{"id":"W2019306339","doi":"10.1109/tmi.2012.2216543","title":"The Relevance Voxel Machine (RVoxM): A Self-Tuning Bayesian Model for Informative Image-Based Prediction","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Center for Research Resources; National Institute of Neurological Disorders and Stroke; Solve ME/CFS Initiative; National Institute on Aging; Canadian Institutes of Health Research","keywords":"Voxel; Artificial intelligence; Computer science; Bayesian probability; Machine learning; Contrast (vision); Probabilistic logic; Pattern recognition (psychology); Relevance (law); Regression; Mathematics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001647262,0.0002394361,0.0001927893,0.0001793993,0.0008218406,0.0001934513,0.0007992538,0.00009099519,0.00003689696],"category_scores_gemma":[0.0002310087,0.0001821374,0.0001503626,0.0003821904,0.0002329115,0.001967123,0.000008870707,0.0006406026,0.00001973157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001864826,"about_ca_system_score_gemma":0.0002443923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001224757,"about_ca_topic_score_gemma":0.000005447645,"domain_scores_codex":[0.9972993,0.0001418996,0.0005671579,0.0003063177,0.00104724,0.0006380718],"domain_scores_gemma":[0.9975941,0.001043261,0.0001664357,0.0005135841,0.0001789387,0.0005036665],"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":[0.00005594252,0.0004286656,0.0000303753,0.00008120081,0.00006270853,0.000004934058,0.003104967,0.00220758,0.001169974,0.0006387457,0.00498081,0.9872341],"study_design_scores_gemma":[0.0007697908,0.00004227943,0.000009984617,0.00009330425,0.00002592253,0.00001809036,0.00007813504,0.9773954,0.02037284,0.0003830095,0.0006356041,0.0001756591],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002651759,0.0001000783,0.9923625,0.004873898,0.0007383229,0.0005839917,0.00002354946,0.001000614,0.0002905513],"genre_scores_gemma":[0.3492981,0.0001196884,0.645319,0.004394185,0.0001252721,0.0005507318,0.000008628063,0.00003555322,0.0001488335],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9870585,"threshold_uncertainty_score":0.742735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01173382650205568,"score_gpt":0.2833064757939247,"score_spread":0.271572649291869,"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."}}