{"id":"W4412375816","doi":"10.1109/tla.2025.11072499","title":"Attention Blocks Improve White Matter Hyperintensity Semantic Segmentation using U-Nets","year":2025,"lang":"en","type":"article","venue":"IEEE Latin America Transactions","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Calgary","funders":"","keywords":"Hyperintensity; Computer science; Segmentation; Artificial intelligence; White matter; Natural language processing; Pattern recognition (psychology); 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":[0.00004631435,0.0001447678,0.000156799,0.0001109065,0.0003661266,0.0001263881,0.0002431969,0.00004838138,0.00008848723],"category_scores_gemma":[0.00000113798,0.0001477186,0.0001091078,0.0007438165,0.00006254178,0.0003058605,0.00001344565,0.0001776168,0.00005710338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005508653,"about_ca_system_score_gemma":0.00003144837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001192358,"about_ca_topic_score_gemma":0.00001752894,"domain_scores_codex":[0.9989473,0.00004097759,0.000261955,0.0003844717,0.0001310602,0.0002342227],"domain_scores_gemma":[0.999316,0.00004497615,0.00009613459,0.000400261,0.00008567957,0.0000569708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002880505,0.0006308396,0.02482924,0.00009416678,0.0002344399,0.00001056787,0.0008614358,0.1028367,0.6116994,0.0004408707,0.005944213,0.2523894],"study_design_scores_gemma":[0.0004900638,0.00004962951,0.061681,0.00006570823,0.0001240031,0.00002251071,0.0001351353,0.9239332,0.01015824,0.0008069701,0.002098973,0.0004345531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1079446,0.00001012359,0.8871502,0.003098268,0.0006082886,0.0002611243,0.000006988994,0.0001433593,0.0007770634],"genre_scores_gemma":[0.9488578,0.0000118842,0.04799454,0.00129194,0.00003563251,0.00005064148,0.000003894781,0.000009027289,0.00174457],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8409133,"threshold_uncertainty_score":0.6023789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01309702027091418,"score_gpt":0.2558730968913985,"score_spread":0.2427760766204843,"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."}}