MAISY: Motion-Aware Image SYnthesis for Medical Image Motion Correction

TL;DR

MAISY is a novel method for correcting motion artifacts in medical images by characterizing motion and adaptively preserving anatomical details, outperforming existing GAN-based approaches.

Contribution

The paper introduces MAISY, a motion-aware image synthesis approach that leverages the Segment Anything Model and a variance-selective SSIM loss for improved motion correction.

Findings

Outperforms state-of-the-art methods in PSNR, SSIM, and Dice scores.

Effectively preserves localized anatomical features during correction.

Demonstrates robustness on chest and head CT datasets.

Abstract

Patient motion during medical image acquisition causes blurring, ghosting, and distorts organs, which makes image interpretation challenging. Current state-of-the-art algorithms using Generative Adversarial Network (GAN)-based methods with their ability to learn the mappings between corrupted images and their ground truth via Structural Similarity Index Measure (SSIM) loss effectively generate motion-free images. However, we identified the following limitations: (i) they mainly focus on global structural characteristics and therefore overlook localized features that often carry critical pathological information, and (ii) the SSIM loss function struggles to handle images with varying pixel intensities, luminance factors, and variance. In this study, we propose Motion-Aware Image SYnthesis (MAISY) which initially characterize motion and then uses it for correction by: (a) leveraging the foundation model Segment Anything Model (SAM), to dynamically learn spatial patterns along anatomical boundaries where motion artifacts are most pronounced and, (b) introducing the Variance-Selective SSIM (VS-SSIM) loss which adaptively emphasizes spatial regions with high pixel variance to preserve essential anatomical details during artifact correction. Experiments on chest and head CT datasets demonstrate that our model outperformed the state-of-the-art counterparts, with Peak Signal-to-Noise Ratio (PSNR) increasing by 40%, SSIM by 10%, and Dice by 16%.