The short-scan trajectory in cone-beam CT (CBCT) imaging effectively decreases the scan time and the patient dose by excluding the redundant measurements. Also, the offset scan geometry improves the efficacy of the detector utilization by achieving the larger field-of-view (FOV) than the normal use. However, the asymmetric HU value recovery in the sinus of the patient has been consistently observed whenever we use the short-scan trajectory with offset detector. Typically, the reconstruction of short-scan CBCT with an offset detector may lead to inaccuracies in the CT attenuation values within the reconstructed image. This is particularly noticeable away from the beam center due to insufficient data consistency. Also, other physical factors (ex) beam-hardening, scattering effect) and truncation artifact due to the small FOV may contribute to asymmetric sinus representation. In this study, we investigate the potential causes of the asymmetric sinus representation through the artifact study. We used a Monte-Carlo (MC) simulation to reproduce asymmetric HU value for the ease artifact study.
KEYWORDS: Computed tomography, Medical imaging, Denoising, Image sharpness, Education and training, Image quality, Tunable filters, Image restoration, Image filtering, Signal to noise ratio
Self-supervised learning for CT image denoising is a promising technique because it does not require clean target data that are usually unavailable in the clinic. Noise2void (N2V) is one of the famous methods to denoise the image without paired target data and it has been used to denoise optical images and also medical images such as MRI, and CT. However, the performance of the N2V is still limited due to the restricted receptive field of the network and it decreases the prediction performance for CT images that have complex image context and non-uniform Poisson random noise. Thus, we proposed enhanced N2V that utilizes penalty-driven network optimization to further denoise the images while preserving the important details. We used the total variation term to further denoise the image and also the laplacian pyramids term to preserve the important edges of the image. The degree of the influence of each penalty term is controlled by the hyperparameter value and they are optimized to achieve the best image quality in terms of noise level and structure sharpness. For the experiment, the real dental CBCT projection data were used to train the network in the projection domain. After the network training, the test results were reconstructed and compared at each different dose level. Meanwhile, PSNR, SNR, and a line profile were also evaluated to quantitatively compare the original FDK images, and proposed method. In conclusion, the proposed method achieved further denoises the image than N2V even preserving the details. By penalty-driven optimization, the network was able to learn the spectral features of the image while still the receptive field is limited to avoid identity mapping. We hope that our method would increase the practical utility of network-based CT images denoising that usually the target data are unavailable.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.