{"id":"W4205470984","doi":"10.1016/j.media.2021.102347","title":"ProstAttention-Net: A deep attention model for prostate cancer segmentation by aggressiveness in MRI scans","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":96,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Lyon; Université Claude Bernard Lyon 1; Agence Nationale de la Recherche","keywords":"Prostate cancer; Prostate; Prostatectomy; Magnetic resonance imaging; Grading (engineering); Segmentation; Medicine; Receiver operating characteristic; Prostate biopsy; Computer science; Biopsy; Artificial intelligence; Radiology; Cancer; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004538257,0.0001849525,0.0004721007,0.0003448436,0.0002205616,0.00003390475,0.0001033815,0.00005555173,0.001112539],"category_scores_gemma":[0.00005656077,0.000164055,0.0003105171,0.001102028,0.00008390061,0.0001424813,0.00006755163,0.0002035051,0.000003298065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006730013,"about_ca_system_score_gemma":0.0002498294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007359889,"about_ca_topic_score_gemma":0.0007831019,"domain_scores_codex":[0.9976964,0.00009255083,0.0004767314,0.0005210219,0.0008504804,0.00036281],"domain_scores_gemma":[0.9991559,0.00004926189,0.0002054575,0.0002172748,0.0001502951,0.0002217663],"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":[0.001167387,0.003778076,0.8170531,0.000514363,0.004421439,0.0003662423,0.002752014,0.03489732,0.006556604,0.00002631962,0.0140593,0.1144078],"study_design_scores_gemma":[0.006497636,0.0003261606,0.01924094,0.000130736,0.00357012,0.000006685596,0.0007727061,0.9669939,0.001432338,0.000140307,0.0006212346,0.0002672949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7995431,0.004393343,0.1745617,0.01696404,0.0001580086,0.002950758,0.001292306,0.00007531583,0.00006142379],"genre_scores_gemma":[0.9795241,0.001639985,0.001371884,0.001416641,0.00004852857,0.01015701,0.004293559,0.00003833691,0.001509999],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9320965,"threshold_uncertainty_score":0.9998006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01021742887747591,"score_gpt":0.3148450577693898,"score_spread":0.3046276288919139,"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."}}