{"id":"W3155792530","doi":"10.1364/oe.439662","title":"Unsupervised hyperspectral stimulated Raman microscopy image enhancement: denoising and segmentation via one-shot deep learning","year":2021,"lang":"en","type":"preprint","venue":"Optics Express","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; SGS (Canada); Vector Institute; National Research Council Canada; University of Ottawa","funders":"National Research Council Canada; School of Graduate Studies, Queen's University; Natural Sciences and Engineering Research Council of Canada; Queen's University; University of Ottawa","keywords":"Hyperspectral imaging; Artificial intelligence; Pattern recognition (psychology); Computer science; Unsupervised learning; Segmentation; Autoencoder; Deep learning; Computer vision; Optics; Materials science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004759664,0.000537698,0.0003942876,0.0003678518,0.0002002797,0.0005073927,0.0008833892,0.0006745414,0.0008497321],"category_scores_gemma":[0.000672648,0.0002761721,0.0004066123,0.0003297545,0.0006218656,0.000776885,0.0009106919,0.0009869434,0.0004449658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004925167,"about_ca_system_score_gemma":0.0005760363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001178161,"about_ca_topic_score_gemma":0.003011912,"domain_scores_codex":[0.9997579,0.00003266185,0.000008106943,0.00007010292,0.00009950854,0.00003171434],"domain_scores_gemma":[0.9997782,0.00005934775,0.00004074832,0.00004701756,0.00005980375,0.00001489761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002795337,0.0002688023,0.001584369,0.0002422782,0.0001037222,0.000151397,0.0002445973,0.1345271,0.591407,0.01502074,0.003451907,0.2527185],"study_design_scores_gemma":[0.000007908018,0.00004379838,0.0008771777,0.000009020533,0.000008079895,0.00008205848,0.00002323064,0.8624386,0.1296408,0.004790626,0.002059535,0.00001911159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06032889,0.0001285222,0.9361355,0.0001735877,0.00001612678,0.00003535231,0.0001609584,0.001077751,0.001943286],"genre_scores_gemma":[0.3592751,0.0002278417,0.6342388,0.0001379495,0.0000209192,0.0001206746,0.0006774219,0.0002795445,0.00502175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001178161,"threshold_uncertainty_score":0.003573477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02108971305472841,"score_gpt":0.3368554691719651,"score_spread":0.3157657561172367,"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."}}