{"id":"W4220672073","doi":"10.1016/j.cmpb.2022.106750","title":"Testing the Ability of Convolutional Neural Networks to Learn Radiomic Features","year":2022,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research","keywords":"Artificial intelligence; Convolutional neural network; Computer science; Pattern recognition (psychology); Radiomics; Deep learning; Feature (linguistics); Artificial neural network; Machine learning","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":[0.002458128,0.001143452,0.0003077096,0.0004445526,0.0001827837,0.000654541,0.0007763641,0.001602042,0.002924228],"category_scores_gemma":[0.01662276,0.0002601966,0.0006151724,0.0002798455,0.0005369986,0.001354678,0.0007157705,0.001009021,0.0008207181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003608177,"about_ca_system_score_gemma":0.0004951278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004325814,"about_ca_topic_score_gemma":0.002261769,"domain_scores_codex":[0.9990865,0.0002237769,0.0000919917,0.0003096739,0.000159756,0.0001283357],"domain_scores_gemma":[0.988762,0.009115178,0.0005298513,0.0006304628,0.0006911061,0.0002714601],"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":[0.01144635,0.005986479,0.1182833,0.00085378,0.001792243,0.0006738794,0.0003831604,0.4392879,0.06880698,0.002867852,0.008067166,0.3415509],"study_design_scores_gemma":[0.0002205711,0.002240112,0.02637344,0.00004590121,0.0001941832,0.0002707605,0.0001066283,0.9343314,0.03365704,0.001385157,0.001128168,0.00004668367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9830778,0.0003115306,0.01209815,0.0002324191,0.0001283621,0.00005366603,0.0006961129,0.0004305532,0.002971538],"genre_scores_gemma":[0.9921557,0.00009286475,0.004330961,0.00006925292,0.00002781015,0.00002778733,0.001479503,0.0000449885,0.001771206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004325814,"threshold_uncertainty_score":0.01299995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04637853673878643,"score_gpt":0.366186759643011,"score_spread":0.3198082229042246,"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."}}