{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:19:09Z","timestamp":1783437549717,"version":"3.54.6"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,7,25]],"date-time":"2021-07-25T00:00:00Z","timestamp":1627171200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,25]],"date-time":"2021-07-25T00:00:00Z","timestamp":1627171200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis. Comput. Ind. Biomed. Art"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>To minimize radiation risk, dose reduction is important in the diagnostic and therapeutic applications of computed tomography (CT). However, image noise degrades image quality owing to the reduced X-ray dose and a possible unacceptably reduced diagnostic performance. Deep learning approaches with convolutional neural networks (CNNs) have been proposed for natural image denoising; however, these approaches might introduce image blurring or loss of original gradients. The aim of this study was to compare the dose-dependent properties of a CNN-based denoising method for low-dose CT with those of other noise-reduction methods on unique CT noise-simulation images. To simulate a low-dose CT image, a Poisson noise distribution was introduced to normal-dose images while convoluting the CT unit-specific modulation transfer function. An abdominal CT of 100 images obtained from a public database was adopted, and simulated dose-reduction images were created from the original dose at equal 10-step dose-reduction intervals with a final dose of 1\/100. These images were denoised using the denoising network structure of CNN (DnCNN) as the general CNN model and for transfer learning. To evaluate the image quality, image similarities determined by the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) were calculated for the denoised images. Significantly better denoising, in terms of SSIM and PSNR, was achieved by the DnCNN than by other image denoising methods, especially at the ultra-low-dose levels used to generate the 10% and 5% dose-equivalent images. Moreover, the developed CNN model can eliminate noise and maintain image sharpness at these dose levels and improve SSIM by approximately 10% from that of the original method. In contrast, under small dose-reduction conditions, this model also led to excessive smoothing of the images. In quantitative evaluations, the CNN denoising method improved the low-dose CT and prevented over-smoothing by tailoring the CNN model.<\/jats:p>","DOI":"10.1186\/s42492-021-00087-9","type":"journal-article","created":{"date-parts":[[2021,7,25]],"date-time":"2021-07-25T13:02:32Z","timestamp":1627218152000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Quantitative evaluation of deep convolutional neural network-based image denoising for low-dose computed tomography"],"prefix":"10.1186","volume":"4","author":[{"given":"Keisuke","family":"Usui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koichi","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masami","family":"Goto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasuaki","family":"Sakano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinsuke","family":"Kyougoku","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroyuki","family":"Daida","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,25]]},"reference":[{"issue":"22","key":"87_CR1","doi-asserted-by":"publisher","first-page":"2277","DOI":"10.1056\/NEJMra072149","volume":"357","author":"DJ Brenner","year":"2007","unstructured":"Brenner DJ, Hall EJ (2007) Computed tomography-an increasing source of radiation exposure. New Engl J Med 357(22):2277\u20132284. https:\/\/doi.org\/10.1056\/NEJMra072149","journal-title":"New Engl J Med"},{"issue":"5","key":"87_CR2","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1056\/NEJMoa1102873","volume":"365","author":"DR Aberle","year":"2011","unstructured":"National Lung Screening Trial Research Team, Aberle DR, Adams AM, Berg CD, Black WC, Clapp JD et al (2011) Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 365(5):395\u2013409. https:\/\/doi.org\/10.1056\/NEJMoa1102873","journal-title":"N Engl J Med"},{"issue":"1","key":"87_CR3","doi-asserted-by":"publisher","first-page":"78","DOI":"10.2214\/AJR.09.3420","volume":"195","author":"AR Kambadakone","year":"2010","unstructured":"Kambadakone AR, Prakash P, Hahn PF, Sahani DV (2010) Low-dose CT examinations in Crohn\u2019s disease: impact on image quality, diagnostic