{"id":"W3142002010","doi":"10.3390/app11073248","title":"SPAER: Sparse Deep Convolutional Autoencoder Model to Extract Low Dimensional Imaging Biomarkers for Early Detection of Breast Cancer Using Dynamic Thermography","year":2021,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Infrared Thermography in Medicine","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Autoencoder; Breast cancer; Artificial intelligence; Mammography; Matrix decomposition; Pattern recognition (psychology); Breast cancer screening; Non-negative matrix factorization; Deep learning; Medicine; Computer science; Cancer; Internal medicine; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005100965,0.0001908929,0.0002973872,0.0004285235,0.0002849191,0.00002239752,0.0001367646,0.00006543461,0.00008180355],"category_scores_gemma":[0.00002693585,0.0001626426,0.0001608764,0.001235415,0.0006598005,0.0001204477,0.00004415509,0.000122574,0.000001541327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009099965,"about_ca_system_score_gemma":0.0004352855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009451007,"about_ca_topic_score_gemma":0.00003621685,"domain_scores_codex":[0.9980646,0.00002175819,0.0003408198,0.0005017522,0.0006607393,0.0004102832],"domain_scores_gemma":[0.9990712,0.0001068658,0.000150773,0.0001889381,0.0003203326,0.0001619006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003149333,0.0001064822,0.008085551,0.00005516042,0.0001114313,0.000006068249,0.0002658756,0.0169152,0.9627644,0.0002743595,0.00002139623,0.01107909],"study_design_scores_gemma":[0.001182698,0.00006891201,0.09281816,0.0002235169,0.0001756262,0.0001165238,0.000459469,0.8751853,0.0281353,0.001387286,0.000008191331,0.000239083],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8735793,0.0004445305,0.1242884,0.0004846505,0.0002677618,0.0005028565,0.00007376107,0.00004327099,0.0003154445],"genre_scores_gemma":[0.9654706,0.00000868948,0.03377888,0.0005546852,0.00007329327,0.00007034179,0.00001043134,0.00002022185,0.0000128799],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9346291,"threshold_uncertainty_score":0.6632373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01818192539363382,"score_gpt":0.2917501883199882,"score_spread":0.2735682629263544,"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."}}