{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T18:55:43Z","timestamp":1790621743027,"version":"4.1.0"},"reference-count":68,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2022,7,30]],"date-time":"2022-07-30T00:00:00Z","timestamp":1659139200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2022,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>As a means to extract biomarkers from medical imaging, radiomics has attracted increased attention from researchers. However, reproducibility and performance of radiomics in low\u2010dose CT scans are still poor, mostly due to noise. Deep learning generative models can be used to denoise these images and in turn improve radiomics\u2019 reproducibility and performance. However, most generative models are trained on paired data, which can be difficult or impossible to collect.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>In this article, we investigate the possibility of denoising low\u2010dose CTs using cycle generative adversarial networks (GANs) to improve radiomics reproducibility and performance based on unpaired datasets.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods and materials<\/jats:title><jats:p>Two cycle GANs were trained: (1) from paired data, by simulating low\u2010dose CTs (i.e., introducing noise) from high\u2010dose CTs and (2) from unpaired real low dose CTs. To accelerate convergence, during GAN training, a slice\u2010paired training strategy was introduced. The trained GANs were applied to three scenarios: (1) improving radiomics reproducibility in simulated low\u2010dose CT images and (2) same\u2010day repeat low dose CTs (RIDER dataset), and (3) improving radiomics performance in survival prediction. Cycle GAN results were compared with a conditional GAN (CGAN) and an encoder\u2013decoder network (EDN) trained on simulated paired data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The cycle GAN trained on simulated data improved concordance correlation coefficients (CCC) of radiomic features from 0.87 (95%CI, [0.833,0.901]) to 0.93 (95%CI, [0.916,0.949]) on simulated noise CT and from 0.89 (95%CI, [0.881,0.914]) to 0.92 (95%CI, [0.908,0.937]) on the RIDER dataset, as well improving the area under the receiver operating characteristic curve (AUC) of survival prediction from 0.52 (95%CI, [0.511,0.538]) to 0.59 (95%CI, [0.578,0.602]). The cycle GAN trained on real data increased the CCCs of features in RIDER to 0.95 (95%CI, [0.933,0.961]) and the AUC of survival prediction to 0.58 (95%CI, [0.576,0.596]).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The results show that cycle GANs trained on both simulated and real data can improve radiomics\u2019 reproducibility and performance in low\u2010dose CT and achieve similar results compared to CGANs and EDNs.<\/jats:p><\/jats:sec>","DOI":"10.1002\/acm2.13739","type":"journal-article","created":{"date-parts":[[2022,7,30]],"date-time":"2022-07-30T11:24:57Z","timestamp":1659180297000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Improving reproducibility and performance of radiomics in low\u2010dose CT using cycle GANs"],"prefix":"10.1002","volume":"23","author":[{"given":"Junhua","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology Maastricht University Medical Centre+  Maastricht ET Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonard","family":"Wee","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology Maastricht University Medical Centre+  Maastricht ET Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andre","family":"Dekker","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology Maastricht University Medical Centre+  Maastricht ET Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Inigo","family":"Bermejo","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology Maastricht University Medical Centre+  Maastricht ET Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,7,30]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrclinonc.2011.121"},{"issue":"1","key":"e_1_2_9_3_1","first-page":"1","article-title":"Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach","volume":"5","author":"Aerts HJWL","year":"2014","journal-title":"Nat Commun"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.116.180919"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/61\/24\/8736"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.111.099127"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/npjbcancer.2016.12"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2018.2796598"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep45639"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-019-02028-w"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018172361"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.10.027"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019190928"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac16c0"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102036"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.852196"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2596743"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","unstructured":"ZhangK ZuoW GuS ZhangL.Learning deep CNN denoiser prior for image restoration:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;21\u201326 July 2017; Honolulu HI.","DOI":"10.1109\/CVPR.2017.300"},{"key":"e_1_2_9_21_1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky A","year":"2012","journal-title":"Adv Neural Inform Process Syst"},{"key":"e_1_2_9_22_1","doi-asserted-by":"crossref","unstructured":"LefkimmiatisS.Non\u2010local color image denoising with convolutional neural networks:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;21\u201326 July 2017; Honolulu HI.","DOI":"10.1109\/CVPR.2017.623"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2715284"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2827462"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.09.003"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2766438"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2715284"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2827462"},{"key":"e_1_2_9_29_1","unstructured":"MirzaM OsinderoS.Conditional generative adversarial nets. arXiv:1411.17842014."