{"id":"W3027358948","doi":"10.1109/isbi45749.2020.9098554","title":"CNN Detection of New and Enlarging Multiple Sclerosis Lesions from Longitudinal Mri Using Subtraction Images","year":2020,"lang":"en","type":"article","venue":"","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"","keywords":"Segmentation; Subtraction; Artificial intelligence; Magnetic resonance imaging; Computer science; Multiple sclerosis; Background subtraction; Pattern recognition (psychology); Image segmentation; Radiology; Medicine; Mathematics","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":[0.0005145248,0.001046077,0.0005533334,0.0007549954,0.0001607534,0.000597143,0.0008591306,0.0007439741,0.001036146],"category_scores_gemma":[0.001009859,0.0003627811,0.000571035,0.0003642548,0.0002356367,0.0005128246,0.0005127594,0.0005294762,0.0004896165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006494276,"about_ca_system_score_gemma":0.000592031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009352837,"about_ca_topic_score_gemma":0.01520718,"domain_scores_codex":[0.9997832,0.00002393815,0.00001154227,0.00008442776,0.0000515731,0.00004522132],"domain_scores_gemma":[0.9997688,0.00006798014,0.00004480543,0.00002882526,0.00006769316,0.00002195191],"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":[0.001154665,0.0004238613,0.02179602,0.0002062686,0.00042473,0.000546162,0.00007799136,0.1987564,0.07685253,0.001071559,0.008120445,0.6905694],"study_design_scores_gemma":[0.00001593821,0.0001455333,0.005938546,0.00001542453,0.00007505336,0.0001467513,0.0000137813,0.9769117,0.0150966,0.0006871911,0.0009403386,0.00001314262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5721987,0.003743754,0.4076784,0.0006663246,0.0002505327,0.0002418679,0.002480859,0.005431161,0.007308384],"genre_scores_gemma":[0.9187745,0.0006886337,0.07347723,0.0002677318,0.00007121485,0.00008512977,0.002052706,0.00007111562,0.004511825],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009352837,"threshold_uncertainty_score":0.01859677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.217136610973914,"score_gpt":0.3350714438358336,"score_spread":0.1179348328619196,"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."}}