{"id":"W4405179410","doi":"10.1109/jbhi.2024.3512417","title":"A Lightweight Deep Convolutional Neural Network Extracting Local and Global Contextual Features for the Classification of Alzheimer's Disease Using Structural MRI","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology); Feature extraction; Deep learning; Artificial neural network; Magnetic resonance imaging; 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":[0.000720082,0.0001018767,0.0001886852,0.00006547503,0.0003435276,0.00008853259,0.00009977291,0.00006231461,0.000005349111],"category_scores_gemma":[0.0001250022,0.00006183168,0.0000686096,0.0002188312,0.0004786791,0.0003048779,0.00001766099,0.0002632487,3.171733e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006749939,"about_ca_system_score_gemma":0.0003112416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005780548,"about_ca_topic_score_gemma":0.000003926327,"domain_scores_codex":[0.9983952,0.00006417977,0.000875649,0.00008407621,0.0003768219,0.0002040932],"domain_scores_gemma":[0.9985421,0.0004247491,0.0005969259,0.0000648855,0.00008708838,0.0002842753],"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":[0.0011959,0.0001313523,0.00092184,0.002041714,0.0002120713,0.0000211036,0.00443744,0.003952527,0.00295592,0.06083358,0.0116417,0.9116548],"study_design_scores_gemma":[0.0004774653,0.0002196824,0.02066273,0.0001683364,0.00007598809,0.0007396601,0.0007707103,0.9711617,0.0001030176,0.00133255,0.00420909,0.00007909372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.303495,0.01593644,0.6410596,0.03359922,0.004837199,0.0008240523,0.0001647586,0.00004992739,0.00003381819],"genre_scores_gemma":[0.9967615,0.0002998381,0.001446403,0.00100818,0.0004712361,0.000002733302,0.000002577398,0.000004846519,0.000002687282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9672092,"threshold_uncertainty_score":0.2642171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07687665072161143,"score_gpt":0.3569410925436676,"score_spread":0.2800644418220561,"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."}}