{"id":"W2991340843","doi":"10.1016/j.compmedimag.2019.101685","title":"Limited One-time Sampling Irregularity Map (LOTS-IM) for Automatic Unsupervised Assessment of White Matter Hyperintensities and Multiple Sclerosis Lesions in Structural Brain Magnetic Resonance Images","year":2019,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"DoD Alzheimer's Disease Neuroimaging Initiative; National Institute on Aging; Mrs Gladys Row Fogo Charitable Trust; Canadian Institutes of Health Research; Biogen","keywords":"Artificial intelligence; Segmentation; Computer science; Pattern recognition (psychology); Deep learning; Voxel; Convolutional neural network; Hyperintensity; Support vector machine; Unsupervised learning; Magnetic resonance imaging; Medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003987441,0.0001659956,0.0003385622,0.00019956,0.0001963938,0.00008169762,0.0001569112,0.00007122109,0.00004934071],"category_scores_gemma":[0.0003107111,0.0001568809,0.00005861248,0.0002403201,0.0004647624,0.0001409033,0.0001546782,0.0002408915,0.000001485614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001721804,"about_ca_system_score_gemma":0.00004099281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002361637,"about_ca_topic_score_gemma":0.000003920495,"domain_scores_codex":[0.9984296,0.000187566,0.000380766,0.0004444236,0.0003075507,0.0002500919],"domain_scores_gemma":[0.9985208,0.0009494477,0.0000992127,0.000231021,0.00006776708,0.0001317566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001368959,0.0002013807,0.1864634,0.001082377,0.00001282665,0.000008092105,0.001099188,0.00001740441,0.7064668,0.001210814,0.0003252148,0.1029757],"study_design_scores_gemma":[0.001340562,0.00003814653,0.5258031,0.0002930904,0.000007140774,0.00001929617,0.00005721388,0.4709946,0.0008835482,0.0003539783,0.00009149681,0.0001178376],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9841582,0.0002088803,0.007720054,0.007150863,0.0002159845,0.000423097,0.00003019666,0.00007816446,0.00001458176],"genre_scores_gemma":[0.9881092,0.00007937269,0.009477928,0.002209233,0.0000235862,0.00001906662,0.000009717247,0.00001889985,0.00005302118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7055832,"threshold_uncertainty_score":0.6397416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04199116770319934,"score_gpt":0.279562491733006,"score_spread":0.2375713240298066,"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."}}