{"id":"W4396778312","doi":"10.3390/cancers16142538","title":"Segmentation-Free Outcome Prediction from Head and Neck Cancer PET/CT Images: Deep Learning-Based Feature Extraction from Multi-Angle Maximum Intensity Projections (MA-MIPs)","year":2024,"lang":"en","type":"preprint","venue":"Cancers","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Artificial intelligence; Deep learning; Computer science; Segmentation; Convolutional neural network; Feature (linguistics); Feature extraction; Projection (relational algebra); Pattern recognition (psychology); Positron emission tomography; Head and neck; Nuclear medicine; Medicine","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":[0.0005819011,0.0007468424,0.0006054152,0.0007203865,0.0001685638,0.0005069099,0.0008325775,0.0004895465,0.0008043239],"category_scores_gemma":[0.0013156,0.0003300039,0.0007981981,0.0004029115,0.0002335445,0.0004146231,0.0007835344,0.0007521517,0.0004373582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003778587,"about_ca_system_score_gemma":0.0007776364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003474924,"about_ca_topic_score_gemma":0.004971254,"domain_scores_codex":[0.9997615,0.00003600943,0.00001662472,0.00008322974,0.00006365217,0.00003906841],"domain_scores_gemma":[0.9997405,0.00008243561,0.00006343571,0.00003969663,0.00004917542,0.00002467706],"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":[0.0005260264,0.0002740038,0.02103669,0.0002201594,0.0002478848,0.0004804516,0.000103251,0.1969195,0.05381196,0.001653137,0.00621009,0.7185169],"study_design_scores_gemma":[0.00003255761,0.000142298,0.007366179,0.00002498322,0.00006280086,0.0003556981,0.00001745418,0.9614918,0.02535815,0.002965008,0.00214078,0.00004234222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0947869,0.0009285424,0.8981416,0.0003528048,0.00006872295,0.000140709,0.001089771,0.003706519,0.0007845358],"genre_scores_gemma":[0.6666601,0.0007674504,0.326016,0.0002726922,0.0001202509,0.0003391744,0.00343301,0.0002357891,0.00215555],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003474924,"threshold_uncertainty_score":0.00690937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02290937549878231,"score_gpt":0.3350893494350402,"score_spread":0.3121799739362578,"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."}}