{"id":"W3130331976","doi":"10.1016/j.compbiomed.2021.104265","title":"Improving blood cells classification in peripheral blood smears using enhanced incremental training","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Deep learning; Peripheral blood; Blood smear; White blood cell; Automation; Machine learning; Pattern recognition (psychology); Medicine; Pathology; Immunology; Engineering","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":[0.0007196283,0.0005502321,0.0005653757,0.0006717332,0.000296617,0.0005204731,0.001118328,0.000790515,0.001449012],"category_scores_gemma":[0.002398264,0.0002219653,0.0005378756,0.0004265243,0.0001804038,0.0005366509,0.0006261226,0.0007620989,0.0008313353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002385374,"about_ca_system_score_gemma":0.0006042283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006488451,"about_ca_topic_score_gemma":0.008889927,"domain_scores_codex":[0.9996638,0.00006258296,0.00002817869,0.00009811252,0.00009049434,0.00005686104],"domain_scores_gemma":[0.9988486,0.0005508298,0.00005363589,0.0001226485,0.000378935,0.00004548708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004461303,0.0002927597,0.008995309,0.00009972337,0.00007481753,0.0001408154,0.000092121,0.04110809,0.03702234,0.000384208,0.003483615,0.9078602],"study_design_scores_gemma":[0.0000112054,0.0001184636,0.005143439,0.00001377991,0.00005606176,0.000135546,0.00002404988,0.9817495,0.01144062,0.0004328844,0.0008634666,0.00001093081],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3745412,0.001986842,0.6134864,0.0004830992,0.000336275,0.0001284101,0.0004144748,0.004828996,0.003794367],"genre_scores_gemma":[0.8163539,0.0003541692,0.1787094,0.0002255836,0.00009626614,0.00005528258,0.0008373097,0.000102381,0.003265808],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006488451,"threshold_uncertainty_score":0.01290137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03373361478076531,"score_gpt":0.3017786389410164,"score_spread":0.2680450241602511,"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."}}