Vol 19 no.2 2019

Oladotun Olusola OKEDIRAN

Department of Computer Science & Engineering, Ladoke Akintola University, Ogbomoso, Nigeria

Abstract

In recent times, many applications have emerged due to the rapid and continuous development in the field of Information and Communications Technology (ICT). One of such applications is telemedicine. Patient medical data are now in electronic formats and available within health information infrastructures which presents considerable benefits for medical providers and patients themselves, including enhanced patient autonomy, improved clinical treatment, advances in health research and public health surveillance. Accompanying these benefits is the risk of the security patient information that are supposed to be confidential being accessible by unauthorized user since the transmission of these electronic medical data are always via open communication channels. Issues bordering on patient identity protection are still very contentious in health information security. In this paper, a security scheme for enhancing patient information privacy on a medical images standard format; the Digital Imaging and Communications in Medicine (DICOM) was proposed. In the proposed scheme DICOM files were partitioned to extract the medical images and the patient information independently. The patient information were then encoded, encrypted and then embedded in the Region of Non-Interest (RONI) of the medical image component of the DICOM file. The performance of the proposed scheme was evaluated using Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE) and Structural Similarity Index Metric (SSIM). For the ten medical images used to test the scheme, the SSIM values were close to 1, while the MSE and PSNR are consistent and they return desirable high values. The average values of the MSE and PSNR are 0.201 and 55.84 dB respectively. Hence, the proposed scheme is utterly robust and highly imperceptible; the original images can be retrieved at the receiver side without any distortion.

Full Text:

PDF