{"id":"W4386524943","doi":"10.1109/usnc-ursi52151.2023.10238149","title":"Deep Feature Learning for Microwave Mammography with Convolutional Autoencoders","year":2023,"lang":"en","type":"article","venue":"","topic":"Microwave Imaging and Scattering Analysis","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Mammography; Computer science; Transmitter; Categorization; Deep learning; Feature (linguistics); Convolutional neural network; Antenna (radio); Pattern recognition (psychology); Feature extraction; Microwave imaging; Microwave; Telecommunications; Breast cancer","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":[0.0006226538,0.0009611831,0.0006193996,0.000550451,0.0002076595,0.0005504639,0.001006106,0.0009122421,0.00160301],"category_scores_gemma":[0.001563101,0.0004143969,0.0005556822,0.0006212601,0.0003504839,0.000711899,0.0007035774,0.001174843,0.0007482422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009464609,"about_ca_system_score_gemma":0.0005971697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007033502,"about_ca_topic_score_gemma":0.009331394,"domain_scores_codex":[0.9998052,0.00004074966,0.00001101901,0.0000586343,0.00004369624,0.00004072005],"domain_scores_gemma":[0.9995714,0.000219475,0.00004602096,0.00005209271,0.0000940663,0.00001698421],"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":[0.0001867739,0.0001359766,0.00203708,0.0001038109,0.0001361139,0.00007898563,0.00005643934,0.5169435,0.01091954,0.005760663,0.006143684,0.4574975],"study_design_scores_gemma":[0.000002754429,0.00001144248,0.0001816172,0.00000507485,0.000004964459,0.000007546304,0.000003249493,0.9961538,0.001492572,0.001797183,0.0003368386,0.000003023793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04208908,0.0009671698,0.951212,0.0004017865,0.00006912397,0.00003645309,0.0003745737,0.003111549,0.001738388],"genre_scores_gemma":[0.6836964,0.0006421807,0.3055811,0.0003590562,0.00009907947,0.0001836785,0.001668083,0.0001812481,0.007589109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007033502,"threshold_uncertainty_score":0.0139851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006005268154154765,"score_gpt":0.1943334089307074,"score_spread":0.1883281407765526,"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."}}