{"id":"W4214603720","doi":"10.1101/2022.02.27.482183","title":"Machine learning meets classical computer vision for accurate cell identification","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Toronto; McGill University Health Centre","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Pipeline (software); Identification (biology); Computer vision; Throughput; Pattern recognition (psychology); Machine learning","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":[0.000815622,0.0004531112,0.0004216064,0.0001956543,0.0002743946,0.0002497074,0.0006827996,0.000466304,0.00004255322],"category_scores_gemma":[0.0001264959,0.0005178554,0.0003481528,0.0002145481,0.00007499663,0.00001316157,0.001249675,0.0006359987,0.00001356689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001191924,"about_ca_system_score_gemma":0.0001913061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001502965,"about_ca_topic_score_gemma":0.000002370531,"domain_scores_codex":[0.9971985,0.0002388858,0.0005708194,0.001305275,0.0002958918,0.0003906087],"domain_scores_gemma":[0.9975904,0.00003490048,0.0005845728,0.001257707,0.000391175,0.0001412831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005619346,0.0001562706,0.0004384942,0.000166359,0.0001047499,0.000008654705,0.0000022318,0.0004484778,0.9948888,0.00002957879,0.003689685,0.00001047523],"study_design_scores_gemma":[0.0003454386,0.0002176826,0.002368426,0.00003347304,0.000154151,1.515417e-8,0.000001035908,0.01275788,0.8381428,0.000001220467,0.1453905,0.0005874533],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8027959,0.00333822,0.1894898,0.0004534799,0.0007901195,0.002187412,0.0003032905,0.0006011961,0.000040648],"genre_scores_gemma":[0.9852696,0.0006404071,0.01261692,0.0001732681,0.0005626377,0.0004431602,0.00003920376,0.0001489108,0.0001059033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1824737,"threshold_uncertainty_score":0.9997273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00936785137153216,"score_gpt":0.2523850480024046,"score_spread":0.2430171966308725,"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."}}