{"id":"W4389990655","doi":"10.1016/j.compbiomed.2023.107873","title":"Improving brain age prediction with anatomical feature attention-enhanced 3D-CNN","year":2023,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"National Key Research and Development Program of China; Science and Technology Department of Gansu Province; National Natural Science Foundation of China","keywords":"Deep learning; Computer science; Artificial intelligence; Convolutional neural network; Context (archaeology); Feature engineering; Feature (linguistics); Feature extraction; Machine learning; Neuroimaging; Pattern recognition (psychology); Salient; Neuroscience; Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005370749,0.001523047,0.001179323,0.001564092,0.0002748092,0.0006498697,0.001228427,0.001360738,0.002256677],"category_scores_gemma":[0.001403217,0.0004644095,0.001326979,0.0009855983,0.0002078096,0.000861946,0.001029651,0.0009239413,0.001970993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005774582,"about_ca_system_score_gemma":0.0007678875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01703032,"about_ca_topic_score_gemma":0.02446776,"domain_scores_codex":[0.9997179,0.00002597279,0.00001319014,0.000121027,0.00005470567,0.00006715091],"domain_scores_gemma":[0.999598,0.00009647174,0.00003930297,0.00006067703,0.0001762825,0.00002932661],"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":[0.0005074131,0.0002604067,0.01832215,0.0001976105,0.0003387298,0.0003741048,0.00005225542,0.07334155,0.02407539,0.001291206,0.02822559,0.8530136],"study_design_scores_gemma":[0.00001298978,0.00006191766,0.005081316,0.00003147532,0.0001151441,0.0003381397,0.00001563123,0.9823653,0.007622301,0.002133899,0.002200973,0.00002083062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2254439,0.01102398,0.7319333,0.001595294,0.001628576,0.0001922228,0.008060569,0.01267312,0.007449033],"genre_scores_gemma":[0.8534629,0.002607223,0.125172,0.0009718583,0.0005212217,0.0001011453,0.00671613,0.0003324694,0.01011509],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01703032,"threshold_uncertainty_score":0.03386241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02640983057501379,"score_gpt":0.3527112814833023,"score_spread":0.3263014509082885,"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."}}