{"id":"W4413099674","doi":"10.1083/jcb.202506102","title":"ReSCU-Nets: Recurrent U-Nets for segmentation of three-dimensional microscopy data","year":2025,"lang":"en","type":"article","venue":"The Journal of Cell Biology","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; Ted Rogers Centre for Heart Research; Toronto Rehabilitation Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canada Foundation for Innovation; Nvidia","keywords":"Segmentation; Computer science; Artificial intelligence; Image segmentation; Image (mathematics); Pattern recognition (psychology); Computer vision","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":[0.0009272078,0.0001009465,0.0002120489,0.00008212173,0.00004750881,0.000005627258,0.0006041958,0.0001060038,0.00001278671],"category_scores_gemma":[0.0001243809,0.00006743966,0.0001022347,0.00008308729,0.0001125471,0.00000537654,0.0002444403,0.0001000628,7.318284e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000138261,"about_ca_system_score_gemma":0.0001256523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001646315,"about_ca_topic_score_gemma":0.00005515189,"domain_scores_codex":[0.9990592,0.0001411441,0.0004527415,0.0001527547,0.00006499521,0.0001291686],"domain_scores_gemma":[0.9986722,0.00009804163,0.0004330952,0.0004979138,0.0002756385,0.00002311683],"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":[0.0004603873,0.00007088162,0.0002204471,0.00001738504,0.0001188088,2.88307e-7,0.00001005235,0.00001792572,0.9709732,0.00001126864,0.02416321,0.003936173],"study_design_scores_gemma":[0.0004815917,0.0005584325,0.00009649509,0.0000236,0.0001554806,0.000007189076,0.00002230549,0.000207478,0.9651004,0.0006418403,0.03264441,0.00006075347],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9382094,0.007166327,0.05316508,0.0005471956,0.0001947581,0.0002916507,0.0000535049,0.000004223194,0.0003678354],"genre_scores_gemma":[0.977405,0.001621436,0.01940881,0.0006378645,0.000144706,0.000005150342,0.0004417538,0.00001396854,0.0003212958],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03919559,"threshold_uncertainty_score":0.2750109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01868574804472379,"score_gpt":0.3369838160328121,"score_spread":0.3182980679880883,"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."}}