{"id":"W4316469650","doi":"10.3390/electronics12020467","title":"Efficient Training on Alzheimer’s Disease Diagnosis with Learnable Weighted Pooling for 3D PET Brain Image Classification","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Overfitting; Pooling; Artificial intelligence; Computer science; Convolutional neural network; Neuroimaging; Pattern recognition (psychology); Alzheimer's Disease Neuroimaging Initiative; Feature (linguistics); Machine learning; Deep learning; Artificial neural network; Cognitive impairment; Disease; Medicine; Psychology; Neuroscience; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009276275,0.001765915,0.001022238,0.0008644681,0.0003386629,0.0007100881,0.001466875,0.0009917472,0.002336807],"category_scores_gemma":[0.001889584,0.0007610759,0.001593586,0.0006886399,0.0003839702,0.001149534,0.001353575,0.001108984,0.00107447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008120752,"about_ca_system_score_gemma":0.001179887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01415725,"about_ca_topic_score_gemma":0.01501727,"domain_scores_codex":[0.9995649,0.00006399197,0.00002686134,0.0001606815,0.00009068088,0.0000928918],"domain_scores_gemma":[0.9997087,0.00008420637,0.00003691567,0.00007019709,0.00007376677,0.00002612032],"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":[0.0005019347,0.0002658806,0.006539369,0.0001587057,0.0003808805,0.0008815036,0.0001459647,0.2468302,0.048991,0.002710894,0.008470904,0.6841227],"study_design_scores_gemma":[0.00001042908,0.00005234398,0.0008958078,0.00000816319,0.00003212385,0.0001300097,0.00001295089,0.9885449,0.008208351,0.001432047,0.0006601888,0.00001270023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1640036,0.001229265,0.8234996,0.0004705281,0.0001462623,0.0001437229,0.0008419455,0.007527279,0.002137817],"genre_scores_gemma":[0.7995244,0.0005498648,0.1930652,0.0003623163,0.00007647827,0.0001803487,0.002625556,0.0002649483,0.003350934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01415725,"threshold_uncertainty_score":0.02814966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06213227830229666,"score_gpt":0.2985805230647909,"score_spread":0.2364482447624943,"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."}}