Histopathology image streaming

  • Authors:
  • Manoranjan Mohanty;Wei Tsang Ooi

  • Affiliations:
  • Department of Computer Science, School of Computing, National University of Singapore, Singapore;Department of Computer Science, School of Computing, National University of Singapore, Singapore

  • Venue:
  • PCM'12 Proceedings of the 13th Pacific-Rim conference on Advances in Multimedia Information Processing
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes an image streaming framework to stream histopathology image of a patient over a lossy network. Firstly, the large histopathology image is divided into a number of fixed size tiles to facilitate ROI-based streaming. Secondly, each tile is compressed using a variant of WebP so that the size of the compressed data is 20% to 30% less than the size of the compressed data when the same tile is compressed using JPEG. Finally, a greedy packetization scheme is proposed to pack the inter-dependent macroblocks of any compressed tile so that the client is able to decode more number of macroblocks than the naive method at any intermediate stage of streaming.