{"id":"W2936340812","doi":"10.1007/s00330-019-06159-y","title":"Head and neck squamous cell carcinoma: prediction of cervical lymph node metastasis by dual-energy CT texture analysis with machine learning","year":2019,"lang":"en","type":"article","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":119,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Royal Victoria Hospital; Jewish General Hospital; Université de Montréal; Royal Victoria Regional Health Centre; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Réseau de cancérologie Rossy","keywords":"Medicine; Neuroradiology; Head and neck squamous-cell carcinoma; Lymph node metastasis; Cervical lymph nodes; Radiology; Interventional radiology; Head and neck; Basal cell; Lymph node; Ultrasound; Head and neck cancer; Metastasis; Radiation therapy; Pathology; Internal medicine; Surgery; Cancer; Neurology","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":[],"consensus_categories":[],"category_scores_codex":[0.0004723051,0.0002457412,0.0007345462,0.0002653985,0.0000789423,0.00001442192,0.0001079704,0.00005507819,0.000194192],"category_scores_gemma":[0.00009643396,0.0001824102,0.000137756,0.0004012495,0.0001827933,0.00004721841,0.00007905679,0.0005226294,0.00001316202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003978816,"about_ca_system_score_gemma":0.0000342094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003860905,"about_ca_topic_score_gemma":0.000004697672,"domain_scores_codex":[0.997949,0.0005966928,0.000387821,0.0005157912,0.0002193463,0.0003313724],"domain_scores_gemma":[0.9990234,0.0001475998,0.0002082031,0.0003372415,0.00005741592,0.000226159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002795409,0.0001525857,0.9827788,0.0001565096,0.0004190542,0.0003285157,0.0002144913,0.003009042,0.008629673,0.00006010343,0.0009071265,0.003064511],"study_design_scores_gemma":[0.007448563,0.001693226,0.8314276,0.00003747899,0.002334716,0.001802128,0.000120112,0.1339286,0.0003867879,0.00000527005,0.02050493,0.000310596],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9840962,0.002746536,0.004218102,0.000603942,0.0000874198,0.0001070697,0.00003442243,0.00007098665,0.008035264],"genre_scores_gemma":[0.9960978,0.000123047,0.0009728752,0.0006136539,0.0001214545,0.000002247707,0.0004024011,0.00006061332,0.001605923],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1513513,"threshold_uncertainty_score":0.7438471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005765094514935071,"score_gpt":0.2201333359373833,"score_spread":0.2143682414224482,"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."}}