{"id":"W4411471974","doi":"10.1371/journal.pdig.0000874","title":"Efficient slice anomaly detection network for 3D brain MRI Volume","year":2025,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Western University","funders":"Vector Institute","keywords":"Computer science; Benchmark (surveying); Feature (linguistics); Anomaly detection; Artificial intelligence; Pattern recognition (psychology); Volume (thermodynamics); Convolutional neural network; Identification (biology); Code (set theory); Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002043549,0.0001228562,0.0001660911,0.0001017736,0.0004252525,0.0002386687,0.0003699602,0.00005985549,0.000002364987],"category_scores_gemma":[0.00003275851,0.0001268489,0.00008232299,0.0007535386,0.00002815855,0.0001679689,0.0001224435,0.0001040755,0.00003257316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001693352,"about_ca_system_score_gemma":0.0001568478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003762747,"about_ca_topic_score_gemma":0.00002538538,"domain_scores_codex":[0.9987527,0.00001663757,0.0003080498,0.0004137881,0.0001299716,0.0003788628],"domain_scores_gemma":[0.9991136,0.0001237685,0.0001235532,0.000436165,0.00009289083,0.0001100741],"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":[0.00003422515,0.0005721653,0.0007241298,0.0002451386,0.0000448983,7.145974e-7,0.000184463,0.003022541,0.0001422626,0.08976585,0.03618662,0.869077],"study_design_scores_gemma":[0.000240791,0.0004127067,0.001875968,0.00006246409,0.000004340498,0.000005163284,0.00001575718,0.8105394,0.000697728,0.006273675,0.1796675,0.0002044329],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005539069,0.0001056017,0.9837956,0.006289917,0.0001579272,0.0008399175,0.00002020446,0.000673516,0.002578222],"genre_scores_gemma":[0.9369978,0.000007116268,0.05682889,0.002898274,0.0001363088,0.0004006514,0.00000975547,0.00001349732,0.002707708],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9314587,"threshold_uncertainty_score":0.5172749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01120280783965157,"score_gpt":0.2659656474192372,"score_spread":0.2547628395795857,"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."}}