{"id":"W2501195497","doi":"10.3389/fnins.2016.00325","title":"Manual-Protocol Inspired Technique for Improving Automated MR Image Segmentation during Label Fusion","year":2016,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto; SickKids Foundation; Centre for Addiction and Mental Health; McGill University; Douglas Mental Health University Institute","funders":"National Institute of Mental Health; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; IXICO; Servier; Eisai; Bristol-Myers Squibb; Government of Ontario; Eli Lilly and Company; Compute Canada; Weston Brain Institute; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; Alzheimer's Society; Synarc; F. Hoffmann-La Roche; University of Toronto; Brain and Behavior Research Foundation; Medpace; Novartis Pharmaceuticals Corporation; AstraZeneca; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Michael J. Fox Foundation for Parkinson's Research","keywords":"Computer science; Artificial intelligence; Segmentation; Pattern recognition (psychology); Markov random field; Robustness (evolution); Markov chain; Inference; Probabilistic logic; Image segmentation; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007202208,0.001422633,0.001042218,0.002152374,0.001421444,0.001883425,0.003064598,0.002113654,0.003303714],"category_scores_gemma":[0.01530753,0.0009086442,0.001623557,0.002150438,0.001689293,0.002257695,0.002867734,0.002375686,0.001701943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001131739,"about_ca_system_score_gemma":0.003413418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005094689,"about_ca_topic_score_gemma":0.008982521,"domain_scores_codex":[0.9964764,0.001091025,0.0002046743,0.001006527,0.0009878041,0.0002336017],"domain_scores_gemma":[0.9940087,0.002212376,0.0006550987,0.001781055,0.001185579,0.0001572945],"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":[0.0007418662,0.0002913187,0.006155821,0.0006283842,0.0003904813,0.0004686128,0.001311914,0.1164605,0.1021737,0.02624518,0.01450967,0.7306225],"study_design_scores_gemma":[0.0001360648,0.0003678354,0.003349355,0.00006580296,0.0001667415,0.0007966082,0.0002095472,0.8384324,0.09615995,0.04188948,0.01828605,0.0001401313],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009496953,0.0001633394,0.9860345,0.0001205933,0.00004908452,0.0001314737,0.0001230382,0.003109714,0.0007712369],"genre_scores_gemma":[0.1593626,0.0001830932,0.8347495,0.0004214543,0.00008844501,0.0004640764,0.0007905539,0.001617549,0.002322764],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007202208,"threshold_uncertainty_score":0.03808939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0146742938399287,"score_gpt":0.3107528252839283,"score_spread":0.2960785314439996,"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."}}