{"id":"W2606209624","doi":"10.15252/msb.20177551","title":"Automated analysis of high‐content microscopy data with deep learning","year":2017,"lang":"en","type":"article","venue":"Molecular Systems Biology","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":298,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"Canadian Institutes of Health Research; National Institutes of Health; Canada Foundation for Innovation; Connaught Fund; National Human Genome Research Institute; University of Toronto; Ontario Ministry of Research, Innovation and Science; Canadian Institute for Advanced Research","keywords":"Deep learning; Convolutional neural network; Artificial intelligence; High-content screening; Computer science; Microscopy; Pattern recognition (psychology); Machine learning; Biology; Artificial neural network; Cell; Pathology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0004252851,0.0002242383,0.00061166,0.0002095925,0.0001587237,0.0000761851,0.001211926,0.0002429388,0.000008023637],"category_scores_gemma":[0.0002070972,0.0001846798,0.0001470254,0.0001795733,0.0002316952,0.000008547131,0.0006476746,0.0001078904,0.00000389762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001387072,"about_ca_system_score_gemma":0.00003689728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002216337,"about_ca_topic_score_gemma":0.0004416756,"domain_scores_codex":[0.9982236,0.0002460859,0.0003967742,0.0007357532,0.0001122581,0.0002854972],"domain_scores_gemma":[0.9961484,0.00001104339,0.0006136279,0.002925085,0.0002350609,0.00006676635],"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":[0.00004866086,0.00003961872,0.03532984,0.00002090684,0.00295311,0.00002211391,0.000009075829,0.0004176884,0.9603964,0.00008287449,0.000142976,0.0005367056],"study_design_scores_gemma":[0.000776203,0.0007100155,0.01792745,0.00004104585,0.002545339,0.00003046014,0.00008212779,0.03148451,0.9383653,0.000005528813,0.007493234,0.0005387388],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9019232,0.001639489,0.09552051,0.00003389992,0.00004607433,0.0002261897,0.00003794045,0.00008531872,0.0004873317],"genre_scores_gemma":[0.9953973,0.0001085115,0.001977165,0.00003953437,0.0000362275,0.00002366626,0.002160628,0.00002915874,0.0002278488],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09354334,"threshold_uncertainty_score":0.7531025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01719669599324931,"score_gpt":0.3037710955816098,"score_spread":0.2865743995883605,"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."}}