{"id":"W3119098051","doi":"10.1364/oe.416824","title":"Learning to autofocus in whole slide imaging via physics-guided deep cascade networks","year":2021,"lang":"en","type":"article","venue":"Optics Express","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Autofocus; Computer science; Artificial intelligence; Cascade; Computer vision; Image quality; Focus (optics); Sample (material); Binary number; Optics; Image (mathematics); Physics; Mathematics","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":[0.00008215314,0.0001379555,0.0001470172,0.00004162383,0.00008256979,0.0001246304,0.0001633716,0.00005319142,0.000009284027],"category_scores_gemma":[0.00002403386,0.0001686631,0.0000360392,0.0003241712,0.00001471167,0.0001246601,0.000106651,0.0003215849,0.00001946793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006319477,"about_ca_system_score_gemma":0.00001270716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001473873,"about_ca_topic_score_gemma":0.000005071652,"domain_scores_codex":[0.9991678,0.00001536022,0.0001970581,0.0002100199,0.0000946297,0.0003151111],"domain_scores_gemma":[0.9995533,0.00003140795,0.00002343403,0.0002536421,0.00006612093,0.0000721073],"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":[8.033806e-7,0.00002086142,0.0001233037,0.00003189486,0.000005868197,0.00003292247,0.0005450131,0.8662904,0.09158741,0.0002459506,0.000878208,0.04023735],"study_design_scores_gemma":[0.0001036176,0.000003290715,0.00005831149,0.00007488618,0.000007422845,0.00001269005,0.00008292771,0.9172103,0.07327691,0.0006681906,0.008290448,0.000211025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01190896,0.0004075152,0.9829015,0.0002072666,0.00007443115,0.0001070096,0.000001573745,0.0004972296,0.003894534],"genre_scores_gemma":[0.8482266,0.00003151991,0.1509493,0.0001036285,0.0001521287,0.00009831205,0.00001907405,0.0000619236,0.0003575032],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8363177,"threshold_uncertainty_score":0.6877883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00876615836669034,"score_gpt":0.2471441172555832,"score_spread":0.2383779588888929,"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."}}