{"id":"W4414997241","doi":"10.1016/j.asoc.2025.114045","title":"Medical image classification with KAN-integrated transformers and dilated neighborhood attention","year":2025,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Robustness (evolution); Pattern recognition (psychology); Feature extraction; Transformer; Convolutional neural network; Kernel (algebra); Medical imaging; Contextual image classification","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009923356,0.0006002316,0.0009449445,0.001492031,0.0005005061,0.001070479,0.000998091,0.0008407691,0.002776356],"category_scores_gemma":[0.00255638,0.0003777843,0.001141087,0.001187262,0.0005361721,0.001356881,0.001761784,0.0009245538,0.001029281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006397811,"about_ca_system_score_gemma":0.000926173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006578831,"about_ca_topic_score_gemma":0.007105604,"domain_scores_codex":[0.9995332,0.0000857253,0.00003661602,0.0001488489,0.000129893,0.0000658658],"domain_scores_gemma":[0.999346,0.0002091498,0.00003914021,0.0001054037,0.0002571193,0.00004320382],"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":[0.0004578567,0.0001512891,0.00170676,0.0001383843,0.0001315842,0.0001249578,0.0001493697,0.05838803,0.03424286,0.01487343,0.003736949,0.8858985],"study_design_scores_gemma":[0.00001456054,0.00009146628,0.0009664078,0.00001017825,0.00005725654,0.0001190138,0.00003833814,0.9758001,0.01138169,0.01012325,0.001384596,0.0000132475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02429373,0.0003760218,0.9725397,0.0001263483,0.0000664746,0.0000521316,0.00009455608,0.001101144,0.001349834],"genre_scores_gemma":[0.6237252,0.0004899268,0.3695957,0.0001553373,0.0001060008,0.0001066249,0.0004248042,0.0002689428,0.005127479],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006578831,"threshold_uncertainty_score":0.01308107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01292357083853082,"score_gpt":0.2524864134414311,"score_spread":0.2395628426029003,"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."}}