MIINet: An Image Quality Improvement Framework for Supporting Medical Diagnosis

TL;DR

MIINet is a novel unsupervised image translation network that enhances medical image quality, especially for throat and endoscopy images, thereby aiding doctors in more accurate diagnoses.

Contribution

The paper introduces MIINet, a new high-resolution image-to-image translation framework that preserves image attributes while improving quality without supervision.

Findings

Significantly increased mean doctor opinion score from 2.36 to 4.11.

Outperformed CycleGAN in image quality enhancement.

Confirmed by physicians to support throat disease diagnosis effectively.

Abstract

Medical images have been indispensable and useful tools for supporting medical experts in making diagnostic decisions. However, taken medical images especially throat and endoscopy images are normally hazy, lack of focus, or uneven illumination. Thus, these could difficult the diagnosis process for doctors. In this paper, we propose MIINet, a novel image-to-image translation network for improving quality of medical images by unsupervised translating low-quality images to the high-quality clean version. Our MIINet is not only capable of generating high-resolution clean images, but also preserving the attributes of original images, making the diagnostic more favorable for doctors. Experiments on dehazing 100 practical throat images show that our MIINet largely improves the mean doctor opinion score (MDOS), which assesses the quality and the reproducibility of the images from the baseline of 2.36 to 4.11, while dehazed images by CycleGAN got lower score of 3.83. The MIINet is confirmed by three physicians to be satisfying in supporting throat disease diagnostic from original low-quality images.