{"id":"W4401241666","doi":"10.1088/1361-6560/ad6ace","title":"Boundary-aware semantic clustering network for segmentation of prostate zones from T2-weighted MRI","year":2024,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; Western University","funders":"City University of Hong Kong","keywords":"Segmentation; Pattern recognition (psychology); Computer science; Artificial intelligence; Ground truth; Boundary (topology); Feature (linguistics); Similarity (geometry); Cluster analysis; Generalizability theory; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001134829,0.001164762,0.0008497916,0.002765168,0.0006391847,0.0008065127,0.001254439,0.001396602,0.00133125],"category_scores_gemma":[0.00221359,0.00039709,0.0009662607,0.001289096,0.0005762003,0.001196978,0.001160687,0.0008170074,0.0005464205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001378555,"about_ca_system_score_gemma":0.001277718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01215825,"about_ca_topic_score_gemma":0.01453823,"domain_scores_codex":[0.9994542,0.00009541406,0.00002590247,0.0002058103,0.0001399291,0.00007878663],"domain_scores_gemma":[0.9994258,0.0001543511,0.00007753655,0.00005945739,0.0002413613,0.0000415239],"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":[0.001455044,0.0003306218,0.00645873,0.0003796404,0.0002831847,0.0002846376,0.0002614962,0.3745833,0.03382207,0.004512568,0.01207416,0.5655545],"study_design_scores_gemma":[0.00001802246,0.00006929044,0.001522481,0.00001966846,0.00005009568,0.00007956714,0.00003863636,0.9865918,0.007845308,0.002617388,0.001129378,0.00001842784],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.223179,0.002372251,0.7622679,0.0005773227,0.0001933573,0.0003596773,0.001357232,0.004930924,0.004762302],"genre_scores_gemma":[0.7469999,0.0006762196,0.242302,0.0004348736,0.0001511145,0.0002306099,0.004123128,0.0003377481,0.004744417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01215825,"threshold_uncertainty_score":0.02417493,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09881275423703526,"score_gpt":0.3814328621370547,"score_spread":0.2826201079000195,"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."}}