{"id":"W4288102880","doi":"10.48550/arxiv.1909.11866","title":"A Hybrid Deep Learning Architecture for Leukemic B-lymphoblast\\n Classification","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saskatoon Medical Imaging; University of Saskatchewan","funders":"","keywords":"Lymphoblast; Deep learning; Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning; Biology; Cell culture; Genetics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001419313,0.0003792628,0.0003371972,0.0003470051,0.0001508185,0.0004107656,0.002143668,0.0001436767,0.00000559683],"category_scores_gemma":[0.0001216418,0.0004546872,0.0003837243,0.0002945115,0.0001052518,0.0005848702,0.001536822,0.0004627673,0.0001625773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003614532,"about_ca_system_score_gemma":0.0003740363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003002165,"about_ca_topic_score_gemma":0.000005229336,"domain_scores_codex":[0.9977102,0.00008637679,0.000207232,0.001412083,0.0001203441,0.0004637597],"domain_scores_gemma":[0.9977744,0.0002028515,0.0003404748,0.001288968,0.0001970438,0.0001963107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007167734,0.0001626524,0.002549866,0.0003249506,0.0001510987,0.00007919416,0.0001535429,0.8861745,0.00012232,0.09208915,0.0006530049,0.01746802],"study_design_scores_gemma":[0.000732251,0.00009616877,0.001176739,0.0001214205,0.00009600719,0.00001260536,0.00003301254,0.9086069,0.0001908511,0.08604137,0.002321603,0.0005710549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1771038,0.0001137725,0.8167351,0.0000810644,0.0004803298,0.0005447289,0.00003245093,0.0005320208,0.004376806],"genre_scores_gemma":[0.9930917,0.00003428239,0.003614757,0.0001190453,0.00007564435,0.000005423798,0.0001132412,0.0000396662,0.002906231],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8159879,"threshold_uncertainty_score":0.9997905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04468868924571715,"score_gpt":0.186653403394945,"score_spread":0.1419647141492278,"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."}}