{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T01:56:51Z","timestamp":1793325411730,"version":"4.5.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T00:00:00Z","timestamp":1775433600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"vor","delay-in-days":52,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In biomedical imaging, noise is a fundamental problem negatively impacting diagnostic quality, and effective noise reduction methods are critical for preserving structural details. This study proposes a hybrid noise reduction framework integrated with a CNN-based fusion network, combining a convolutional autoencoder, a specially designed hybrid wavelet filtering approach, and multi-level adaptive wavelet transformation. The autoencoder component learns clean image matches from noisy inputs, while the wavelet-based arm ensures the preservation of high-frequency structural and textural information through multi-level decomposition. The CNN-based fusion module adaptively combines these complementary representations to produce the final enhanced image. Experimental results demonstrate that the proposed method provides consistent superiority across different noise types and datasets. In the fetal ultrasound dataset, the highest performance was achieved at all levels under Gaussian and speckle noise; for speckle noise low-level PSNR values of 48.12 dB and SSIM of 0.99 were obtained. For brain tumor MR dataset, the method was effective not only under Gaussian and speckle noise but also under Rician noise; the PSNR value was obtained as 22.90 dB at the low level, 27.11 dB at the medium level, and 22.17 dB at the high level, with corresponding SSIM values of 0.90, 0.59, and 0.47. Furthermore, in non-referenced evaluations performed on the wrist trauma clinical X-ray dataset, mean NIQE = 3.12 and SSEQ = 0.26 values were obtained. These results confirm that the proposed approach offers balanced and generalizable denoising performance without excessive smoothing or the creation of artificial artifacts on real clinical images. These findings demonstrate that combining wavelet-based detail preservation with deep learning-based reconstruction delivers robust and reliable noise reduction performance across diverse biomedical imaging modalities and noise types.<\/jats:p>","DOI":"10.1038\/s41598-026-47179-1","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T16:14:34Z","timestamp":1775492074000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Wavelet-enhanced autoencoder based image denoising with CNN fusion"],"prefix":"10.1038","volume":"16","author":[{"given":"Iclal","family":"Cetin Tas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,6]]},"reference":[{"issue":"7","key":"47179_CR1","doi-asserted-by":"publisher","first-page":"5777","DOI":"10.1109\/TII.2025.3558347","volume":"21","author":"Y Wang","year":"2025","unstructured":"Wang, Y., Tao, K., Wang, Z. & Sun, J. Memristor-based GFMM neural network circuit of biology with multiobjective decision and its application in industrial autonomous firefighting. IEEE Trans. Indus. Inform. 21(7), 5777\u20135786. https:\/\/doi.org\/10.1109\/TII.2025.3558347 (2025).","journal-title":"IEEE Trans. Indus. Inform."},{"issue":"10","key":"47179_CR2","doi-asserted-by":"publisher","first-page":"8154","DOI":"10.1109\/TII.2025.3585200","volume":"21","author":"Y Wang","year":"2025","unstructured":"Wang, Y., Tao, K., Wang, Y. & Sun, J. Memristor-based reward and punishment neural network circuit with approach and inhibition and its application in industrial vehicle autonomous navigation. IEEE Trans. Indus. Inform. 21(10), 8154\u20138164. https:\/\/doi.org\/10.1109\/TII.2025.3585200 (2025).","journal-title":"IEEE Trans. Indus. Inform."