{"id":"W2920892325","doi":"10.48550/arxiv.1903.07011","title":"Deep Features for Tissue-Fold Detection in Histopathology Images","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Convolutional neural network; Digital pathology; Computer science; Magnification; Pattern recognition (psychology); Digitization; H&E stain; Classifier (UML); Support vector machine; Feature (linguistics); Feature vector; Pathology; Computer vision; Medicine; Immunohistochemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009418812,0.0009954533,0.0005797731,0.001362393,0.00023032,0.0006735759,0.0009266916,0.0007676961,0.001715026],"category_scores_gemma":[0.001955267,0.0003250504,0.0005699188,0.0008186381,0.0003007978,0.001028482,0.0009460628,0.0008879665,0.0007186651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007597567,"about_ca_system_score_gemma":0.0005292983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004303266,"about_ca_topic_score_gemma":0.006120814,"domain_scores_codex":[0.999505,0.00007731076,0.00002981352,0.0001189797,0.0001716869,0.0000972276],"domain_scores_gemma":[0.9993426,0.0002040833,0.0001056263,0.0001262935,0.0001768144,0.00004452778],"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":[0.0005223514,0.0002786323,0.006548163,0.0002303607,0.0001311733,0.0001824091,0.0001047046,0.1114582,0.07523056,0.00235742,0.0130044,0.7899517],"study_design_scores_gemma":[0.00001710002,0.000125768,0.005487745,0.00002773334,0.00003523209,0.0001263537,0.0000429343,0.9562601,0.03145751,0.003130866,0.00326875,0.00001990049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2647531,0.002573485,0.714671,0.0005805051,0.0001953001,0.0001686877,0.002546564,0.01183604,0.002675366],"genre_scores_gemma":[0.7724368,0.0006662679,0.2172461,0.0001812262,0.00007133115,0.0001113871,0.005349929,0.0002248949,0.003712003],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004303266,"threshold_uncertainty_score":0.008556485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03747591586253522,"score_gpt":0.197078227388787,"score_spread":0.1596023115262518,"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."}}