{"id":"W2972080651","doi":"10.3390/cells8091019","title":"Automated Counting of Cancer Cells by Ensembling Deep Features","year":2019,"lang":"en","type":"article","venue":"Cells","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"CancerCare Manitoba; Research Institute in Oncology and Hematology; University of Manitoba","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Deep learning; Computer science; Mean squared error; Pattern recognition (psychology); Correlation; Feature (linguistics); Pearson product-moment correlation coefficient; Mean absolute error; Regression; Statistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.000115972,0.0001232246,0.000173917,0.00004008181,0.00002301387,0.00001958998,0.0001794944,0.0001349544,0.0001149161],"category_scores_gemma":[0.00000909459,0.0001198639,0.00009726294,0.0001001642,0.00003458306,0.000003314038,0.0000782716,0.0000685086,0.00002297555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000116968,"about_ca_system_score_gemma":0.00002640465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001822226,"about_ca_topic_score_gemma":0.00003390211,"domain_scores_codex":[0.9992226,0.00002601626,0.0001827064,0.0002707235,0.000112992,0.0001849383],"domain_scores_gemma":[0.9993774,0.00001183108,0.0001364452,0.0003356701,0.0001042705,0.00003434227],"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":[0.000008888867,0.00002359688,0.0006697767,0.00003345871,0.00004971049,7.224218e-7,0.00002313298,0.0001236173,0.9571515,9.115126e-7,0.04118172,0.000732951],"study_design_scores_gemma":[0.0001413826,0.00003671693,0.00008414012,0.00001614119,0.00003268912,5.843616e-7,0.00002904785,0.0008933382,0.9767702,0.000002583221,0.02185654,0.0001366388],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931933,0.002729181,0.0003754229,0.0000132576,0.00006415328,0.00014465,0.000009627464,0.00006965575,0.003400784],"genre_scores_gemma":[0.9948107,0.0005507158,0.0008583469,0.0001917528,0.00005355361,0.000006877401,0.0000665081,0.00002513457,0.003436405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01961869,"threshold_uncertainty_score":0.4887909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00301021127587156,"score_gpt":0.2523881995942577,"score_spread":0.2493779883183862,"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."}}