Non-Reference Quality Assessment for Medical Imaging: Application to Synthetic Brain MRIs

TL;DR

This paper introduces a deep learning-based non-reference quality assessment method for 3D brain MRI images, capable of evaluating both real and synthetic data without reference images, addressing limitations of existing metrics.

Contribution

It presents the first comprehensive non-reference quality assessment approach for 3D medical images, utilizing a 3D ResNet and a diffusion model for high-fidelity synthetic image evaluation.

Findings

Outperforms state-of-the-art metrics in accuracy

Operates effectively without reference images

Provides intuitive quality scores across datasets

Abstract

Generating high-quality synthetic data is crucial for addressing challenges in medical imaging, such as domain adaptation, data scarcity, and privacy concerns. Existing image quality metrics often rely on reference images, are tailored for group comparisons, or are intended for 2D natural images, limiting their efficacy in complex domains like medical imaging. This study introduces a novel deep learning-based non-reference approach to assess brain MRI quality by training a 3D ResNet. The network is designed to estimate quality across six distinct artifacts commonly encountered in MRI scans. Additionally, a diffusion model is trained on diverse datasets to generate synthetic 3D images of high fidelity. The approach leverages several datasets for training and comprehensive quality assessment, benchmarking against state-of-the-art metrics for real and synthetic images. Results demonstrate superior performance in accurately estimating distortions and reflecting image quality from multiple perspectives. Notably, the method operates without reference images, indicating its applicability for evaluating deep generative models. Besides, the quality scores in the [0, 1] range provide an intuitive assessment of image quality across heterogeneous datasets. Evaluation of generated images offers detailed insights into specific artifacts, guiding strategies for improving generative models to produce high-quality synthetic images. This study presents the first comprehensive method for assessing the quality of real and synthetic 3D medical images in MRI contexts without reliance on reference images.