{"id":"W2110436599","doi":"10.1109/tmi.2012.2186639","title":"Automatic Detection of Gadolinium-Enhancing Multiple Sclerosis Lesions in Brain MRI Using Conditional Random Fields","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"NeuroRx Research (Canada); Montreal Neurological Institute and Hospital; McGill University; McGill University Health Centre","funders":"","keywords":"Conditional random field; Gadolinium; Multiple sclerosis; Voxel; Pattern recognition (psychology); Artificial intelligence; Support vector machine; Magnetic resonance imaging; Segmentation; Computer science; Probabilistic logic; Image segmentation; Context (archaeology); Markov random field; Lesion; Medicine; Radiology; Pathology","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":[0.001715053,0.000147389,0.0002670575,0.0003775637,0.0002182407,0.0000447596,0.0002886212,0.0001052824,0.0001195107],"category_scores_gemma":[0.0002501504,0.0001436139,0.0001366165,0.0005394553,0.0001108562,0.000747701,0.000006082918,0.0004837379,0.00001161432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008409737,"about_ca_system_score_gemma":0.0001134225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001832986,"about_ca_topic_score_gemma":0.00005216292,"domain_scores_codex":[0.9978678,0.0004237943,0.000505682,0.0002401455,0.0005842358,0.0003783565],"domain_scores_gemma":[0.9977478,0.001636822,0.0001015923,0.0002506769,0.00006138763,0.0002016607],"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":[0.00007520451,0.0006984343,0.0003114178,0.0001138083,0.00004560261,0.00002811892,0.002622451,0.01353214,0.2754375,0.000071656,0.00007069139,0.706993],"study_design_scores_gemma":[0.001886464,0.0000179077,0.0008655034,0.0003106808,0.0000166582,0.00005771921,0.00007690908,0.7861635,0.2102294,0.0002181505,0.00001424607,0.0001429232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09051131,0.00008733883,0.9076644,0.000595923,0.0008842965,0.000130256,0.000002734405,0.00009224618,0.00003155553],"genre_scores_gemma":[0.950404,0.00001350466,0.04879915,0.0006609611,0.00008206705,0.00001539623,7.620102e-7,0.00001204426,0.00001208688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8598927,"threshold_uncertainty_score":0.5856404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03954835024606344,"score_gpt":0.3042364306717774,"score_spread":0.2646880804257139,"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."}}