Lossy Medical Image Compression using Residual Learning-based Dual Autoencoder Model
This work addresses the problem of high storage requirements for medical images in disease diagnosis, specifically for malaria cell images, by providing an incremental improvement in compression efficiency.
The paper tackles compressing large malaria red blood cell images by proposing a residual learning-based dual autoencoder model, achieving improvements of approximately 35% in PSNR, 10% in Color SSIM, and 5% in MS-SSIM over other neural network methods, along with bit savings of 74-78% over traditional and recent approaches.
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.