{"id":"W4319230693","doi":"10.1101/2023.02.03.526929","title":"Label-free tumor cells classification using deep learning and high-content imaging","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Chulalongkorn University; Asahi Glass Foundation","keywords":"Organoid; Cancer cell; Homogeneous; Tumor cells; Cell; Cancer; Pathology; Cell culture; Deep learning; Receiver operating characteristic; Cell type; Artificial intelligence; Biology; Computer science; Medicine; Cancer research; Cell biology; Machine learning; Internal medicine; Mathematics","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":[0.0006563975,0.0005139363,0.0004625484,0.0002755602,0.0002044697,0.0002765425,0.0005593603,0.0003381159,0.000008906778],"category_scores_gemma":[0.0003582786,0.0005972725,0.0001442939,0.0002777473,0.000159315,0.00001610171,0.00144483,0.0005915933,0.00001588424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001308487,"about_ca_system_score_gemma":0.0001683922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001863756,"about_ca_topic_score_gemma":0.00001061414,"domain_scores_codex":[0.9972183,0.0001809665,0.0005250322,0.001311947,0.0002760683,0.0004876792],"domain_scores_gemma":[0.9973923,0.00002571629,0.0005227433,0.001396083,0.0004804096,0.0001827639],"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":[0.00001561181,0.00004636635,0.008181826,0.0001371224,0.0001341119,0.00003508829,0.00000273891,0.00004309027,0.9910766,0.00002799774,0.0002875185,0.00001194942],"study_design_scores_gemma":[0.0003871739,0.00003644596,0.01484715,0.0001566001,0.0002317413,5.933023e-8,0.00001190922,0.007266496,0.974017,0.000003688627,0.00232811,0.0007136655],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784519,0.002061074,0.01817835,0.0001131466,0.0002505683,0.000495453,0.00004560484,0.000396456,0.000007446602],"genre_scores_gemma":[0.9789423,0.0010398,0.0191329,0.0001335449,0.0004129276,0.0001042086,0.000004684219,0.0002021959,0.00002745928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01705962,"threshold_uncertainty_score":0.9996479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02229429403968755,"score_gpt":0.245648406989304,"score_spread":0.2233541129496164,"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."}}