{"id":"W4289291866","doi":"10.48550/arxiv.1811.06038","title":"Focus Quality Assessment of High-Throughput Whole Slide Imaging in\\n Digital Pathology","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Digital pathology; Computer science; Focus (optics); Computer vision; Artificial intelligence; Image quality; Kernel (algebra); Workflow; Metric (unit); Quality (philosophy); Image resolution; Scanner; Image (mathematics); Optics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.003000112,0.0006920584,0.0004775283,0.003008217,0.0004346508,0.001882294,0.0008684063,0.000854905,0.002025816],"category_scores_gemma":[0.00754426,0.0004463851,0.0007168896,0.00110479,0.000655561,0.001194819,0.001175008,0.0006642403,0.0005533509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001057245,"about_ca_system_score_gemma":0.0007396864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005014446,"about_ca_topic_score_gemma":0.007792889,"domain_scores_codex":[0.9984797,0.0002566743,0.00009974649,0.0003329922,0.000725965,0.0001050112],"domain_scores_gemma":[0.9956359,0.001599504,0.0007595342,0.0004958227,0.001356722,0.0001525011],"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":[0.0009829887,0.0002412533,0.04229677,0.001193086,0.0003433402,0.0005732097,0.0012224,0.1066199,0.311018,0.00389929,0.006512737,0.5250971],"study_design_scores_gemma":[0.00004251731,0.0003882032,0.0727347,0.0001400696,0.0001949824,0.00131792,0.0004537254,0.6505823,0.2620742,0.00401589,0.007870192,0.0001851682],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2037043,0.002152495,0.785538,0.0003286791,0.0001045522,0.0003101951,0.0005801256,0.00505688,0.002224794],"genre_scores_gemma":[0.5754026,0.001117448,0.4189722,0.0001964182,0.00007703459,0.0001723101,0.0009537046,0.0007911682,0.002317135],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005014446,"threshold_uncertainty_score":0.01586628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04717142400077898,"score_gpt":0.2373219756414771,"score_spread":0.1901505516406981,"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."}}