{"id":"W3200172539","doi":"10.1016/j.tice.2021.101653","title":"Automatic segmentation of blood cells from microscopic slides: A comparative analysis","year":2021,"lang":"en","type":"article","venue":"Tissue and Cell","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Segmentation; Benchmark (surveying); Biology; Blood smear; Artificial intelligence; Gametocyte; Deep learning; Cell type; Computer science; Cell; Pattern recognition (psychology); Machine learning; Malaria; Immunology; Plasmodium falciparum","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":[0.00002450134,0.00008153231,0.0002055625,0.00006216562,0.00002851891,0.0001417313,0.0001569637,0.00001281335,0.00006945981],"category_scores_gemma":[0.000003011284,0.00008219494,0.00004653735,0.0004291853,0.00003429514,0.0002744054,0.0000949056,0.0000235964,0.0000282875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003840939,"about_ca_system_score_gemma":0.00003595734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001022919,"about_ca_topic_score_gemma":0.00001666793,"domain_scores_codex":[0.9993533,0.0000342897,0.0001651227,0.0002285211,0.0001205385,0.00009819157],"domain_scores_gemma":[0.999486,0.00006619627,0.00008281461,0.0002544649,0.00005009353,0.00006039914],"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":[0.00000244527,0.0008950339,0.005767015,0.0001451227,0.0007236537,0.0001050201,0.005157567,0.000126156,0.9731663,0.0004319697,0.0006837564,0.01279595],"study_design_scores_gemma":[0.0002923681,0.00003500486,0.002850472,0.00001681417,0.0005120969,0.000001241871,0.0002266638,0.004040326,0.991317,0.0004969716,0.0001206143,0.00009045957],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895909,0.002054906,0.006345356,0.00003174103,0.00004404582,0.00006040719,0.00003401107,0.00003987638,0.001798752],"genre_scores_gemma":[0.9668905,0.00001630371,0.03251892,0.00006970214,0.000006549667,0.000003268738,0.00003285953,0.000002383453,0.0004595422],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02617356,"threshold_uncertainty_score":0.3351812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01110962736779869,"score_gpt":0.2592765626802589,"score_spread":0.2481669353124602,"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."}}