{"id":"W2971686199","doi":"10.1371/journal.pcbi.1007348","title":"Learning unsupervised feature representations for single cell microscopy images with paired cell inpainting","year":2019,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":104,"is_retracted":false,"has_abstract":true,"ca_institutions":"Genome Canada; Toronto Centre for Phenogenomics; University of Toronto","funders":"Canada Research Chairs","keywords":"Convolutional neural network; Artificial intelligence; Microscopy; Inpainting; Pattern recognition (psychology); Feature (linguistics); Computer science; Fluorescence microscope; Proteome; Computer vision; Image (mathematics); Biology; Bioinformatics; Fluorescence; Pathology; Physics","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":[0.0001198459,0.0001700231,0.0001967598,0.00008507651,0.0001162107,0.00003817304,0.0001652537,0.000145635,0.00003131232],"category_scores_gemma":[0.00006595968,0.0001565006,0.0001059012,0.0001251845,0.0000794985,0.000008037571,0.00008405967,0.0001220536,0.00001622551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001689452,"about_ca_system_score_gemma":0.00006148969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008534135,"about_ca_topic_score_gemma":0.000003032856,"domain_scores_codex":[0.9988822,0.0001131492,0.0001872909,0.0005029285,0.00007861772,0.0002358526],"domain_scores_gemma":[0.9991549,0.0001445001,0.0001502476,0.0002106444,0.0002961297,0.0000435366],"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":[0.00007670202,0.0001388952,0.02016678,0.00004394606,0.00006236581,9.348606e-7,0.0000484826,0.003897022,0.9735605,0.0000124353,0.001811767,0.0001801367],"study_design_scores_gemma":[0.0008535278,0.0008673836,0.0006125689,0.00001241847,0.00004973,0.00000610054,0.0001534649,0.003881794,0.989197,0.0001934312,0.003930984,0.0002415779],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9502265,0.0002366878,0.04516482,0.0002350486,0.00002138485,0.0005255542,0.00002262476,0.00007473291,0.003492652],"genre_scores_gemma":[0.9240692,0.00001242816,0.07133833,0.0002759972,0.00008511561,0.0000541073,0.00229922,0.00003259222,0.001833048],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02617351,"threshold_uncertainty_score":0.6381911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007760557730760474,"score_gpt":0.2519632656610531,"score_spread":0.2442027079302926,"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."}}