Segmentation-Based Multilayer Diagnosis Lossless Medical Image compression

Bai, X., Jin, J.S. and Feng, D.D.

    Hospital and clinical environments are moving towards computerisation, digitisation and centralisation, resulting in prohibitive amounts of digital medical image data. Compression techniques are, therefore, essential in archival and communication of medical image. Although lossy compression yields much higher compression rates, the medical community has relied on lossless compression for legal and clinical reasons. In this paper, we propose a segmentation-based multilayer (SML) coding scheme for lossless medical image compression. A fully automatic unseeded region growing (URG) segmentation approach is used for extracting diagnostically important regions, i.e., the regions of interest (ROI), for multilayer lossless ROI compression with the efficient Barrows-Wheeler coding (BWC) and wavelet-based JPEG2000 coding. Our proposed SML compression scheme can provide efficient compression for various medical imaging data and offer potential advantages in content-based medical image retrieval and semantic progressive transmission in telemedicine.
Cite as: Bai, X., Jin, J.S. and Feng, D.D. (2004). Segmentation-Based Multilayer Diagnosis Lossless Medical Image compression. In Proc. 2003 Pan-Sydney Area Workshop on Visual Information Processing (VIP2003), Sydney, Australia. CRPIT, 36. Piccardi, M., Hintz, T., He, S., Huang, M. L. and Feng, D. D., Eds. ACS. 9-14.
pdf (from crpit.com) pdf (local if available) BibTeX EndNote GS