Regularized Compression of MRI Data: Modular Optimization of Joint Reconstruction and Coding

TL;DR

This paper introduces a modular joint optimization framework for MRI data reconstruction and lossy compression, improving image quality and bit-rate trade-offs using total-variation regularization and ADMM, with potential to enhance medical image storage and transmission.

Contribution

It presents a novel modular optimization method combining MRI reconstruction and lossy compression with total-variation regularization, outperforming existing approaches in image quality.

Findings

Achieves 4-9 dB PSNR gains at high bit-rates over non-regularized methods.

Provides 0.5-1 dB PSNR improvements over other regularized solutions.

Demonstrates improved trade-offs between image quality and compression rate.

Abstract

The Magnetic Resonance Imaging (MRI) processing chain starts with a critical acquisition stage that provides raw data for reconstruction of images for medical diagnosis. This flow usually includes a near-lossless data compression stage that enables digital storage and/or transmission in binary formats. In this work we propose a framework for joint optimization of the MRI reconstruction and lossy compression, producing compressed representations of medical images that achieve improved trade-offs between quality and bit-rate. Moreover, we demonstrate that lossy compression can even improve the reconstruction quality compared to settings based on lossless compression. Our method has a modular optimization structure, implemented using the alternating direction method of multipliers (ADMM) technique and the state-of-the-art image compression technique (BPG) as a black-box module iteratively applied. This establishes a medical data compression approach compatible with a lossy compression standard of choice. A main novelty of the proposed algorithm is in the total-variation regularization added to the modular compression process, leading to decompressed images of higher quality without any additional processing at/after the decompression stage. Our experiments show that our regularization-based approach for joint MRI reconstruction and compression often achieves significant PSNR gains between 4 to 9 dB at high bit-rates compared to non-regularized solutions of the joint task. Compared to regularization-based solutions, our optimization method provides PSNR gains between 0.5 to 1 dB at high bit-rates, which is the range of interest for medical image compression.