{"id":"W4405696252","doi":"10.1007/s12559-024-10390-1","title":"Convolutional Cross-Modal Autoencoder-Based Few-Shot Learning for Data Augmentation with Application to Alzheimer Dementia Diagnosis","year":2024,"lang":"en","type":"article","venue":"Cognitive Computation","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bishop's University","funders":"","keywords":"Autoencoder; Dementia; Modal; Computer science; Artificial intelligence; Shot (pellet); Convolutional neural network; Multimodality; Deep learning; Pattern recognition (psychology); Machine learning; Medicine; Disease; Internal medicine; Materials science; World Wide Web","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":[0.0002950731,0.0001643744,0.0001072015,0.0001971466,0.0004244884,0.0003434648,0.0001330823,0.000053306,0.00005116444],"category_scores_gemma":[0.0003860823,0.0001670819,0.00003870204,0.0005514981,0.0001102294,0.0005306279,0.00004352496,0.0001399796,0.0001692655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007429525,"about_ca_system_score_gemma":0.0001453577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001024177,"about_ca_topic_score_gemma":0.0000133928,"domain_scores_codex":[0.998214,0.0001328273,0.0002639537,0.0008450596,0.0003396454,0.0002044981],"domain_scores_gemma":[0.9984053,0.001009551,0.0001192028,0.00009798376,0.0002818302,0.00008611905],"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":[0.001086013,0.0004829895,0.007480797,0.0002175863,0.000305648,0.000009306396,0.000642536,0.07824954,0.06348973,0.00281563,0.002025848,0.8431944],"study_design_scores_gemma":[0.0008025242,0.0002444157,0.01537569,0.00008005755,0.0001957396,0.000006520157,0.00008835563,0.9340624,0.04655275,0.000282216,0.002090039,0.0002192927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0492508,0.0001056671,0.9475488,0.0008181519,0.0002724933,0.001290684,0.0001461399,0.0003401582,0.0002271138],"genre_scores_gemma":[0.9936268,0.000003797525,0.002585941,0.0007704223,0.0001226878,0.001189316,0.001630695,0.00003621276,0.00003415636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9449629,"threshold_uncertainty_score":0.6813402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.14747935753565,"score_gpt":0.3945093489615839,"score_spread":0.2470299914259339,"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."}}