{"id":"W2269649163","doi":"10.1093/bioinformatics/btw252","title":"Classifying and segmenting microscopy images with deep multiple instance learning","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":449,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Pooling; Artificial intelligence; Convolutional neural network; Computer science; Pattern recognition (psychology); Segmentation; Deep learning; Feature (linguistics); Microscopy; Pixel; Contextual image classification; Machine learning; Computer vision; Image (mathematics)","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":[0.0001328838,0.0001214603,0.0001088113,0.00004269223,0.0001037762,0.00005503358,0.00008999562,0.00006410146,0.000005471034],"category_scores_gemma":[0.0001004637,0.00008007123,0.0000302966,0.00005995881,0.00009892211,0.00002218395,0.0001094426,0.00005486533,0.000005964717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001186603,"about_ca_system_score_gemma":0.00001841204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002932687,"about_ca_topic_score_gemma":0.0000189929,"domain_scores_codex":[0.9993795,0.00001512031,0.0001922526,0.0001363466,0.0000854042,0.0001913702],"domain_scores_gemma":[0.9995422,0.00001931299,0.0001350156,0.0001961038,0.00006141303,0.00004591305],"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":[0.00002316507,0.00001020384,0.03802434,0.00004281202,0.00003704259,0.000001398025,0.00009950177,0.000004866135,0.9302178,0.000003654847,0.0006743136,0.03086091],"study_design_scores_gemma":[0.0005446231,0.0001411794,0.001065364,0.00007593694,0.00002382797,0.00001817398,0.0003272377,0.001520451,0.9733163,0.00000513125,0.022741,0.0002208386],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6323153,0.0004303746,0.3627881,0.00005139917,0.00001034478,0.0001452363,0.000002717309,0.000068395,0.004188184],"genre_scores_gemma":[0.8870393,0.0005013921,0.1115132,0.0001355698,0.00003491537,0.000009361403,0.00001838576,0.00001786079,0.0007299411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2547241,"threshold_uncertainty_score":0.326521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005466362266401763,"score_gpt":0.232331095263102,"score_spread":0.2268647329967002,"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."}}