{"id":"W2790764362","doi":"10.1101/256180","title":"Label-free assessment of red blood cell storage lesions by deep learning","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Blood Services; University of Alberta; Lunenfeld-Tanenbaum Research Institute; Toronto Metropolitan University","funders":"","keywords":"Flow cytometry; Deep learning; Whole blood; Red blood cell; Blood flow; Biomedical engineering; Human blood; Transfusion medicine; Computer science; Pathology; Medicine; Artificial intelligence; Blood transfusion; Physiology; Radiology; Surgery; Internal medicine; Immunology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007850523,0.0005455701,0.0003675853,0.0005474628,0.0001290007,0.0006894831,0.0006364775,0.0008051179,0.0008554604],"category_scores_gemma":[0.001684704,0.0001696324,0.0003546983,0.000273044,0.0003580222,0.0006087393,0.0004522754,0.0006896647,0.0003580371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008910206,"about_ca_system_score_gemma":0.0005861511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002328031,"about_ca_topic_score_gemma":0.001975483,"domain_scores_codex":[0.9997944,0.00004056195,0.00001085939,0.00007223643,0.00004933657,0.0000325583],"domain_scores_gemma":[0.9993648,0.0002016248,0.0001320796,0.00008179525,0.0001771287,0.00004251526],"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":[0.0007325047,0.0004858461,0.02014438,0.0001916773,0.0001301973,0.00025239,0.000115437,0.4797884,0.1864031,0.002906903,0.005206029,0.3036432],"study_design_scores_gemma":[0.000003296057,0.00003235212,0.0009517468,0.000005656326,0.000006991728,0.00002206429,0.000004955665,0.97817,0.01968293,0.0008247077,0.0002891643,0.000006088322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4843581,0.0008026696,0.509236,0.000652759,0.00009691397,0.00006975633,0.000486289,0.002297253,0.002000236],"genre_scores_gemma":[0.9386095,0.0001975357,0.05836637,0.0001730618,0.00002179787,0.00003467073,0.0003703288,0.00006010411,0.002166686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002328031,"threshold_uncertainty_score":0.006464779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01146979647479435,"score_gpt":0.2302413670649493,"score_spread":0.2187715705901549,"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."}}