{"id":"W4401015780","doi":"10.1016/j.heliyon.2024.e35276","title":"Biophysical profiling of red blood cells from thin-film blood smears using deep learning","year":2024,"lang":"en","type":"article","venue":"Heliyon","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vancouver General Hospital; British Columbia Institute of Technology; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institutes of Health Research; Health Canada; Canadian Blood Services; Australian Government","keywords":"Red blood cell; Blood smear; Convolutional neural network; Pathology; Biomedical engineering; Deep learning; Blood cell; Medicine; Artificial intelligence; Computer science; Immunology; Malaria","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001120808,0.0002063772,0.0002465051,0.0001595191,0.00007938869,0.0004931474,0.0005860908,0.0000603063,0.00001451179],"category_scores_gemma":[0.00006989127,0.0002036625,0.0001610464,0.0006388783,0.00007766334,0.000900784,0.0003687473,0.0002439172,0.00007506731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001673385,"about_ca_system_score_gemma":0.0001136064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003324205,"about_ca_topic_score_gemma":0.000001244596,"domain_scores_codex":[0.9982575,0.00006511825,0.000312615,0.0005900268,0.000424609,0.0003501729],"domain_scores_gemma":[0.9991005,0.0001429328,0.00008672447,0.0004574667,0.00007604923,0.0001362957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009286525,0.0005053006,0.0009065132,0.0005472525,0.0002127173,0.0003211124,0.000640856,0.005607343,0.9846408,0.002984726,0.00003333286,0.003590785],"study_design_scores_gemma":[0.0003427781,0.0001147555,0.0002665689,0.0009102934,0.0002204628,0.00001843171,0.00005360441,0.2704654,0.7258318,0.001166544,0.0002930473,0.0003163138],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9829366,0.00488008,0.009270182,0.00007158689,0.0005570024,0.00014937,0.00002998229,0.0006335542,0.001471618],"genre_scores_gemma":[0.9484565,0.00006185375,0.05105188,0.00005666081,0.0001625757,0.000004761125,0.00001815562,0.00003909651,0.0001485312],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2648581,"threshold_uncertainty_score":0.8305114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01412293277057575,"score_gpt":0.2421881181730614,"score_spread":0.2280651854024857,"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."}}