{"id":"W4379031899","doi":"10.1007/978-3-658-41657-7_18","title":"Deep Learning Approaches for Contrast Removal from Contrast-enhanced CT","year":2023,"lang":"en","type":"book-chapter","venue":"Informatik aktuell","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Hounsfield scale; Contrast (vision); Computed tomography; Dosimetry; Nuclear medicine; Contrast enhancement; Selective internal radiation therapy; Medicine; Artificial intelligence; Computer science; Radiology; Magnetic resonance imaging","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004268674,0.001100534,0.0007281909,0.0006301668,0.0002071291,0.0009352998,0.001314012,0.001032559,0.00428615],"category_scores_gemma":[0.001003886,0.0005578543,0.0008880206,0.0008543704,0.0004380115,0.0008721635,0.001155607,0.001881586,0.002258178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005762661,"about_ca_system_score_gemma":0.0005336448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003900714,"about_ca_topic_score_gemma":0.007425771,"domain_scores_codex":[0.9998562,0.00001632625,0.000008077017,0.00003168595,0.00006698161,0.00002064115],"domain_scores_gemma":[0.9996989,0.0001374309,0.00002473522,0.00003875515,0.00008551275,0.00001466735],"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":[0.00006576864,0.00005785863,0.0002780328,0.0003148966,0.00008981487,0.0001048441,0.00004854362,0.1449485,0.02469751,0.01577827,0.01589877,0.7977172],"study_design_scores_gemma":[0.000006239241,0.0000345162,0.0004596139,0.00007626213,0.00004020311,0.0002555342,0.00001859195,0.9405162,0.01648093,0.02476907,0.01732149,0.00002136034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003279593,0.004972927,0.9866175,0.0003233161,0.0001344444,0.00002176374,0.0002226967,0.0009693784,0.003458402],"genre_scores_gemma":[0.1235073,0.01477985,0.8056661,0.0006101389,0.0004636926,0.0001134205,0.001904009,0.0009508091,0.05200451],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00428615,"threshold_uncertainty_score":0.01433855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02319343401328017,"score_gpt":0.2455315421095663,"score_spread":0.2223381080962862,"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."}}