A Mixed-Supervision Multilevel GAN Framework for Image Quality Enhancement

TL;DR

This paper introduces a novel GAN framework that utilizes mixed-quality training data to enhance image quality, reducing data curation costs while improving performance in medical image enhancement tasks.

Contribution

A new multilevel GAN architecture that leverages both high- and medium-quality images for improved image enhancement performance.

Findings

Outperforms state-of-the-art methods in histopathology image super-resolution.

Effectively enhances laparoscopy images by combining super-resolution and smoke removal.

Demonstrates benefits on large clinical and pre-clinical datasets.

Abstract

Deep neural networks for image quality enhancement typically need large quantities of highly-curated training data comprising pairs of low-quality images and their corresponding high-quality images. While high-quality image acquisition is typically expensive and time-consuming, medium-quality images are faster to acquire, at lower equipment costs, and available in larger quantities. Thus, we propose a novel generative adversarial network (GAN) that can leverage training data at multiple levels of quality (e.g., high and medium quality) to improve performance while limiting costs of data curation. We apply our mixed-supervision GAN to (i) super-resolve histopathology images and (ii) enhance laparoscopy images by combining super-resolution and surgical smoke removal. Results on large clinical and pre-clinical datasets show the benefits of our mixed-supervision GAN over the state of the art.