{"id":"W2795981973","doi":"10.1016/j.neuroimage.2018.04.001","title":"Supervoxel based method for multi-atlas segmentation of brain MR images","year":2018,"lang":"en","type":"article","venue":"NeuroImage","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Voxel; Markov random field; Pairwise comparison; Atlas (anatomy); Inference; Pattern recognition (psychology); Consistency (knowledge bases); Grid; Image segmentation; Grid cell; Computer vision; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006822814,0.0001440406,0.0001867337,0.0001584764,0.00008722836,0.00008357386,0.0006420666,0.00004829178,0.00008330391],"category_scores_gemma":[0.0006448824,0.0001372081,0.00009298321,0.0003058391,0.0001535182,0.0005457263,0.0001174245,0.00008700519,0.00002296894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002131832,"about_ca_system_score_gemma":0.00006766786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003000351,"about_ca_topic_score_gemma":0.000003713401,"domain_scores_codex":[0.9984127,0.000237007,0.0003499326,0.0004417646,0.0003215482,0.0002370559],"domain_scores_gemma":[0.9984388,0.0005239074,0.0001535202,0.0005106184,0.0002749134,0.00009817626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001086154,0.0001036623,0.0000867387,0.00004967417,0.00000516618,0.000004154067,0.0002064847,0.000001749273,0.9099907,0.0002316933,0.01769461,0.0716145],"study_design_scores_gemma":[0.0008225164,0.0003222935,0.0009253336,0.00001386781,0.000007087999,0.00000317488,0.00001488328,0.1146269,0.882372,0.0001995031,0.0005782741,0.0001141346],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001010407,0.0000122551,0.9962773,0.001433713,0.0002050858,0.0005547732,0.00002456562,0.0002722447,0.0002095934],"genre_scores_gemma":[0.007209744,0.000002302319,0.9884584,0.003809348,0.00006722035,0.00007531162,0.0000144122,0.00001889129,0.0003443515],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1146252,"threshold_uncertainty_score":0.5595183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05499210990206533,"score_gpt":0.381986541458561,"score_spread":0.3269944315564957,"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."}}