{"id":"W4309763239","doi":"10.1016/j.media.2022.102690","title":"Symmetry-based regularization in deep breast cancer screening","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia; Canadian Mennonite University; Nvidia","keywords":"Regularization (linguistics); Computer science; Artificial intelligence; Machine learning; Breast cancer; Generalization; Artificial neural network; Theoretical computer science; Mathematics; Medicine; Cancer","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001191328,0.0004827807,0.0007126131,0.0005780545,0.0002559247,0.0005343581,0.001025506,0.0008530798,0.001864264],"category_scores_gemma":[0.002238377,0.0004025631,0.0007358379,0.0004888356,0.0005648037,0.000720358,0.001035822,0.000951313,0.0005231587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004729622,"about_ca_system_score_gemma":0.0009769794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003219483,"about_ca_topic_score_gemma":0.004009002,"domain_scores_codex":[0.9996717,0.0001324903,0.00001484211,0.00004552873,0.00008552788,0.00004978265],"domain_scores_gemma":[0.9993487,0.0003041176,0.00006851327,0.0001000617,0.0001330426,0.00004548937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004592218,0.000236872,0.002028742,0.0002809927,0.0001923661,0.0001358295,0.0001111721,0.4431933,0.05546835,0.04937588,0.008301659,0.4402156],"study_design_scores_gemma":[0.000006233307,0.00002303816,0.0002483283,0.000005341569,0.00001035577,0.00003997068,0.000006733477,0.9896039,0.003740922,0.005712149,0.0005983116,0.000004820182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02956895,0.0006380475,0.9666771,0.0004181583,0.00004017598,0.00003772472,0.0001224525,0.0005418397,0.001955565],"genre_scores_gemma":[0.6584563,0.0008599747,0.3286088,0.0004053883,0.0001240784,0.0001219385,0.0005130329,0.0003151578,0.01059522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003219483,"threshold_uncertainty_score":0.006401479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006943077669812815,"score_gpt":0.2585088927304301,"score_spread":0.2515658150606173,"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."}}