{"id":"W4407490272","doi":"10.1117/12.3046813","title":"Is segmentation performance of deep-learning models affected by cancer type? A performance analysis on PET/CT","year":2025,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Deep learning; Cancer; Machine learning; Medicine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007273585,0.001748867,0.00113849,0.00152265,0.000432442,0.00172345,0.001123897,0.002069737,0.001073964],"category_scores_gemma":[0.01482629,0.0004722097,0.001414997,0.0008528531,0.0009006358,0.001330118,0.001109898,0.001303778,0.0008200004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001361491,"about_ca_system_score_gemma":0.001109489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01511052,"about_ca_topic_score_gemma":0.01138254,"domain_scores_codex":[0.9978474,0.0007833556,0.0001694672,0.0005768398,0.0003529473,0.0002699512],"domain_scores_gemma":[0.9940776,0.003481627,0.0004701694,0.0005913143,0.001046593,0.0003326792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006488572,0.0005431375,0.1389135,0.0009623886,0.001826093,0.0004697029,0.0003984093,0.5509,0.01457632,0.0009456722,0.01337607,0.2706001],"study_design_scores_gemma":[0.000098211,0.00100232,0.02948474,0.0002499592,0.0004034504,0.0003031116,0.0002350806,0.9523715,0.01233078,0.001447567,0.002002296,0.00007096969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9534378,0.01168003,0.02483653,0.00141366,0.0004352037,0.0001251796,0.002162098,0.001828878,0.004080691],"genre_scores_gemma":[0.981481,0.001346793,0.009756984,0.0004050676,0.00008893244,0.00004204526,0.005200157,0.0002225807,0.001456383],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01511052,"threshold_uncertainty_score":0.03846687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009121825037143311,"score_gpt":0.2998814277911506,"score_spread":0.2907596027540073,"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."}}