Improving Access to Radiology Health Care Services in Rural Areas of Developing Nations through a Secure Web Based Teleradiology Steganographic Method

Abstract

Access to specialized health care services in rural areas of developing nations and in particular sub Saharan Africa countries like Kenya is severely limited due to shortage of experts available in the medical field particularly in special domains of practice like radiology which involves professional examination of medical images e.g. X-rays and Scans (CAT, MRI etc.) for clinical interpretation and diagnosis. These experts albeit in their minimal number are only found within metropolitan areas where wellequipped referral hospitals are located. Consequently, patients from rural areas who survive on meager incomes are forced to make high sacrifices in visiting distant referral hospitals in order to access radiology and other specialized medical services. While it is possible to make a patient's medical images available to a practicing radiologist online e.g. through open network systems inter connectivity and email attachments, these methods don't guarantee the security, confidentiality and tamper free reliability required for a medical information system infrastructure. The possibility of securely and covertly transmitting such medical images to a remote radiologist for clinical interpretation and diagnosis through an enhanced Least Significant Bit (LSB) digital image steganographic technique was the focus of this study. The proposed method was tested in an experimental research that involved a comparison in the carrier file's statistical properties from this technique and the traditional LSB steganographic technique of information hiding. The study revealed improvements in imperceptibility levels in the carrier files used in this technique besides ensuring that the original MI fidelity is preserved one hundred percent by embedding it in a primary random image signal carrier file. The technique recorded a Peak Signal to Noise Ratio(PSNR) of well above 50 decibels for each image used which is well above the 30 decibels recommended for a fairly imperceptible carrier file.