},{"issue":"6","key":"47179_CR3","doi-asserted-by":"publisher","first-page":"11466","DOI":"10.1109\/TNNLS.2025.3539842","volume":"36","author":"J Sun","year":"2025","unstructured":"Sun, J., Shen, Y., Wang, Y. & Wang, Y. A memristor-based neural network circuit with retrospective revaluation effect and application in intelligent household robots. IEEE Trans. Neural Netw. Learn. Syst. 36(6), 11466\u201311478. https:\/\/doi.org\/10.1109\/TNNLS.2025.3539842 (2025).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"47179_CR4","doi-asserted-by":"publisher","unstructured":"Sadia, R.T., Chen, J. & Zhang, J. CT image denoising methods for image quality improvement and radiation dose reduction. J. Appl. Clin. Med. Phys. https:\/\/doi.org\/10.1002\/acm2.14270 (2024).","DOI":"10.1002\/acm2.14270"},{"issue":"1218","key":"47179_CR5","doi-asserted-by":"publisher","first-page":"37591","DOI":"10.1007\/s11042-022-12791-y","volume":"81","author":"KASH Kulathilake","year":"2022","unstructured":"Kulathilake, K. A. S. H., Abdullah, N. A., Sabri, A. Q. M., Bandara, A. M. R. R. & Lai, K. W. A review on self-adaptation approaches and techniques in medical image denoising algorithms. Multimed. Tools Appl. 81(1218), 37591\u201337626. https:\/\/doi.org\/10.1007\/s11042-022-12791-y (2022).","journal-title":"Multimed. Tools Appl."},{"key":"47179_CR6","doi-asserted-by":"publisher","unstructured":"El-Shafai, W., Abd El-Nabi, S., Ali, A.M., El-Rabaie, E.S.M. & Abd El-Samie, F.E. Traditional and deep-learning-based denoising methods for medical images. Multimed. Tools Appl. 83, 52061\u201352088. https:\/\/doi.org\/10.1007\/s11042-023-16406-9 (2024).","DOI":"10.1007\/s11042-023-16406-9"},{"key":"47179_CR7","doi-asserted-by":"publisher","unstructured":"Shiferaw, T.\u00a0G. & \u00a0Yao, L. Autoencoder-based unsupervised surface defect detection using two-stage training. J. Imaging 10(5), 111. https:\/\/doi.org\/10.3390\/jimaging10050111, Available: https:\/\/www.mdpi.com\/2313-433X\/10\/5\/111 (2024).","DOI":"10.3390\/jimaging10050111"},{"key":"47179_CR8","doi-asserted-by":"crossref","unstructured":"Bhute, S., \u00a0Mandal, S. & \u00a0Guha, D. Speckle Noise Reduction in Ultrasound Images Using Denoising Auto-Encoder with Skip Connection. arXiv preprint arXiv:2403.02750 (2024).","DOI":"10.1109\/SAUS61785.2024.10563715"},{"key":"47179_CR9","doi-asserted-by":"publisher","unstructured":"Gu, F., Discetti, S., Liu, Y., Cao, Z. & Peng, D. Denoising image-based experimental data without clean targets based on deep autoencoders. Comput. Methods Programs Biomed. 244, 107521. https:\/\/doi.org\/10.1016\/j.cmpb.2024.107521. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S247263032400027X (2024).","DOI":"10.1016\/j.cmpb.2024.107521"},{"key":"47179_CR10","doi-asserted-by":"publisher","unstructured":"Byeon, H. et al. Deep neural network model for enhancing disease prediction using auto encoder based broad learning. Comput. Biol. Med. 160, 107204. https:\/\/doi.org\/10.1016\/j.compbiomed.2024.107204. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0894177724000645 (2024).","DOI":"10.1016\/j.compbiomed.2024.107204"},{"key":"47179_CR11","unstructured":"Ankit. Fetal Head Ultrasound Dataset for Image Segmentation. https:\/\/www.kaggle.com\/datasets\/ankit8467\/fetal-head-ultrasound-dataset-for-image-segmentation. Accessed 14 Aug 2025 (Kaggle, 2020)."},{"key":"47179_CR12","doi-asserted-by":"publisher","unstructured":"Cheng, J. Brain tumor dataset. Figshare. https:\/\/doi.org\/10.6084\/m9.figshare.1512427.v5. Accessed 02 Jun 2025 (2017).","DOI":"10.6084\/m9.figshare.1512427.v5"},{"key":"47179_CR13","doi-asserted-by":"publisher","unstructured":"Suresh, S.\u00a0G.\u00a0R. & \u00a0Sukanesh, R. Speckle noise reduction in ultrasound images by wavelet thresholding based on weighted variance. Int. J. Comput. Theory Eng. 1(2), 7\u201312. https:\/\/doi.org\/10.7763\/IJCTE.2009.V1.2 (2009).","DOI":"10.7763\/IJCTE.2009.V1.2"},{"key":"47179_CR14","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/3-540-44680-X_6","volume":"84","author":"J Jensen","year":"2002","unstructured":"Jensen, J. Ultrasound imaging and its modeling. Imaging Complex Med. Acoust. Seismic Waves 84, 135\u2013166 (2002).","journal-title":"Imaging Complex Med. Acoust. Seismic Waves"},{"key":"47179_CR15","doi-asserted-by":"publisher","unstructured":"Thakur, A. & \u00a0Anand, R.