Block-based conditional entropy coding for medical image compression

S. V. Bharath Kumar, Nithin Nagaraj, Sudipta Mukhopadhyay, Xiaofeng Xu

Research output: Contribution to journalConference articlepeer-review

3 Scopus citations


In this paper, we propose a block-based conditional entropy coding scheme for medical image compression using the 2-D integer Haar wavelet transform. The main motivation to pursue conditional entropy coding is that the first-order conditional entropy is always theoretically lesser than the first and second-order entropies. We propose a sub-optimal scan order and an optimum block size to perform conditional entropy coding for various modalities. We also propose that a similar scheme can be used to obtain a sub-optimal scan order and an optimum block size for other wavelets. The proposed approach is motivated by a desire to perform better than JPEG2000 in terms of compression ratio. We hint towards developing a block-based conditional entropy coder, which has the potential to perform better than JPEG2000. Though we don't indicate a method to achieve the first-order conditional entropy coder, the use of conditional adaptive arithmetic coder would achieve arbitrarily close to the theoretical conditional entropy. All the results in this paper are based on the medical image data set of various bit-depths and various modalities.

Original languageEnglish (US)
Pages (from-to)375-381
Number of pages7
JournalProceedings of SPIE - The International Society for Optical Engineering
StatePublished - Sep 15 2003
EventMedical Imaging 2003: PACS and Integrated Medical Information Systems: Design and Evaluation - San Diego, CA, United States
Duration: Feb 18 2003Feb 20 2003

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Block-based conditional entropy coding for medical image compression'. Together they form a unique fingerprint.

Cite this