{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T06:27:31Z","timestamp":1787120851139,"version":"build-2736575974"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>Steganography plays a critical role in preserving the privacy of medical images by protecting sensitive patient information without compromising image quality or diagnostic utility. This paper proposes a novel lossless privacy protection algorithm for medical images based on pixel displacement. The core innovation lies in the synergistic combination of physical transformation and deep learning\u2014specifically, the integration of shift-rectification with a dual-carrier embedding mechanism. The proposed method begins by applying byte-level pixel shifting to the confidential medical image to generate a shift-rectified version. A deep convolutional neural network is then employed to embed both the original and the rectified medical images into two separate carrier images, ensuring that the resulting container images are visually indistinguishable from the carriers. Subsequently, a dedicated recovery network extracts and reconstructs the lossy shift-rectified image and a degraded version of the original from the two carriers, using the former to calibrate and fully restore the original medical image in a lossless manner. Experimental results demonstrate the algorithm\u2019s effectiveness in preserving privacy while enabling perfect image recovery: the container images achieve an average PSNR of 40.08\u202fdB and MSSIM of 0.988 relative to the carriers, confirming near-perceptual-indistinguishability; the reconstructed secret images are recovered with a bit-level accuracy of 100%; and the algorithm maintains robustness under Gaussian noise, salt-and-pepper noise, and PCA compression with lossless recovery guaranteed. Moreover, the method shows excellent generalization across multiple medical imaging datasets (CT, MRI, and X-ray), highlighting its clinical applicability and innovation in secure medical image transmission systems.<\/jats:p>","DOI":"10.3389\/fmed.2026.1871854","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T05:46:23Z","timestamp":1787118383000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Pixel shift-based reversible steganography for privacy-preserving medical images"],"prefix":"10.3389","volume":"13","author":[{"given":"Xiaofeng","family":"Huang","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Hainan Normal University","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Intelligent Manufacturing, Nanyang Institute of Technology","place":["Nanyang, Henan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xishun","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Hainan Normal University","place":["Haikou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1227515","DOI":"10.3389\/fmed.2023.1227515","article-title":"Privacy-preserving continual learning methods for medical image classification: a comparative analysis","volume":"10","author":"Verma","year":"2023","journal-title":"Front Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"47731","DOI":"10.1109\/access.2021.3061710","article-title":"Lightweight encryption technique to enhance medical image security on internet of medical things applications","volume":"9","author":"Hasan","year":"2021","journal-title":"IEEE Access"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.1109\/ojcoms.2023.3316922","article-title":"Efficient personal-health-records sharing in internet of medical things using searchable symmetric encryption, blockchain and IPFS","volume":"4","author":"Bisht","year":"2023","journal-title":"IEEE Open J Commun Soc"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"11147","DOI":"10.1007\/s11042-023-15818-8","article-title":"DeepEnc: deep learning-based CT image encryption approach","volume":"83","author":"Abdellatef","year":"2024","journal-title":"Multim Tools Appl"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"19425","DOI":"10.1007\/s11071-023-08900-1","article-title":"A robust privacy protection scheme for stereoscopic medical images based on fractal chaos","volume":"111","author":"C","year":"2023","journal-title":"Nonlinear Dyn"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"4915","DOI":"10.1109\/tnnls.2021.3062754","article-title":"DeepKeyGen: a deep learning-based stream cipher generator for medical image encryption and decryption","volume":"33","author":"Ding","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"3231","DOI":"10.3233\/THC-231927","article-title":"Deep-KEDI: deep learning-based zigzag generative adversarial network for encryption and decryption of medical images","volume":"32","author":"Selvakumar","year":"2024","journal-title":"Technol Health Care"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"66345","DOI":"10.1109\/access.2022.3185206","article-title":"Privacy-preserving deep learning with learnable image encryption on medical images","volume":"10","author":"Huang","year":"2022","journal-title":"IEEE Access"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1807","DOI":"10.18280\/ts.410413","article-title":"Partial encryption scheme of medical images based on DWT, secret image sharing and hyperchaotic system","volume":"41","author":"Alwan","year":"2024","journal-title":"Traitement Signal"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3394658","article-title":"Homomorphic encryption for machine learning in