A novel fuzzy logic-based image steganography method to ensure medical data security

Comput Biol Med. 2015 Dec 1:67:172-83. doi: 10.1016/j.compbiomed.2015.10.011. Epub 2015 Oct 27.

Abstract

This study aims to secure medical data by combining them into one file format using steganographic methods. The electroencephalogram (EEG) is selected as hidden data, and magnetic resonance (MR) images are also used as the cover image. In addition to the EEG, the message is composed of the doctor׳s comments and patient information in the file header of images. Two new image steganography methods that are based on fuzzy-logic and similarity are proposed to select the non-sequential least significant bits (LSB) of image pixels. The similarity values of the gray levels in the pixels are used to hide the message. The message is secured to prevent attacks by using lossless compression and symmetric encryption algorithms. The performance of stego image quality is measured by mean square of error (MSE), peak signal-to-noise ratio (PSNR), structural similarity measure (SSIM), universal quality index (UQI), and correlation coefficient (R). According to the obtained result, the proposed method ensures the confidentiality of the patient information, and increases data repository and transmission capacity of both MR images and EEG signals.

Keywords: Fuzzy logic algorithm; Least significant bit; Medical data security; Medical image steganography; Similarity based algorithm.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Computer Security*
  • Confidentiality*
  • Electronic Health Records / organization & administration*
  • Fuzzy Logic*
  • Humans
  • Image Interpretation, Computer-Assisted / methods*
  • Information Storage and Retrieval / methods*
  • Logistic Models
  • Reproducibility of Results
  • Sensitivity and Specificity