{"id":"W3092560349","doi":"10.3390/cancers12102934","title":"Integrative Data Augmentation with U-Net Segmentation Masks Improves Detection of Lymph Node Metastases in Breast Cancer Patients","year":2020,"lang":"en","type":"article","venue":"Cancers","topic":"AI in cancer detection","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"CancerCare Manitoba; Research Institute in Oncology and Hematology; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; CancerCare Manitoba Foundation; Manitoba Medical Service Foundation","keywords":"Segmentation; Convolutional neural network; Computer science; Artificial intelligence; Lymph node; Histopathology; Pattern recognition (psychology); Breast cancer; Image segmentation; Medicine; Cancer; Pathology; Internal medicine","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":[0.00143928,0.001159709,0.000735125,0.0007174863,0.0002502824,0.0008480816,0.000756182,0.0009516167,0.001003983],"category_scores_gemma":[0.003202492,0.000364355,0.0009325849,0.0003706418,0.0004085172,0.0009423363,0.0009098822,0.0008061705,0.0005442363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006117107,"about_ca_system_score_gemma":0.0007159458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006436821,"about_ca_topic_score_gemma":0.008923951,"domain_scores_codex":[0.9995098,0.0001238596,0.0000344509,0.0001788828,0.00007741479,0.00007554825],"domain_scores_gemma":[0.9993413,0.0002537293,0.0000905994,0.0001030669,0.0001504655,0.00006074782],"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":[0.003532991,0.0007977054,0.1210999,0.0004313487,0.0005741839,0.0005868141,0.0003753708,0.2288004,0.07002549,0.0009468597,0.009462391,0.5633664],"study_design_scores_gemma":[0.00005072675,0.000649814,0.02942595,0.00007279943,0.000236416,0.0003828353,0.0001171392,0.9134057,0.05197781,0.001199316,0.002429555,0.00005200195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9368426,0.002022151,0.05204445,0.0006865538,0.0001993131,0.0001034455,0.001136577,0.003940299,0.003024524],"genre_scores_gemma":[0.9733745,0.000242197,0.023254,0.0002169876,0.00004517339,0.00003621171,0.00168441,0.0001236966,0.001022882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006436821,"threshold_uncertainty_score":0.01279873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02166422355006293,"score_gpt":0.2719270725993069,"score_spread":0.250262849049244,"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."}}