\u00a0S. Speckle reduction in ultrasound medical images using adaptive filter based on second order statistics. J. Med. Eng. Technol. 31(4), \u00a0263\u2013279. https:\/\/doi.org\/10.1080\/03091900600718402 (2007).","DOI":"10.1080\/03091900600718402"},{"key":"47179_CR16","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.media.2018.05.006","volume":"48","author":"DCT Nguyen","year":"2018","unstructured":"Nguyen, D. C. T., Benameur, S., Mignotte, M. & Lavoie, F. Superpixel and multi-atlas based fusion entropic model for the segmentation of X-ray images. Med. Image Anal. 48, 58\u201374. https:\/\/doi.org\/10.1016\/j.media.2018.05.006 (2018).","journal-title":"Med. Image Anal."},{"issue":"2","key":"47179_CR17","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s11263-007-0052-1","volume":"76","author":"A Buades","year":"2008","unstructured":"Buades, A., Coll, B. & Morel, J. M. Nonlocal image and movie denoising. Int. J. Comput. Vis. 76(2), 123\u2013139. https:\/\/doi.org\/10.1007\/s11263-007-0052-1 (2008).","journal-title":"Int. J. Comput. Vis."},{"key":"47179_CR18","first-page":"136","volume":"13","author":"K Kun","year":"2020","unstructured":"Kun, K., Zhao, H. & Zhang, Q. Deep learning-based ultrasound image denoising: A review. IEEE Rev. Biomed. Eng. 13, 136\u2013150 (2020).","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"47179_CR19","doi-asserted-by":"publisher","unstructured":"Rogg, J. GRAZPEDWRI-DX: A pediatric wrist trauma X-ray dataset. Sci. Data 9, 312. https:\/\/doi.org\/10.1038\/s41597-022-01328-z (2022).","DOI":"10.1038\/s41597-022-01328-z"},{"key":"47179_CR20","doi-asserted-by":"publisher","first-page":"104063","DOI":"10.1016\/j.chemolab.2020.104063","volume":"203","author":"C Zhang","year":"2020","unstructured":"Zhang, C. et al. Noise reduction in the spectral domain of hyperspectral images using denoising autoencoder methods. Chemom. Intell. Lab. Syst. 203, 104063. https:\/\/doi.org\/10.1016\/j.chemolab.2020.104063 (2020).","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"47179_CR21","doi-asserted-by":"publisher","unstructured":"Cheng, R. et al. Histopathological image recognition with discriminant-oriented extreme learning machine autoencoder based deep feature dimension reduction. Signal Image Video Process. Accessed 28 Mar 2025. https:\/\/doi.org\/10.1007\/s11760-025-03954-7 (2025).","DOI":"10.1007\/s11760-025-03954-7"},{"key":"47179_CR22","doi-asserted-by":"publisher","first-page":"102842","DOI":"10.1016\/j.bspc.2021.102842","volume":"69","author":"AS Ahmed","year":"2021","unstructured":"Ahmed, A. S., El-Behaidy, W. H. & Youssif, A. A. A. Medical image denoising system based on stacked convolutional autoencoder for enhancing 2-dimensional gel electrophoresis noise reduction. Biomed. Signal Process. Control 69, 102842. https:\/\/doi.org\/10.1016\/j.bspc.2021.102842 (2021).","journal-title":"Biomed. Signal Process. Control"},{"key":"47179_CR23","doi-asserted-by":"publisher","unstructured":"Yasenko, L. , Klyatchenko, Y. & Tarasenko-Klyatchenko, O. Image noise reduction by denoising autoencoder. In Proceedings of the 2020 IEEE 11th International Conference on Dependable Systems, Services and Technologies (DESSERT), Kyiv, Ukraine. 