{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T16:49:32Z","timestamp":1764175772497,"version":"build-2065373602"},"reference-count":32,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T00:00:00Z","timestamp":1740960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"NSERC Discovery","doi-asserted-by":"publisher","award":["RGPIN-202004441"],"award-info":[{"award-number":["RGPIN-202004441"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>X-ray computed tomography (CT) is vital for medical diagnostics, but frequent radiation exposure raises concerns, driving the adoption of low-dose CT (LDCT) to mitigate risks. However, LDCT often introduces noise, compromising diagnostic accuracy. This paper proposes a pure vision transformer (PViT) for LDCT denoising, enhanced with a gradient\u2013Laplacian attention module (GLAM) to improve edge preservation and fine structural detail reconstruction. The model\u2019s robustness was validated across five diverse datasets (piglet, head, abdomen, chest, thoracic), demonstrating consistent performance in preserving anatomical structures. Extensive ablation studies on attention configurations and loss functions further substantiated the contributions of each module. Quantitative evaluation using PSNR and SSIM, alongside radiologist assessment, confirmed significant noise suppression and sharper anatomical boundaries, particularly in regions with fine details such as organ interfaces and bone structures. Additionally, in benchmark comparisons against state-of-the-art LDCT models (RED-CNN, TED-Net, DSC-GAN, DRL-EMP) and traditional methods (BM3D), the model exhibited lower parameter and stable training performance. These findings highlight the model\u2019s robustness, efficiency, and clinical applicability, making it a promising solution for improving LDCT image quality while maintaining computational efficiency.<\/jats:p>","DOI":"10.3390\/a18030134","type":"journal-article","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T03:22:44Z","timestamp":1740972164000},"page":"134","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Edge Detection Attention Module in Pure Vision Transformer for Low-Dose X-Ray Computed Tomography Image Denoising"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0728-2904","authenticated-orcid":false,"given":"Luella","family":"Marcos","sequence":"first","affiliation":[{"name":"Department of Electrical, Computer and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON M5B 2K3, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8965-7305","authenticated-orcid":false,"given":"Paul","family":"Babyn","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging, University of Saskatchewan, Saskatoon, SK S7N 0W8, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7129-4825","authenticated-orcid":false,"given":"Javad","family":"Alirezaie","sequence":"additional","affiliation":[{"name":"Department of Electrical, Computer and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON M5B 2K3, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Shin, E., Lee, S., Kang, H., Kim, J., Kim, K., Youn, H., Jin, Y.W., Seo, S., and Youn, B. (2020). Organ-specific Effects of Low Dose Radiation Exposure: A Comprehensive Review. Front. Genet., 11.","DOI":"10.3389\/fgene.2020.566244"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhang, J., Gong, W., Ye, L., Wang, F., Shangguan, Z., and Cheng, Y. (2024). A Review of deep learning methods for denoising of medical low-dose CT images. Comput. Biol. Med., 171.","DOI":"10.1016\/j.compbiomed.2024.108112"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"57","DOI":"10.2299\/jsp.28.57","article-title":"Poisson\u2013Gaussian Noise Removal for Low-Dose CT Images by Integrating Noisy Image Patch and Impulse Response of Low-Pass Filter in CNN","volume":"28","author":"Tun","year":"2024","journal-title":"J. Signal Process."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, Y., Zhang, P., Lu, J., Ren, S., and Gui, Z. (2024). Adaptive Weighted Total Variation Expansion and Gaussian curvature Guided Low-dose CT Image Denoising Network. Biomed. Signal Process. Control, 94.","DOI":"10.1016\/j.bspc.2024.106329"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hu, Y., Ren, J., Yang, J., Bai, R., and Liu, J. (2021). Noise Reduction by Adaptive-sin Filtering for Retinal OCT Images. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-98832-w"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Lepcha, D.C., Dogra, A., Goyal, B., Goyal, V., Kukreja, V., and Bavirisetti, D.P. (2023). A Constructive Non-local Means Algorithm for Low-dose Computed Tomography Denoising with Morphological Residual Processing. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0291911"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1080\/13682199.2023.2176809","article-title":"Low-dose CT Image Denoising using Sparse 3D Transformation with Probabilistic Non-local Means for Clinical Applications","volume":"71","author":"Goyal","year":"2023","journal-title":"Imaging Sci. J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"50114","DOI":"10.1109\/ACCESS.2022.3172975","article-title":"Image Processing for Low-dose CT via Novel Anisotropic Fourth-order Diffusion Model","volume":"10","author":"Wang","year":"2022","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2831","DOI":"10.3934\/mbe.2023133","article-title":"A Region-adaptive Non-local Denoising Algorithm for Low-dose Computed Tomography Images","volume":"20","author":"Zhang","year":"2023","journal-title":"Math. Biosci. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"9105","DOI":"10.1007\/s00500-023-08419-y","article-title":"CT and MRI Multi-modal Medical Image Fusion using Weight-Optimized Anisotropic Diffusion Filtering","volume":"27","author":"Vasu","year":"2023","journal-title":"Soft Comput."