{"id":"W4327770651","doi":"10.1007/978-3-031-27420-6_10","title":"A U-Net Convolutional Neural Network with Multiclass Dice Loss for Automated Segmentation of Tumors and Lymph Nodes from Head and Neck Cancer PET/CT Images","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Dice; Segmentation; Computer science; Test set; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Encoder; Head and neck; Medicine; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002580884,0.000230594,0.0004264083,0.0001469432,0.0001203359,0.00006387562,0.0001353403,0.00002890455,0.00000554577],"category_scores_gemma":[0.00009490159,0.0001778038,0.0000336843,0.0001439753,0.0009702202,0.00008841762,0.0001140885,0.0002777221,3.446917e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008356844,"about_ca_system_score_gemma":0.0002198661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004770328,"about_ca_topic_score_gemma":0.00005803551,"domain_scores_codex":[0.998531,0.0000165393,0.0002642559,0.0005444664,0.0003680338,0.0002757353],"domain_scores_gemma":[0.9988276,0.0006014004,0.0001820938,0.0001512667,0.0001208379,0.0001168388],"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":[0.0006303298,0.00007749015,0.2394464,0.001149828,0.000276028,0.00114847,0.001014054,0.4723193,0.002689794,0.0005397425,0.000203315,0.2805052],"study_design_scores_gemma":[0.001551083,0.0001279777,0.06363514,0.001485644,0.00006170523,0.0002637056,9.142445e-7,0.9310614,0.0001148995,0.001493489,0.00002308854,0.0001809949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5431119,0.001353007,0.4514171,0.002418849,0.0006206257,0.0007502221,0.0001027466,0.0001814335,0.00004420284],"genre_scores_gemma":[0.8284417,0.0001296706,0.1698315,0.0009635875,0.0003919678,0.00001936127,0.00007687212,0.00004257053,0.0001027887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.458742,"threshold_uncertainty_score":0.7250628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01221877756972753,"score_gpt":0.2889093639235616,"score_spread":0.276690586353834,"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."}}