performance, and radiation dose. AJR Am J Roentgenol 195(1):78\u201388. https:\/\/doi.org\/10.2214\/AJR.09.3420","journal-title":"AJR Am J Roentgenol"},{"issue":"10","key":"87_CR4","doi-asserted-by":"publisher","first-page":"1272","DOI":"10.1109\/TMI.2006.882141","volume":"25","author":"J Wang","year":"2006","unstructured":"Wang J, Li T, Lu H, Liang Z (2006) Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose X-ray computed tomography. IEEE Trans Med Imaging 25(10):1272\u20131283. https:\/\/doi.org\/10.1109\/TMI.2006.882141","journal-title":"IEEE Trans Med Imaging"},{"issue":"6","key":"87_CR5","doi-asserted-by":"publisher","first-page":"1266","DOI":"10.2214\/AJR.12.9382","volume":"199","author":"PJ Pickhardt","year":"2012","unstructured":"Pickhardt PJ, Lubner MG, Kim DH, Tang J, Ruma JA, Rio AM et al (2012) Abdominal CT with model-based iterative reconstruction (MBIR): initial results of a prospective trial comparing ultralow-dose with standard-dose imaging. AJR Am J Roentgenol 199(6):1266\u20131274. https:\/\/doi.org\/10.2214\/AJR.12.9382","journal-title":"AJR Am J Roentgenol"},{"issue":"18","key":"87_CR6","doi-asserted-by":"publisher","first-page":"5949","DOI":"10.1088\/0031-9155\/56\/18\/011","volume":"56","author":"Z Tian","year":"2011","unstructured":"Tian Z, Jia X, Yuan K, Pan T, Jiang SB (2011) Low dose CT reconstruction via edge-preserving total variation regularization. Phys Med Biol 56(18):5949\u20135967. https:\/\/doi.org\/10.1088\/0031-9155\/56\/18\/011","journal-title":"Phys Med Biol"},{"issue":"9","key":"87_CR7","doi-asserted-by":"publisher","first-page":"3941","DOI":"10.1002\/mp.13666","volume":"46","author":"T Zhao","year":"2019","unstructured":"Zhao T, McNitt-Gray M, Ruan D (2019) A convolutional neural network for ultra-low-dose CT denoising and emphysema screening. Med Phys 46(9):3941\u20133950. https:\/\/doi.org\/10.1002\/mp.13666","journal-title":"Med Phys"},{"issue":"9","key":"87_CR8","doi-asserted-by":"publisher","first-page":"3906","DOI":"10.1002\/mp.13713","volume":"46","author":"B Kim","year":"2019","unstructured":"Kim B, Han M, Shim H, Baek J (2019) A performance comparison of convolutional neural network-based image denoising methods: the effect of loss functions on low-dose CT images. Med Phys 46(9):3906\u20133923. https:\/\/doi.org\/10.1002\/mp.13713","journal-title":"Med Phys"},{"issue":"12","key":"87_CR9","doi-asserted-by":"publisher","first-page":"2536","DOI":"10.1109\/TMI.2017.2708987","volume":"36","author":"JM Wolterink","year":"2017","unstructured":"Wolterink JM, Leiner T, Viergever MA, Isgum I (2017) Generative adversarial networks for noise reduction in low-dose CT. IEEE Trans Med Imaging 36(12):2536\u20132545. https:\/\/doi.org\/10.1109\/TMI.2017.2708987","journal-title":"IEEE Trans Med Imaging"},{"issue":"7","key":"87_CR10","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","volume":"26","author":"K Zhang","year":"2017","unstructured":"Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process 26(7):3142\u20133155. https:\/\/doi.org\/10.1109\/TIP.2017.2662206","journal-title":"IEEE Trans Image Process"},{"issue":"8","key":"87_CR11","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/s10916-019-1371-9","volume":"43","author":"R Rajeev","year":"2019","unstructured":"Rajeev R, Samath JA, Karthikeyan NK (2019) An intelligent recurrent neural network with long short-term memory (LSTM) BASED batch normalization for medical image denoising. J Med Syst 43(8):234. https:\/\/doi.org\/10.1007\/s10916-019-1371-9","journal-title":"J Med Syst"},{"key":"87_CR12","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.neunet.2020.07.025","volume":"131","author":"C Tian","year":"2020","unstructured":"Tian C, Fei L, Zheng W, Xu Y, Zuo W, Lin CW (2020) Deep learning on image denoising: an overview. Neural Netw 131:251\u2013275. https:\/\/doi.org\/10.1016\/j.neunet.2020.07.025","journal-title":"Neural Netw"},{"issue":"2","key":"87_CR13","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1364\/BOE.8.000679","volume":"8","author":"H Chen","year":"2017","unstructured":"Chen H, Zhang Y, Zhang W, Liao P, Li K, Zhou J et al (2017) Low-dose CT via convolutional neural network. Biomed Opt Express 8(2):679\u2013694. https:\/\/doi.org\/10.1364\/BOE.8.000679","journal-title":"Biomed Opt Express"},{"issue":"12","key":"87_CR14","doi-asserted-by":"publisher","first-page":"2524","DOI":"10.1109\/TMI.2017.2715284","volume":"36","author":"H