Artifact correction in low‐dose dental CT imaging using Wasserstein generative adversarial networks

Abstract

Purpose: In recent years, health risks concerning high-dose x-ray radiation have become a major concern in dental computed tomography (CT) examinations. Therefore, adopting low-dose computed tomography (LDCT) technology has become a major focus in the CT imaging field. One of these LDCT technologies is downsampling data acquisition during low-dose x-ray imaging processes. However, reducing the radiation dose can adversely affect CT image quality by introducing noise and artifacts in the resultant image that can compromise diagnostic information. In this paper, we propose an artifact correction method for downsampling CT reconstruction based on deep learning. Method: We used clinical dental CT data with low-dose artifacts reconstructed by conventional filtered back projection (FBP) as inputs to a deep neural network and corresponding high-quality labeled normal-dose CT data during training. We trained a generative adversarial network (GAN) with Wasserstein distance (WGAN) and mean squared error (MSE) loss, called m-WGAN, to remove artifacts and obtain high-quality CT dental images in a clinical dental CT examination environment. Results: The experimental results confirmed that the proposed algorithm effectively removes lowdose artifacts from dental CT scans. In addition, we showed that the proposed method is efficient for removing noise from low-dose CT scan images compared to existing approaches. We compared the performances of the general GAN, convolutional neural networks, and m-WGAN. Through quantitative and qualitative analysis of the results, we concluded that the proposed m-WGAN method resulted in better artifact correction performance preserving the texture in dental CT scanning. Conclusions: The image quality evaluation metrics indicated that the proposed method effectively improves image quality when used as a postprocessing technique for dental CT images. To the best of our knowledge, this work is the first deep learning architecture used with a commercial cone-beam dental CT scanner. The artifact correction performance was rigorously evaluated and demonstrated to be effective. Therefore, we believe that the proposed algorithm represents a new direction in the research area of low-dose dental CT artifact correction.

PWLS-PR: low-dose computed tomography image reconstruction using a patch-based regularization method based on the penalized weighted least squares total variation approach

“…The third parameter of interest is the patch size in equation (12). A larger patch size can lead to a slower runtime, and an excessively large patch size may hinder the recognition of small image features, resulting in the inability to preserve the corresponding edges.…”

“…Using these algorithms, the projection must be discretized at a high sampling rate to make the image quality satisfactory, but an excessively high radiation dose will have a negative impact on the health of the patient; in addition, if the sparse view measurement sampling is insufficient, the traditional algorithm FBP method cannot produce acceptable image quality for diagnosis (4)(5)(6). Scholars have conducted many studies in recent years, including studies on hardwarebased scanning protocols (7)(8)(9) and software-based image reconstruction techniques (10)(11)(12)(13), to determine how to reduce the radiation dose of CT scans. Low-dose CT imaging can be achieved by reducing the X-ray current (14) and by reducing the number of projections per rotation of the human body (11).…”

A review on Deep Learning approaches for low-dose Computed Tomography restoration

“…Apart from the noise, the LDCT images are degraded by blurring [ 13 , 60 , 73 ] and streaking artifacts [ 28 , 34 , 50 , 71 , 75 , 81 , 91 ]. Lack of X-ray photons during the CT scanning and patient motion cause blurring.…”

LCPR-Net: low-count PET image reconstruction using the domain transform and cycle-consistent generative adversarial networks

“…In Figure 3, reference is made to recent successful applications of GANs (42). The discriminator D is composed of eight convolutional layers and two fully connected layers.…”