{"id":"W4412467872","doi":"10.1016/j.msard.2025.106620","title":"Automated multiple sclerosis lesion segmentation from 3D-FLAIR MRI using R2AUNet: A deep learning approach with recurrent residual and attention mechanisms","year":2025,"lang":"en","type":"article","venue":"Multiple Sclerosis and Related Disorders","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; McMaster University Medical Centre","funders":"","keywords":"Fluid-attenuated inversion recovery; Medicine; Multiple sclerosis; Segmentation; Lesion; Magnetic resonance imaging; Residual; Radiology; Neuroscience; Artificial intelligence; Pathology; Computer science; 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":[0.001118302,0.001342836,0.001544545,0.00153273,0.000542963,0.001290436,0.002413003,0.002516907,0.002397577],"category_scores_gemma":[0.001275733,0.001059296,0.001556924,0.001108814,0.0004202602,0.001161885,0.00187821,0.001508988,0.001726637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007782558,"about_ca_system_score_gemma":0.001586961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01184136,"about_ca_topic_score_gemma":0.02154996,"domain_scores_codex":[0.9996611,0.00004770041,0.00002117048,0.0001227178,0.00006615375,0.00008117658],"domain_scores_gemma":[0.9995936,0.0001228983,0.00004697177,0.00006132453,0.0001359181,0.0000393487],"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":[0.0005992763,0.0003254848,0.002496913,0.0002536068,0.0002976878,0.0002905712,0.0001526626,0.1929106,0.03799263,0.002652837,0.009911804,0.752116],"study_design_scores_gemma":[0.00001055586,0.0000467121,0.0003584541,0.00001291119,0.00002980521,0.00006646609,0.00001462681,0.9916359,0.005928888,0.001177107,0.0007053508,0.00001322134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04182843,0.0007133851,0.9477476,0.0003048791,0.00009419939,0.0001388961,0.0006349113,0.00751521,0.001022481],"genre_scores_gemma":[0.3444187,0.0006239716,0.6444001,0.0004467003,0.0001307817,0.0002114519,0.002701446,0.001008972,0.00605786],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01184136,"threshold_uncertainty_score":0.02354485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04276670581017344,"score_gpt":0.2768785187555187,"score_spread":0.2341118129453452,"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."}}