{"id":"W3131464794","doi":"10.1016/j.bpj.2020.11.2193","title":"Machine Learning Enabled Phase Unwrapping for Digitalholographic Microscopy","year":2021,"lang":"en","type":"article","venue":"Biophysical Journal","topic":"Digital Holography and Microscopy","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Robustness (evolution); Holography; Computer science; Speckle pattern; Convolutional neural network; Speckle noise; Digital holography; Artificial intelligence; Microscopy; Optics; Computation; Phase (matter); Biological system; Materials science; Computer vision; Algorithm; Physics; Chemistry","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001052523,0.0002166947,0.0003015044,0.00009428048,0.000396364,0.0004075893,0.0001755193,0.00004874115,0.0001300164],"category_scores_gemma":[0.00001615418,0.000194363,0.0005569172,0.000375691,0.0001121784,0.0003323139,0.00005921147,0.0004140031,0.00002091952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001116299,"about_ca_system_score_gemma":0.00007573917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000358595,"about_ca_topic_score_gemma":1.823632e-7,"domain_scores_codex":[0.9987586,0.00004746274,0.0003029187,0.0002934458,0.0001215326,0.0004760477],"domain_scores_gemma":[0.9992408,0.00008887297,0.0001588564,0.0001451425,0.0001669252,0.0001994047],"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":[0.000113365,0.00107155,0.003538648,0.00001498882,0.0002245817,0.00003697161,0.00006084228,0.00001494627,0.9618834,0.008132636,0.0005531161,0.02435498],"study_design_scores_gemma":[0.007662043,0.0009525914,0.0004355964,0.0001278947,0.0001659888,0.0001136085,0.0004789328,0.0004839076,0.8529512,0.01790226,0.1179297,0.0007963226],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9430729,0.0002090994,0.04923891,0.0001844951,0.0004678204,0.0001648709,0.0001854103,0.00006086289,0.006415597],"genre_scores_gemma":[0.9968393,0.00001730842,0.001485706,0.0001061137,0.0006915603,0.00001497175,0.0001592154,0.00002958346,0.0006561827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1173765,"threshold_uncertainty_score":0.7925892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0124330876142327,"score_gpt":0.2847918986746432,"score_spread":0.2723588110604105,"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."}}