REGION OF INTEREST BASED COMPRESSION OF MEDICAL IMAGES FOR TELEMEDICINE

P. SHARMA¹, R.R. SHAH², R.R. SHAH^3
1Institute of Science and Technology for Advanced Studies and Research, Vallabh Vidya Nagar- 388 120, Gujarat, India.
²Institute of Technology, Nirma University, Ahmedabad- 382 481, Gujarat, India.
³Shri Chimanbahi Patel Institute of Computer Applications, Ahmedabad- 380 015, Gujarat, India.

Received : 11-11-2014     Accepted : 20-03-2014     Published : 30-04-2014
Volume : 2     Issue : 1       Pages : 20 - 24
Bioinfo Med Imag 2.1 (2014):20-24

Keywords : Telemedicine, Hybrid Image Compression, Region of Interest, Healthcare
Conflict of Interest : None declared

Telemedicine uses Information and Communication technologies to overcome geographical barriers, and increase access to health care services. With the widespread expansion of broadband technology, Telemedicine is becoming an incredibly effective solution that is providing a new alternative to improve our current health care landscape. With this technology, medical reports - videos or radiology images can be transmitted to facilitate an accurate diagnosis. Medical images are critically important in medical field, especially for diagnosis and surgical planning. Proper assessment requires high image quality, which is translated into higher requirements for storage capacity and transmission bandwidth in applications like telemedicine applications. The image transmission time depends on the bandwidth and the data transfer rate, so for the optimum use of the channel bandwidth and the faster data transfer, it is necessary to transmit the medical image data in compressed form. Even small quality reduction introduced by lossy compression might alter subsequent diagnosis, which might cause severe medical and legal consequences. It has been observed that only some part of the image actually is of interest to the practitioners, and hence Region of Interest (ROI) -based techniques have become popular. In this paper we try to explain how ROI-based hybrid image compression of medical images can help to achieve higher ratio of compression along with safeguard of the diagnostically important part of the medical image. The main advantage of using ROI-based compression techniques is that it combines the usage of both lossy and lossless techniques to compress images. There are several methods for selsction of ROI from a medical image. The method used can be either manual or automatic, both with the same aim of achieving optimal compression balance between lossy and lossless regions. In this paper, we also try to propose segmentation method for identifying ROI and applying ROI-based hybrid compression method on medical images.