{"id":"W3131390313","doi":"10.1016/j.mri.2021.02.001","title":"A 3D densely connected convolution neural network with connection-wise attention mechanism for Alzheimer's disease classification","year":2021,"lang":"en","type":"article","venue":"Magnetic Resonance Imaging","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":215,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Shenzhen Municipal Science and Technology Innovation Council; Science, Technology and Innovation Commission of Shenzhen Municipality; National Institute on Aging; Guangdong Science and Technology Department","keywords":"Artificial intelligence; Converters; Pattern recognition (psychology); Computer science; Convolution (computer science); Artificial neural network; Convolutional neural network; Mechanism (biology); Deep learning; Feature (linguistics); Machine learning; Voltage; Engineering","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":[0.0002357399,0.000195531,0.0002266354,0.00008167295,0.0002781523,0.0001076598,0.00006390346,0.0000370779,0.0002423616],"category_scores_gemma":[0.000213549,0.000182523,0.00009855221,0.0003976876,0.0001199836,0.0001697352,0.00003442264,0.0001553435,0.00002149594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007018347,"about_ca_system_score_gemma":0.0002440562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001802266,"about_ca_topic_score_gemma":0.0000201112,"domain_scores_codex":[0.9980974,0.0001310177,0.0002860902,0.0005486824,0.0004214699,0.0005153298],"domain_scores_gemma":[0.9981987,0.0001266698,0.00009853848,0.0002901747,0.00106286,0.0002230198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00423442,0.0007341758,0.6733023,0.0002793591,0.0001407647,0.0006763564,0.0001069385,0.00004883677,0.02280722,0.01213486,0.004546561,0.2809882],"study_design_scores_gemma":[0.004461244,0.0003726834,0.82349,0.0002855204,0.000597105,0.0001433171,0.0002795037,0.16306,0.0007956004,0.001166871,0.005101645,0.0002465255],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9111316,0.01816794,0.05366756,0.01205443,0.0004679195,0.002994178,0.00004456528,0.0002718644,0.001199984],"genre_scores_gemma":[0.9927413,0.0001339265,0.003358835,0.001005747,0.0002569654,0.0005308912,0.0003049578,0.00004042224,0.001626997],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2807417,"threshold_uncertainty_score":0.744307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02289303016377921,"score_gpt":0.2849189838586484,"score_spread":0.2620259536948692,"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."}}