{"id":"W2992206721","doi":"10.1101/867218","title":"CellCountCV – a web-application for accurate cell counting and automated batch processing of microscopy images using fully-convolutional neural networks","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Endoplasmic Reticulum Stress and Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"Russian Science Foundation","keywords":"Endoplasmic reticulum; Convolutional neural network; Computer science; Artificial intelligence; Tunicamycin; Automation; Image processing; Microscopy; Fluorescence microscope; Artificial neural network; Machine learning; Biological system; Chemistry; Cell biology; Biology; Fluorescence; Image (mathematics); Pathology; Unfolded protein response; Engineering; Physics; Optics; 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":[0.000767927,0.001586281,0.0006290745,0.00112814,0.0002224668,0.0007061269,0.001773258,0.001206002,0.01925673],"category_scores_gemma":[0.001375836,0.0007890557,0.0007028988,0.0005564669,0.0003055006,0.00070361,0.00114404,0.001170358,0.007034205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007704286,"about_ca_system_score_gemma":0.0007046961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003954859,"about_ca_topic_score_gemma":0.00391561,"domain_scores_codex":[0.9996407,0.00004329775,0.00002868178,0.000103682,0.0001394936,0.00004403159],"domain_scores_gemma":[0.9993905,0.000245376,0.00004305902,0.0001022552,0.0001719908,0.00004686845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001518733,0.0004412025,0.003971038,0.00114463,0.0005443672,0.0009308936,0.0002240298,0.08721332,0.1452832,0.007331325,0.1860583,0.565339],"study_design_scores_gemma":[0.00008151218,0.00004857396,0.001547854,0.0000368376,0.00002101347,0.0001994436,0.00001312091,0.9007258,0.07474342,0.002550924,0.01997447,0.00005704095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01187934,0.0002436177,0.6743077,0.0001175297,0.0001543753,0.0001642057,0.003322559,0.3080197,0.001790809],"genre_scores_gemma":[0.2127695,0.000516623,0.7141085,0.0004202976,0.0001051515,0.00118137,0.01914664,0.03234192,0.01941],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01925673,"threshold_uncertainty_score":0.06442022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007304268909314925,"score_gpt":0.2411046871532805,"score_spread":0.2338004182439656,"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."}}