{"id":"W4384154714","doi":"10.1364/boe.492739","title":"Design and validation of a convolutional neural network for fast, model-free blood flow imaging with multiple exposure speckle imaging","year":2023,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Thermoregulation and physiological responses","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Chang Gung Memorial Hospital, Linkou; Campus France; Chang Gung Medical Foundation; Ministère de l'Education Nationale, de l'Enseignement Superieur et de la Recherche; Ministère de l'Économie, de la Science et de l'Innovation - Québec; National Science and Technology Council","keywords":"Speckle pattern; Convolutional neural network; Speckle imaging; Computer science; Medical imaging; Blood flow; Image processing; Artificial intelligence; Optics; Image (mathematics); Medicine; Radiology; 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":[0.0002828079,0.0001297827,0.0002394044,0.0000756631,0.00008022411,0.0000159168,0.00009712409,0.00005432928,0.0000197484],"category_scores_gemma":[0.0003279183,0.00009451451,0.00005126989,0.0001971802,0.0002837305,0.00006023085,0.00007430752,0.00008536931,0.000001005081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001035576,"about_ca_system_score_gemma":0.0000689493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001972899,"about_ca_topic_score_gemma":1.08424e-7,"domain_scores_codex":[0.998885,0.00005778705,0.0002469899,0.0002341451,0.0003156564,0.0002604004],"domain_scores_gemma":[0.9987637,0.0006521642,0.00008464219,0.0001985585,0.0001276217,0.0001733228],"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":[0.01097386,0.0005686902,0.007982817,0.0003928871,0.0002174363,0.00007407158,0.0006798206,0.248645,0.7057814,0.001486144,0.007308451,0.01588948],"study_design_scores_gemma":[0.003453491,0.00025176,0.01422829,0.0001078518,0.00008586243,0.00002169621,0.00005096147,0.977116,0.003330419,0.001099841,0.000138752,0.0001151002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6167911,0.0001507018,0.3815139,0.0007351922,0.00007371135,0.0005281609,0.00009059405,0.000101354,0.00001537606],"genre_scores_gemma":[0.8708542,0.00001307011,0.1284652,0.0001207822,0.0001914814,0.00004526147,0.0001910973,0.00001901846,0.0000999283],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.728471,"threshold_uncertainty_score":0.385419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03163396041473376,"score_gpt":0.2707316502277993,"score_spread":0.2390976898130655,"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."}}