{"id":"W3094888049","doi":"10.48550/arxiv.2010.14782","title":"Classification Beats Regression: Counting of Cells from Greyscale Microscopic Images based on Annotation-free Training Samples","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Cell counting; Grayscale; Pattern recognition (psychology); Convolutional neural network; Segmentation; Image (mathematics); Code (set theory); Machine learning; Cell","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001980454,0.001510498,0.00136331,0.001737029,0.0004050383,0.001291486,0.003009183,0.001477353,0.002266437],"category_scores_gemma":[0.005843946,0.0006034353,0.0009925134,0.001439861,0.000673574,0.001500645,0.001302201,0.001846082,0.002818896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001012284,"about_ca_system_score_gemma":0.001104006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005531009,"about_ca_topic_score_gemma":0.008300523,"domain_scores_codex":[0.9987878,0.0001779976,0.00006588733,0.0005145166,0.0003269846,0.0001269153],"domain_scores_gemma":[0.9973974,0.0007906577,0.0004161109,0.0006073884,0.0006771527,0.0001112173],"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":[0.0005875455,0.0003089366,0.02228539,0.0007376876,0.0001866058,0.0003055849,0.0002200484,0.06806635,0.10021,0.006439354,0.02753326,0.7731192],"study_design_scores_gemma":[0.00003097957,0.00009579729,0.007183547,0.00005947984,0.00005564366,0.0002363661,0.0000678391,0.9250435,0.0506838,0.00612576,0.01037325,0.00004394108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03683773,0.001031669,0.9439964,0.0003967463,0.0002251682,0.0001932618,0.001862601,0.01268973,0.00276665],"genre_scores_gemma":[0.2796125,0.001164413,0.7002847,0.0005219456,0.0002439692,0.0007391244,0.008450259,0.001371955,0.007611122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005531009,"threshold_uncertainty_score":0.01099765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0741008396638951,"score_gpt":0.2267020316791175,"score_spread":0.1526011920152224,"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."}}