{"id":"W4289277730","doi":"10.21203/rs.3.rs-1903862/v1","title":"Three-round learning strategy based on 3D Deep Convolutional GANs for Alzheimer’s disease staging","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; H. Lundbeck A/S; Servier; Eisai; Genentech; IXICO; National Natural Science Foundation of China; Northern California Institute for Research and Education; Novartis Pharmaceuticals Corporation; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; F. Hoffmann-La Roche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Overfitting; Artificial intelligence; Computer science; Deep learning; Discriminator; Transfer of learning; Convolutional neural network; Context (archaeology); Pattern recognition (psychology); Task (project management); Dementia; Contextual image classification; Machine learning; Artificial neural network; Image (mathematics); Disease; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006796104,0.0009875101,0.0006514566,0.0004632562,0.0002304164,0.0004198358,0.001289849,0.000757921,0.00128043],"category_scores_gemma":[0.0009329408,0.0003675237,0.0007893182,0.0002364483,0.0004738896,0.0005910892,0.0008958171,0.001067849,0.0004465705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005656697,"about_ca_system_score_gemma":0.0006456557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005218398,"about_ca_topic_score_gemma":0.006414978,"domain_scores_codex":[0.9997489,0.00006184388,0.00001176209,0.00007676137,0.00005240654,0.00004830362],"domain_scores_gemma":[0.9997142,0.00009905937,0.00003134719,0.00005129692,0.00007208097,0.00003204139],"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":[0.0003149886,0.0001482501,0.003782793,0.00007154634,0.0001294344,0.0002397054,0.00009616738,0.7573929,0.01615856,0.005728242,0.0046948,0.2112426],"study_design_scores_gemma":[0.000003305263,0.0000178081,0.0001276508,0.000002936898,0.000007022887,0.00001975735,0.000002588871,0.9977983,0.001181315,0.0006757759,0.0001600119,0.000003575744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1122963,0.001041552,0.877804,0.0005031234,0.000147589,0.0001410009,0.0002281177,0.003514279,0.004323993],"genre_scores_gemma":[0.9059395,0.0002442819,0.08911123,0.0003582684,0.00004970851,0.0001102534,0.0004193429,0.0001034331,0.003664152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005218398,"threshold_uncertainty_score":0.01037604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2292483617956827,"score_gpt":0.4237864902843942,"score_spread":0.1945381284887116,"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."}}