{"id":"W2979634944","doi":"10.1007/978-3-030-32692-0_3","title":"Globally-Aware Multiple Instance Classifier for Breast Cancer Screening","year":2019,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute","keywords":"Computer science; Artificial intelligence; Classifier (UML); Residual neural network; Mammography; Pixel; Pattern recognition (psychology); Artificial neural network; Breast cancer; Contextual image classification; Computer vision; Machine learning; Image (mathematics); Cancer; Medicine","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006771925,0.00027906,0.0002833928,0.0002938253,0.0002760449,0.000486556,0.002644439,0.0001272082,0.00001612678],"category_scores_gemma":[0.00005543913,0.000259024,0.00009076151,0.002333441,0.0002231586,0.001485852,0.0006896109,0.0003057809,0.00001722959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004981892,"about_ca_system_score_gemma":0.0004137041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001514967,"about_ca_topic_score_gemma":0.0004214398,"domain_scores_codex":[0.9967753,0.00004488867,0.0003258625,0.001305936,0.0007433926,0.0008045618],"domain_scores_gemma":[0.9979964,0.0003900311,0.0001680598,0.0009873327,0.0003183969,0.0001397966],"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":[0.00002664204,0.00002497133,0.02154021,0.00002999451,0.000006053788,0.000002941278,0.0002997509,0.1457518,0.001733121,0.0002686077,0.00003407952,0.8302819],"study_design_scores_gemma":[0.0007236145,0.00009328723,0.02787184,0.0001506868,0.000002268451,0.00003727014,0.000001135882,0.961357,0.006155666,0.002675022,0.0005730865,0.0003591494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01933264,0.0001620113,0.9739141,0.002401534,0.003305795,0.0006221827,0.00002172245,0.0002164281,0.0000236171],"genre_scores_gemma":[0.6882924,0.000007246728,0.309672,0.001718763,0.0002465131,0.00004696203,6.477264e-7,0.00001222034,0.000003268745],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8299227,"threshold_uncertainty_score":0.9999862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01585183058171993,"score_gpt":0.2640917233260536,"score_spread":0.2482398927443337,"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."}}