Lossy Medical Image Compression using Residual Learning-based Dual Autoencoder Model

Mishra, Dipti; Singh, Satish K.; Singh, Rajat

doi:10.48550/arxiv.2108.10579

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[2] and using SIREN with our architecture with 2, 3 and 4 layers. Table 7 shows the comparison of the results of Shen's [52], Mishra's [53], SIREN [2] and ours in terms of PSNR. Table 6.…”

Section: Comparison With Existing Methodsmentioning

confidence: 99%

“…The Ref. [53] suggests CNN-based image compression to compress malaria cell images using a compressor-decompressor framework. According to their technique, there are two autoencoders, where one learns low-frequency components and another learns high-frequency components.…”

Section: Volume Data Compressionmentioning

confidence: 99%

“…Comparison of results of our technique with SIREN [2], Mishra's[53] and Shen's[52] in terms of PSNR.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Novel Implicit Neural Representation for Volume Data

Sheibanifard

2023

Applied Sciences

View full text Add to dashboard Cite

The storage of medical images is one of the challenges in the medical imaging field. There are variable works that use implicit neural representation (INR) to compress volumetric medical images. However, there is room to improve the compression rate for volumetric medical images. Most of the INR techniques need a huge amount of GPU memory and a long training time for high-quality medical volume rendering. In this paper, we present a novel implicit neural representation to compress volume data using our proposed architecture, that is, the Lanczos downsampling scheme, SIREN deep network, and SRDenseNet high-resolution scheme. Our architecture can effectively reduce training time, and gain a high compression rate while retaining the final rendering quality. Moreover, it can save GPU memory in comparison with the existing works. The experiments show that the quality of reconstructed images and training speed using our architecture is higher than current works which use the SIREN only. Besides, the GPU memory cost is evidently decreased.

show abstract

“…[2] and using SIREN with our architecture with 2, 3 and 4 layers. Table 7 shows the comparison of the results of Shen's [52], Mishra's [53], SIREN [2] and ours in terms of PSNR. Table 6.…”

Section: Comparison With Existing Methodsmentioning

confidence: 99%

Section: Volume Data Compressionmentioning

confidence: 99%