A Mixed-Supervision Multilevel GAN Framework for Image Quality Enhancement
This work addresses the high cost of acquiring high-quality training data for medical imaging applications, offering a practical solution for domains like histopathology and laparoscopy, though it appears incremental as it builds on existing GAN frameworks.
The paper tackles the problem of reducing data curation costs for image quality enhancement by proposing a mixed-supervision GAN that leverages multiple quality levels of training data, such as high and medium quality images, and demonstrates improved performance on histopathology and laparoscopy image tasks.
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.