Feedback Assisted Adversarial Learning to Improve the Quality of Cone-beam CT Images
This work addresses image quality enhancement in cone-beam CT for medical imaging applications, representing an incremental improvement over existing adversarial learning methods.
The paper tackled the problem of insufficient translation performance for locally different image features in unsupervised adversarial learning for medical image quality improvement, and the proposed feedback-assisted framework achieved a correlation coefficient of 0.93 with reference images in CBCT image synthesis.
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.