{"id":"W4312247626","doi":"10.1109/jbhi.2022.3231905","title":"Contrastive Learning for Prediction of Alzheimer's Disease Using Brain 18F-FDG PET","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Feature extraction; Deep learning; Abnormality; Feature (linguistics); Robustness (evolution); Feature learning; Positron emission tomography; Medicine; Radiology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001324537,0.00006643144,0.0001978594,0.0001924317,0.0004099263,0.00001626859,0.00008346283,0.00001497257,0.00002291555],"category_scores_gemma":[0.0004039729,0.00005667906,0.00006194662,0.0002021174,0.0001399801,0.0001809248,0.00002131818,0.0003106205,3.171864e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007401303,"about_ca_system_score_gemma":0.0003318772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003148491,"about_ca_topic_score_gemma":1.854205e-7,"domain_scores_codex":[0.9982596,0.0001202138,0.000953813,0.00005467491,0.0004528647,0.0001588352],"domain_scores_gemma":[0.99819,0.0002087889,0.001184629,0.00004683213,0.00007347506,0.000296258],"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":[0.006233048,0.003426368,0.003985037,0.006025502,0.0004193896,0.0001353675,0.0419132,0.01985836,0.1499768,0.007655903,0.07641543,0.6839556],"study_design_scores_gemma":[0.004726721,0.00482068,0.009259526,0.0002380377,0.0001170836,0.001585526,0.006137235,0.8914868,0.003490784,0.001009187,0.07691313,0.0002152996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7853262,0.000381777,0.1907878,0.01910261,0.00283416,0.0008759129,0.0005758043,0.00004439419,0.00007131433],"genre_scores_gemma":[0.9969686,0.00008466667,0.0007786421,0.001996163,0.0001387208,0.000006088272,0.000005355356,0.000005906631,0.00001587361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8716285,"threshold_uncertainty_score":0.3152863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.100632899660496,"score_gpt":0.3436996724820143,"score_spread":0.2430667728215183,"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."}}