{"id":"W2887263930","doi":"10.1007/978-3-030-27272-2_33","title":"TriResNet: A Deep Triple-Stream Residual Network for Histopathology Grading","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Histopathology; Grading (engineering); Computer science; Artificial intelligence; Residual; Convolutional neural network; Benchmark (surveying); Pattern recognition (psychology); Pathology; Algorithm; Medicine; Engineering","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":[0.0008182646,0.001543271,0.0008601438,0.001390586,0.0003470504,0.0008241978,0.002489641,0.001463956,0.007126721],"category_scores_gemma":[0.001786161,0.0005344781,0.0008329433,0.0007053165,0.0002621768,0.001045269,0.001271376,0.00133766,0.004968358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006411161,"about_ca_system_score_gemma":0.001107226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008147547,"about_ca_topic_score_gemma":0.01777823,"domain_scores_codex":[0.9997049,0.00004365192,0.00001582327,0.0001027845,0.00008211451,0.00005071284],"domain_scores_gemma":[0.9995758,0.00009619188,0.00004035016,0.00008962453,0.0001471279,0.0000508094],"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":[0.0006977653,0.0004072537,0.003737678,0.0002912646,0.0002780103,0.0002354501,0.00006317339,0.08643433,0.01603012,0.003700513,0.07616779,0.8119567],"study_design_scores_gemma":[0.00004655878,0.0002018773,0.001074888,0.0000598865,0.00009369732,0.0001403383,0.00002933201,0.9645742,0.01662981,0.006603826,0.01051437,0.00003119435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07593549,0.002626631,0.854709,0.001172277,0.0008868333,0.0004458181,0.01358069,0.04177479,0.008868439],"genre_scores_gemma":[0.4576351,0.001498266,0.4577634,0.001161706,0.0004326077,0.0005176553,0.03189692,0.002000547,0.04709368],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008147547,"threshold_uncertainty_score":0.02384126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02036168619445137,"score_gpt":0.2725924015869833,"score_spread":0.2522307153925319,"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."}}