Chen","year":"2017","unstructured":"Chen H, Zhang Y, Kalra MK, Lin F, Chen Y, Liao P et al (2017) Low-dose CT with a residual encoder-decoder convolutional neural network (RED-CNN). IEEE Trans Med Imaging 36(12):2524\u20132535. https:\/\/doi.org\/10.1109\/TMI.2017.2715284","journal-title":"IEEE Trans Med Imaging"},{"issue":"6","key":"87_CR15","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","volume":"26","author":"K Clark","year":"2013","unstructured":"Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P et al (2013) The Cancer imaging archive (TCIA): maintaining and operating a public information repository. J Digit Imaging 26(6):1045\u20131057. https:\/\/doi.org\/10.1007\/s10278-013-9622-7","journal-title":"J Digit Imaging"},{"issue":"1","key":"87_CR16","doi-asserted-by":"publisher","first-page":"011901","DOI":"10.1118\/1.4830431","volume":"41","author":"CW Kim","year":"2014","unstructured":"Kim CW, Kim JH (2014) Realistic simulation of reduced-dose CT with noise modeling and sinogram synthesis using DICOM CT images. Med Phys 41(1):011901. https:\/\/doi.org\/10.1118\/1.4830431","journal-title":"Med Phys"},{"issue":"4","key":"87_CR17","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600\u2013612. https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans Image Process"},{"issue":"8","key":"87_CR18","doi-asserted-by":"publisher","first-page":"e0235672","DOI":"10.1371\/journal.pone.0235672","volume":"15","author":"S Tang","year":"2020","unstructured":"Tang S, Yang M, Bai J (2020) Detection of pulmonary nodules based on a multiscale feature 3D U-net convolutional neural network of transfer learning. PLoS One 15(8):e0235672. https:\/\/doi.org\/10.1371\/journal.pone.0235672","journal-title":"PLoS One"},{"key":"87_CR19","doi-asserted-by":"publisher","first-page":"104964","DOI":"10.1016\/j.cmpb.2019.06.023","volume":"187","author":"G Liang","year":"2019","unstructured":"Liang G, Zheng L (2019) A transfer learning method with deep residual network for pediatric pneumonia diagnosis. Comput Methods Prog Biomed 187:104964. https:\/\/doi.org\/10.1016\/j.cmpb.2019.06.023","journal-title":"Comput Methods Prog Biomed"},{"key":"87_CR20","doi-asserted-by":"publisher","first-page":"804","DOI":"10.3389\/fnins.2018.00804","volume":"12","author":"Y Yang","year":"2018","unstructured":"Yang Y, Yan LF, Zhang X, Han Y, Nan HY, Hu YC et al (2018) Glioma grading on conventional MR images: a deep learning study with transfer learning. Front Neurosci 12:804. https:\/\/doi.org\/10.3389\/fnins.2018.00804","journal-title":"Front Neurosci"},{"issue":"9","key":"87_CR21","doi-asserted-by":"publisher","first-page":"e0222406","DOI":"10.1371\/journal.pone.0222406","volume":"14","author":"T Gomi","year":"2019","unstructured":"Gomi T, Sakai R, Hara H, Watanabe Y, Mizukami S (2019) Development of a denoising convolutional neural network-based algorithm for metal artifact reduction in digital tomosynthesis for arthroplasty: a phantom study. PLoS One 14(9):e0222406. https:\/\/doi.org\/10.1371\/journal.pone.0222406","journal-title":"PLoS One"},{"issue":"4","key":"87_CR22","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1016\/j.nic.2020.07.002","volume":"30","author":"DS Chow","year":"2020","unstructured":"Chow DS, Khatri D, Chang PD, Zlochower A, Boockvar JA, Filippi CG (2020) Updates on deep learning and glioma: use of convolutional neural networks to image glioma heterogeneity. Neuroimaging Clin N Am 30(4):493\u2013503. https:\/\/doi.org\/10.1016\/j.nic.2020.07.002","journal-title":"Neuroimaging Clin N Am"}],"container-title":["Visual Computing for Industry, Biomedicine, and Art"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s42492-021-00087-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s42492-021-00087-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s42492-021-00087-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,25]],"date-time":"2021-07-25T13:02:34Z","timestamp":1627218154000},"score":1,"resource":{"primary":{"URL":"https:\/\/vciba.springeropen.com\/articles\/10.1186\/s42492-021-00087-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,25]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["87"],"URL":"https:\/\/doi.org\/10.1186\/s42492-021-00087-9","relation":{},"ISSN":["2524-4442"],"issn-type":[{"value":"2524-4442","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,25]]},"assertion":[{"value":"31 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"21"}}