MultiScale Wavelet-based Compression Schemes for Preserving Diagnostic Information in Medical Imaging

DOI

10.2991/978-94-6463-718-2_111How to use a DOI?

Keywords

Medical image compression; Wavelet transform; Diagnostic preservation; Machine learning; Healthcare informatics

Abstract

Medical imaging is now an integral part of the diagnosis of most diseases and ailments; handling and transferring image data and maintaining diagnostic image quality has become a daunting task. Typically, reduction techniques obstruct vital and sensitive diagnostic information, necessitating the need to prioritize better methods of data handling. In this paper we present a new multistage wavelet-based compression approach with threshold level selection and region-of-interest preservation. We optimize the method to work with medical imaging modalities such as MRI, CT, and X-ray, integrating DWT with residual feature preservation. The method’s implementation across diverse medical image datasets demonstrated compression ratios of 15:1, ranging from 1 to 25:1, and achieved diagnostic accuracy of 98.7%. The average PSNR was 42.3, and the SSIM score was 0.985. Radiologists confirmed the preservation accuracy of the diagnostic features, which resulted in a direct match of 96.5% with the uncompressed images. The suggested framework achieves significantly higher compression performance rates while maintaining diagnostic quality, positioning it as a viable option for managing medical images in scenarios with limited facilities.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - K. Sathish
AU  - R. Rajesh Sharma
AU  - Mohit Tiwari
AU  - Akey Sungheetha
AU  - G. G. S. Pradeep
AU  - V. Ellappan
PY  - 2025
DA  - 2025/05/23
TI  - MultiScale Wavelet-based Compression Schemes for Preserving Diagnostic Information in Medical Imaging
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 1332
EP  - 1342
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_111
DO  - 10.2991/978-94-6463-718-2_111
ID  - Sathish2025
ER  -