{"id":"W3000139888","doi":"10.1101/2020.01.09.900605","title":"Cell segmentation using deep learning: comparing label and label-free approaches using hyper-labeled image stacks","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; University of Toronto","funders":"Banting and Best Diabetes Centre, University of Toronto; Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Segmentation; Computer science; Focus (optics); Deep learning; Pattern recognition (psychology); Multi-label classification; Range (aeronautics); Training set; Image (mathematics); Ranging; Machine learning; Materials science","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":[0.000506623,0.0007242871,0.0007453651,0.0002175843,0.0002848656,0.0004117261,0.0006511033,0.000611358,0.000008954839],"category_scores_gemma":[0.0002180945,0.0008706741,0.0001459502,0.0003624725,0.0002020679,0.00003635565,0.001948303,0.0008208763,0.000004964605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001745227,"about_ca_system_score_gemma":0.0002510737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000831251,"about_ca_topic_score_gemma":0.000005265624,"domain_scores_codex":[0.9966475,0.0002877551,0.0006308989,0.001512815,0.0003543375,0.0005667339],"domain_scores_gemma":[0.9974365,0.00002214026,0.0006539265,0.001247292,0.0003625126,0.0002776392],"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":[0.00004605582,0.0001522703,0.009919661,0.0004255087,0.0002228713,0.00002075856,0.00001824775,0.0003016049,0.9887748,0.000008209518,0.0001035821,0.000006474014],"study_design_scores_gemma":[0.001084251,0.0000944793,0.001068775,0.0001035027,0.0004809243,1.084502e-7,0.00002641517,0.05663336,0.939275,0.000002173495,0.000311165,0.0009198256],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9536289,0.002986938,0.04236666,0.00003538353,0.00007621807,0.0006359454,0.00002814472,0.0002150388,0.00002677539],"genre_scores_gemma":[0.8556513,0.0004475761,0.1432612,0.00009476556,0.0002960078,0.00004786116,0.000008402943,0.0001870516,0.000005817906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1008945,"threshold_uncertainty_score":0.9993744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03760709078512398,"score_gpt":0.2544156776830903,"score_spread":0.2168085868979663,"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."}}