{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002338375,0.000137046,0.0002527426,0.0001653095,0.00005146358,0.00003859609,0.0002579054,0.00006506902,0.000004053232],"category_scores_gemma":[0.00007044287,0.0001314897,0.00002338405,0.0003435035,0.0002131821,0.0002634671,0.0002155951,0.0001447054,4.809267e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003228339,"about_ca_system_score_gemma":0.0001025394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006347504,"about_ca_topic_score_gemma":0.00002453478,"domain_scores_codex":[0.9987663,0.000098045,0.0002934023,0.0004725441,0.00008011327,0.0002896001],"domain_scores_gemma":[0.9994753,0.0001038142,0.00008112816,0.0002199589,0.00003295781,0.00008681577],"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":[0.00001294487,0.0003032893,0.0169533,0.00005024851,0.00004035226,0.0002200176,0.002949045,0.00006563855,0.8632895,0.007240142,0.00001720782,0.1088583],"study_design_scores_gemma":[0.03052714,0.001994296,0.1319624,0.002762508,0.0003019947,0.001224165,0.005546586,0.565626,0.2370702,0.02042792,0.0003366761,0.002220063],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9362556,0.001007071,0.06124129,0.0003774776,0.0005715308,0.00009614845,0.000001597531,0.00004718633,0.0004020575],"genre_scores_gemma":[0.9549461,0.00004147367,0.04421699,0.0006821582,0.00008059183,0.00000471586,0.00001361868,0.000005924905,0.000008451732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6262194,"threshold_uncertainty_score":0.5361994,"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."}}