{"id":"W4308662651","doi":"10.1007/s00330-022-09229-w","title":"Deep learning–based harmonization of CT reconstruction kernels towards improved clinical task performance","year":2022,"lang":"en","type":"article","venue":"European Radiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; China Scholarship Council; Postdoctoral Research Foundation of China; National Natural Science Foundation of China","keywords":"Medicine; Convolutional neural network; Artificial intelligence; Neuroradiology; Feature (linguistics); Kernel (algebra); Deep learning; Radiology; Pattern recognition (psychology); Nuclear medicine; Computer science; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.001889817,0.0001228287,0.0003668711,0.0001325937,0.0001778129,0.000006231324,0.0001557856,0.00002545451,0.0003887977],"category_scores_gemma":[0.0008276266,0.00011579,0.0001245294,0.0001886692,0.0002453292,0.00003686326,0.00009113838,0.001011923,0.00001787076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006293771,"about_ca_system_score_gemma":0.00009847442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001098318,"about_ca_topic_score_gemma":1.299459e-7,"domain_scores_codex":[0.9975884,0.00115146,0.0005618414,0.0003234726,0.0001530221,0.000221805],"domain_scores_gemma":[0.999178,0.000107448,0.0003080177,0.0002260444,0.00006597021,0.0001145008],"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":[0.0004002069,0.0001575153,0.2887751,0.00008247911,0.0001032884,0.0001365597,0.0002013771,0.01322773,0.007391089,0.00004223775,0.000745321,0.6887372],"study_design_scores_gemma":[0.003175939,0.001877933,0.2617979,0.00002964288,0.000099704,0.0017246,0.00009587074,0.6928759,0.0002782666,0.000009613954,0.0378608,0.0001738635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9773716,0.0002053416,0.01601198,0.0008071634,0.0009985458,0.0001879021,0.000002130927,0.0001045597,0.004310748],"genre_scores_gemma":[0.9949517,0.0001254074,0.003069527,0.000874309,0.0003336592,0.000006609068,0.000107495,0.00004248537,0.0004888329],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6885633,"threshold_uncertainty_score":0.4721779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01696325247613244,"score_gpt":0.286316956899957,"score_spread":0.2693537044238246,"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."}}