medicine and bioinformatics","volume":"53","author":"Kahrobaei","year":"2020","journal-title":"ACM Comput Surv"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3531016","article-title":"BMIF: privacy-preserving blockchain-based medical image fusion","volume":"19","author":"Xiang","year":"2022","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"28445","DOI":"10.1007\/s11042-022-14300-1","article-title":"Reversible information hiding scheme based on interpolation and histogram shift for medical images","volume":"82","author":"Ren","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1007\/s00521-022-07830-0","article-title":"A robust medical image steganography approach based on particle swarm optimization algorithm and quantum walks","volume":"35","author":"Abd-El-Atty","year":"2023","journal-title":"Neural Comput Appl"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"108170","DOI":"10.1016\/j.asoc.2021.108170","article-title":"Generative high-capacity image hiding based on residual CNN in wavelet domain","volume":"115","author":"Zhu","year":"2022","journal-title":"Appl Soft Comput"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"25539","DOI":"10.1007\/s11042-021-10904-1","article-title":"AdvSGAN: adversarial image steganography with adversarial networks","volume":"80","author":"Li","year":"2021","journal-title":"Multimed Tools Appl"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"6681","DOI":"10.1007\/s11042-021-11778-z","article-title":"GAN-based image steganography for enhancing security via adversarial attack and pixel-wise deep fusion","volume":"81","author":"Yuan","year":"2022","journal-title":"Multimed Tools Appl"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"5040","DOI":"10.1109\/TMM.2023.3330098","article-title":"Provably secure robust image steganography","volume":"26","author":"Yang","year":"2023","journal-title":"IEEE Trans Multimed"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"2951","DOI":"10.1109\/tnse.2024.3354941","article-title":"Joint coverless steganography and image transformation for covert communication of secret messages","volume":"11","author":"Wen","year":"2024","journal-title":"IEEE Trans Netw Sci Eng"},{"key":"ref19","first-page":"240","author":"Su","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"126391","DOI":"10.1016\/j.eswa.2025.126391","article-title":"A transformer-based adversarial network framework for steganography","volume":"269","author":"Xiao","year":"2025","journal-title":"Expert Syst Appl"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"7166","DOI":"10.1038\/s41598-024-55639-9","article-title":"High-capacity data hiding for medical images based on the mask-RCNN model","volume":"14","author":"Saidi","year":"2024","journal-title":"Sci Rep"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.32604\/jihpp.2024.051354","article-title":"Pairwise reversible data hiding for medical images with contrast enhancement","volume":"6","author":"Boateng","year":"2024","journal-title":"J Inf Hiding Priv Protect"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"83113","DOI":"10.1007\/s11042-024-18600-6","article-title":"A separable privacy-preserving technique based on reversible medical data hiding in plain text encrypted images using neural network","volume":"83","author":"Shi","year":"2024","journal-title":"Multim Tools Appl"},{"key":"ref24","first-page":"288","volume-title":"Communications in Computer and Information Science","author":"Cheng","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"101932","DOI":"10.1016\/j.jksuci.2024.101932","article-title":"Encryption-then-embedding-based hybrid data hiding scheme for medical images","volume":"36","author":"Meng","year":"2024","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"23","DOI":"10.33260\/zictjournal.v7i1.151","article-title":"A privacy-preserving scheme for medical diagnosis records based on encrypted image steganography","volume":"7","author":"Lishomwaa","year":"2023","journal-title":"Zambia ICT J"},{"key":"ref27","year":""},{"key":"ref28","year":""},{"key":"ref29","year":""},{"key":"ref30","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1109\/tifs.2012.2190402","article-title":"Rich models for steganalysis of digital images","volume":"7","author":"Fridrich","year":"2012","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"ref31","first-page":"48","volume-title":"IEEE International Workshop on Information Forensics and Security (WIFS)","author":"Denemark","year":"2014"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"2545","DOI":"10.1109\/tifs.2017.2710946","article-title":"Deep learning hierarchical representations for image steganalysis","volume":"12","author":"Ye","year":"2017","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"233","DOI":"10.3724\/SP.J.1249.2025.02233","article-title":"Image steganalysis based on CNN-transformer","volume":"42","author":"Jiahao","year":"2025","journal-title":"J Shenzhen Univ Sci Eng"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1871854\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T05:46:23Z","timestamp":1787118383000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1871854\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":33,"alternative-id":["10.3389\/fmed.2026.1871854"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1871854","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]},"article-number":"1871854"}}