{"id":"W2050978844","doi":"10.1016/j.media.2010.04.007","title":"High-throughput detection of prostate cancer in histological sections using probabilistic pairwise Markov models","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":123,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; American Cancer Society","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Markov chain; Pixel; Pairwise comparison; Markov model; Probabilistic logic; Markov random field; Markov process; Prior probability; Segmentation; Image segmentation; Bayesian probability; Machine learning; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003680818,0.0001700966,0.0006442488,0.0003397124,0.00006162476,0.0000121707,0.00007646207,0.0001689186,0.0009964013],"category_scores_gemma":[0.0003680087,0.000126987,0.0002530941,0.001263856,0.0002935095,0.0001240393,0.00004625193,0.0004217245,0.00000275857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003223407,"about_ca_system_score_gemma":0.0002595139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006246711,"about_ca_topic_score_gemma":0.00858908,"domain_scores_codex":[0.9982095,0.00007559799,0.0005171529,0.0004140589,0.0005042817,0.0002794011],"domain_scores_gemma":[0.9989894,0.00009960793,0.000149878,0.0003185535,0.0001988828,0.0002436571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001588653,0.009539846,0.5899922,0.001154429,0.008169443,0.002254929,0.00224477,0.02498825,0.1141781,0.0005118715,0.000413371,0.2449641],"study_design_scores_gemma":[0.006417333,0.0007842769,0.1935881,0.000392959,0.01283369,0.00009170148,0.0002045684,0.7488137,0.03302523,0.002866473,0.0003487798,0.0006331553],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9906296,0.0004240137,0.006920497,0.001255993,0.000175854,0.000403646,0.0000433861,0.0000395003,0.000107492],"genre_scores_gemma":[0.9965256,0.0004532286,0.00247135,0.0001311626,0.00008799662,0.0002058631,0.00003306252,0.00001472669,0.00007703579],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7238255,"threshold_uncertainty_score":0.9999169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01819696402735157,"score_gpt":0.3014415382075682,"score_spread":0.2832445741802166,"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."}}