{"id":"W4291415397","doi":"10.3390/brainsci12081067","title":"A Novel Deep Learning Radiomics Model to Discriminate AD, MCI and NC: An Exploratory Study Based on Tau PET Scans from ADNI","year":2022,"lang":"en","type":"article","venue":"Brain Sciences","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":13,"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; Genentech; IXICO; H. Lundbeck A/S; Servier; Key Laboratory of Nuclear Medicine and Molecular Imaging of Sichuan Province; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Eisai; National Institute on Aging; Alzheimer's Association","keywords":"Alzheimer's Disease Neuroimaging Initiative; Artificial intelligence; Positron emission tomography; Neuroimaging; Cognitive impairment; Radiomics; Support vector machine; Nuclear medicine; Deep learning; Pattern recognition (psychology); Machine learning; Computer science; Psychology; Medicine; Cognition; Neuroscience","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":[0.002142081,0.0001808665,0.0002894239,0.0003030583,0.0008928856,0.0001137802,0.0003497028,0.0000183787,0.00005764015],"category_scores_gemma":[0.0008467496,0.00015423,0.0000446923,0.00048766,0.0002674398,0.0001662779,0.0001955855,0.0005541813,0.000002309277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008693458,"about_ca_system_score_gemma":0.0001856344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002082869,"about_ca_topic_score_gemma":0.00009072406,"domain_scores_codex":[0.9976941,0.0002291729,0.0002337314,0.0006948219,0.0007924961,0.0003556283],"domain_scores_gemma":[0.9989499,0.0002974808,0.00008637044,0.0002623359,0.0000308068,0.0003731076],"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":[0.0002276109,0.0009261064,0.01874876,0.00001548747,0.000021279,0.0001415138,0.02345053,0.9143647,0.009684798,0.0001717678,0.0005807947,0.03166665],"study_design_scores_gemma":[0.001367044,0.001684991,0.007361344,0.00002688295,0.00003463887,0.00002237891,0.02168317,0.9669405,0.00002143815,0.0000761688,0.0005879973,0.0001934273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9360197,0.00007076473,0.05613011,0.006811103,0.0001560387,0.0004006618,0.00001283962,0.00007823793,0.0003205274],"genre_scores_gemma":[0.9791901,0.000004630453,0.01408237,0.006354573,0.00007023448,0.00007248709,0.00002183243,0.00002629406,0.0001774979],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05257583,"threshold_uncertainty_score":0.6867445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0394434818300856,"score_gpt":0.3239879280370927,"score_spread":0.2845444462070071,"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."}}