{"id":"W4313985049","doi":"10.3389/fnins.2022.1050777","title":"A transfer learning approach for multiclass classification of Alzheimer's disease using MRI images","year":2023,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Zhejiang Province; 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; Pfizer; Novartis Pharmaceuticals Corporation; F. Hoffmann-La Roche; Biogen; Zhejiang Normal University; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Transfer of learning; Cognitive impairment; Computer science; Artificial intelligence; Segmentation; Disease; Alzheimer's disease; Deep learning; Cognition; Machine learning; Pattern recognition (psychology); Neuroscience; Pathology; Medicine; Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004965446,0.000139799,0.0001763624,0.0004347466,0.0002543268,0.00005519533,0.000352244,0.00004681284,0.000001124896],"category_scores_gemma":[0.000995602,0.0001442311,0.00008847391,0.001792585,0.0004184273,0.0004486498,0.00003276478,0.0001776008,0.000001464433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004703287,"about_ca_system_score_gemma":0.00007776392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003314198,"about_ca_topic_score_gemma":2.211047e-7,"domain_scores_codex":[0.998,0.0002043462,0.0003304101,0.0007212559,0.0003525559,0.0003914033],"domain_scores_gemma":[0.9993764,0.00009379006,0.0001024273,0.0002615679,0.00004048745,0.0001253429],"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":[0.00006272876,0.00008273642,0.002993364,0.00003497123,6.796636e-7,0.000002742971,0.0001426678,0.02977048,0.9634904,0.0005476345,0.0002407284,0.002630874],"study_design_scores_gemma":[0.0003474217,0.00003688615,0.02893364,0.00001074248,0.00001336079,0.000002388457,0.0002543837,0.8337758,0.1356538,0.0001359918,0.0007003324,0.0001352921],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3623986,0.00004338983,0.634177,0.0004859658,0.001370371,0.0009656756,0.00003806129,0.0002495055,0.000271502],"genre_scores_gemma":[0.9958452,0.00004997444,0.00358662,0.0001635971,0.00002525509,0.0001157002,0.000004546476,0.00002454481,0.0001845408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8278366,"threshold_uncertainty_score":0.5881572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08743507618567069,"score_gpt":0.3053575217799552,"score_spread":0.2179224455942845,"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."}}