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

TL;DR

This paper introduces a residual learning-based dual autoencoder framework for lossy medical image compression, significantly improving compression efficiency and image quality over existing methods, especially for large-scale medical images.

Contribution

The novel dual autoencoder model effectively captures residual features for improved compression and image reconstruction in medical imaging.

Findings

Outperforms existing neural network compression techniques by 5-35% in quality metrics.

Achieves over 75% bit savings compared to JPEG-LS, JP2K-LM, CALIC, and recent neural methods.

Significantly improves PSNR, Color SSIM, and MS-SSIM metrics.

Abstract

In this work, we propose a two-stage autoencoder based compressor-decompressor framework for compressing malaria RBC cell image patches. We know that the medical images used for disease diagnosis are around multiple gigabytes size, which is quite huge. The proposed residual-based dual autoencoder network is trained to extract the unique features which are then used to reconstruct the original image through the decompressor module. The two latent space representations (first for the original image and second for the residual image) are used to rebuild the final original image. Color-SSIM has been exclusively used to check the quality of the chrominance part of the cell images after decompression. The empirical results indicate that the proposed work outperformed other neural network related compression technique for medical images by approximately 35%, 10% and 5% in PSNR, Color SSIM and MS-SSIM respectively. The algorithm exhibits a significant improvement in bit savings of 76%, 78%, 75% & 74% over JPEG-LS, JP2K-LM, CALIC and recent neural network approach respectively, making it a good compression-decompression technique.