{"id":"W2035801028","doi":"10.1117/12.430974","title":"<title>Unsupervised partial volume estimation using 3D and statistical priors</title>","year":2001,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec","funders":"","keywords":"Prior probability; Markov random field; Segmentation; Artificial intelligence; Maximum a posteriori estimation; Autoregressive model; Computer science; A priori and a posteriori; Mixture model; Partial volume; Pattern recognition (psychology); Image segmentation; Gaussian; Scale-space segmentation; Computer vision; Mathematics; Bayesian probability; Statistics; Maximum likelihood","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":[0.0008307893,0.0009678584,0.0009849154,0.001586202,0.0004640529,0.001809046,0.001332172,0.001162348,0.03695761],"category_scores_gemma":[0.002033463,0.0005754993,0.000861652,0.001771546,0.0007350564,0.001756596,0.001009585,0.001099532,0.0268847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007237476,"about_ca_system_score_gemma":0.0008013567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002760165,"about_ca_topic_score_gemma":0.005812551,"domain_scores_codex":[0.9995017,0.00008442314,0.00002451375,0.0001515118,0.0002076927,0.00003011943],"domain_scores_gemma":[0.9989826,0.0002560081,0.00007748695,0.0003275884,0.000294835,0.0000613794],"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":[0.0002138936,0.00005429409,0.0005953397,0.0002881248,0.00006503843,0.0001828833,0.00004846123,0.05028672,0.04172277,0.02670734,0.08670668,0.7931284],"study_design_scores_gemma":[0.00005118991,0.0001109904,0.002295964,0.0001173044,0.00003799495,0.0005352583,0.00003278614,0.6615181,0.07425482,0.04224361,0.2186686,0.0001333853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001996367,0.0006556252,0.9822602,0.0004343478,0.0003118155,0.00008924791,0.000748073,0.006019451,0.007484918],"genre_scores_gemma":[0.04908421,0.001848214,0.8822646,0.0003645189,0.0005287933,0.0002634515,0.005435844,0.005400797,0.05480961],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03695761,"threshold_uncertainty_score":0.1236356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01447609153947423,"score_gpt":0.2556738998168649,"score_spread":0.2411978082773907,"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."}}