{"id":"W4283032073","doi":"10.1364/boe.452645","title":"HoloPhaseNet: fully automated deep-learning-based hologram reconstruction using a conditional generative adversarial model","year":2022,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Digital Holography and Microscopy","field":"Physics and Astronomy","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Computer science; Holography; Artificial intelligence; Iterative reconstruction; Digital holography; Generator (circuit theory); Pixel; Generalization; Computer vision; Deep learning; Phase (matter); Image (mathematics); Pattern recognition (psychology); Algorithm; Optics; Mathematics; Power (physics); Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001453636,0.0001964205,0.0002180784,0.0001708072,0.0004892291,0.00007046249,0.0001997989,0.00007979995,0.0004606361],"category_scores_gemma":[0.00001014096,0.0002066697,0.0001633784,0.0003151193,0.0004223674,0.0001310149,0.0001255275,0.0003581477,0.000006131354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005211535,"about_ca_system_score_gemma":0.0001891159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001676471,"about_ca_topic_score_gemma":1.520085e-7,"domain_scores_codex":[0.9985403,0.0001215769,0.0002990547,0.0003667985,0.0003257578,0.0003464633],"domain_scores_gemma":[0.9993815,0.00005809255,0.0001698653,0.0001477505,0.00007243039,0.00017034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004747746,0.002120276,0.001301818,0.00002345151,0.000378363,0.00006141788,0.000403444,0.8436219,0.1283989,0.01077182,0.001718643,0.01072531],"study_design_scores_gemma":[0.001932717,0.0003019947,0.00004663055,0.00001015643,0.00005033157,0.00001517124,0.0003162398,0.9898099,0.002601163,0.002660627,0.001956939,0.0002980744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5507362,0.00002709086,0.4461158,0.00005694976,0.0006303018,0.0002418658,0.0008834146,0.0002549394,0.001053448],"genre_scores_gemma":[0.9688418,4.730356e-7,0.02908936,0.0001074455,0.000236541,0.00008098526,0.001564512,0.00002330539,0.0000556091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4181055,"threshold_uncertainty_score":0.8427746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01348688860606803,"score_gpt":0.268158924207886,"score_spread":0.2546720356018179,"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."}}