,0.00001925647],"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":[0.0003301733,0.00008454971,0.0001400621,0.00001621122,0.0001319553,8.487841e-8,0.000007967852,0.0008524219,0.9861144,0.00061251,0.01007887,0.001630821],"study_design_scores_gemma":[0.0005247089,0.0004085583,0.0002106224,0.00001479435,0.00005141902,9.608134e-7,0.00001007826,0.004428411,0.9878875,0.00321978,0.003127432,0.0001157277],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5840148,0.00007985685,0.4122088,0.001879466,0.000052502,0.0008455447,0.0005904765,0.00004155669,0.0002870017],"genre_scores_gemma":[0.9547152,0.00001945151,0.01982892,0.002576525,0.00007373726,0.0003123363,0.02235347,0.00001275961,0.0001076168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3923799,"threshold_uncertainty_score":0.462333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008197295960440006,"score_gpt":0.3107505432427145,"score_spread":0.3025532472822745,"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."}}