{"id":"W4391948150","doi":"10.1002/acm2.14297","title":"A deep learning‐based framework (Co‐ReTr) for auto‐segmentation of non‐small cell‐lung cancer in computed tomography images","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Clinical Medical Physics","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kelowna General Hospital; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Convolutional neural network; Segmentation; Workflow; Transformer; Pattern recognition (psychology); Dice; Image segmentation","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":[0.0008236043,0.0001980909,0.0006478035,0.000119497,0.00003902732,0.00002884719,0.000297639,0.000181264,0.0001488998],"category_scores_gemma":[0.00004222314,0.000166013,0.0004781999,0.0004171591,0.0001800544,0.00008554915,0.00002484461,0.001377764,5.760804e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005271111,"about_ca_system_score_gemma":0.0003014838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007750143,"about_ca_topic_score_gemma":4.910435e-7,"domain_scores_codex":[0.9977974,0.00006789102,0.001177973,0.0002503447,0.0004571632,0.0002492861],"domain_scores_gemma":[0.9969704,0.001972078,0.0006080685,0.0001358612,0.0001242276,0.0001893338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007476991,0.001856706,0.05520522,0.0007436927,0.0007679741,0.00001838102,0.000677022,0.01718185,0.005099381,0.005695391,0.001489709,0.910517],"study_design_scores_gemma":[0.009387891,0.002205499,0.008570935,0.004074553,0.000652519,0.000001393234,0.0003409253,0.7582532,0.0904837,0.1215649,0.003377341,0.001087139],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02454798,0.0004147185,0.9738641,0.0002096371,0.0003251879,0.0003908563,0.00001611936,0.0000350855,0.0001962523],"genre_scores_gemma":[0.869347,0.0001148792,0.1286151,0.0002093755,0.001591286,0.00005844983,0.00001250724,0.00004635475,0.000005023203],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9094298,"threshold_uncertainty_score":0.6769813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01482261792125131,"score_gpt":0.3793075685646387,"score_spread":0.3644849506433874,"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."}}