},{"key":"e_1_2_9_30_1","volume-title":"Foundations of statistical natural language processing","author":"Manning C","year":"1999"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(82)90112-4"},{"key":"e_1_2_9_32_1","doi-asserted-by":"crossref","unstructured":"JohnsonJ AlahiA Fei\u2010Fei L.Perceptual losses for real\u2010time style transfer and super\u2010resolution:European Conference on Computer Vision. Amsterdam The Netherlands at Oct 8 2016.Springer;2016.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.7937\/9npb\u20102637"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2522081593"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13284"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab8319"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3077615"},{"key":"e_1_2_9_38_1","doi-asserted-by":"crossref","unstructured":"IsolaP ZhuJ\u2010Y ZhouT EfrosAA.Image\u2010to\u2010image translation with conditional adversarial networks:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;21\u201326 July 2017; Honolulu HI.","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.2307\/2532051"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2022.04.008"},{"key":"e_1_2_9_41_1","unstructured":"ChenJ ZengH ZhangC et\u00a0al.Lung cancer diagnosis using deep attention based on multiple instance learning and radiomics. arXiv:2104.146552021."},{"key":"e_1_2_9_42_1","doi-asserted-by":"crossref","unstructured":"ZhuJ\u2010Y et\u00a0al.Unpaired image\u2010to\u2010image translation using cycle\u2010consistent adversarial networks:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 21\u201326 July 2017; Honolulu HI.","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_2_9_43_1","doi-asserted-by":"crossref","unstructured":"DengJ DongW SocherR LiLi\u2010J LiK Fei\u2010FeiLi.Imagenet: a large\u2010scale hierarchical image database:2009 IEEE Conference on Computer Vision and Pattern recognition Miami FL 20\u201325 June 2009.IEEE;2009.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3015379"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctro.2019.07.003"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.7937\/K9\/TCIA.2015.PF0M9REI"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3528204"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.7937\/K9\/TCIA.2016.JGNIHEP5"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.202"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.05.053"},{"key":"e_1_2_9_51_1","first-page":"2079","article-title":"On over\u2010fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley GC","year":"2010","journal-title":"J Mach Learn Res"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.50"},{"key":"e_1_2_9_53_1","unstructured":"KingmaDP BaJ.Adam: a method for stochastic optimization. arXiv:1412.69802014."},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-17-0339"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-011-9205-2"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3101363"},{"key":"e_1_2_9_57_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 27\u201330 June 2016; Las Vegas NV.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007844"},{"key":"e_1_2_9_59_1","doi-asserted-by":"crossref","unstructured":"IsenseeF KickingerederP WickW BendszusM Maier\u2010HeinKH.Brain tumor segmentation and radiomics survival prediction: contribution to the brats 2017 challenge:International MICCAI Brainlesion Workshop Quebec City Canada 14 September 2017.Springer;2017.","DOI":"10.1007\/978-3-319-75238-9_25"},{"key":"e_1_2_9_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2377694"},{"key":"e_1_2_9_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-06737-5"},{"key":"e_1_2_9_62_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018180200"},{"key":"e_1_2_9_63_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27908"},{"key":"e_1_2_9_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106622"},{"key":"e_1_2_9_65_1","first-page":"826","article-title":"Understanding sources of variation to improve the reproducibility of radiomics","volume":"11","author":"Zhao B","year":"2021","journal-title":"Front Oncol"},{"key":"e_1_2_9_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2900993"},{"key":"e_1_2_9_67_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-10649-8"},{"key":"e_1_2_9_68_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.2409481"},{"key":"e_1_2_9_69_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aba798"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.13739","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/acm2.13739","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.13739","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T07:21:38Z","timestamp":1692688898000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.13739"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,30]]},"references-count":68,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["10.1002\/acm2.13739"],"URL":"https:\/\/doi.org\/10.1002\/acm2.13739","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,30]]},"assertion":[{"value":"2022-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-11","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e13739"}}