{"id":"W3031359424","doi":"10.48550/arxiv.2005.14017","title":"A Normalized Fully Convolutional Approach to Head and Neck Cancer Outcome Prediction","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Preprocessor; Computer science; Artificial intelligence; Deep learning; Feature extraction; Feature (linguistics); Modalities; Residual; Convolutional neural network; Head and neck; Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001763218,0.0002629888,0.0005087312,0.0001813604,0.00011435,0.00003385046,0.0001922375,0.0002201697,0.00006563838],"category_scores_gemma":[0.0001472712,0.0002755782,0.0001501611,0.0002656462,0.0001326903,0.00006647947,0.0004845166,0.001065758,0.00002023821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002490813,"about_ca_system_score_gemma":0.0002375375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000598483,"about_ca_topic_score_gemma":0.000009024227,"domain_scores_codex":[0.9984595,0.00006330172,0.0002443649,0.000813822,0.0001398229,0.0002792104],"domain_scores_gemma":[0.9988844,0.00003537029,0.0001184666,0.0003046007,0.0001112501,0.0005459229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001230163,0.0003194781,0.8695519,0.001331684,0.0006524005,0.0003744853,0.000685972,0.100707,0.0005270884,0.01813242,0.005347033,0.001140393],"study_design_scores_gemma":[0.003401734,0.0001555607,0.1834178,0.0003240576,0.0005520672,0.00004715193,0.00009543366,0.8017033,0.000007828073,0.0009047647,0.009020173,0.0003700909],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.897316,0.000151792,0.09307393,0.002696907,0.0004704036,0.0006545873,0.00008533458,0.0001944474,0.005356553],"genre_scores_gemma":[0.9932629,0.0002133543,0.002556371,0.001675828,0.0003574676,0.000005376649,0.0001301757,0.00003187829,0.001766575],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7009963,"threshold_uncertainty_score":0.9999697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08422657778240779,"score_gpt":0.2485409579365757,"score_spread":0.1643143801541679,"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."}}