{"id":"W3160730820","doi":"10.1016/j.compbiomed.2021.104472","title":"MRI and CT bladder segmentation from classical to deep learning based approaches: Current limitations and lessons","year":2021,"lang":"en","type":"review","venue":"Computers in Biology and Medicine","topic":"Bladder and Urothelial Cancer Treatments","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Bell (Canada)","funders":"","keywords":"Segmentation; Bladder cancer; Deep learning; Artificial intelligence; Computer science; Context (archaeology); Medicine; Machine learning; Image segmentation; Medical physics; Radiology; Cancer; Internal medicine","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":[0.0001468513,0.0002870609,0.001195251,0.000220886,0.00007960404,0.000009869648,0.00004409048,0.0001466924,0.00001698679],"category_scores_gemma":[0.00009078388,0.0002037451,0.00005356744,0.0001780895,0.000244414,0.00001960027,0.00007061623,0.0004414276,0.000001619314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006263623,"about_ca_system_score_gemma":0.000110883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002770172,"about_ca_topic_score_gemma":0.00003396941,"domain_scores_codex":[0.9985707,0.0002558882,0.0003415278,0.0005676101,0.00007496194,0.0001893255],"domain_scores_gemma":[0.9988591,0.0006814423,0.00009256517,0.0001365172,0.00002415001,0.0002062234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001813831,0.0000677899,0.001019004,0.0007741341,0.0001847672,0.0000286726,0.0004770449,0.000001511431,0.000001238938,0.0001653152,0.0002497248,0.9970127],"study_design_scores_gemma":[0.004473602,0.001110086,0.002890846,0.01671525,0.002444902,0.0001433727,0.000502267,0.001001778,0.000001591246,0.0001901868,0.9701505,0.0003755916],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002373699,0.9842436,0.01222635,0.002131239,0.0003929029,0.0006397142,0.0000155961,0.00002065009,0.00009252013],"genre_scores_gemma":[0.001121566,0.9926416,0.004149412,0.0004787462,0.0003247295,0.0001141683,0.00112765,0.00001977593,0.00002241229],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.996637,"threshold_uncertainty_score":0.8308485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1731117576690547,"score_gpt":0.4136077935122064,"score_spread":0.2404960358431518,"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."}}