{"id":"W4406700413","doi":"10.1101/2025.01.20.633744","title":"A self-supervised deep learning pipeline for segmentation in two-photon fluorescence microscopy","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; University of Toronto; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Pipeline (software); Segmentation; Fluorescence; Microscopy; Artificial intelligence; Fluorescence microscope; Deep learning; Computer science; Two-photon excitation microscopy; Materials science; Pattern recognition (psychology); Physics; Optics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006344852,0.0004832304,0.0004796544,0.0003156786,0.0001085681,0.0001385616,0.0005284994,0.0004327317,0.000009633146],"category_scores_gemma":[0.0002626461,0.0005832665,0.0002327445,0.0003723415,0.00005664423,0.00001207373,0.0005020772,0.0004813593,0.000004649945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001863005,"about_ca_system_score_gemma":0.0003609853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001129317,"about_ca_topic_score_gemma":0.00004291095,"domain_scores_codex":[0.9974275,0.0001667891,0.0005834716,0.001179765,0.0001825496,0.0004599313],"domain_scores_gemma":[0.9981368,0.00003232663,0.0003090664,0.0009399481,0.0004777994,0.0001041029],"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":[0.00007739737,0.0001444182,0.004615337,0.0004599405,0.0001004014,0.000006903369,0.0000103064,0.0001291307,0.9941968,0.00001069745,0.0002185882,0.00003007905],"study_design_scores_gemma":[0.0008585174,0.00006914821,0.0005724645,0.0001966905,0.0001413422,8.009948e-9,0.000005481174,0.01649299,0.9765759,0.000001218868,0.00454381,0.0005424768],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8832483,0.002406952,0.1110492,0.0000836953,0.0002367563,0.002474224,0.00008895492,0.000377137,0.00003482308],"genre_scores_gemma":[0.8495473,0.001296997,0.1477716,0.0001887955,0.0002494588,0.0008049735,0.0000166996,0.00008830981,0.00003586543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03672234,"threshold_uncertainty_score":0.9996619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006676962149549079,"score_gpt":0.2636912232392497,"score_spread":0.2570142610897005,"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."}}