{"id":"W2017735759","doi":"10.1118/1.3359459","title":"Supervised and unsupervised methods for prostate cancer segmentation with multispectral MRI","year":2010,"lang":"en","type":"article","venue":"Medical Physics","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":130,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto General Hospital; Princess Margaret Cancer Centre; University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Multispectral image; Artificial intelligence; Computer science; Thresholding; Pattern recognition (psychology); Support vector machine; Segmentation; Medical imaging; Image segmentation; Image (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":[0.0001758975,0.0001566936,0.0002700093,0.0000190209,0.00008176102,0.00001924642,0.00004375988,0.00007106006,0.0001338721],"category_scores_gemma":[0.00004351365,0.0001040963,0.00004922929,0.0001001056,0.0001575216,0.00007631816,0.00001785607,0.000207257,0.000001872319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004682423,"about_ca_system_score_gemma":0.000221449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001202647,"about_ca_topic_score_gemma":0.00009233197,"domain_scores_codex":[0.9990403,0.00002138233,0.0001542006,0.0002881074,0.0002494566,0.0002465626],"domain_scores_gemma":[0.9992518,0.0001422228,0.00004020118,0.0001558595,0.00009833392,0.000311628],"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":[0.0004738061,0.0004641363,0.06632628,0.0002732802,0.0002107959,0.00001847072,0.001105941,0.000002213105,0.01416608,0.0002915967,0.0005077001,0.9161597],"study_design_scores_gemma":[0.04218825,0.003844023,0.08524578,0.0006928366,0.0012434,0.00006296109,0.0003422045,0.01614096,0.8317592,0.004288894,0.01336494,0.0008265138],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9413624,0.0006946287,0.04605477,0.0090833,0.0003452462,0.002161467,0.00007049533,0.00008600876,0.0001417034],"genre_scores_gemma":[0.8968663,0.001310563,0.09678814,0.002128137,0.0006714254,0.001795148,0.0002117015,0.00006341602,0.0001651661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9153332,"threshold_uncertainty_score":0.4244924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01935200495020621,"score_gpt":0.3588388141063028,"score_spread":0.3394868091560965,"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."}}