{"id":"W3119301020","doi":"10.1063/5.0027993","title":"Leveraging multimodal microscopy to optimize deep learning models for cell segmentation","year":2021,"lang":"en","type":"article","venue":"APL Bioengineering","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"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; Canada Foundation for Innovation; Government of Ontario","keywords":"Segmentation; Computer science; Artificial intelligence; Deep learning; Focus (optics); Training set; Machine learning; Microscopy; Ranging; Pattern recognition (psychology); Range (aeronautics); Fluorescent labelling; Fluorescence; 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":[],"consensus_categories":[],"category_scores_codex":[0.00009475918,0.0001373698,0.0001231881,0.00005717009,0.00006263332,0.00004985734,0.00009487345,0.00007145067,0.000007834267],"category_scores_gemma":[0.0000395843,0.0001659555,0.0001031315,0.0001064338,0.000006726028,0.000008400259,0.00009490285,0.00006684016,0.000003327061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003399414,"about_ca_system_score_gemma":0.00002381538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009390081,"about_ca_topic_score_gemma":0.000003953485,"domain_scores_codex":[0.9992023,0.00001401494,0.0001549474,0.0003358716,0.00006627205,0.0002266674],"domain_scores_gemma":[0.9995893,0.00001198317,0.00003199696,0.0002028568,0.00009884097,0.00006500013],"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":[0.000009698419,0.00001572941,0.00004905929,0.00002327895,0.00002434334,0.000002208137,0.000133055,0.1748269,0.8231127,0.000002248025,0.000122991,0.00167786],"study_design_scores_gemma":[0.0002476517,0.00004662851,0.000009340542,0.000008983734,0.00002098555,0.00000313612,0.0001452349,0.1640502,0.8335766,0.000009566749,0.00171644,0.000165246],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2684014,0.0004044076,0.7307954,0.00002623834,0.0000252004,0.0001305099,0.000001397454,0.00004460122,0.0001708566],"genre_scores_gemma":[0.7011821,0.00007637087,0.2977413,0.0001202057,0.00007163786,0.00005511659,0.0001753524,0.00003193715,0.0005459748],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4330541,"threshold_uncertainty_score":0.6767469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009431741311838987,"score_gpt":0.2526666099643495,"score_spread":0.2432348686525105,"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."}}