Micro-CT Synthesis and Inner Ear Super Resolution via Generative Adversarial Networks and Bayesian Inference

TL;DR

This paper presents a novel unpaired super-resolution method for Micro-CT images of the inner ear using GANs and Bayesian inference, achieving significant resolution enhancement and improved shape accuracy.

Contribution

It introduces a cycle-consistency GAN framework combined with Bayesian inference for super-resolution on unpaired data, specifically applied to inner ear Micro-CT images.

Findings

Achieved eight times higher resolution in Micro-CT images.

Outperformed state-of-the-art methods visually and quantitatively.

Expert raters rated the proposed method highest in quality.

Abstract

Existing medical image super-resolution methods rely on pairs of low- and high- resolution images to learn a mapping in a fully supervised manner. However, such image pairs are often not available in clinical practice. In this paper, we address super-resolution problem in a real-world scenario using unpaired data and synthesize linearly \textbf{eight times} higher resolved Micro-CT images of temporal bone structure, which is embedded in the inner ear. We explore cycle-consistency generative adversarial networks for super-resolution task and equip the translation approach with Bayesian inference. We further introduce \emph{Hu Moment distance} the evaluation metric to quantify the shape of the temporal bone. We evaluate our method on a public inner ear CT dataset and have seen both visual and quantitative improvement over state-of-the-art deep-learning-based methods. In addition, we perform a multi-rater visual evaluation experiment and find that trained experts consistently rate the proposed method the highest quality scores among all methods. Furthermore, we are able to quantify uncertainty in the unpaired translation task and the uncertainty map can provide structural information of the temporal bone.