{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008694059,0.00117396,0.0005763955,0.0008989658,0.0003337716,0.001129354,0.002074155,0.001040791,0.002805634],"category_scores_gemma":[0.002250276,0.0005613337,0.0007966441,0.001041529,0.000665987,0.001878366,0.001118359,0.001604627,0.001607862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001225008,"about_ca_system_score_gemma":0.0008391787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00472064,"about_ca_topic_score_gemma":0.005642443,"domain_scores_codex":[0.9995301,0.00005632332,0.00003058498,0.00020203,0.0001210975,0.00005993437],"domain_scores_gemma":[0.9992092,0.0002000166,0.0001486113,0.000222064,0.0001641569,0.00005591803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004650955,0.0003908076,0.007303204,0.0004686926,0.0001845631,0.0003233078,0.0001233135,0.2686735,0.1531197,0.008284786,0.01476449,0.5458985],"study_design_scores_gemma":[0.000009698023,0.00004508037,0.001490837,0.00001825669,0.000023121,0.00008726282,0.00002831269,0.9165812,0.07404254,0.005044286,0.002611697,0.00001763801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06715748,0.0006550043,0.9133796,0.0006891648,0.00006013166,0.0001493363,0.001772044,0.01358616,0.002551069],"genre_scores_gemma":[0.3999055,0.0005197762,0.5898533,0.0002692629,0.00005397101,0.0001669591,0.005851295,0.0004068594,0.002973181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00472064,"threshold_uncertainty_score":0.009386301,"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."}}