Super-resolution of clinical CT volumes with modified CycleGAN using micro CT volumes

TL;DR

This paper introduces a CycleGAN-based super-resolution method for clinical CT volumes that does not require paired training data, enabling detailed micro-CT level resolution from clinical scans.

Contribution

It proposes a novel unpaired training approach with new loss functions to enhance super-resolution of clinical CT to micro-CT level.

Findings

Successfully performed super-resolution of clinical CT to micro-CT level.

Demonstrated effectiveness on lung cancer patient data.

Achieved detailed imaging without paired datasets.

Abstract

This paper presents a super-resolution (SR) method with unpaired training dataset of clinical CT and micro CT volumes. For obtaining very detailed information such as cancer invasion from pre-operative clinical CT volumes of lung cancer patients, SR of clinical CT volumes to $\m$}CT level is desired. While most SR methods require paired low- and high- resolution images for training, it is infeasible to obtain paired clinical CT and {\mu}CT volumes. We propose a SR approach based on CycleGAN, which could perform SR on clinical CT into $\mu$CT level. We proposed new loss functions to keep cycle consistency, while training without paired volumes. Experimental results demonstrated that our proposed method successfully performed SR of clinical CT volume of lung cancer patients into $\mu$CT level.