{"id":"W4396665374","doi":"10.32920/25758126.v1","title":"Predicting Head & Neck Cancer Treatment Outcomes with Quantitative Ultrasound Texture Features & Optimizing Machine Learning Classifiers with Novel Texture-of-Texture Features","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University; University of Manitoba; Thunder Bay Regional Research Institute; University of Toronto; Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; University of Toronto; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Medicine; Radiomics; Head and neck cancer; Cancer; Head and neck; Artificial intelligence; Texture (cosmology); Lymph node; Nuclear medicine; Internal medicine; Radiology; Computer science; Surgery; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008317101,0.0004103923,0.0004824605,0.0006419157,0.0001196585,0.0007323917,0.0003357782,0.0004646228,0.000923763],"category_scores_gemma":[0.002831378,0.0001716445,0.0004986397,0.0003206918,0.0002260493,0.0003809148,0.0003285843,0.0005420367,0.000323929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004749976,"about_ca_system_score_gemma":0.000418628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002375663,"about_ca_topic_score_gemma":0.002251871,"domain_scores_codex":[0.9997477,0.00006702021,0.00001766053,0.00006496275,0.00005885665,0.00004385934],"domain_scores_gemma":[0.9992452,0.0003966906,0.0001458608,0.00004867953,0.0001242244,0.0000394126],"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":[0.001480134,0.0007821887,0.2183769,0.0002349503,0.0002339476,0.0003142412,0.000165414,0.2550483,0.04349805,0.0009206697,0.004977208,0.4739679],"study_design_scores_gemma":[0.00002412083,0.0003703593,0.05449943,0.0000269734,0.00005873687,0.000130626,0.00009681949,0.9352869,0.007604088,0.001175335,0.0007019181,0.00002465011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.851959,0.0008693278,0.1433833,0.0005929833,0.00007278287,0.0001346767,0.0007545062,0.0003937754,0.001839612],"genre_scores_gemma":[0.9807448,0.0001280384,0.01783809,0.00005577817,0.00003630472,0.00006534327,0.0003735478,0.00002152045,0.0007364738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002375663,"threshold_uncertainty_score":0.004723668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03021776226692748,"score_gpt":0.341865553244745,"score_spread":0.3116477909778176,"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."}}