Lightening Anything in Medical Images

TL;DR

UniMIE is a training-free, unsupervised diffusion model that enhances various medical images without fine-tuning, improving diagnostic accuracy and robustness across multiple modalities.

Contribution

It introduces UniMIE, a novel universal medical image enhancement method that operates without training on medical data, using only a pre-trained ImageNet model.

Findings

Outperforms modality-specific models in quality and robustness

Works across 13 imaging modalities and 15 medical types

Enhances downstream diagnostic tasks effectively

Abstract

The development of medical imaging techniques has made a significant contribution to clinical decision-making. However, the existence of suboptimal imaging quality, as indicated by irregular illumination or imbalanced intensity, presents significant obstacles in automating disease screening, analysis, and diagnosis. Existing approaches for natural image enhancement are mostly trained with numerous paired images, presenting challenges in data collection and training costs, all while lacking the ability to generalize effectively. Here, we introduce a pioneering training-free Diffusion Model for Universal Medical Image Enhancement, named UniMIE. UniMIE demonstrates its unsupervised enhancement capabilities across various medical image modalities without the need for any fine-tuning. It accomplishes this by relying solely on a single pre-trained model from ImageNet. We conduct a comprehensive evaluation on 13 imaging modalities and over 15 medical types, demonstrating better qualities, robustness, and accuracy than other modality-specific and data-inefficient models. By delivering high-quality enhancement and corresponding accuracy downstream tasks across a wide range of tasks, UniMIE exhibits considerable potential to accelerate the advancement of diagnostic tools and customized treatment plans.