Open Access

ARTICLE

Privacy Protection for Medical Images Based on DenseNet and Coverless Steganography

Yun Tan¹, Jiaohua Qin^{1, *}, Hao Tang², Xuyu Xiang¹, Ling Tan², Neal N. Xiong³

1 College of Computer Science and Information Technology, Central South University of Forestry & Technology, Changsha, 410114, China.
2 The Second Xiangya Hospital of Central South University, Changsha, 410011, China.
3 Department of Mathematics and Computer Science, Northeastern State University, Tahlequah, 74464, USA.

* Corresponding Author: Jiaohua Qin. Email: .

Computers, Materials & Continua 2020, 64(3), 1797-1817. https://doi.org/10.32604/cmc.2020.010802

Received 30 March 2020; Accepted 29 April 2020; Issue published 30 June 2020

Abstract

With the development of the internet of medical things (IoMT), the privacy protection problem has become more and more critical. In this paper, we propose a privacy protection scheme for medical images based on DenseNet and coverless steganography. For a given group of medical images of one patient, DenseNet is used to regroup the images based on feature similarity comparison. Then the mapping indexes can be constructed based on LBP feature and hash generation. After mapping the privacy information with the hash sequences, the corresponding mapped indexes of secret information will be packed together with the medical images group and released to the authorized user. The user can extract the privacy information successfully with a similar method of feature analysis and index construction. The simulation results show good performance of robustness. And the hiding success rate also shows good feasibility and practicability for application. Since the medical images are kept original without embedding and modification, the performance of crack resistance is outstanding and can keep better quality for diagnosis compared with traditional schemes with data embedding.

---

Keywords

---

Citations