{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:23:19Z","timestamp":1793132599118,"version":"4.5.0"},"reference-count":24,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2019,7,17]],"date-time":"2019-07-17T00:00:00Z","timestamp":1563321600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2019,9]]},"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>Reducing dose level to achieve ALARA is an important task in diagnostic and therapeutic applications of computed tomography (CT) imaging. Effective image quality enhancement strategies are crucial to compensate for the degradation caused by dose reduction. In the past few years, deep learning approaches have demonstrated promising denoising performance on natural\/synthetic images. This study tailors a neural network model for (ultra\u2010)low\u2010dose CT denoising, and assesses its performance in enhancing CT image quality and emphysema quantification.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>The noise statistics in low\u2010dose CT images has its unique characteristics and differs from that used in general denoising models. In this study, we first simulate the paired ultra\u2010low\u2010dose and targeted high\u2010quality image of reference, with a well\u2010validated pipeline. These paired images are used to train a denoising convolutional neural network (DnCNN) with residual mapping. The performance of the DnCNN tailored to CT denoising (DnCNN\u2010CT) is assessed over various dose reduction levels, with respect to both image quality and emphysema scoring quantification. The possible over\u2010smoothing behavior of DnCNN and its impact on different subcohort of patients are also investigated.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Performance evaluation results showed that DnCNN\u2010CT provided significant image quality enhancement, especially for very\u2010low\u2010dose level. With DnCNN\u2010CT denoising on 3%\u2010dose cases, the peak signal\u2010to\u2010noise ratio improved by 8\u00a0dB and the structure similarity index increased by 0.15. This outperformed the original DnCNN and the state\u2010of\u2010the\u2010art nonlocal\u2010mean\u2010type denoising scheme. Emphysema mask was also investigated, where lung voxels of abnormally low attenuation coefficient were marked as potential emphysema. Emphysema mask generated after DnCNN\u2010CT denoising on 3%\u2010dose image was demonstrated to agree well with that from the full\u2010dose reference. Despite over\u2010smoothing in DnCNN denoising, which contributed to slight underestimation of emphysema score compared to the reference, such minor overcorrection did not affect clinical conclusions. The proposed method provided effective detection for cases with appreciable emphysema while serving as a reasonable correction for normal cases without emphysema.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>This work provides a tailored DnCNN for (ultra\u2010)low\u2010dose CT denoising, and demonstrates significant improvement on both the image quality and the clinical emphysema quantification accuracy over various dose levels. The clinical conclusion of emphysema obtained from the denoised low\u2010dose images agrees well with that from the full\u2010dose ones.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.13666","type":"journal-article","created":{"date-parts":[[2019,6,20]],"date-time":"2019-06-20T18:13:24Z","timestamp":1561054404000},"page":"3941-3950","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["A convolutional neural network for ultra\u2010low\u2010dose CT denoising and emphysema screening"],"prefix":"10.1002","volume":"46","author":[{"given":"Tingting","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology University of California Los Angeles CA 90095 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"McNitt\u2010Gray","sequence":"additional","affiliation":[{"name":"Departments of Biomedical Physics and Radiology University of California Los Angeles CA 90095 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Ruan","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of California Los Angeles CA 90095 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2019,7,17]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1102873"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2312030880"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra072149"},{"key":"e_1_2_6_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2007.901238"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.5201\/ipol.2012.l-bm3d"},{"key":"e_1_2_6_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881969"},{"key":"e_1_2_6_8_1","doi-asserted-by":"crossref","unstructured":"MairalJ BachF PonceJ SapiroG ZissermanA.Non\u2010local sparse models for image restoration. 2009 IEEE 12th International Conference on Computer Vision;2009:2272\u20132279.","DOI":"10.1109\/ICCV.2009.5459452"},{"key":"e_1_2_6_9_1","first-page":"769","article-title":"Natural image denoising with convolutional networks","author":"Jain V","year":"2009","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_6_10_1","doi-asserted-by":"crossref","unstructured":"BurgerHC SchulerCJ HarmelingS.Image denoising: Can plain neural networks compete with BM3D?. Computer Vision and Pattern Recognition (CVPR) 2012 IEEE Conference on 2012;2392\u20132399.","DOI":"10.1109\/CVPR.2012.6247952"},{"key":"e_1_2_6_11_1","doi-asserted-by":"crossref","unstructured":"PlotzT RothS.Benchmarking Denoising Algorithms with Real Photographs. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR);2017:1:6.","DOI":"10.1109\/CVPR.2017.294"},{"key":"e_1_2_6_12_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR);2016:770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_6_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2662206"},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2008.2004557"},{"key":"e_1_2_6_15_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4941953"},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2323030899"},{"key":"e_1_2_6_17_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.06-2325"},{"key":"e_1_2_6_18_1","doi-asserted-by":"publisher","DOI":"10.1136\/thx.2005.054890"},{"key":"e_1_2_6_19_1","doi-asserted-by":"publisher","DOI":"10.1136\/thx.2010.145995"},{"key":"e_1_2_6_20_1","unstructured":"IoffeS SzegedyC.Batch normalization: accelerating deep network training by reducing internal covariate shift. International Conference on Machine Learning 2015."},{"key":"e_1_2_6_21_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4789628"},{"key":"e_1_2_6_22_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4918919"},{"key":"e_1_2_6_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-013-3078-5"},{"key":"e_1_2_6_24_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.15.15684"},{"key":"e_1_2_6_25_1","doi-asserted-by":"crossref","unstructured":"HeK GirshickR Doll\u00e1rP.Rethinking ImageNet Pre\u2010training.arXiv preprint arXiv:1811.08883 2018.","DOI":"10.1109\/ICCV.2019.00502"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fmp.13666","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.13666","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.13666","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.13666","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T07:55:40Z","timestamp":1693900540000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.13666"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,17]]},"references-count":24,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["10.1002\/mp.13666"],"URL":"https:\/\/doi.org\/10.1002\/mp.13666","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,17]]},"assertion":[{"value":"2019-03-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-05-21","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-07-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}