{"id":"W2949980035","doi":"10.1109/jbhi.2019.2914970","title":"Studying the Manifold Structure of Alzheimer's Disease: A Deep Learning Approach Using Convolutional Autoencoders","year":2019,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":250,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; Eisai; AbbVie; Ministerio de Ciencia e Innovación; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Takeda Pharmaceutical Company; Roche; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Drug Discovery Foundation; Merck; Fujirebio Europe; Alzheimer's Association; Foundation for the National Institutes of Health; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative","keywords":"Artificial intelligence; Pattern recognition (psychology); Autoencoder; Computer science; Deep learning; Principal component analysis; Convolutional neural network; Medical diagnosis; Machine learning; Medicine; Radiology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007852067,0.00008071085,0.000196925,0.0001263586,0.0002222128,0.00002956974,0.0001429468,0.00004493768,0.00002540928],"category_scores_gemma":[0.0001086358,0.00004975247,0.00005144243,0.0002170857,0.0001645981,0.0001987083,0.00002324245,0.0004101042,0.000001544864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004453671,"about_ca_system_score_gemma":0.000251086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003790335,"about_ca_topic_score_gemma":2.98188e-7,"domain_scores_codex":[0.9982491,0.0001218137,0.0008193707,0.00005857526,0.0005832934,0.0001678847],"domain_scores_gemma":[0.9985098,0.0001042904,0.001024174,0.00007945148,0.00006504838,0.000217236],"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":[0.00183797,0.002522721,0.03914026,0.01253497,0.0008998212,0.00004356512,0.1205204,0.120266,0.1491372,0.04187847,0.004837699,0.5063809],"study_design_scores_gemma":[0.001050936,0.0004361309,0.01414413,0.0001613509,0.0000514579,0.0004624602,0.004889195,0.9743976,0.0005403577,0.0003663823,0.003373008,0.000127019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9356601,0.000600212,0.06026802,0.001923908,0.001022178,0.0003718334,0.00001404477,0.00001812713,0.0001215435],"genre_scores_gemma":[0.9969256,0.0001057769,0.001868647,0.0009857313,0.0001006216,4.213666e-7,0.000001067265,0.000004687051,0.000007484146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8541316,"threshold_uncertainty_score":0.2028847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07445546892299126,"score_gpt":0.3138618827632492,"score_spread":0.2394064138402579,"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."}}