{"id":"W2799291955","doi":"10.1016/j.compbiomed.2018.04.004","title":"Mass detection in digital breast tomosynthesis data using convolutional neural networks and multiple instance learning","year":2018,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Department of Biotechnology, Ministry of Science and Technology, India","keywords":"Computer science; Artificial intelligence; CAD; Convolutional neural network; Mammography; Pattern recognition (psychology); Digital Breast Tomosynthesis; Digital mammography; Voxel; Artificial neural network; Deep learning; Breast cancer; Computer vision; Cancer","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":[0.0007252255,0.0008858323,0.0007592975,0.001618401,0.0002135485,0.000820453,0.001073431,0.001170337,0.001276549],"category_scores_gemma":[0.002326798,0.0003529038,0.0007592754,0.0007781672,0.0002793808,0.0006479041,0.0006966953,0.0009291963,0.0006576183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000617366,"about_ca_system_score_gemma":0.0005243209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006099377,"about_ca_topic_score_gemma":0.008353946,"domain_scores_codex":[0.9997659,0.00003669545,0.00001801677,0.00008438693,0.00005047848,0.000044499],"domain_scores_gemma":[0.9993196,0.0003989168,0.00006876348,0.00008907537,0.00009162184,0.00003207821],"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":[0.001415112,0.0004941835,0.02187065,0.0003475056,0.0003060378,0.0006985834,0.00009022008,0.1851683,0.0378231,0.001663325,0.008208594,0.7419145],"study_design_scores_gemma":[0.00001090439,0.00003005883,0.002614025,0.00000982101,0.00003498907,0.000136135,0.00001840763,0.9869117,0.008540901,0.001096459,0.000589146,0.000007583156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.561765,0.003187072,0.4207542,0.001298754,0.0002355956,0.0001600234,0.003956991,0.006292366,0.002349944],"genre_scores_gemma":[0.8676337,0.0005458526,0.1250863,0.0001471253,0.0001282095,0.00007113542,0.003990591,0.0001302625,0.002266742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006099377,"threshold_uncertainty_score":0.01212776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02959589168776544,"score_gpt":0.2876600106828396,"score_spread":0.2580641189950742,"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."}}