{"id":"W4309246358","doi":"10.1002/hbm.26146","title":"Generative adversarial network constrained multiple loss autoencoder: A deep learning‐based individual atrophy detection for Alzheimer's disease and mild cognitive impairment","year":2022,"lang":"en","type":"article","venue":"Human Brain Mapping","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Key Research and Development Program of China; Canadian Institutes of Health Research; National Institutes of Health; Higher Education Discipline Innovation Project; Foundation for the National Institutes of Health; National Natural Science Foundation of China; U.S. Department of Defense","keywords":"Autoencoder; Cognitive impairment; Atrophy; Cognition; Neuroscience; Generative grammar; Alzheimer's disease; Artificial intelligence; Dementia; Disease; Neuroimaging; Psychology; Adversarial system; Deep learning; Cognitive psychology; Computer science; Machine learning; Medicine; Pathology","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0009017244,0.0002779012,0.0003308831,0.0002530866,0.002048804,0.00008986187,0.00009495999,0.00005537928,0.0004579903],"category_scores_gemma":[0.0002516978,0.0002996391,0.0002032165,0.000276435,0.000274962,0.00009563567,0.0002035759,0.0004756514,0.000003830605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000132011,"about_ca_system_score_gemma":0.0002072795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002382967,"about_ca_topic_score_gemma":0.00002350046,"domain_scores_codex":[0.9973097,0.0004917755,0.0003393077,0.0006060618,0.0006096524,0.0006435278],"domain_scores_gemma":[0.9986214,0.0005586015,0.0001651745,0.0001249559,0.0001897693,0.0003400685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.04203544,0.005542126,0.7637939,0.001466054,0.01316556,0.00187579,0.02136669,0.02928989,0.03440199,0.001293877,0.006323196,0.07944551],"study_design_scores_gemma":[0.03865867,0.007048537,0.7463759,0.0002619869,0.001569641,0.00004514023,0.006940712,0.1921871,0.0004367505,0.001034706,0.004610896,0.000830056],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8952453,0.0006784887,0.09694146,0.001364454,0.0002227024,0.004942979,0.0002017877,0.0002019317,0.0002008664],"genre_scores_gemma":[0.9943617,0.000004393764,0.001031789,0.001478202,0.0005525507,0.001476933,0.0008897363,0.00004451925,0.0001601804],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1628972,"threshold_uncertainty_score":0.9999456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0358569893801258,"score_gpt":0.3000260737377834,"score_spread":0.2641690843576576,"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."}}