{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T11:21:58Z","timestamp":1761218518293,"version":"build-2065373602"},"reference-count":41,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T00:00:00Z","timestamp":1663286400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Computed Tomography (CT) is commonly used for cancer screening as it utilizes low radiation for the scan. One problem with low-dose scans is the noise artifacts associated with low photon count that can lead to a reduced success rate of cancer detection during radiologist assessment. The noise had to be removed to restore detail clarity. We propose a noise removal method using a new model Convolutional Neural Network (CNN). Even though the network training time is long, the result is better than other CNN models in quality score and visual observation. The proposed CNN model uses a stacked modified U-Net with a specific number of feature maps per layer to improve the image quality, observable on an average PSNR quality score improvement out of 174 images. The next best model has 0.54 points lower in the average score. The score difference is less than 1 point, but the image result is closer to the full-dose scan image. We used separate testing data to clarify that the model can handle different noise densities. Besides comparing the CNN configuration, we discuss the denoising quality of CNN compared to classical denoising in which the noise characteristics affect quality.<\/jats:p>","DOI":"10.3390\/s22187031","type":"journal-article","created":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T04:49:22Z","timestamp":1663562962000},"page":"7031","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Image Recovery from Synthetic Noise Artifacts in CT Scans Using Modified U-Net"],"prefix":"10.3390","volume":"22","author":[{"given":"Rudy","family":"Gunawan","sequence":"first","affiliation":[{"name":"School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Hawthorn, VIC 3122, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1741-4205","authenticated-orcid":false,"given":"Yvonne","family":"Tran","sequence":"additional","affiliation":[{"name":"Macquarie University Hearing (MU Hearing), Centre for Healthcare Resilience and Implementation Science, Macquarie University, Macquarie Park, NSW 2109, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-9223","authenticated-orcid":false,"given":"Jinchuan","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Hawthorn, VIC 3122, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3373-8178","authenticated-orcid":false,"given":"Hung","family":"Nguyen","sequence":"additional","affiliation":[{"name":"School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Hawthorn, VIC 3122, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1922-7024","authenticated-orcid":false,"given":"Rifai","family":"Chai","sequence":"additional","affiliation":[{"name":"School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Hawthorn, VIC 3122, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1056\/NEJMoa1911793","article-title":"Reduced Lung-Cancer Mortality with Volume CT Screening in a Randomized Trial","volume":"382","author":"Scholten","year":"2020","journal-title":"N. Engl. J. Med."},{"key":"ref_3","first-page":"153","article-title":"Dose Reduction and Optimization in Computed Tomography of the Chest","volume":"Volume 10","author":"Genevois","year":"2007","journal-title":"Radiation Dose from Adult and Pediatric Multidetector Computed Tomography"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1148\/radiology.175.3.2343122","article-title":"Low-dose CT of the lungs: Preliminary observations","volume":"175","author":"Naidich","year":"1990","journal-title":"Radiology"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1118\/1.3031114","article-title":"Validation of CT dose-reduction simulation","volume":"36","author":"Massoumzadeh","year":"2008","journal-title":"Med. Phys."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1002","DOI":"10.1200\/JCO.2012.43.3110","article-title":"Computed Tomography Screening for Lung Cancer: Has It Finally Arrived? Implications of the National Lung Screening Trial","volume":"31","author":"Aberle","year":"2013","journal-title":"J. Clin. Oncol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"W626","DOI":"10.2214\/AJR.12.10234","article-title":"Electronic noise in CT detectors: Impact on image noise and artifacts","volume":"201","author":"Duan","year":"2013","journal-title":"Am. J. Roentgenol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1441","DOI":"10.1109\/TIP.2017.2651370","article-title":"Data-Driven Affine Deformation Estimation and Correction in Cone Beam Computed Tomography","volume":"26","author":"Nieuwenhove","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"461","DOI":"10.2214\/ajr.179.2.1790461","article-title":"Standard-Dose and 50%\u2014Reduced-Dose Chest CT: Comparing the Effect on Image Quality","volume":"179","author":"Prasad","year":"2002","journal-title":"Am. J. Roentgenol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.ejro.2016.03.002","article-title":"Standard-dose vs. low-dose CT protocols in the evaluation of localized lung lesions: Capability for lesion characterization\u2014iLEAD study","volume":"3","author":"Kubo","year":"2016","journal-title":"Eur. J. Radiol. Open"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, L.L., Gou, S.P., Yao, Y., Bai, J., Jiao, L., and Sheng, K. (2016, January 22\u201325). Denoising of Low Dose CT Image with Context-Based BM3D. Proceedings of the IEEE Region 10 Conference (TENCON), Singapore.","DOI":"10.1109\/TENCON.2016.7848089"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2536","DOI":"10.1109\/TMI.2017.2708987","article-title":"Generative Adversarial Networks for Noise Reduction in Low-Dose CT","volume":"36","author":"Wolterink","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2510","DOI":"10.1109\/TMI.2017.2757035","article-title":"Low-Dose Lung CT Image Restoration Using Adaptive Prior Features From Full-Dose Training Database","volume":"36","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_14","unstructured":"Yu, F., Chen, Y., and Luo, L. (2013, January 25\u201328). CT image denoising based on sparse representation using global dictionary. Proceedings of the ICME International Conference on Complex Medical Engineering, Beijing, China."