Feedback Assisted Adversarial Learning to Improve the Quality of Cone-beam CT Images

TL;DR

This paper introduces a feedback mechanism in adversarial learning to enhance the local feature translation in CBCT images, resulting in higher quality synthetic images closely matching reference CT images.

Contribution

It proposes a novel feedback-based adversarial learning framework using a U-net discriminator for improved local feature translation in CBCT image enhancement.

Findings

Achieved a correlation coefficient of 0.93 with reference images.

Captured more diverse image features than conventional methods.

Produced synthetic images with pixel values close to references.

Abstract

Unsupervised image translation using adversarial learning has been attracting attention to improve the image quality of medical images. However, adversarial training based on the global evaluation values of discriminators does not provide sufficient translation performance for locally different image features. We propose adversarial learning with a feedback mechanism from a discriminator to improve the quality of CBCT images. This framework employs U-net as the discriminator and outputs a probability map representing the local discrimination results. The probability map is fed back to the generator and used for training to improve the image translation. Our experiments using 76 corresponding CT-CBCT images confirmed that the proposed framework could capture more diverse image features than conventional adversarial learning frameworks and produced synthetic images with pixel values close to the reference image and a correlation coefficient of 0.93.