351\u2013355. https:\/\/doi.org\/10.1109\/DESSERT50317.2020.9125027 (2020).","DOI":"10.1109\/DESSERT50317.2020.9125027"},{"key":"47179_CR24","doi-asserted-by":"publisher","unstructured":"Duan, Z., Luo, X. & Zhang, T. Combining transformers with CNN for multi-focus image fusion. Expert Syst. Appl. 235, 121156. https:\/\/doi.org\/10.1016\/j.eswa.2023.121156 (2024).","DOI":"10.1016\/j.eswa.2023.121156"},{"key":"47179_CR25","doi-asserted-by":"crossref","unstructured":"Tian, C. et al. Multi-Stage Image Denoising with the Wavelet Transform (2022).","DOI":"10.1016\/j.patcog.2022.109050"},{"key":"47179_CR26","doi-asserted-by":"publisher","first-page":"58869","DOI":"10.1109\/ACCESS.2022.3179517","volume":"10","author":"T Guo","year":"2022","unstructured":"Guo, T. et al. A review of wavelet analysis and its applications: challenges and opportunities. IEEE Access 10, 58869\u201358903. https:\/\/doi.org\/10.1109\/ACCESS.2022.3179517 (2022).","journal-title":"IEEE Access"},{"key":"47179_CR27","doi-asserted-by":"publisher","first-page":"111420","DOI":"10.1016\/j.measurement.2022.111420","volume":"198","author":"T Qi","year":"2022","unstructured":"Qi, T. et al. A method for reducing transient electromagnetic noise: Combination of variational mode decomposition and wavelet denoising algorithm. Measurement 198, 111420. https:\/\/doi.org\/10.1016\/j.measurement.2022.111420 (2022).","journal-title":"Measurement"},{"key":"47179_CR28","doi-asserted-by":"publisher","first-page":"41539","DOI":"10.1007\/s11042-023-15127-0","volume":"82","author":"A Halidou","year":"2023","unstructured":"Halidou, A. et al. Review of wavelet denoising algorithms. Multimed. Tools Appl. 82, 41539\u201341569. https:\/\/doi.org\/10.1007\/s11042-023-15127-0 (2023).","journal-title":"Multimed. Tools Appl."},{"key":"47179_CR29","doi-asserted-by":"publisher","unstructured":"Saleh Ahmed, A. et al. Medical image denoising system based on stacked convolutional autoencoder for enhancing 2-dimensional gel electrophoresis noise reduction. Biomed. Signal Process. Control 69, 102842. https:\/\/doi.org\/10.1016\/j.bspc.2021.102842 (2021).","DOI":"10.1016\/j.bspc.2021.102842"},{"key":"47179_CR30","doi-asserted-by":"publisher","unstructured":"Kit, T. et al. Enhancing a convolutional autoencoder with a quantum approximate optimization algorithm for image noise reduction. Mach. Learn. Sci. Technol. 6(4). https:\/\/doi.org\/10.1088\/2632-2153\/ae1656 (2025).","DOI":"10.1088\/2632-2153\/ae1656"},{"issue":"1","key":"47179_CR31","doi-asserted-by":"publisher","first-page":"21","DOI":"10.57020\/ject.1390428","volume":"3","author":"Y Farooq","year":"2024","unstructured":"Farooq, Y. & Sava\u015f, S. Noise removal from the image using convolutional neural networks-based denoising auto encoder. J. Emerg. Comput. Technol. 3(1), 21\u201328. https:\/\/doi.org\/10.57020\/ject.1390428 (2024).","journal-title":"J. Emerg. Comput. Technol."},{"key":"47179_CR32","doi-asserted-by":"publisher","first-page":"012116","DOI":"10.1088\/1757-899X\/1055\/1\/012116","volume":"1055","author":"S Pradeep","year":"2021","unstructured":"Pradeep, S. & Nirmaladevi, P. A review on speckle noise reduction techniques in ultrasound medical images based on spatial domain, transform domain and CNN methods. IOP Conf. Ser. Mater. Sci. Eng. 1055, 012116. https:\/\/doi.org\/10.1088\/1757-899X\/1055\/1\/012116 (2021).","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"47179_CR33","doi-asserted-by":"publisher","first-page":"17221","DOI":"10.1007\/s00521-024-09996-1","volume":"36","author":"R Kumar","year":"2024","unstructured":"Kumar, R. & Bhandari, A. K. Noise reduction deep CNN-based retinal fundus image enhancement using recursive histogram. Neural Comput. Appl. 36, 17221\u201317243. https:\/\/doi.org\/10.1007\/s00521-024-09996-1 (2024).","journal-title":"Neural Comput. Appl."