{"id":"W4416117870","doi":"10.48550/arxiv.2504.04911","title":"IterMask3D: Unsupervised Anomaly Detection and Segmentation with Test-Time Iterative Mask Refinement in 3D Brain MR","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; Avid Radiopharmaceuticals; National Institutes of Health; University of Oxford; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Meso Scale Diagnostics; Department of Health and Social Care; National Institute for Health and Care Research; Northern California Institute for Research and Education; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; Wellcome Trust; University of Southern California; UK Research and Innovation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Alzheimer's Association","keywords":"Segmentation; Iterative reconstruction; Pattern recognition (psychology); Anomaly detection; Image segmentation; Process (computing); Feature (linguistics); Image (mathematics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001527178,0.002232356,0.00162821,0.001659543,0.0007547382,0.002035346,0.005445382,0.002123377,0.004896348],"category_scores_gemma":[0.004366474,0.001915965,0.002482072,0.001079646,0.001379634,0.001630886,0.003727102,0.002566963,0.00313441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001239478,"about_ca_system_score_gemma":0.002529171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01029616,"about_ca_topic_score_gemma":0.02158992,"domain_scores_codex":[0.9988857,0.0001867807,0.00008260921,0.0002646004,0.0004782042,0.0001020502],"domain_scores_gemma":[0.9986995,0.0005347659,0.0001330216,0.0003397911,0.0001937795,0.00009907913],"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":[0.000659761,0.0002095903,0.003458231,0.0006657081,0.0005063011,0.0005371188,0.0007964094,0.2453697,0.0515133,0.01221548,0.0323635,0.6517048],"study_design_scores_gemma":[0.00004104104,0.00004520382,0.0002934588,0.00001669781,0.00002423283,0.0002690586,0.00003490752,0.9723345,0.01622146,0.005661784,0.005010681,0.00004688535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004239482,0.0001987881,0.972785,0.000107569,0.00002909687,0.0001022661,0.0002417504,0.02182988,0.0004661585],"genre_scores_gemma":[0.04253463,0.0001789232,0.9504573,0.000193828,0.00002307121,0.0002785058,0.00121327,0.003868481,0.001251939],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01029616,"threshold_uncertainty_score":0.02047247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01426190354241507,"score_gpt":0.2524771708589169,"score_spread":0.2382152673165018,"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."}}