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Alsamadony, K.L., Yildirim, E.U., Glatz, G., Waheed, U.B., and Hanafy, S.M. (2021). Deep Learning Driven Noise Reduction for Reduced Flux Computed Tomography. Sensors, 21.","DOI":"10.3390\/s21051921"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Nasrin, S., Alom, M.Z., Burada, R., Taha, T.M., and Asari, V.K. (2019, January 15\u201319). Medical Image Denoising with Recurrent Residual U-Net (R2U-Net) base Auto-Encoder. Proceedings of the IEEE National Aerospace and Electronics Conference (NAECON), Dayton, OH, USA.","DOI":"10.1109\/NAECON46414.2019.9057834"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Huang, S.C., Hoang, Q.V., Le, T.H., Peng, Y.T., Huang, C.C., Zhang, C., Fung, B.C.M., Cheng, K.H., and Huang, S.W. (2021). An Advanced Noise Reduction and Edge Enhancement Algorithm. Sensors, 21.","DOI":"10.3390\/s21165391"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"24698","DOI":"10.1109\/ACCESS.2017.2766438","article-title":"Improving Low-Dose CT Image Using Residual Convolutional Network","volume":"5","author":"Yang","year":"2017","journal-title":"IEEE Access"},{"key":"ref_19","unstructured":"McCollough, C.H., Chen, B., Holmes, D.R.I., Duan, X., Yu, Z., Yu, L., Leng, S., and Fletcher, J.G. (2020). Low Dose CT Image and Projection Data (LDCT-and-Projection-data) (Version 4) [Data set]. The Cancer Imaging Archive, TCIA."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"8823861","DOI":"10.1155\/2020\/8823861","article-title":"A Multifeature Extraction Method Using Deep Residual Network for MR Image Denoising","volume":"2020","author":"Yao","year":"2020","journal-title":"Comput. Math. Methods Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/s42492-019-0016-7","article-title":"Brief review of image denoising techniques","volume":"2","author":"Fan","year":"2019","journal-title":"Vis. Comput. Ind. Biomed. Art"},{"key":"ref_22","unstructured":"Buades, A., Coll, B., and Morel, J.M. (2005, January 20\u201326). A non-local algorithm for image denoising. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), San Diego, CA, USA."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1109\/TIP.2007.901238","article-title":"Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering","volume":"16","author":"Dabov","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"31742","DOI":"10.1109\/ACCESS.2021.3061062","article-title":"A Residual Dense U-Net Neural Network for Image Denoising","volume":"9","author":"Dalmau","year":"2021","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1515\/cdbme-2018-0072","article-title":"Residual U-Net Convolutional Neural Network Architecture for Low-Dose CT Denoising","volume":"4","author":"Heinrich","year":"2018","journal-title":"Curr. Dir. Biomed. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., and Han, B. (2015, January 7\u201313). Learning Deconvolution Network for Semantic Segmentation. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref_29","unstructured":"Mao, X.J., Shen, C., and Yang, T.B. (2016). Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2524","DOI":"10.1109\/TMI.2017.2715284","article-title":"Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network","volume":"36","author":"Chen","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Ehrlich, M., Shah, S., Davis, L., and Chellappa, R. (2018, January 18\u201322). Stacked U-Nets for Ground Material Segmentation in Remote Sensing Imagery. Proceedings of the Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake CIty, UT, USA.","DOI":"10.1109\/CVPRW.2018.00047"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Sevastopolsky, A., Drapak, S., Kiselev, K., Snyder, B., Keenan, J., and Georgievskaya, A. (2019, January 16\u201321). Stack-U-Net: Refinement network for improved optic disc and cup image segmentation. Proceedings of the Image Processing, San Diego, CA, USA.","DOI":"10.1117\/12.2511572"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"101920","DOI":"10.1016\/j.compmedimag.2021.101920","article-title":"Computed tomography image reconstruction using stacked U-Net","volume":"90","author":"Mizusawa","year":"2021","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ayachi, R., Afif, M., Said, Y., and Atri, M. (2018, January 18\u201320). Strided Convolution Instead of Max Pooling for Memory Efficiency of Convolutional Neural Networks. Proceedings of the SETIT 2018, Maghreb, Tunisia.","DOI":"10.1007\/978-3-030-21005-2_23"},{"key":"ref_35","unstructured":"Kingma, D.P., and Ba, J.L. (2015, January 7\u20139). ADAM: A Method for Stochastic Optimization. Proceedings of the ICLR 2015, San Diego, CA, USA."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"4608","DOI":"10.1109\/TIP.2018.2839891","article-title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","volume":"27","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a \u201cCompletely Blind\u201d Image Quality Analyzer","volume":"20","author":"Mittal","year":"2013","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"140030","DOI":"10.1109\/ACCESS.2019.2943319","article-title":"A Comprehensive Performance Evaluation of Image Quality Assessment Algorithms","volume":"7","author":"Athar","year":"2019","journal-title":"IEEE Access"},{"key":"ref_40","unstructured":"Clark, K. (2013). Data from the National Lung Screening Trial (NLST) [Data set]. The Cancer Imaging Archive, TCIA."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","article-title":"The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository","volume":"26","author":"Clark","year":"2013","journal-title":"J. Digit. Imaging"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/18\/7031\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:33:16Z","timestamp":1760142796000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/18\/7031"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,16]]},"references-count":41,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["s22187031"],"URL":"https:\/\/doi.org\/10.3390\/s22187031","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,9,16]]}}}