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wang, Z., Ma, F., Ji, P., and Fu, C. (2024, January 5\u20138). Image Denoising Based on an Improved Wavelet Threshold and Total Variation Model. Proceedings of the International Conference on Intelligent Computing, Tianjin, China.","DOI":"10.1007\/978-981-97-5603-2_12"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1007\/s10278-022-00720-w","article-title":"Bilateral Weighted Relative Total Variation for Low-Dose CT Reconstruction","volume":"36","author":"He","year":"2023","journal-title":"J. Digit. Imaging"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Kong, Z., Huang, T., Ahn, E., Li, H., and Ding, L. (2024). WaveletDFDS-Net: A Dual Forward Denoising Stream Network for Low-Dose CT Noise Reduction. Electronics, 13.","DOI":"10.3390\/electronics13101906"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1808","DOI":"10.1007\/s10278-023-00805-0","article-title":"Multi-scale Feature Fusion Network for Low-dose CT Denoising","volume":"36","author":"Li","year":"2023","journal-title":"J. Digit. Imaging"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yang, X., Gong, G., Meng, X., Wang, X., and Zhang, Z. (2024, January 5\u20138). FMUnet: Frequency Feature Enhancement Multi-level U-Net for Low-Dose CT Denoising with a Real Collected LDCT Image Dataset. Proceedings of the International Conference on Intelligent Computing, Tianjin, China.","DOI":"10.1007\/978-981-97-5600-1_15"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3736","DOI":"10.1109\/TIP.2006.881969","article-title":"Image Denoising via Sparse and Redundant Representations Over Learned Dictionaries","volume":"15","author":"Elad","year":"2006","journal-title":"IEEE Trans. Image Process."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gao, Y., Lu, S., Shi, Y., Chang, S., Zhang, H., Hou, W., Li, L., and Liang, Z. (2023). A Joint-parameter Estimation and Bayesian Reconstruction Approach to Low-dose CT. Sensors, 23.","DOI":"10.3390\/s23031374"},{"key":"ref_18","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 4). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations (ICLR), Vienna, Austria."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2669","DOI":"10.1007\/s10278-024-01108-8","article-title":"Pure Vision Transformer (CT-ViT) with Noise2Neighbors Interpolation for Low-Dose CT Image Denoising","volume":"37","author":"Marcos","year":"2024","journal-title":"J. Imaging Inform. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1007\/s11760-023-02853-z","article-title":"A Multi-Attention Uformer for Low-Lose CT Image Denoising","volume":"18","author":"Yan","year":"2024","journal-title":"Signal Image Video Process."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.1007\/s13534-024-00419-7","article-title":"A Systematic Review of Deep Learning-based Denoising for Low-dose Computed Tomography from a Perceptual Quality Perspective","volume":"14","author":"Kim","year":"2024","journal-title":"Biomed. Eng. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"79025","DOI":"10.1109\/ACCESS.2024.3407774","article-title":"Enabling Predication of the Deep Learning Algorithms for Low-Dose CT Scan Image Denoising Models: A Systematic Literature Review","volume":"12","author":"Zubair","year":"2024","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"113","DOI":"10.4103\/2229-3485.100662","article-title":"What to use to express the variability of data: Standard deviation or standard error of mean?","volume":"3","author":"Barde","year":"2012","journal-title":"Perspect. Clin. Res."},{"key":"ref_24","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1007\/s10278-018-0056-0","article-title":"Sharpness-Aware Low Dose CT Denoising Using Conditional Generative Adversarial Network","volume":"31","author":"Yi","year":"2018","journal-title":"J. Digit. Imaging"},{"key":"ref_26","unstructured":"McCollough, C., Chen, B., Holmes, D., III Duan, X., Yu, Z., Yu, L., Leng, S., and Fletcher, J. (2021). Data from Low Dose CT Image and Projection Data [Data Set], The Cancer Imaging Archive."},{"key":"ref_27","first-page":"505","article-title":"Deep Learning for Low-Dose CT Denoising using Perceptual Loss and Edge Detection Layer","volume":"33","author":"Alirezaie","year":"2019","journal-title":"J. Digit. Imaging"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"8339","DOI":"10.1109\/TIP.2020.3014721","article-title":"Collaborative Filtering of Correlated Noise: Exact Transform-Domain Variance for Improved Shrinkage and Patch Matching","volume":"29","author":"Makinen","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wang, D., Wu, Z., and Yu, H. (2021). TED-Net: Convolution-Free T2T Vision Transformer-Based Encoder-Decoder Dilation Network for Low-Dose CT Denoising. Machine Learning in Medical Imaging, Springer.","DOI":"10.1007\/978-3-030-87589-3_43"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhao, F., Liu, M., Gao, Z., Jiang, X., Wang, R., and Zhang, L. (2023). Dual-scale similarity-guided cycle generative adversarial network for unsupervised low-dose CT denoising. Comput. Biol. Med., 161.","DOI":"10.1016\/j.compbiomed.2023.107029"},{"key":"ref_31","unstructured":"Batson, J., and Royer, L. (2019, January 9\u201315). Noise2self: Blind denoising by self-supervision. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Fadnavis, S., Chowdhury, A., Batson, J., Drineas, P., and Garyfallidis, E. (2024, January 16\u201322). Patch2Self2: Self-supervised Denoising on Coresets via Matrix Sketching. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02610"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/3\/134\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:46:04Z","timestamp":1760028364000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/3\/134"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,3]]},"references-count":32,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["a18030134"],"URL":"https:\/\/doi.org\/10.3390\/a18030134","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2025,3,3]]}}}