{"id":"W2966077510","doi":"10.1002/jbio.201900128","title":"Convolutional neural networks for reconstruction of undersampled optical projection tomography data applied to in vivo imaging of zebrafish","year":2019,"lang":"en","type":"article","venue":"Journal of Biophotonics","topic":"Photoacoustic and Ultrasonic Imaging","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council; Medical Research Council; Francis Crick Institute; Medical Research Council Canada; Home Office; British Heart Foundation; University College London; Imperial College London; National Institute for Health and Care Research; Cancer Research UK; Academy of Medical Sciences; Wellcome Trust; Nvidia","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Projection (relational algebra); Iterative reconstruction; Computer vision; Tomographic reconstruction; Compressed sensing; Preclinical imaging; Tomography; Pattern recognition (psychology); Algorithm; In vivo; Optics; Physics; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005765653,0.0007344472,0.000341086,0.0005806415,0.0002027169,0.00038948,0.0004990596,0.0004869704,0.001021857],"category_scores_gemma":[0.001707349,0.0003985858,0.0004866126,0.0005744447,0.0002865288,0.0003894262,0.0005449498,0.0008522178,0.0003041444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008022326,"about_ca_system_score_gemma":0.0009555511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01727071,"about_ca_topic_score_gemma":0.02322992,"domain_scores_codex":[0.9998167,0.00003020724,0.00001238748,0.00004479113,0.00006788674,0.00002795013],"domain_scores_gemma":[0.9996785,0.0001167251,0.0000467515,0.00004230204,0.0001002425,0.00001555625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002466763,0.000062532,0.002925789,0.0001635055,0.0001245956,0.0002713233,0.0001065873,0.7234365,0.09101417,0.003011217,0.002305014,0.1763322],"study_design_scores_gemma":[0.00000225349,0.00001386955,0.0006111089,0.000005850484,0.000006678775,0.00002507352,0.000006807378,0.9903239,0.008107769,0.0004559492,0.0004352937,0.000005522434],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1610673,0.0006377468,0.8332131,0.0003949319,0.0000621712,0.00007615623,0.001135237,0.001963528,0.001449866],"genre_scores_gemma":[0.5826871,0.0006737127,0.4103157,0.0001280362,0.00002353608,0.0001404618,0.003068929,0.0002659588,0.002696596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01727071,"threshold_uncertainty_score":0.03434038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01263365973258037,"score_gpt":0.2281953449555876,"score_spread":0.2155616852230073,"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."}}