{"id":"W2589663521","doi":"10.1016/j.media.2017.02.007","title":"Longitudinal segmentation of age-related white matter hyperintensities","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; Takeda Pharmaceutical Company; IXICO; H. Lundbeck A/S; Wolfson Foundation; National Institute on Aging; National Institute for Health and Care Research; Seventh Framework Programme; Northern California Institute for Research and Education; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; National Institute on Handicapped Research; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Roche; Merck; Alzheimer's Drug Discovery Foundation; AbbVie; Fujirebio Europe; Alzheimer's Association; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Medical Research Council; Johnson and Johnson; Meso Scale Diagnostics","keywords":"Hyperintensity; Segmentation; Lesion; Robustness (evolution); Computer science; Artificial intelligence; Longitudinal data; Longitudinal study; Pattern recognition (psychology); Medicine; Magnetic resonance imaging; Data mining; Radiology; Pathology","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":[0.0009894902,0.0004839639,0.0004206835,0.001116263,0.0003171851,0.000867972,0.0004506033,0.0008704155,0.001282938],"category_scores_gemma":[0.001846574,0.0003687921,0.0004355236,0.0005290105,0.0002506805,0.0005265215,0.0006214793,0.0003533303,0.0006818242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002198743,"about_ca_system_score_gemma":0.0006568531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001621381,"about_ca_topic_score_gemma":0.003560433,"domain_scores_codex":[0.9998317,0.00003319444,0.00001869598,0.00006149182,0.0000348422,0.00002012884],"domain_scores_gemma":[0.9992303,0.0001713402,0.0001823827,0.000137006,0.0002165659,0.00006247467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001133803,0.0004085841,0.09453228,0.0005465348,0.000417129,0.001109955,0.001087973,0.07698049,0.3901796,0.00273777,0.00378872,0.4270772],"study_design_scores_gemma":[0.00003804455,0.0009016762,0.09886456,0.0001250876,0.0003157304,0.004061054,0.000386104,0.7012201,0.1809894,0.005102786,0.007870829,0.000124802],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4686315,0.001370121,0.5243413,0.0002350721,0.00006354012,0.0001900727,0.00112706,0.00246579,0.001575531],"genre_scores_gemma":[0.7520885,0.000780642,0.242038,0.00007511723,0.00005836326,0.0001510508,0.002095214,0.000267174,0.002445901],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001621381,"threshold_uncertainty_score":0.005233049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01634924168965397,"score_gpt":0.3072204340925042,"score_spread":0.2908711924028503,"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."}}