{"id":"W2970612217","doi":"10.1016/j.radonc.2019.08.008","title":"Sensitivity of radiomic features to inter-observer variability and image pre-processing in Apparent Diffusion Coefficient (ADC) maps of cervix cancer patients","year":2019,"lang":"en","type":"article","venue":"Radiotherapy and Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"Princess Margaret Cancer Foundation","keywords":"Effective diffusion coefficient; Sensitivity (control systems); Cervix; Medicine; Observer (physics); Diffusion MRI; Diffusion imaging; Nuclear medicine; Cancer; Radiology; Artificial intelligence; Computer science; Internal medicine; Magnetic resonance imaging; Physics; Engineering","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":[0.0007812359,0.000129952,0.0005897564,0.0001235982,0.00002822986,0.000005299552,0.00004722753,0.0001099388,0.00004922613],"category_scores_gemma":[0.0001231747,0.0001030735,0.00004096961,0.000129456,0.0001860488,0.00004067843,0.00005244249,0.0002480409,1.857291e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002249305,"about_ca_system_score_gemma":0.00009505309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007289249,"about_ca_topic_score_gemma":0.00007504964,"domain_scores_codex":[0.9988309,0.0002395463,0.0003148363,0.0002971862,0.0001362152,0.0001813502],"domain_scores_gemma":[0.9993391,0.0001891145,0.0001446683,0.0001451161,0.00007097317,0.0001110286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009933216,0.0005699882,0.7537464,0.0005277869,0.00002677064,0.000008842728,0.003680468,0.0001253557,0.1256282,0.0000186495,0.0001686225,0.1145056],"study_design_scores_gemma":[0.004025492,0.0009105692,0.9691894,0.0003200603,0.00003153753,0.00002950507,0.00007227824,0.02253755,0.001342878,0.00002175825,0.001407175,0.0001118184],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953394,0.0006303411,0.002374174,0.0008527465,0.000185233,0.0004915327,0.0000142913,0.000009220887,0.0001030797],"genre_scores_gemma":[0.9962513,0.0003400905,0.002742011,0.0005404578,0.00004139227,0.000008126076,0.00001035118,0.00001457814,0.00005162216],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.215443,"threshold_uncertainty_score":0.4203217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006537182572388001,"score_gpt":0.3033597934002563,"score_spread":0.2968226108278683,"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."}}