{"id":"W3088345887","doi":"10.1101/2020.09.19.20198077","title":"Testing the Ability of Convolutional Neural Networks to Learn Radiomic Features","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Canadian Institutes of Health Research; National Institutes of Health; University of British Columbia","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Pattern recognition (psychology); Deep learning; Feature (linguistics); Radiomics; Artificial neural network; Image (mathematics); Machine learning; Sphericity; Mathematics","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":[0.002384299,0.001302368,0.0003380034,0.0005345899,0.0002055412,0.0006346055,0.0007945581,0.001142,0.001160671],"category_scores_gemma":[0.008416586,0.0003929332,0.0005897791,0.0003492349,0.0005794129,0.0009153237,0.0005708,0.0008482161,0.0003357564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007889408,"about_ca_system_score_gemma":0.0006172601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007115114,"about_ca_topic_score_gemma":0.003587521,"domain_scores_codex":[0.9993266,0.0001392115,0.00006204207,0.0002466888,0.0001176495,0.0001077999],"domain_scores_gemma":[0.9963798,0.002229583,0.0003960659,0.0003291286,0.0005222887,0.0001430898],"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":[0.00173854,0.001405892,0.0840094,0.0002416878,0.0006418637,0.0001821794,0.00008387868,0.7407057,0.04147129,0.00077278,0.001820593,0.1269262],"study_design_scores_gemma":[0.00002560282,0.0004709956,0.008447822,0.00001567408,0.00004680526,0.00002819249,0.00001750378,0.97336,0.0171955,0.0002415903,0.0001389673,0.00001137686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856907,0.0002555224,0.01189064,0.0001284281,0.00006031528,0.00004724319,0.0002418167,0.000389338,0.001296109],"genre_scores_gemma":[0.9941591,0.00005941497,0.004849184,0.00004897715,0.000009650749,0.00003290422,0.0004082618,0.00001831298,0.0004142353],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007115114,"threshold_uncertainty_score":0.0141474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03091230249516949,"score_gpt":0.30184059753124,"score_spread":0.2709282950360705,"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."}}