},{"key":"47179_CR34","doi-asserted-by":"crossref","unstructured":"Abuya, T.K., Rimiru, R.M. & Okeyo, G.O. An Image Denoising Technique Using Wavelet-Anisotropic Gaussian Filter-Based CNN for CT Images (2023).","DOI":"10.3390\/app132112069"},{"key":"47179_CR35","doi-asserted-by":"crossref","unstructured":"Fan, H. et al. Wavelet-Domain Frequency-Mixing Transformer Unfolding Network for Low-Dose CT Image Denoising (2025).","DOI":"10.21037\/qims-2024-2368"},{"key":"47179_CR36","doi-asserted-by":"publisher","unstructured":"Katta, S., \u00a0Singh, P., \u00a0Garg, D. & \u00a0Diwakar, M. A hybrid approach for CT image noise reduction combining method noise-CNN and Shearlet transform. Biosci. Biotechnol. Res. Commun. https:\/\/doi.org\/10.13005\/bpj\/2991 (2021) .","DOI":"10.13005\/bpj\/2991"},{"key":"47179_CR37","doi-asserted-by":"publisher","unstructured":"Salehi, H. & \u00a0Vahidi, J. A novel hybrid filter for image despeckling based on improved adaptive Wiener filter, bilateral filter and wavelet filter. Int. J. Image Graph. 21(03). https:\/\/doi.org\/10.1142\/S0219467821500307 (2021).","DOI":"10.1142\/S0219467821500307"},{"key":"47179_CR38","doi-asserted-by":"crossref","unstructured":"Shi, L., Di, W. & Liu, J. Ultrasound Image Denoising Autoencoder Model Based on Lightweight Attention Mechanism (2023).","DOI":"10.21037\/qims-23-1654"},{"key":"47179_CR39","unstructured":"Liang, Y. & Liang, W. ResWCAE: Biometric Pattern Image Denoising Using Residual Wavelet-Conditioned Autoencoder (2023)."},{"key":"47179_CR40","unstructured":"Zhou, Y. et al. AE-Based LAD-CNN with Lightweight Attention Blocks for Ultrasound Image Denoising (2024)."},{"issue":"7","key":"47179_CR41","doi-asserted-by":"publisher","first-page":"2047","DOI":"10.3390\/s25072047","volume":"25","author":"A Malyugina","year":"2025","unstructured":"Malyugina, A., Anantrasirichai, N. & Bull, D. Wavelet-based topological loss for low-light image denoising. Sensors 25(7), 2047 (2025).","journal-title":"Sensors"},{"key":"47179_CR42","doi-asserted-by":"publisher","unstructured":"Chitnis, S.\u00a0M.\u00a0 & \u00a0Mukherji, P. Denoising of multiview images to 3D point cloud visualization using VisualSfM. In Proceedings of the 8th International Conference on Computing, Communication, Control and Automation (ICCUBEA), Pune, India.\u00a01\u20135. https:\/\/doi.org\/10.1109\/ICCUBEA61740.2024.10774767 (2024).","DOI":"10.1109\/ICCUBEA61740.2024.10774767"},{"issue":"1","key":"47179_CR43","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s42492-019-0016-7","volume":"2","author":"L Fan","year":"2019","unstructured":"Fan, L., Zhang, F., Fan, H. & Zhang, C. Brief review of image denoising techniques. Visual Comput. Indus. Biomed. Art 2(1), 7. https:\/\/doi.org\/10.1186\/s42492-019-0016-7 (2019).","journal-title":"Visual Comput. Indus. Biomed. Art"},{"issue":"1","key":"47179_CR44","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/s10796-014-9527-0","volume":"18","author":"P Jain","year":"2016","unstructured":"Jain, P. & Tyagi, V. A survey of edge-preserving image denoising methods. Inf. Syst. Front. 18(1), 159\u2013170. https:\/\/doi.org\/10.1007\/s10796-014-9527-0 (2016).","journal-title":"Inf. Syst. Front."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47179-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47179-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47179-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:33:15Z","timestamp":1781645595000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47179-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,6]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["47179"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-47179-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,6]]},"assertion":[{"value":"28 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2026","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The brain MRI and fetal ultrasound datasets used in this study were obtained from publicly available sources. The data were completely anonymized, and no new data were collected from human participants. Therefore, no additional ethical approval or consent was required for the study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval and consent to participate"}}],"article-number":"16503"}}