{"id":"W3109976697","doi":"10.21203/rs.3.rs-125179/v1","title":"Overcoming the Limitations of Patch-Based Learning to Detect Cancer in Whole Slide Images","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre; University of British Columbia; Sunnybrook Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Workflow; Artificial intelligence; Context (archaeology); Task (project management); Binary classification; Deep learning; Image (mathematics); Machine learning; Pattern recognition (psychology); Class (philosophy)","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":[0.001683928,0.0009487012,0.0008396843,0.0004956285,0.0003565688,0.0008551372,0.001404764,0.001224303,0.001775747],"category_scores_gemma":[0.005836324,0.0004303901,0.0005872846,0.0004450733,0.000845838,0.001151967,0.001296738,0.001198382,0.0009166346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005340549,"about_ca_system_score_gemma":0.0006360936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005723459,"about_ca_topic_score_gemma":0.007623284,"domain_scores_codex":[0.9992363,0.000158348,0.00004108678,0.0003064827,0.0001740063,0.00008366202],"domain_scores_gemma":[0.9974202,0.001252026,0.0002112227,0.0006130518,0.0003877571,0.0001158593],"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":[0.00113921,0.0003066624,0.01567968,0.0004962148,0.0002816375,0.0003065736,0.0002647973,0.3279068,0.07496291,0.001915868,0.007508672,0.5692309],"study_design_scores_gemma":[0.00003556562,0.000322002,0.006196207,0.00004631784,0.0000645561,0.0002118101,0.00009054836,0.955376,0.0326498,0.003033726,0.001954362,0.00001906452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4303341,0.002133998,0.55564,0.0009732463,0.000169526,0.0002516166,0.0006598522,0.005912472,0.003925206],"genre_scores_gemma":[0.8632801,0.0004276157,0.1305255,0.0003722609,0.00008794489,0.0001277177,0.001060461,0.0003433987,0.003775134],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005723459,"threshold_uncertainty_score":0.01138026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.138877638261455,"score_gpt":0.4032478553859268,"score_spread":0.2643702171244718,"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."}}