{"id":"W2093976454","doi":"10.1109/icra.2014.6907081","title":"A system for automated counting of fetal and maternal red blood cells in clinical KB test","year":2014,"lang":"en","type":"article","venue":"","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Sinai Hospital; University of Toronto","funders":"","keywords":"Cell counting; Cluster analysis; Cytometry; Artificial intelligence; Computer science; Benchmarking; k-means clustering; Computer vision; Biomedical engineering; Flow cytometry; Pattern recognition (psychology); Medicine; Immunology; Internal medicine","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":[0.001423827,0.0009222672,0.001230501,0.002307189,0.0006680711,0.0009438468,0.001712734,0.001342724,0.007958241],"category_scores_gemma":[0.003174146,0.0005951265,0.0004082746,0.0009256579,0.0003324619,0.000789796,0.001372435,0.0008494035,0.005322573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006346378,"about_ca_system_score_gemma":0.001242722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001411106,"about_ca_topic_score_gemma":0.001701836,"domain_scores_codex":[0.9981245,0.0002696417,0.000190446,0.0005671118,0.0007433785,0.0001047715],"domain_scores_gemma":[0.9978472,0.00056875,0.0002186151,0.0003050274,0.0009084673,0.0001519296],"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":[0.001831956,0.0005751986,0.02542213,0.0006913108,0.0001683055,0.0009479488,0.0002974802,0.003570109,0.2771206,0.001325387,0.03861035,0.6494392],"study_design_scores_gemma":[0.0008140253,0.002546015,0.09596574,0.0003984878,0.0005603295,0.009538509,0.0002820218,0.3742571,0.4172047,0.002386349,0.09541257,0.0006341494],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08641724,0.001725482,0.8243263,0.0006191444,0.0006870318,0.00218301,0.003283815,0.07502674,0.005731108],"genre_scores_gemma":[0.2957506,0.0007591319,0.6842948,0.001150612,0.0003841179,0.003437977,0.004052037,0.00104108,0.00912964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007958241,"threshold_uncertainty_score":0.02662295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01216992885460433,"score_gpt":0.2647853892532168,"score_spread":0.2526154603986124,"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."}}